mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-08-26 10:49:33 +00:00
![Christian Brauner](/assets/img/avatar_default.png)
Extend some inode methods with an additional user namespace argument. A filesystem that is aware of idmapped mounts will receive the user namespace the mount has been marked with. This can be used for additional permission checking and also to enable filesystems to translate between uids and gids if they need to. We have implemented all relevant helpers in earlier patches. As requested we simply extend the exisiting inode method instead of introducing new ones. This is a little more code churn but it's mostly mechanical and doesnt't leave us with additional inode methods. Link: https://lore.kernel.org/r/20210121131959.646623-25-christian.brauner@ubuntu.com Cc: Christoph Hellwig <hch@lst.de> Cc: David Howells <dhowells@redhat.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: linux-fsdevel@vger.kernel.org Reviewed-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Christian Brauner <christian.brauner@ubuntu.com>
370 lines
9.1 KiB
C
370 lines
9.1 KiB
C
// SPDX-License-Identifier: GPL-2.0-only
|
|
/*
|
|
* Copyright (C) 2017-2018 HUAWEI, Inc.
|
|
* https://www.huawei.com/
|
|
* Created by Gao Xiang <gaoxiang25@huawei.com>
|
|
*/
|
|
#include "xattr.h"
|
|
|
|
#include <trace/events/erofs.h>
|
|
|
|
/*
|
|
* if inode is successfully read, return its inode page (or sometimes
|
|
* the inode payload page if it's an extended inode) in order to fill
|
|
* inline data if possible.
|
|
*/
|
|
static struct page *erofs_read_inode(struct inode *inode,
|
|
unsigned int *ofs)
|
|
{
|
|
struct super_block *sb = inode->i_sb;
|
|
struct erofs_sb_info *sbi = EROFS_SB(sb);
|
|
struct erofs_inode *vi = EROFS_I(inode);
|
|
const erofs_off_t inode_loc = iloc(sbi, vi->nid);
|
|
|
|
erofs_blk_t blkaddr, nblks = 0;
|
|
struct page *page;
|
|
struct erofs_inode_compact *dic;
|
|
struct erofs_inode_extended *die, *copied = NULL;
|
|
unsigned int ifmt;
|
|
int err;
|
|
|
|
blkaddr = erofs_blknr(inode_loc);
|
|
*ofs = erofs_blkoff(inode_loc);
|
|
|
|
erofs_dbg("%s, reading inode nid %llu at %u of blkaddr %u",
|
|
__func__, vi->nid, *ofs, blkaddr);
|
|
|
|
page = erofs_get_meta_page(sb, blkaddr);
|
|
if (IS_ERR(page)) {
|
|
erofs_err(sb, "failed to get inode (nid: %llu) page, err %ld",
|
|
vi->nid, PTR_ERR(page));
|
|
return page;
|
|
}
|
|
|
|
dic = page_address(page) + *ofs;
|
|
ifmt = le16_to_cpu(dic->i_format);
|
|
|
|
vi->datalayout = erofs_inode_datalayout(ifmt);
|
|
if (vi->datalayout >= EROFS_INODE_DATALAYOUT_MAX) {
|
|
erofs_err(inode->i_sb, "unsupported datalayout %u of nid %llu",
|
|
vi->datalayout, vi->nid);
|
|
err = -EOPNOTSUPP;
|
|
goto err_out;
|
|
}
|
|
|
|
switch (erofs_inode_version(ifmt)) {
|
|
case EROFS_INODE_LAYOUT_EXTENDED:
|
|
vi->inode_isize = sizeof(struct erofs_inode_extended);
|
|
/* check if the inode acrosses page boundary */
|
|
if (*ofs + vi->inode_isize <= PAGE_SIZE) {
|
|
*ofs += vi->inode_isize;
|
|
die = (struct erofs_inode_extended *)dic;
|
|
} else {
|
|
const unsigned int gotten = PAGE_SIZE - *ofs;
|
|
|
|
copied = kmalloc(vi->inode_isize, GFP_NOFS);
|
|
if (!copied) {
|
|
err = -ENOMEM;
|
|
goto err_out;
|
|
}
|
|
memcpy(copied, dic, gotten);
|
|
unlock_page(page);
|
|
put_page(page);
|
|
|
|
page = erofs_get_meta_page(sb, blkaddr + 1);
|
|
if (IS_ERR(page)) {
|
|
erofs_err(sb, "failed to get inode payload page (nid: %llu), err %ld",
|
|
vi->nid, PTR_ERR(page));
|
|
kfree(copied);
|
|
return page;
|
|
}
|
|
*ofs = vi->inode_isize - gotten;
|
|
memcpy((u8 *)copied + gotten, page_address(page), *ofs);
|
|
die = copied;
|
|
}
|
|
vi->xattr_isize = erofs_xattr_ibody_size(die->i_xattr_icount);
|
|
|
|
inode->i_mode = le16_to_cpu(die->i_mode);
|
|
switch (inode->i_mode & S_IFMT) {
|
|
case S_IFREG:
|
|
case S_IFDIR:
|
|
case S_IFLNK:
|
|
vi->raw_blkaddr = le32_to_cpu(die->i_u.raw_blkaddr);
|
|
break;
|
|
case S_IFCHR:
|
|
case S_IFBLK:
|
|
inode->i_rdev =
|
|
new_decode_dev(le32_to_cpu(die->i_u.rdev));
|
|
break;
|
|
case S_IFIFO:
|
|
case S_IFSOCK:
|
|
inode->i_rdev = 0;
|
|
break;
|
|
default:
|
|
goto bogusimode;
|
|
}
|
|
i_uid_write(inode, le32_to_cpu(die->i_uid));
|
|
i_gid_write(inode, le32_to_cpu(die->i_gid));
|
|
set_nlink(inode, le32_to_cpu(die->i_nlink));
|
|
|
|
/* extended inode has its own timestamp */
|
|
inode->i_ctime.tv_sec = le64_to_cpu(die->i_ctime);
|
|
inode->i_ctime.tv_nsec = le32_to_cpu(die->i_ctime_nsec);
|
|
|
|
inode->i_size = le64_to_cpu(die->i_size);
|
|
|
|
/* total blocks for compressed files */
|
|
if (erofs_inode_is_data_compressed(vi->datalayout))
|
|
nblks = le32_to_cpu(die->i_u.compressed_blocks);
|
|
|
|
kfree(copied);
|
|
break;
|
|
case EROFS_INODE_LAYOUT_COMPACT:
|
|
vi->inode_isize = sizeof(struct erofs_inode_compact);
|
|
*ofs += vi->inode_isize;
|
|
vi->xattr_isize = erofs_xattr_ibody_size(dic->i_xattr_icount);
|
|
|
|
inode->i_mode = le16_to_cpu(dic->i_mode);
|
|
switch (inode->i_mode & S_IFMT) {
|
|
case S_IFREG:
|
|
case S_IFDIR:
|
|
case S_IFLNK:
|
|
vi->raw_blkaddr = le32_to_cpu(dic->i_u.raw_blkaddr);
|
|
break;
|
|
case S_IFCHR:
|
|
case S_IFBLK:
|
|
inode->i_rdev =
|
|
new_decode_dev(le32_to_cpu(dic->i_u.rdev));
|
|
break;
|
|
case S_IFIFO:
|
|
case S_IFSOCK:
|
|
inode->i_rdev = 0;
|
|
break;
|
|
default:
|
|
goto bogusimode;
|
|
}
|
|
i_uid_write(inode, le16_to_cpu(dic->i_uid));
|
|
i_gid_write(inode, le16_to_cpu(dic->i_gid));
|
|
set_nlink(inode, le16_to_cpu(dic->i_nlink));
|
|
|
|
/* use build time for compact inodes */
|
|
inode->i_ctime.tv_sec = sbi->build_time;
|
|
inode->i_ctime.tv_nsec = sbi->build_time_nsec;
|
|
|
|
inode->i_size = le32_to_cpu(dic->i_size);
|
|
if (erofs_inode_is_data_compressed(vi->datalayout))
|
|
nblks = le32_to_cpu(dic->i_u.compressed_blocks);
|
|
break;
|
|
default:
|
|
erofs_err(inode->i_sb,
|
|
"unsupported on-disk inode version %u of nid %llu",
|
|
erofs_inode_version(ifmt), vi->nid);
|
|
err = -EOPNOTSUPP;
|
|
goto err_out;
|
|
}
|
|
|
|
inode->i_mtime.tv_sec = inode->i_ctime.tv_sec;
|
|
inode->i_atime.tv_sec = inode->i_ctime.tv_sec;
|
|
inode->i_mtime.tv_nsec = inode->i_ctime.tv_nsec;
|
|
inode->i_atime.tv_nsec = inode->i_ctime.tv_nsec;
|
|
|
|
if (!nblks)
|
|
/* measure inode.i_blocks as generic filesystems */
|
|
inode->i_blocks = roundup(inode->i_size, EROFS_BLKSIZ) >> 9;
|
|
else
|
|
inode->i_blocks = nblks << LOG_SECTORS_PER_BLOCK;
|
|
return page;
|
|
|
|
bogusimode:
|
|
erofs_err(inode->i_sb, "bogus i_mode (%o) @ nid %llu",
|
|
inode->i_mode, vi->nid);
|
|
err = -EFSCORRUPTED;
|
|
err_out:
|
|
DBG_BUGON(1);
|
|
kfree(copied);
|
|
unlock_page(page);
|
|
put_page(page);
|
|
return ERR_PTR(err);
|
|
}
|
|
|
|
static int erofs_fill_symlink(struct inode *inode, void *data,
|
|
unsigned int m_pofs)
|
|
{
|
|
struct erofs_inode *vi = EROFS_I(inode);
|
|
char *lnk;
|
|
|
|
/* if it cannot be handled with fast symlink scheme */
|
|
if (vi->datalayout != EROFS_INODE_FLAT_INLINE ||
|
|
inode->i_size >= PAGE_SIZE) {
|
|
inode->i_op = &erofs_symlink_iops;
|
|
return 0;
|
|
}
|
|
|
|
lnk = kmalloc(inode->i_size + 1, GFP_KERNEL);
|
|
if (!lnk)
|
|
return -ENOMEM;
|
|
|
|
m_pofs += vi->xattr_isize;
|
|
/* inline symlink data shouldn't cross page boundary as well */
|
|
if (m_pofs + inode->i_size > PAGE_SIZE) {
|
|
kfree(lnk);
|
|
erofs_err(inode->i_sb,
|
|
"inline data cross block boundary @ nid %llu",
|
|
vi->nid);
|
|
DBG_BUGON(1);
|
|
return -EFSCORRUPTED;
|
|
}
|
|
|
|
memcpy(lnk, data + m_pofs, inode->i_size);
|
|
lnk[inode->i_size] = '\0';
|
|
|
|
inode->i_link = lnk;
|
|
inode->i_op = &erofs_fast_symlink_iops;
|
|
return 0;
|
|
}
|
|
|
|
static int erofs_fill_inode(struct inode *inode, int isdir)
|
|
{
|
|
struct erofs_inode *vi = EROFS_I(inode);
|
|
struct page *page;
|
|
unsigned int ofs;
|
|
int err = 0;
|
|
|
|
trace_erofs_fill_inode(inode, isdir);
|
|
|
|
/* read inode base data from disk */
|
|
page = erofs_read_inode(inode, &ofs);
|
|
if (IS_ERR(page))
|
|
return PTR_ERR(page);
|
|
|
|
/* setup the new inode */
|
|
switch (inode->i_mode & S_IFMT) {
|
|
case S_IFREG:
|
|
inode->i_op = &erofs_generic_iops;
|
|
inode->i_fop = &generic_ro_fops;
|
|
break;
|
|
case S_IFDIR:
|
|
inode->i_op = &erofs_dir_iops;
|
|
inode->i_fop = &erofs_dir_fops;
|
|
break;
|
|
case S_IFLNK:
|
|
err = erofs_fill_symlink(inode, page_address(page), ofs);
|
|
if (err)
|
|
goto out_unlock;
|
|
inode_nohighmem(inode);
|
|
break;
|
|
case S_IFCHR:
|
|
case S_IFBLK:
|
|
case S_IFIFO:
|
|
case S_IFSOCK:
|
|
inode->i_op = &erofs_generic_iops;
|
|
init_special_inode(inode, inode->i_mode, inode->i_rdev);
|
|
goto out_unlock;
|
|
default:
|
|
err = -EFSCORRUPTED;
|
|
goto out_unlock;
|
|
}
|
|
|
|
if (erofs_inode_is_data_compressed(vi->datalayout)) {
|
|
err = z_erofs_fill_inode(inode);
|
|
goto out_unlock;
|
|
}
|
|
inode->i_mapping->a_ops = &erofs_raw_access_aops;
|
|
|
|
out_unlock:
|
|
unlock_page(page);
|
|
put_page(page);
|
|
return err;
|
|
}
|
|
|
|
/*
|
|
* erofs nid is 64bits, but i_ino is 'unsigned long', therefore
|
|
* we should do more for 32-bit platform to find the right inode.
|
|
*/
|
|
static int erofs_ilookup_test_actor(struct inode *inode, void *opaque)
|
|
{
|
|
const erofs_nid_t nid = *(erofs_nid_t *)opaque;
|
|
|
|
return EROFS_I(inode)->nid == nid;
|
|
}
|
|
|
|
static int erofs_iget_set_actor(struct inode *inode, void *opaque)
|
|
{
|
|
const erofs_nid_t nid = *(erofs_nid_t *)opaque;
|
|
|
|
inode->i_ino = erofs_inode_hash(nid);
|
|
return 0;
|
|
}
|
|
|
|
static inline struct inode *erofs_iget_locked(struct super_block *sb,
|
|
erofs_nid_t nid)
|
|
{
|
|
const unsigned long hashval = erofs_inode_hash(nid);
|
|
|
|
return iget5_locked(sb, hashval, erofs_ilookup_test_actor,
|
|
erofs_iget_set_actor, &nid);
|
|
}
|
|
|
|
struct inode *erofs_iget(struct super_block *sb,
|
|
erofs_nid_t nid,
|
|
bool isdir)
|
|
{
|
|
struct inode *inode = erofs_iget_locked(sb, nid);
|
|
|
|
if (!inode)
|
|
return ERR_PTR(-ENOMEM);
|
|
|
|
if (inode->i_state & I_NEW) {
|
|
int err;
|
|
struct erofs_inode *vi = EROFS_I(inode);
|
|
|
|
vi->nid = nid;
|
|
|
|
err = erofs_fill_inode(inode, isdir);
|
|
if (!err)
|
|
unlock_new_inode(inode);
|
|
else {
|
|
iget_failed(inode);
|
|
inode = ERR_PTR(err);
|
|
}
|
|
}
|
|
return inode;
|
|
}
|
|
|
|
int erofs_getattr(struct user_namespace *mnt_userns, const struct path *path,
|
|
struct kstat *stat, u32 request_mask,
|
|
unsigned int query_flags)
|
|
{
|
|
struct inode *const inode = d_inode(path->dentry);
|
|
|
|
if (erofs_inode_is_data_compressed(EROFS_I(inode)->datalayout))
|
|
stat->attributes |= STATX_ATTR_COMPRESSED;
|
|
|
|
stat->attributes |= STATX_ATTR_IMMUTABLE;
|
|
stat->attributes_mask |= (STATX_ATTR_COMPRESSED |
|
|
STATX_ATTR_IMMUTABLE);
|
|
|
|
generic_fillattr(&init_user_ns, inode, stat);
|
|
return 0;
|
|
}
|
|
|
|
const struct inode_operations erofs_generic_iops = {
|
|
.getattr = erofs_getattr,
|
|
.listxattr = erofs_listxattr,
|
|
.get_acl = erofs_get_acl,
|
|
};
|
|
|
|
const struct inode_operations erofs_symlink_iops = {
|
|
.get_link = page_get_link,
|
|
.getattr = erofs_getattr,
|
|
.listxattr = erofs_listxattr,
|
|
.get_acl = erofs_get_acl,
|
|
};
|
|
|
|
const struct inode_operations erofs_fast_symlink_iops = {
|
|
.get_link = simple_get_link,
|
|
.getattr = erofs_getattr,
|
|
.listxattr = erofs_listxattr,
|
|
.get_acl = erofs_get_acl,
|
|
};
|
|
|