diff options
author | Gao Xiang <hsiangkao@aol.com> | 2019-08-23 05:36:59 +0800 |
---|---|---|
committer | Greg Kroah-Hartman <gregkh@linuxfoundation.org> | 2019-08-24 14:20:10 +0200 |
commit | 47e4937a4a7ca4184fd282791dfee76c6799966a (patch) | |
tree | fc68338c13a00ac74ac9f1a838491bd3f7649c28 /fs/erofs/zdata.h | |
parent | f401441deda68326852560bf70d59e95f585bbb3 (diff) | |
download | linux-47e4937a4a7ca4184fd282791dfee76c6799966a.tar.gz linux-47e4937a4a7ca4184fd282791dfee76c6799966a.tar.bz2 linux-47e4937a4a7ca4184fd282791dfee76c6799966a.zip |
erofs: move erofs out of staging
EROFS filesystem has been merged into linux-staging for a year.
EROFS is designed to be a better solution of saving extra storage
space with guaranteed end-to-end performance for read-only files
with the help of reduced metadata, fixed-sized output compression
and decompression inplace technologies.
In the past year, EROFS was greatly improved by many people as
a staging driver, self-tested, betaed by a large number of our
internal users, successfully applied to almost all in-service
HUAWEI smartphones as the part of EMUI 9.1 and proven to be stable
enough to be moved out of staging.
EROFS is a self-contained filesystem driver. Although there are
still some TODOs to be more generic, we have a dedicated team
actively keeping on working on EROFS in order to make it better
with the evolution of Linux kernel as the other in-kernel filesystems.
As Pavel suggested, it's better to do as one commit since git
can do moves and all histories will be saved in this way.
Let's promote it from staging and enhance it more actively as
a "real" part of kernel for more wider scenarios!
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Stephen Rothwell <sfr@canb.auug.org.au>
Cc: Theodore Ts'o <tytso@mit.edu>
Cc: Pavel Machek <pavel@denx.de>
Cc: David Sterba <dsterba@suse.cz>
Cc: Amir Goldstein <amir73il@gmail.com>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Darrick J . Wong <darrick.wong@oracle.com>
Cc: Dave Chinner <david@fromorbit.com>
Cc: Jaegeuk Kim <jaegeuk@kernel.org>
Cc: Jan Kara <jack@suse.cz>
Cc: Richard Weinberger <richard@nod.at>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Chao Yu <yuchao0@huawei.com>
Cc: Miao Xie <miaoxie@huawei.com>
Cc: Li Guifu <bluce.liguifu@huawei.com>
Cc: Fang Wei <fangwei1@huawei.com>
Signed-off-by: Gao Xiang <gaoxiang25@huawei.com>
Link: https://lore.kernel.org/r/20190822213659.5501-1-hsiangkao@aol.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Diffstat (limited to 'fs/erofs/zdata.h')
-rw-r--r-- | fs/erofs/zdata.h | 193 |
1 files changed, 193 insertions, 0 deletions
diff --git a/fs/erofs/zdata.h b/fs/erofs/zdata.h new file mode 100644 index 000000000000..4fc547bc01f9 --- /dev/null +++ b/fs/erofs/zdata.h @@ -0,0 +1,193 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2018 HUAWEI, Inc. + * http://www.huawei.com/ + * Created by Gao Xiang <gaoxiang25@huawei.com> + */ +#ifndef __EROFS_FS_ZDATA_H +#define __EROFS_FS_ZDATA_H + +#include "internal.h" +#include "zpvec.h" + +#define Z_EROFS_NR_INLINE_PAGEVECS 3 + +/* + * Structure fields follow one of the following exclusion rules. + * + * I: Modifiable by initialization/destruction paths and read-only + * for everyone else; + * + * L: Field should be protected by pageset lock; + * + * A: Field should be accessed / updated in atomic for parallelized code. + */ +struct z_erofs_collection { + struct mutex lock; + + /* I: page offset of start position of decompression */ + unsigned short pageofs; + + /* L: maximum relative page index in pagevec[] */ + unsigned short nr_pages; + + /* L: total number of pages in pagevec[] */ + unsigned int vcnt; + + union { + /* L: inline a certain number of pagevecs for bootstrap */ + erofs_vtptr_t pagevec[Z_EROFS_NR_INLINE_PAGEVECS]; + + /* I: can be used to free the pcluster by RCU. */ + struct rcu_head rcu; + }; +}; + +#define Z_EROFS_PCLUSTER_FULL_LENGTH 0x00000001 +#define Z_EROFS_PCLUSTER_LENGTH_BIT 1 + +/* + * let's leave a type here in case of introducing + * another tagged pointer later. + */ +typedef void *z_erofs_next_pcluster_t; + +struct z_erofs_pcluster { + struct erofs_workgroup obj; + struct z_erofs_collection primary_collection; + + /* A: point to next chained pcluster or TAILs */ + z_erofs_next_pcluster_t next; + + /* A: compressed pages (including multi-usage pages) */ + struct page *compressed_pages[Z_EROFS_CLUSTER_MAX_PAGES]; + + /* A: lower limit of decompressed length and if full length or not */ + unsigned int length; + + /* I: compression algorithm format */ + unsigned char algorithmformat; + /* I: bit shift of physical cluster size */ + unsigned char clusterbits; +}; + +#define z_erofs_primarycollection(pcluster) (&(pcluster)->primary_collection) + +/* let's avoid the valid 32-bit kernel addresses */ + +/* the chained workgroup has't submitted io (still open) */ +#define Z_EROFS_PCLUSTER_TAIL ((void *)0x5F0ECAFE) +/* the chained workgroup has already submitted io */ +#define Z_EROFS_PCLUSTER_TAIL_CLOSED ((void *)0x5F0EDEAD) + +#define Z_EROFS_PCLUSTER_NIL (NULL) + +#define Z_EROFS_WORKGROUP_SIZE sizeof(struct z_erofs_pcluster) + +struct z_erofs_unzip_io { + atomic_t pending_bios; + z_erofs_next_pcluster_t head; + + union { + wait_queue_head_t wait; + struct work_struct work; + } u; +}; + +struct z_erofs_unzip_io_sb { + struct z_erofs_unzip_io io; + struct super_block *sb; +}; + +#define MNGD_MAPPING(sbi) ((sbi)->managed_cache->i_mapping) +static inline bool erofs_page_is_managed(const struct erofs_sb_info *sbi, + struct page *page) +{ + return page->mapping == MNGD_MAPPING(sbi); +} + +#define Z_EROFS_ONLINEPAGE_COUNT_BITS 2 +#define Z_EROFS_ONLINEPAGE_COUNT_MASK ((1 << Z_EROFS_ONLINEPAGE_COUNT_BITS) - 1) +#define Z_EROFS_ONLINEPAGE_INDEX_SHIFT (Z_EROFS_ONLINEPAGE_COUNT_BITS) + +/* + * waiters (aka. ongoing_packs): # to unlock the page + * sub-index: 0 - for partial page, >= 1 full page sub-index + */ +typedef atomic_t z_erofs_onlinepage_t; + +/* type punning */ +union z_erofs_onlinepage_converter { + z_erofs_onlinepage_t *o; + unsigned long *v; +}; + +static inline unsigned int z_erofs_onlinepage_index(struct page *page) +{ + union z_erofs_onlinepage_converter u; + + DBG_BUGON(!PagePrivate(page)); + u.v = &page_private(page); + + return atomic_read(u.o) >> Z_EROFS_ONLINEPAGE_INDEX_SHIFT; +} + +static inline void z_erofs_onlinepage_init(struct page *page) +{ + union { + z_erofs_onlinepage_t o; + unsigned long v; + /* keep from being unlocked in advance */ + } u = { .o = ATOMIC_INIT(1) }; + + set_page_private(page, u.v); + smp_wmb(); + SetPagePrivate(page); +} + +static inline void z_erofs_onlinepage_fixup(struct page *page, + uintptr_t index, bool down) +{ + unsigned long *p, o, v, id; +repeat: + p = &page_private(page); + o = READ_ONCE(*p); + + id = o >> Z_EROFS_ONLINEPAGE_INDEX_SHIFT; + if (id) { + if (!index) + return; + + DBG_BUGON(id != index); + } + + v = (index << Z_EROFS_ONLINEPAGE_INDEX_SHIFT) | + ((o & Z_EROFS_ONLINEPAGE_COUNT_MASK) + (unsigned int)down); + if (cmpxchg(p, o, v) != o) + goto repeat; +} + +static inline void z_erofs_onlinepage_endio(struct page *page) +{ + union z_erofs_onlinepage_converter u; + unsigned int v; + + DBG_BUGON(!PagePrivate(page)); + u.v = &page_private(page); + + v = atomic_dec_return(u.o); + if (!(v & Z_EROFS_ONLINEPAGE_COUNT_MASK)) { + ClearPagePrivate(page); + if (!PageError(page)) + SetPageUptodate(page); + unlock_page(page); + } + debugln("%s, page %p value %x", __func__, page, atomic_read(u.o)); +} + +#define Z_EROFS_VMAP_ONSTACK_PAGES \ + min_t(unsigned int, THREAD_SIZE / 8 / sizeof(struct page *), 96U) +#define Z_EROFS_VMAP_GLOBAL_PAGES 2048 + +#endif + |