[v6,05/24] erofs: add inode operations

Message ID	20190802125347.166018-6-gaoxiang25@huawei.com (mailing list archive)
State	New, archived
Headers	show Return-Path: <linux-fsdevel-owner@kernel.org> From: Gao Xiang <gaoxiang25@huawei.com> To: Alexander Viro <viro@zeniv.linux.org.uk>, Greg Kroah-Hartman <gregkh@linuxfoundation.org>, Andrew Morton <akpm@linux-foundation.org>, Stephen Rothwell <sfr@canb.auug.org.au>, Theodore Ts'o <tytso@mit.edu>, "Pavel Machek" <pavel@denx.de>, David Sterba <dsterba@suse.cz>, Amir Goldstein <amir73il@gmail.com>, Christoph Hellwig <hch@infradead.org>, "Darrick J . Wong" <darrick.wong@oracle.com>, Dave Chinner <david@fromorbit.com>, "Jaegeuk Kim" <jaegeuk@kernel.org>, Jan Kara <jack@suse.cz>, Linus Torvalds <torvalds@linux-foundation.org> CC: <linux-fsdevel@vger.kernel.org>, <devel@driverdev.osuosl.org>, LKML <linux-kernel@vger.kernel.org>, <linux-erofs@lists.ozlabs.org>, Chao Yu <yuchao0@huawei.com>, Miao Xie <miaoxie@huawei.com>, Li Guifu <bluce.liguifu@huawei.com>, Fang Wei <fangwei1@huawei.com>, Gao Xiang <gaoxiang25@huawei.com> Subject: [PATCH v6 05/24] erofs: add inode operations Date: Fri, 2 Aug 2019 20:53:28 +0800 Message-ID: <20190802125347.166018-6-gaoxiang25@huawei.com> In-Reply-To: <20190802125347.166018-1-gaoxiang25@huawei.com> References: <20190802125347.166018-1-gaoxiang25@huawei.com> MIME-Version: 1.0 Content-Type: text/plain Sender: linux-fsdevel-owner@vger.kernel.org Precedence: bulk
Series	erofs: promote erofs from staging \| expand [v6,00/24] erofs: promote erofs from staging [v6,01/24] erofs: add on-disk layout [v6,02/24] erofs: add erofs in-memory stuffs [v6,03/24] erofs: add super block operations [v6,04/24] erofs: add raw address_space operations [v6,05/24] erofs: add inode operations [v6,06/24] erofs: support special inode [v6,07/24] erofs: add directory operations [v6,08/24] erofs: add namei functions [v6,09/24] erofs: support tracepoint [v6,10/24] erofs: update Kconfig and Makefile [v6,11/24] erofs: introduce xattr & posixacl support [v6,12/24] erofs: introduce tagged pointer [v6,13/24] erofs: add compression indexes support [v6,14/24] erofs: introduce superblock registration [v6,15/24] erofs: introduce erofs shrinker [v6,16/24] erofs: introduce workstation for decompression [v6,17/24] erofs: introduce per-CPU buffers implementation [v6,18/24] erofs: introduce pagevec for decompression subsystem [v6,19/24] erofs: add erofs_allocpage() [v6,20/24] erofs: introduce generic decompression backend [v6,21/24] erofs: introduce LZ4 decompression inplace [v6,22/24] erofs: introduce the decompression frontend [v6,23/24] erofs: introduce cached decompression [v6,24/24] erofs: add document

diff --git a/fs/erofs/inode.c b/fs/erofs/inode.c new file mode 100644 index 000000000000..b6ea997bc4ae --- /dev/null +++ b/fs/erofs/inode.c @@ -0,0 +1,291 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * linux/fs/erofs/inode.c + * + * Copyright (C) 2017-2018 HUAWEI, Inc. + * http://www.huawei.com/ + * Created by Gao Xiang <gaoxiang25@huawei.com> + */ +#include "internal.h" + +#include <trace/events/erofs.h> + +/* no locking */ +static int read_inode(struct inode *inode, void *data) +{ + struct erofs_vnode *vi = EROFS_V(inode); + struct erofs_inode_v1 *v1 = data; + const unsigned int advise = le16_to_cpu(v1->i_advise); + erofs_blk_t nblks = 0; + + vi->datamode = __inode_data_mapping(advise); + + if (unlikely(vi->datamode >= EROFS_INODE_LAYOUT_MAX)) { + errln("unsupported data mapping %u of nid %llu", + vi->datamode, vi->nid); + DBG_BUGON(1); + return -EIO; + } + + if (__inode_version(advise) == EROFS_INODE_LAYOUT_V2) { + struct erofs_inode_v2 *v2 = data; + + vi->inode_isize = sizeof(struct erofs_inode_v2); + vi->xattr_isize = ondisk_xattr_ibody_size(v2->i_xattr_icount); + + inode->i_mode = le16_to_cpu(v2->i_mode); + vi->raw_blkaddr = le32_to_cpu(v2->i_u.raw_blkaddr); + + i_uid_write(inode, le32_to_cpu(v2->i_uid)); + i_gid_write(inode, le32_to_cpu(v2->i_gid)); + set_nlink(inode, le32_to_cpu(v2->i_nlink)); + + /* ns timestamp */ + inode->i_mtime.tv_sec = inode->i_ctime.tv_sec = + le64_to_cpu(v2->i_ctime); + inode->i_mtime.tv_nsec = inode->i_ctime.tv_nsec = + le32_to_cpu(v2->i_ctime_nsec); + + inode->i_size = le64_to_cpu(v2->i_size); + + /* total blocks for compressed files */ + if (is_inode_layout_compression(inode)) + nblks = le32_to_cpu(v2->i_u.compressed_blocks); + } else if (__inode_version(advise) == EROFS_INODE_LAYOUT_V1) { + struct erofs_sb_info *sbi = EROFS_SB(inode->i_sb); + + vi->inode_isize = sizeof(struct erofs_inode_v1); + vi->xattr_isize = ondisk_xattr_ibody_size(v1->i_xattr_icount); + + inode->i_mode = le16_to_cpu(v1->i_mode); + vi->raw_blkaddr = le32_to_cpu(v1->i_u.raw_blkaddr); + + i_uid_write(inode, le16_to_cpu(v1->i_uid)); + i_gid_write(inode, le16_to_cpu(v1->i_gid)); + set_nlink(inode, le16_to_cpu(v1->i_nlink)); + + /* use build time to derive all file time */ + inode->i_mtime.tv_sec = inode->i_ctime.tv_sec = + sbi->build_time; + inode->i_mtime.tv_nsec = inode->i_ctime.tv_nsec = + sbi->build_time_nsec; + + inode->i_size = le32_to_cpu(v1->i_size); + if (is_inode_layout_compression(inode)) + nblks = le32_to_cpu(v1->i_u.compressed_blocks); + } else { + errln("unsupported on-disk inode version %u of nid %llu", + __inode_version(advise), vi->nid); + DBG_BUGON(1); + return -EIO; + } + + 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 0; +} + +/* + * try_lock can be required since locking order is: + * file data(fs_inode) + * meta(bd_inode) + * but the majority of the callers is "iget", + * in that case we are pretty sure no deadlock since + * no data operations exist. However I tend to + * try_lock since it takes no much overhead and + * will success immediately. + */ +static int fill_inline_data(struct inode *inode, void *data, + unsigned int m_pofs) +{ + struct erofs_vnode *vi = EROFS_V(inode); + struct erofs_sb_info *sbi = EROFS_I_SB(inode); + + /* should be inode inline C */ + if (!is_inode_flat_inline(inode)) + return 0; + + /* fast symlink (following ext4) */ + if (S_ISLNK(inode->i_mode) && inode->i_size < PAGE_SIZE) { + char *lnk = erofs_kmalloc(sbi, inode->i_size + 1, GFP_KERNEL); + + if (unlikely(!lnk)) + return -ENOMEM; + + m_pofs += vi->inode_isize + vi->xattr_isize; + + /* inline symlink data shouldn't across page boundary as well */ + if (unlikely(m_pofs + inode->i_size > PAGE_SIZE)) { + DBG_BUGON(1); + kfree(lnk); + return -EIO; + } + + /* get in-page inline data */ + memcpy(lnk, data + m_pofs, inode->i_size); + lnk[inode->i_size] = '\0'; + + inode->i_link = lnk; + set_inode_fast_symlink(inode); + } + return 0; +} + +static int fill_inode(struct inode *inode, int isdir) +{ + struct erofs_sb_info *sbi = EROFS_SB(inode->i_sb); + struct erofs_vnode *vi = EROFS_V(inode); + struct page *page; + void *data; + int err; + erofs_blk_t blkaddr; + unsigned int ofs; + + trace_erofs_fill_inode(inode, isdir); + + blkaddr = erofs_blknr(iloc(sbi, vi->nid)); + ofs = erofs_blkoff(iloc(sbi, vi->nid)); + + debugln("%s, reading inode nid %llu at %u of blkaddr %u", + __func__, vi->nid, ofs, blkaddr); + + page = erofs_get_meta_page(inode->i_sb, blkaddr, isdir); + + if (IS_ERR(page)) { + errln("failed to get inode (nid: %llu) page, err %ld", + vi->nid, PTR_ERR(page)); + return PTR_ERR(page); + } + + DBG_BUGON(!PageUptodate(page)); + data = page_address(page); + + err = read_inode(inode, data + ofs); + if (!err) { + /* setup the new inode */ + if (S_ISREG(inode->i_mode)) { + inode->i_op = &erofs_generic_iops; + inode->i_fop = &generic_ro_fops; + } else if (S_ISDIR(inode->i_mode)) { + inode->i_op = &erofs_dir_iops; + inode->i_fop = &erofs_dir_fops; + } else if (S_ISLNK(inode->i_mode)) { + /* by default, page_get_link is used for symlink */ + inode->i_op = &erofs_symlink_iops; + inode_nohighmem(inode); + } else { + err = -EIO; + goto out_unlock; + } + + if (is_inode_layout_compression(inode)) { + err = -ENOTSUPP; + goto out_unlock; + } + + inode->i_mapping->a_ops = &erofs_raw_access_aops; + + /* fill last page if inline data is available */ + err = fill_inline_data(inode, data, ofs); + } + +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. + */ +#if BITS_PER_LONG == 32 +static int erofs_ilookup_test_actor(struct inode *inode, void *opaque) +{ + const erofs_nid_t nid = *(erofs_nid_t *)opaque; + + return EROFS_V(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; +} +#endif + +static inline struct inode *erofs_iget_locked(struct super_block *sb, + erofs_nid_t nid) +{ + const unsigned long hashval = erofs_inode_hash(nid); + +#if BITS_PER_LONG >= 64 + /* it is safe to use iget_locked for >= 64-bit platform */ + return iget_locked(sb, hashval); +#else + return iget5_locked(sb, hashval, erofs_ilookup_test_actor, + erofs_iget_set_actor, &nid); +#endif +} + +struct inode *erofs_iget(struct super_block *sb, + erofs_nid_t nid, + bool isdir) +{ + struct inode *inode = erofs_iget_locked(sb, nid); + + if (unlikely(!inode)) + return ERR_PTR(-ENOMEM); + + if (inode->i_state & I_NEW) { + int err; + struct erofs_vnode *vi = EROFS_V(inode); + + vi->nid = nid; + + err = fill_inode(inode, isdir); + if (likely(!err)) + unlock_new_inode(inode); + else { + iget_failed(inode); + inode = ERR_PTR(err); + } + } + return inode; +} + +int erofs_getattr(const struct path *path, struct kstat *stat, + u32 request_mask, unsigned int query_flags) +{ + struct inode *const inode = d_inode(path->dentry); + + if (is_inode_layout_compression(inode)) + stat->attributes |= STATX_ATTR_COMPRESSED; + + stat->attributes |= STATX_ATTR_IMMUTABLE; + stat->attributes_mask |= (STATX_ATTR_COMPRESSED | + STATX_ATTR_IMMUTABLE); + + generic_fillattr(inode, stat); + return 0; +} + +const struct inode_operations erofs_generic_iops = { + .getattr = erofs_getattr, +}; + +const struct inode_operations erofs_symlink_iops = { + .get_link = page_get_link, + .getattr = erofs_getattr, +}; + +const struct inode_operations erofs_fast_symlink_iops = { + .get_link = simple_get_link, + .getattr = erofs_getattr, +}; +

[v6,05/24] erofs: add inode operations

Commit Message

Comments

Patch