OpenCloudOS-Kernel/fs/erofs/inode.c

399 lines
10 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0-only
/*
* Copyright (C) 2017-2018 HUAWEI, Inc.
* https://www.huawei.com/
* Copyright (C) 2021, Alibaba Cloud
*/
#include "xattr.h"
#include <trace/events/erofs.h>
static void *erofs_read_inode(struct erofs_buf *buf,
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 = erofs_iloc(inode);
erofs_blk_t blkaddr, nblks = 0;
void *kaddr;
struct erofs_inode_compact *dic;
struct erofs_inode_extended *die, *copied = NULL;
unsigned int ifmt;
int err;
erofs: avoid hardcoded blocksize for subpage block support As the first step of converting hardcoded blocksize to that specified in on-disk superblock, convert all call sites of hardcoded blocksize to sb->s_blocksize except for: 1) use sbi->blkszbits instead of sb->s_blocksize in erofs_superblock_csum_verify() since sb->s_blocksize has not been updated with the on-disk blocksize yet when the function is called. 2) use inode->i_blkbits instead of sb->s_blocksize in erofs_bread(), since the inode operated on may be an anonymous inode in fscache mode. Currently the anonymous inode is allocated from an anonymous mount maintained in erofs, while in the near future we may allocate anonymous inodes from a generic API directly and thus have no access to the anonymous inode's i_sb. Thus we keep the block size in i_blkbits for anonymous inodes in fscache mode. Be noted that this patch only gets rid of the hardcoded blocksize, in preparation for actually setting the on-disk block size in the following patch. The hard limit of constraining the block size to PAGE_SIZE still exists until the next patch. Signed-off-by: Jingbo Xu <jefflexu@linux.alibaba.com> Reviewed-by: Gao Xiang <hsiangkao@linux.alibaba.com> Reviewed-by: Yue Hu <huyue2@coolpad.com> Reviewed-by: Chao Yu <chao@kernel.org> Link: https://lore.kernel.org/r/20230313135309.75269-2-jefflexu@linux.alibaba.com [ Gao Xiang: fold a patch to fix incorrect truncated offsets. ] Link: https://lore.kernel.org/r/20230413035734.15457-1-zhujia.zj@bytedance.com Signed-off-by: Gao Xiang <hsiangkao@linux.alibaba.com>
2023-03-13 21:53:08 +08:00
blkaddr = erofs_blknr(sb, inode_loc);
*ofs = erofs_blkoff(sb, inode_loc);
kaddr = erofs_read_metabuf(buf, sb, blkaddr, EROFS_KMAP);
if (IS_ERR(kaddr)) {
erofs_err(sb, "failed to get inode (nid: %llu) page, err %ld",
vi->nid, PTR_ERR(kaddr));
return kaddr;
}
dic = kaddr + *ofs;
ifmt = le16_to_cpu(dic->i_format);
if (ifmt & ~EROFS_I_ALL) {
erofs_err(inode->i_sb, "unsupported i_format %u of nid %llu",
ifmt, vi->nid);
err = -EOPNOTSUPP;
goto err_out;
}
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 extended inode acrosses block boundary */
erofs: avoid hardcoded blocksize for subpage block support As the first step of converting hardcoded blocksize to that specified in on-disk superblock, convert all call sites of hardcoded blocksize to sb->s_blocksize except for: 1) use sbi->blkszbits instead of sb->s_blocksize in erofs_superblock_csum_verify() since sb->s_blocksize has not been updated with the on-disk blocksize yet when the function is called. 2) use inode->i_blkbits instead of sb->s_blocksize in erofs_bread(), since the inode operated on may be an anonymous inode in fscache mode. Currently the anonymous inode is allocated from an anonymous mount maintained in erofs, while in the near future we may allocate anonymous inodes from a generic API directly and thus have no access to the anonymous inode's i_sb. Thus we keep the block size in i_blkbits for anonymous inodes in fscache mode. Be noted that this patch only gets rid of the hardcoded blocksize, in preparation for actually setting the on-disk block size in the following patch. The hard limit of constraining the block size to PAGE_SIZE still exists until the next patch. Signed-off-by: Jingbo Xu <jefflexu@linux.alibaba.com> Reviewed-by: Gao Xiang <hsiangkao@linux.alibaba.com> Reviewed-by: Yue Hu <huyue2@coolpad.com> Reviewed-by: Chao Yu <chao@kernel.org> Link: https://lore.kernel.org/r/20230313135309.75269-2-jefflexu@linux.alibaba.com [ Gao Xiang: fold a patch to fix incorrect truncated offsets. ] Link: https://lore.kernel.org/r/20230413035734.15457-1-zhujia.zj@bytedance.com Signed-off-by: Gao Xiang <hsiangkao@linux.alibaba.com>
2023-03-13 21:53:08 +08:00
if (*ofs + vi->inode_isize <= sb->s_blocksize) {
*ofs += vi->inode_isize;
die = (struct erofs_inode_extended *)dic;
} else {
erofs: avoid hardcoded blocksize for subpage block support As the first step of converting hardcoded blocksize to that specified in on-disk superblock, convert all call sites of hardcoded blocksize to sb->s_blocksize except for: 1) use sbi->blkszbits instead of sb->s_blocksize in erofs_superblock_csum_verify() since sb->s_blocksize has not been updated with the on-disk blocksize yet when the function is called. 2) use inode->i_blkbits instead of sb->s_blocksize in erofs_bread(), since the inode operated on may be an anonymous inode in fscache mode. Currently the anonymous inode is allocated from an anonymous mount maintained in erofs, while in the near future we may allocate anonymous inodes from a generic API directly and thus have no access to the anonymous inode's i_sb. Thus we keep the block size in i_blkbits for anonymous inodes in fscache mode. Be noted that this patch only gets rid of the hardcoded blocksize, in preparation for actually setting the on-disk block size in the following patch. The hard limit of constraining the block size to PAGE_SIZE still exists until the next patch. Signed-off-by: Jingbo Xu <jefflexu@linux.alibaba.com> Reviewed-by: Gao Xiang <hsiangkao@linux.alibaba.com> Reviewed-by: Yue Hu <huyue2@coolpad.com> Reviewed-by: Chao Yu <chao@kernel.org> Link: https://lore.kernel.org/r/20230313135309.75269-2-jefflexu@linux.alibaba.com [ Gao Xiang: fold a patch to fix incorrect truncated offsets. ] Link: https://lore.kernel.org/r/20230413035734.15457-1-zhujia.zj@bytedance.com Signed-off-by: Gao Xiang <hsiangkao@linux.alibaba.com>
2023-03-13 21:53:08 +08:00
const unsigned int gotten = sb->s_blocksize - *ofs;
copied = kmalloc(vi->inode_isize, GFP_NOFS);
if (!copied) {
err = -ENOMEM;
goto err_out;
}
memcpy(copied, dic, gotten);
kaddr = erofs_read_metabuf(buf, sb, blkaddr + 1,
EROFS_KMAP);
if (IS_ERR(kaddr)) {
erofs_err(sb, "failed to get inode payload block (nid: %llu), err %ld",
vi->nid, PTR_ERR(kaddr));
kfree(copied);
return kaddr;
}
*ofs = vi->inode_isize - gotten;
memcpy((u8 *)copied + gotten, kaddr, *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_mtime);
inode->i_ctime.tv_nsec = le32_to_cpu(die->i_mtime_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);
else if (vi->datalayout == EROFS_INODE_CHUNK_BASED)
/* fill chunked inode summary info */
vi->chunkformat = le16_to_cpu(die->i_u.c.format);
kfree(copied);
copied = NULL;
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);
else if (vi->datalayout == EROFS_INODE_CHUNK_BASED)
vi->chunkformat = le16_to_cpu(dic->i_u.c.format);
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;
}
if (vi->datalayout == EROFS_INODE_CHUNK_BASED) {
if (vi->chunkformat & ~EROFS_CHUNK_FORMAT_ALL) {
erofs_err(inode->i_sb,
"unsupported chunk format %x of nid %llu",
vi->chunkformat, vi->nid);
err = -EOPNOTSUPP;
goto err_out;
}
erofs: avoid hardcoded blocksize for subpage block support As the first step of converting hardcoded blocksize to that specified in on-disk superblock, convert all call sites of hardcoded blocksize to sb->s_blocksize except for: 1) use sbi->blkszbits instead of sb->s_blocksize in erofs_superblock_csum_verify() since sb->s_blocksize has not been updated with the on-disk blocksize yet when the function is called. 2) use inode->i_blkbits instead of sb->s_blocksize in erofs_bread(), since the inode operated on may be an anonymous inode in fscache mode. Currently the anonymous inode is allocated from an anonymous mount maintained in erofs, while in the near future we may allocate anonymous inodes from a generic API directly and thus have no access to the anonymous inode's i_sb. Thus we keep the block size in i_blkbits for anonymous inodes in fscache mode. Be noted that this patch only gets rid of the hardcoded blocksize, in preparation for actually setting the on-disk block size in the following patch. The hard limit of constraining the block size to PAGE_SIZE still exists until the next patch. Signed-off-by: Jingbo Xu <jefflexu@linux.alibaba.com> Reviewed-by: Gao Xiang <hsiangkao@linux.alibaba.com> Reviewed-by: Yue Hu <huyue2@coolpad.com> Reviewed-by: Chao Yu <chao@kernel.org> Link: https://lore.kernel.org/r/20230313135309.75269-2-jefflexu@linux.alibaba.com [ Gao Xiang: fold a patch to fix incorrect truncated offsets. ] Link: https://lore.kernel.org/r/20230413035734.15457-1-zhujia.zj@bytedance.com Signed-off-by: Gao Xiang <hsiangkao@linux.alibaba.com>
2023-03-13 21:53:08 +08:00
vi->chunkbits = sb->s_blocksize_bits +
(vi->chunkformat & EROFS_CHUNK_FORMAT_BLKBITS_MASK);
}
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;
inode->i_flags &= ~S_DAX;
if (test_opt(&sbi->opt, DAX_ALWAYS) && S_ISREG(inode->i_mode) &&
vi->datalayout == EROFS_INODE_FLAT_PLAIN)
inode->i_flags |= S_DAX;
erofs: avoid hardcoded blocksize for subpage block support As the first step of converting hardcoded blocksize to that specified in on-disk superblock, convert all call sites of hardcoded blocksize to sb->s_blocksize except for: 1) use sbi->blkszbits instead of sb->s_blocksize in erofs_superblock_csum_verify() since sb->s_blocksize has not been updated with the on-disk blocksize yet when the function is called. 2) use inode->i_blkbits instead of sb->s_blocksize in erofs_bread(), since the inode operated on may be an anonymous inode in fscache mode. Currently the anonymous inode is allocated from an anonymous mount maintained in erofs, while in the near future we may allocate anonymous inodes from a generic API directly and thus have no access to the anonymous inode's i_sb. Thus we keep the block size in i_blkbits for anonymous inodes in fscache mode. Be noted that this patch only gets rid of the hardcoded blocksize, in preparation for actually setting the on-disk block size in the following patch. The hard limit of constraining the block size to PAGE_SIZE still exists until the next patch. Signed-off-by: Jingbo Xu <jefflexu@linux.alibaba.com> Reviewed-by: Gao Xiang <hsiangkao@linux.alibaba.com> Reviewed-by: Yue Hu <huyue2@coolpad.com> Reviewed-by: Chao Yu <chao@kernel.org> Link: https://lore.kernel.org/r/20230313135309.75269-2-jefflexu@linux.alibaba.com [ Gao Xiang: fold a patch to fix incorrect truncated offsets. ] Link: https://lore.kernel.org/r/20230413035734.15457-1-zhujia.zj@bytedance.com Signed-off-by: Gao Xiang <hsiangkao@linux.alibaba.com>
2023-03-13 21:53:08 +08:00
if (!nblks)
/* measure inode.i_blocks as generic filesystems */
erofs: avoid hardcoded blocksize for subpage block support As the first step of converting hardcoded blocksize to that specified in on-disk superblock, convert all call sites of hardcoded blocksize to sb->s_blocksize except for: 1) use sbi->blkszbits instead of sb->s_blocksize in erofs_superblock_csum_verify() since sb->s_blocksize has not been updated with the on-disk blocksize yet when the function is called. 2) use inode->i_blkbits instead of sb->s_blocksize in erofs_bread(), since the inode operated on may be an anonymous inode in fscache mode. Currently the anonymous inode is allocated from an anonymous mount maintained in erofs, while in the near future we may allocate anonymous inodes from a generic API directly and thus have no access to the anonymous inode's i_sb. Thus we keep the block size in i_blkbits for anonymous inodes in fscache mode. Be noted that this patch only gets rid of the hardcoded blocksize, in preparation for actually setting the on-disk block size in the following patch. The hard limit of constraining the block size to PAGE_SIZE still exists until the next patch. Signed-off-by: Jingbo Xu <jefflexu@linux.alibaba.com> Reviewed-by: Gao Xiang <hsiangkao@linux.alibaba.com> Reviewed-by: Yue Hu <huyue2@coolpad.com> Reviewed-by: Chao Yu <chao@kernel.org> Link: https://lore.kernel.org/r/20230313135309.75269-2-jefflexu@linux.alibaba.com [ Gao Xiang: fold a patch to fix incorrect truncated offsets. ] Link: https://lore.kernel.org/r/20230413035734.15457-1-zhujia.zj@bytedance.com Signed-off-by: Gao Xiang <hsiangkao@linux.alibaba.com>
2023-03-13 21:53:08 +08:00
inode->i_blocks = round_up(inode->i_size, sb->s_blocksize) >> 9;
else
erofs: avoid hardcoded blocksize for subpage block support As the first step of converting hardcoded blocksize to that specified in on-disk superblock, convert all call sites of hardcoded blocksize to sb->s_blocksize except for: 1) use sbi->blkszbits instead of sb->s_blocksize in erofs_superblock_csum_verify() since sb->s_blocksize has not been updated with the on-disk blocksize yet when the function is called. 2) use inode->i_blkbits instead of sb->s_blocksize in erofs_bread(), since the inode operated on may be an anonymous inode in fscache mode. Currently the anonymous inode is allocated from an anonymous mount maintained in erofs, while in the near future we may allocate anonymous inodes from a generic API directly and thus have no access to the anonymous inode's i_sb. Thus we keep the block size in i_blkbits for anonymous inodes in fscache mode. Be noted that this patch only gets rid of the hardcoded blocksize, in preparation for actually setting the on-disk block size in the following patch. The hard limit of constraining the block size to PAGE_SIZE still exists until the next patch. Signed-off-by: Jingbo Xu <jefflexu@linux.alibaba.com> Reviewed-by: Gao Xiang <hsiangkao@linux.alibaba.com> Reviewed-by: Yue Hu <huyue2@coolpad.com> Reviewed-by: Chao Yu <chao@kernel.org> Link: https://lore.kernel.org/r/20230313135309.75269-2-jefflexu@linux.alibaba.com [ Gao Xiang: fold a patch to fix incorrect truncated offsets. ] Link: https://lore.kernel.org/r/20230413035734.15457-1-zhujia.zj@bytedance.com Signed-off-by: Gao Xiang <hsiangkao@linux.alibaba.com>
2023-03-13 21:53:08 +08:00
inode->i_blocks = nblks << (sb->s_blocksize_bits - 9);
return kaddr;
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);
erofs_put_metabuf(buf);
return ERR_PTR(err);
}
static int erofs_fill_symlink(struct inode *inode, void *kaddr,
unsigned int m_pofs)
{
struct erofs_inode *vi = EROFS_I(inode);
erofs: avoid hardcoded blocksize for subpage block support As the first step of converting hardcoded blocksize to that specified in on-disk superblock, convert all call sites of hardcoded blocksize to sb->s_blocksize except for: 1) use sbi->blkszbits instead of sb->s_blocksize in erofs_superblock_csum_verify() since sb->s_blocksize has not been updated with the on-disk blocksize yet when the function is called. 2) use inode->i_blkbits instead of sb->s_blocksize in erofs_bread(), since the inode operated on may be an anonymous inode in fscache mode. Currently the anonymous inode is allocated from an anonymous mount maintained in erofs, while in the near future we may allocate anonymous inodes from a generic API directly and thus have no access to the anonymous inode's i_sb. Thus we keep the block size in i_blkbits for anonymous inodes in fscache mode. Be noted that this patch only gets rid of the hardcoded blocksize, in preparation for actually setting the on-disk block size in the following patch. The hard limit of constraining the block size to PAGE_SIZE still exists until the next patch. Signed-off-by: Jingbo Xu <jefflexu@linux.alibaba.com> Reviewed-by: Gao Xiang <hsiangkao@linux.alibaba.com> Reviewed-by: Yue Hu <huyue2@coolpad.com> Reviewed-by: Chao Yu <chao@kernel.org> Link: https://lore.kernel.org/r/20230313135309.75269-2-jefflexu@linux.alibaba.com [ Gao Xiang: fold a patch to fix incorrect truncated offsets. ] Link: https://lore.kernel.org/r/20230413035734.15457-1-zhujia.zj@bytedance.com Signed-off-by: Gao Xiang <hsiangkao@linux.alibaba.com>
2023-03-13 21:53:08 +08:00
unsigned int bsz = i_blocksize(inode);
char *lnk;
/* if it cannot be handled with fast symlink scheme */
if (vi->datalayout != EROFS_INODE_FLAT_INLINE ||
erofs: avoid hardcoded blocksize for subpage block support As the first step of converting hardcoded blocksize to that specified in on-disk superblock, convert all call sites of hardcoded blocksize to sb->s_blocksize except for: 1) use sbi->blkszbits instead of sb->s_blocksize in erofs_superblock_csum_verify() since sb->s_blocksize has not been updated with the on-disk blocksize yet when the function is called. 2) use inode->i_blkbits instead of sb->s_blocksize in erofs_bread(), since the inode operated on may be an anonymous inode in fscache mode. Currently the anonymous inode is allocated from an anonymous mount maintained in erofs, while in the near future we may allocate anonymous inodes from a generic API directly and thus have no access to the anonymous inode's i_sb. Thus we keep the block size in i_blkbits for anonymous inodes in fscache mode. Be noted that this patch only gets rid of the hardcoded blocksize, in preparation for actually setting the on-disk block size in the following patch. The hard limit of constraining the block size to PAGE_SIZE still exists until the next patch. Signed-off-by: Jingbo Xu <jefflexu@linux.alibaba.com> Reviewed-by: Gao Xiang <hsiangkao@linux.alibaba.com> Reviewed-by: Yue Hu <huyue2@coolpad.com> Reviewed-by: Chao Yu <chao@kernel.org> Link: https://lore.kernel.org/r/20230313135309.75269-2-jefflexu@linux.alibaba.com [ Gao Xiang: fold a patch to fix incorrect truncated offsets. ] Link: https://lore.kernel.org/r/20230413035734.15457-1-zhujia.zj@bytedance.com Signed-off-by: Gao Xiang <hsiangkao@linux.alibaba.com>
2023-03-13 21:53:08 +08:00
inode->i_size >= bsz || inode->i_size < 0) {
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 block boundary */
erofs: avoid hardcoded blocksize for subpage block support As the first step of converting hardcoded blocksize to that specified in on-disk superblock, convert all call sites of hardcoded blocksize to sb->s_blocksize except for: 1) use sbi->blkszbits instead of sb->s_blocksize in erofs_superblock_csum_verify() since sb->s_blocksize has not been updated with the on-disk blocksize yet when the function is called. 2) use inode->i_blkbits instead of sb->s_blocksize in erofs_bread(), since the inode operated on may be an anonymous inode in fscache mode. Currently the anonymous inode is allocated from an anonymous mount maintained in erofs, while in the near future we may allocate anonymous inodes from a generic API directly and thus have no access to the anonymous inode's i_sb. Thus we keep the block size in i_blkbits for anonymous inodes in fscache mode. Be noted that this patch only gets rid of the hardcoded blocksize, in preparation for actually setting the on-disk block size in the following patch. The hard limit of constraining the block size to PAGE_SIZE still exists until the next patch. Signed-off-by: Jingbo Xu <jefflexu@linux.alibaba.com> Reviewed-by: Gao Xiang <hsiangkao@linux.alibaba.com> Reviewed-by: Yue Hu <huyue2@coolpad.com> Reviewed-by: Chao Yu <chao@kernel.org> Link: https://lore.kernel.org/r/20230313135309.75269-2-jefflexu@linux.alibaba.com [ Gao Xiang: fold a patch to fix incorrect truncated offsets. ] Link: https://lore.kernel.org/r/20230413035734.15457-1-zhujia.zj@bytedance.com Signed-off-by: Gao Xiang <hsiangkao@linux.alibaba.com>
2023-03-13 21:53:08 +08:00
if (m_pofs + inode->i_size > bsz) {
kfree(lnk);
erofs_err(inode->i_sb,
"inline data cross block boundary @ nid %llu",
vi->nid);
DBG_BUGON(1);
return -EFSCORRUPTED;
}
memcpy(lnk, kaddr + 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)
{
struct erofs_inode *vi = EROFS_I(inode);
struct erofs_buf buf = __EROFS_BUF_INITIALIZER;
void *kaddr;
unsigned int ofs;
int err = 0;
trace_erofs_fill_inode(inode);
/* read inode base data from disk */
kaddr = erofs_read_inode(&buf, inode, &ofs);
if (IS_ERR(kaddr))
return PTR_ERR(kaddr);
/* setup the new inode */
switch (inode->i_mode & S_IFMT) {
case S_IFREG:
inode->i_op = &erofs_generic_iops;
if (erofs_inode_is_data_compressed(vi->datalayout))
inode->i_fop = &generic_ro_fops;
else
inode->i_fop = &erofs_file_fops;
break;
case S_IFDIR:
inode->i_op = &erofs_dir_iops;
inode->i_fop = &erofs_dir_fops;
inode_nohighmem(inode);
break;
case S_IFLNK:
err = erofs_fill_symlink(inode, kaddr, 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)) {
#ifdef CONFIG_EROFS_FS_ZIP
if (!erofs_is_fscache_mode(inode->i_sb) &&
inode->i_sb->s_blocksize_bits == PAGE_SHIFT) {
inode->i_mapping->a_ops = &z_erofs_aops;
err = 0;
goto out_unlock;
}
#endif
err = -EOPNOTSUPP;
goto out_unlock;
}
inode->i_mapping->a_ops = &erofs_raw_access_aops;
mapping_set_large_folios(inode->i_mapping);
#ifdef CONFIG_EROFS_FS_ONDEMAND
if (erofs_is_fscache_mode(inode->i_sb))
inode->i_mapping->a_ops = &erofs_fscache_access_aops;
#endif
out_unlock:
erofs_put_metabuf(&buf);
return err;
}
/*
* ino_t is 32-bits on 32-bit arch. We have to squash the 64-bit value down
* so that it will fit.
*/
static ino_t erofs_squash_ino(erofs_nid_t nid)
{
ino_t ino = (ino_t)nid;
if (sizeof(ino_t) < sizeof(erofs_nid_t))
ino ^= nid >> (sizeof(erofs_nid_t) - sizeof(ino_t)) * 8;
return ino;
}
static int erofs_iget5_eq(struct inode *inode, void *opaque)
{
return EROFS_I(inode)->nid == *(erofs_nid_t *)opaque;
}
static int erofs_iget5_set(struct inode *inode, void *opaque)
{
const erofs_nid_t nid = *(erofs_nid_t *)opaque;
inode->i_ino = erofs_squash_ino(nid);
EROFS_I(inode)->nid = nid;
return 0;
}
struct inode *erofs_iget(struct super_block *sb, erofs_nid_t nid)
{
struct inode *inode;
inode = iget5_locked(sb, erofs_squash_ino(nid), erofs_iget5_eq,
erofs_iget5_set, &nid);
if (!inode)
return ERR_PTR(-ENOMEM);
if (inode->i_state & I_NEW) {
int err = erofs_fill_inode(inode);
if (err) {
iget_failed(inode);
return ERR_PTR(err);
}
unlock_new_inode(inode);
}
return inode;
}
int erofs_getattr(struct mnt_idmap *idmap, 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(idmap, inode, stat);
return 0;
}
const struct inode_operations erofs_generic_iops = {
.getattr = erofs_getattr,
.listxattr = erofs_listxattr,
fs: rename current get acl method The current way of setting and getting posix acls through the generic xattr interface is error prone and type unsafe. The vfs needs to interpret and fixup posix acls before storing or reporting it to userspace. Various hacks exist to make this work. The code is hard to understand and difficult to maintain in it's current form. Instead of making this work by hacking posix acls through xattr handlers we are building a dedicated posix acl api around the get and set inode operations. This removes a lot of hackiness and makes the codepaths easier to maintain. A lot of background can be found in [1]. The current inode operation for getting posix acls takes an inode argument but various filesystems (e.g., 9p, cifs, overlayfs) need access to the dentry. In contrast to the ->set_acl() inode operation we cannot simply extend ->get_acl() to take a dentry argument. The ->get_acl() inode operation is called from: acl_permission_check() -> check_acl() -> get_acl() which is part of generic_permission() which in turn is part of inode_permission(). Both generic_permission() and inode_permission() are called in the ->permission() handler of various filesystems (e.g., overlayfs). So simply passing a dentry argument to ->get_acl() would amount to also having to pass a dentry argument to ->permission(). We should avoid this unnecessary change. So instead of extending the existing inode operation rename it from ->get_acl() to ->get_inode_acl() and add a ->get_acl() method later that passes a dentry argument and which filesystems that need access to the dentry can implement instead of ->get_inode_acl(). Filesystems like cifs which allow setting and getting posix acls but not using them for permission checking during lookup can simply not implement ->get_inode_acl(). This is intended to be a non-functional change. Link: https://lore.kernel.org/all/20220801145520.1532837-1-brauner@kernel.org [1] Suggested-by/Inspired-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Christian Brauner (Microsoft) <brauner@kernel.org>
2022-09-22 23:17:00 +08:00
.get_inode_acl = erofs_get_acl,
.fiemap = erofs_fiemap,
};
const struct inode_operations erofs_symlink_iops = {
.get_link = page_get_link,
.getattr = erofs_getattr,
.listxattr = erofs_listxattr,
fs: rename current get acl method The current way of setting and getting posix acls through the generic xattr interface is error prone and type unsafe. The vfs needs to interpret and fixup posix acls before storing or reporting it to userspace. Various hacks exist to make this work. The code is hard to understand and difficult to maintain in it's current form. Instead of making this work by hacking posix acls through xattr handlers we are building a dedicated posix acl api around the get and set inode operations. This removes a lot of hackiness and makes the codepaths easier to maintain. A lot of background can be found in [1]. The current inode operation for getting posix acls takes an inode argument but various filesystems (e.g., 9p, cifs, overlayfs) need access to the dentry. In contrast to the ->set_acl() inode operation we cannot simply extend ->get_acl() to take a dentry argument. The ->get_acl() inode operation is called from: acl_permission_check() -> check_acl() -> get_acl() which is part of generic_permission() which in turn is part of inode_permission(). Both generic_permission() and inode_permission() are called in the ->permission() handler of various filesystems (e.g., overlayfs). So simply passing a dentry argument to ->get_acl() would amount to also having to pass a dentry argument to ->permission(). We should avoid this unnecessary change. So instead of extending the existing inode operation rename it from ->get_acl() to ->get_inode_acl() and add a ->get_acl() method later that passes a dentry argument and which filesystems that need access to the dentry can implement instead of ->get_inode_acl(). Filesystems like cifs which allow setting and getting posix acls but not using them for permission checking during lookup can simply not implement ->get_inode_acl(). This is intended to be a non-functional change. Link: https://lore.kernel.org/all/20220801145520.1532837-1-brauner@kernel.org [1] Suggested-by/Inspired-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Christian Brauner (Microsoft) <brauner@kernel.org>
2022-09-22 23:17:00 +08:00
.get_inode_acl = erofs_get_acl,
};
const struct inode_operations erofs_fast_symlink_iops = {
.get_link = simple_get_link,
.getattr = erofs_getattr,
.listxattr = erofs_listxattr,
fs: rename current get acl method The current way of setting and getting posix acls through the generic xattr interface is error prone and type unsafe. The vfs needs to interpret and fixup posix acls before storing or reporting it to userspace. Various hacks exist to make this work. The code is hard to understand and difficult to maintain in it's current form. Instead of making this work by hacking posix acls through xattr handlers we are building a dedicated posix acl api around the get and set inode operations. This removes a lot of hackiness and makes the codepaths easier to maintain. A lot of background can be found in [1]. The current inode operation for getting posix acls takes an inode argument but various filesystems (e.g., 9p, cifs, overlayfs) need access to the dentry. In contrast to the ->set_acl() inode operation we cannot simply extend ->get_acl() to take a dentry argument. The ->get_acl() inode operation is called from: acl_permission_check() -> check_acl() -> get_acl() which is part of generic_permission() which in turn is part of inode_permission(). Both generic_permission() and inode_permission() are called in the ->permission() handler of various filesystems (e.g., overlayfs). So simply passing a dentry argument to ->get_acl() would amount to also having to pass a dentry argument to ->permission(). We should avoid this unnecessary change. So instead of extending the existing inode operation rename it from ->get_acl() to ->get_inode_acl() and add a ->get_acl() method later that passes a dentry argument and which filesystems that need access to the dentry can implement instead of ->get_inode_acl(). Filesystems like cifs which allow setting and getting posix acls but not using them for permission checking during lookup can simply not implement ->get_inode_acl(). This is intended to be a non-functional change. Link: https://lore.kernel.org/all/20220801145520.1532837-1-brauner@kernel.org [1] Suggested-by/Inspired-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Christian Brauner (Microsoft) <brauner@kernel.org>
2022-09-22 23:17:00 +08:00
.get_inode_acl = erofs_get_acl,
};