diff options
Diffstat (limited to 'fs/erofs')
-rw-r--r-- | fs/erofs/Kconfig | 58 | ||||
-rw-r--r-- | fs/erofs/Makefile | 9 | ||||
-rw-r--r-- | fs/erofs/compress.h | 88 | ||||
-rw-r--r-- | fs/erofs/data.c | 596 | ||||
-rw-r--r-- | fs/erofs/decompressor.c | 481 | ||||
-rw-r--r-- | fs/erofs/decompressor_lzma.c | 291 | ||||
-rw-r--r-- | fs/erofs/dir.c | 45 | ||||
-rw-r--r-- | fs/erofs/erofs_fs.h | 253 | ||||
-rw-r--r-- | fs/erofs/fscache.c | 674 | ||||
-rw-r--r-- | fs/erofs/inode.c | 237 | ||||
-rw-r--r-- | fs/erofs/internal.h | 426 | ||||
-rw-r--r-- | fs/erofs/namei.c | 83 | ||||
-rw-r--r-- | fs/erofs/pcpubuf.c | 148 | ||||
-rw-r--r-- | fs/erofs/super.c | 872 | ||||
-rw-r--r-- | fs/erofs/sysfs.c | 277 | ||||
-rw-r--r-- | fs/erofs/tagptr.h | 3 | ||||
-rw-r--r-- | fs/erofs/utils.c | 141 | ||||
-rw-r--r-- | fs/erofs/xattr.c | 160 | ||||
-rw-r--r-- | fs/erofs/xattr.h | 15 | ||||
-rw-r--r-- | fs/erofs/zdata.c | 1712 | ||||
-rw-r--r-- | fs/erofs/zdata.h | 181 | ||||
-rw-r--r-- | fs/erofs/zmap.c | 637 | ||||
-rw-r--r-- | fs/erofs/zpvec.h | 157 |
23 files changed, 5176 insertions, 2368 deletions
diff --git a/fs/erofs/Kconfig b/fs/erofs/Kconfig index 74b0aaa7114c..85490370e0ca 100644 --- a/fs/erofs/Kconfig +++ b/fs/erofs/Kconfig @@ -3,18 +3,25 @@ config EROFS_FS tristate "EROFS filesystem support" depends on BLOCK + select FS_IOMAP select LIBCRC32C help - EROFS (Enhanced Read-Only File System) is a lightweight - read-only file system with modern designs (eg. page-sized - blocks, inline xattrs/data, etc.) for scenarios which need - high-performance read-only requirements, e.g. Android OS - for mobile phones and LIVECDs. - - It also provides fixed-sized output compression support, - which improves storage density, keeps relatively higher - compression ratios, which is more useful to achieve high - performance for embedded devices with limited memory. + EROFS (Enhanced Read-Only File System) is a lightweight read-only + file system with modern designs (e.g. no buffer heads, inline + xattrs/data, chunk-based deduplication, multiple devices, etc.) for + scenarios which need high-performance read-only solutions, e.g. + smartphones with Android OS, LiveCDs and high-density hosts with + numerous containers; + + It also provides fixed-sized output compression support in order to + improve storage density as well as keep relatively higher compression + ratios and implements in-place decompression to reuse the file page + for compressed data temporarily with proper strategies, which is + quite useful to ensure guaranteed end-to-end runtime decompression + performance under extremely memory pressure without extra cost. + + See the documentation at <file:Documentation/filesystems/erofs.rst> + for more details. If unsure, say N. @@ -76,17 +83,28 @@ config EROFS_FS_ZIP If you don't want to enable compression feature, say N. -config EROFS_FS_CLUSTER_PAGE_LIMIT - int "EROFS Cluster Pages Hard Limit" +config EROFS_FS_ZIP_LZMA + bool "EROFS LZMA compressed data support" depends on EROFS_FS_ZIP - range 1 256 - default "1" + select XZ_DEC + select XZ_DEC_MICROLZMA help - Indicates maximum # of pages of a compressed - physical cluster. + Saying Y here includes support for reading EROFS file systems + containing LZMA compressed data, specifically called microLZMA. it + gives better compression ratios than the LZ4 algorithm, at the + expense of more CPU overhead. + + LZMA support is an experimental feature for now and so most file + systems will be readable without selecting this option. + + If unsure, say N. - For example, if files in a image were compressed - into 8k-unit, hard limit should not be configured - less than 2. Otherwise, the image will be refused - to mount on this kernel. +config EROFS_FS_ONDEMAND + bool "EROFS fscache-based on-demand read support" + depends on CACHEFILES_ONDEMAND && (EROFS_FS=m && FSCACHE || EROFS_FS=y && FSCACHE=y) + default n + help + This permits EROFS to use fscache-backed data blobs with on-demand + read support. + If unsure, say N. diff --git a/fs/erofs/Makefile b/fs/erofs/Makefile index 46f2aa4ba46c..99bbc597a3e9 100644 --- a/fs/erofs/Makefile +++ b/fs/erofs/Makefile @@ -1,11 +1,8 @@ # SPDX-License-Identifier: GPL-2.0-only -EROFS_VERSION = "1.0" - -ccflags-y += -DEROFS_VERSION=\"$(EROFS_VERSION)\" - obj-$(CONFIG_EROFS_FS) += erofs.o -erofs-objs := super.o inode.o data.o namei.o dir.o utils.o +erofs-objs := super.o inode.o data.o namei.o dir.o utils.o pcpubuf.o sysfs.o erofs-$(CONFIG_EROFS_FS_XATTR) += xattr.o erofs-$(CONFIG_EROFS_FS_ZIP) += decompressor.o zmap.o zdata.o - +erofs-$(CONFIG_EROFS_FS_ZIP_LZMA) += decompressor_lzma.o +erofs-$(CONFIG_EROFS_FS_ONDEMAND) += fscache.o diff --git a/fs/erofs/compress.h b/fs/erofs/compress.h index 07d279fd5d67..26fa170090b8 100644 --- a/fs/erofs/compress.h +++ b/fs/erofs/compress.h @@ -1,60 +1,98 @@ /* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (C) 2019 HUAWEI, Inc. - * http://www.huawei.com/ - * Created by Gao Xiang <gaoxiang25@huawei.com> + * https://www.huawei.com/ */ #ifndef __EROFS_FS_COMPRESS_H #define __EROFS_FS_COMPRESS_H #include "internal.h" -enum { - Z_EROFS_COMPRESSION_SHIFTED = Z_EROFS_COMPRESSION_MAX, - Z_EROFS_COMPRESSION_RUNTIME_MAX -}; - struct z_erofs_decompress_req { struct super_block *sb; struct page **in, **out; - unsigned short pageofs_out; + unsigned short pageofs_in, pageofs_out; unsigned int inputsize, outputsize; /* indicate the algorithm will be used for decompression */ unsigned int alg; - bool inplace_io, partial_decoding; + bool inplace_io, partial_decoding, fillgaps; +}; + +struct z_erofs_decompressor { + int (*decompress)(struct z_erofs_decompress_req *rq, + struct page **pagepool); + char *name; }; +/* some special page->private (unsigned long, see below) */ +#define Z_EROFS_SHORTLIVED_PAGE (-1UL << 2) +#define Z_EROFS_PREALLOCATED_PAGE (-2UL << 2) + /* - * - 0x5A110C8D ('sallocated', Z_EROFS_MAPPING_STAGING) - - * used to mark temporary allocated pages from other - * file/cached pages and NULL mapping pages. + * For all pages in a pcluster, page->private should be one of + * Type Last 2bits page->private + * short-lived page 00 Z_EROFS_SHORTLIVED_PAGE + * preallocated page (tryalloc) 00 Z_EROFS_PREALLOCATED_PAGE + * cached/managed page 00 pointer to z_erofs_pcluster + * online page (file-backed, 01/10/11 sub-index << 2 | count + * some pages can be used for inplace I/O) + * + * page->mapping should be one of + * Type page->mapping + * short-lived page NULL + * preallocated page NULL + * cached/managed page non-NULL or NULL (invalidated/truncated page) + * online page non-NULL + * + * For all managed pages, PG_private should be set with 1 extra refcount, + * which is used for page reclaim / migration. */ -#define Z_EROFS_MAPPING_STAGING ((void *)0x5A110C8D) -/* check if a page is marked as staging */ -static inline bool z_erofs_page_is_staging(struct page *page) +/* + * short-lived pages are pages directly from buddy system with specific + * page->private (no need to set PagePrivate since these are non-LRU / + * non-movable pages and bypass reclaim / migration code). + */ +static inline bool z_erofs_is_shortlived_page(struct page *page) { - return page->mapping == Z_EROFS_MAPPING_STAGING; + if (page->private != Z_EROFS_SHORTLIVED_PAGE) + return false; + + DBG_BUGON(page->mapping); + return true; } -static inline bool z_erofs_put_stagingpage(struct list_head *pagepool, - struct page *page) +static inline bool z_erofs_put_shortlivedpage(struct page **pagepool, + struct page *page) { - if (!z_erofs_page_is_staging(page)) + if (!z_erofs_is_shortlived_page(page)) return false; - /* staging pages should not be used by others at the same time */ - if (page_ref_count(page) > 1) + /* short-lived pages should not be used by others at the same time */ + if (page_ref_count(page) > 1) { put_page(page); - else - list_add(&page->lru, pagepool); + } else { + /* follow the pcluster rule above. */ + erofs_pagepool_add(pagepool, page); + } return true; } +#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); +} + +int z_erofs_fixup_insize(struct z_erofs_decompress_req *rq, const char *padbuf, + unsigned int padbufsize); int z_erofs_decompress(struct z_erofs_decompress_req *rq, - struct list_head *pagepool); + struct page **pagepool); +/* prototypes for specific algorithms */ +int z_erofs_lzma_decompress(struct z_erofs_decompress_req *rq, + struct page **pagepool); #endif - diff --git a/fs/erofs/data.c b/fs/erofs/data.c index fc3a8d8064f8..fe8ac0e163f7 100644 --- a/fs/erofs/data.c +++ b/fs/erofs/data.c @@ -1,75 +1,96 @@ // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2017-2018 HUAWEI, Inc. - * http://www.huawei.com/ - * Created by Gao Xiang <gaoxiang25@huawei.com> + * https://www.huawei.com/ + * Copyright (C) 2021, Alibaba Cloud */ #include "internal.h" #include <linux/prefetch.h> - +#include <linux/sched/mm.h> +#include <linux/dax.h> #include <trace/events/erofs.h> -static void erofs_readendio(struct bio *bio) +void erofs_unmap_metabuf(struct erofs_buf *buf) { - struct bio_vec *bvec; - blk_status_t err = bio->bi_status; - struct bvec_iter_all iter_all; - - bio_for_each_segment_all(bvec, bio, iter_all) { - struct page *page = bvec->bv_page; - - /* page is already locked */ - DBG_BUGON(PageUptodate(page)); + if (buf->kmap_type == EROFS_KMAP) + kunmap(buf->page); + else if (buf->kmap_type == EROFS_KMAP_ATOMIC) + kunmap_atomic(buf->base); + buf->base = NULL; + buf->kmap_type = EROFS_NO_KMAP; +} - if (err) - SetPageError(page); - else - SetPageUptodate(page); +void erofs_put_metabuf(struct erofs_buf *buf) +{ + if (!buf->page) + return; + erofs_unmap_metabuf(buf); + put_page(buf->page); + buf->page = NULL; +} - unlock_page(page); - /* page could be reclaimed now */ +void *erofs_bread(struct erofs_buf *buf, struct inode *inode, + erofs_blk_t blkaddr, enum erofs_kmap_type type) +{ + struct address_space *const mapping = inode->i_mapping; + erofs_off_t offset = blknr_to_addr(blkaddr); + pgoff_t index = offset >> PAGE_SHIFT; + struct page *page = buf->page; + struct folio *folio; + unsigned int nofs_flag; + + if (!page || page->index != index) { + erofs_put_metabuf(buf); + + nofs_flag = memalloc_nofs_save(); + folio = read_cache_folio(mapping, index, NULL, NULL); + memalloc_nofs_restore(nofs_flag); + if (IS_ERR(folio)) + return folio; + + /* should already be PageUptodate, no need to lock page */ + page = folio_file_page(folio, index); + buf->page = page; } - bio_put(bio); + if (buf->kmap_type == EROFS_NO_KMAP) { + if (type == EROFS_KMAP) + buf->base = kmap(page); + else if (type == EROFS_KMAP_ATOMIC) + buf->base = kmap_atomic(page); + buf->kmap_type = type; + } else if (buf->kmap_type != type) { + DBG_BUGON(1); + return ERR_PTR(-EFAULT); + } + if (type == EROFS_NO_KMAP) + return NULL; + return buf->base + (offset & ~PAGE_MASK); } -struct page *erofs_get_meta_page(struct super_block *sb, erofs_blk_t blkaddr) +void *erofs_read_metabuf(struct erofs_buf *buf, struct super_block *sb, + erofs_blk_t blkaddr, enum erofs_kmap_type type) { - struct address_space *const mapping = sb->s_bdev->bd_inode->i_mapping; - struct page *page; - - page = read_cache_page_gfp(mapping, blkaddr, - mapping_gfp_constraint(mapping, ~__GFP_FS)); - /* should already be PageUptodate */ - if (!IS_ERR(page)) - lock_page(page); - return page; + if (erofs_is_fscache_mode(sb)) + return erofs_bread(buf, EROFS_SB(sb)->s_fscache->inode, + blkaddr, type); + + return erofs_bread(buf, sb->s_bdev->bd_inode, blkaddr, type); } static int erofs_map_blocks_flatmode(struct inode *inode, struct erofs_map_blocks *map, int flags) { - int err = 0; erofs_blk_t nblocks, lastblk; u64 offset = map->m_la; struct erofs_inode *vi = EROFS_I(inode); bool tailendpacking = (vi->datalayout == EROFS_INODE_FLAT_INLINE); - trace_erofs_map_blocks_flatmode_enter(inode, map, flags); - - nblocks = DIV_ROUND_UP(inode->i_size, PAGE_SIZE); + nblocks = DIV_ROUND_UP(inode->i_size, EROFS_BLKSIZ); lastblk = nblocks - tailendpacking; - if (offset >= inode->i_size) { - /* leave out-of-bound access unmapped */ - map->m_flags = 0; - map->m_plen = 0; - goto out; - } - /* there is no hole in flatmode */ map->m_flags = EROFS_MAP_MAPPED; - if (offset < blknr_to_addr(lastblk)) { map->m_pa = blknr_to_addr(vi->raw_blkaddr) + map->m_la; map->m_plen = blknr_to_addr(lastblk) - offset; @@ -81,284 +102,345 @@ static int erofs_map_blocks_flatmode(struct inode *inode, vi->xattr_isize + erofs_blkoff(map->m_la); map->m_plen = inode->i_size - offset; - /* inline data should be located in one meta block */ - if (erofs_blkoff(map->m_pa) + map->m_plen > PAGE_SIZE) { + /* inline data should be located in the same meta block */ + if (erofs_blkoff(map->m_pa) + map->m_plen > EROFS_BLKSIZ) { erofs_err(inode->i_sb, "inline data cross block boundary @ nid %llu", vi->nid); DBG_BUGON(1); - err = -EFSCORRUPTED; - goto err_out; + return -EFSCORRUPTED; } - map->m_flags |= EROFS_MAP_META; } else { erofs_err(inode->i_sb, "internal error @ nid: %llu (size %llu), m_la 0x%llx", vi->nid, inode->i_size, map->m_la); DBG_BUGON(1); - err = -EIO; - goto err_out; + return -EIO; } - -out: - map->m_llen = map->m_plen; - -err_out: - trace_erofs_map_blocks_flatmode_exit(inode, map, flags, 0); - return err; + return 0; } int erofs_map_blocks(struct inode *inode, struct erofs_map_blocks *map, int flags) { - if (erofs_inode_is_data_compressed(EROFS_I(inode)->datalayout)) { - int err = z_erofs_map_blocks_iter(inode, map, flags); - - if (map->mpage) { - put_page(map->mpage); - map->mpage = NULL; - } - return err; - } - return erofs_map_blocks_flatmode(inode, map, flags); -} - -static inline struct bio *erofs_read_raw_page(struct bio *bio, - struct address_space *mapping, - struct page *page, - erofs_off_t *last_block, - unsigned int nblocks, - bool ra) -{ - struct inode *const inode = mapping->host; - struct super_block *const sb = inode->i_sb; - erofs_off_t current_block = (erofs_off_t)page->index; - int err; - - DBG_BUGON(!nblocks); + struct super_block *sb = inode->i_sb; + struct erofs_inode *vi = EROFS_I(inode); + struct erofs_inode_chunk_index *idx; + struct erofs_buf buf = __EROFS_BUF_INITIALIZER; + u64 chunknr; + unsigned int unit; + erofs_off_t pos; + void *kaddr; + int err = 0; - if (PageUptodate(page)) { - err = 0; - goto has_updated; + trace_erofs_map_blocks_enter(inode, map, flags); + map->m_deviceid = 0; + if (map->m_la >= inode->i_size) { + /* leave out-of-bound access unmapped */ + map->m_flags = 0; + map->m_plen = 0; + goto out; } - /* note that for readpage case, bio also equals to NULL */ - if (bio && - /* not continuous */ - *last_block + 1 != current_block) { -submit_bio_retry: - submit_bio(bio); - bio = NULL; + if (vi->datalayout != EROFS_INODE_CHUNK_BASED) { + err = erofs_map_blocks_flatmode(inode, map, flags); + goto out; } - if (!bio) { - struct erofs_map_blocks map = { - .m_la = blknr_to_addr(current_block), - }; - erofs_blk_t blknr; - unsigned int blkoff; - - err = erofs_map_blocks(inode, &map, EROFS_GET_BLOCKS_RAW); - if (err) - goto err_out; + if (vi->chunkformat & EROFS_CHUNK_FORMAT_INDEXES) + unit = sizeof(*idx); /* chunk index */ + else + unit = EROFS_BLOCK_MAP_ENTRY_SIZE; /* block map */ - /* zero out the holed page */ - if (!(map.m_flags & EROFS_MAP_MAPPED)) { - zero_user_segment(page, 0, PAGE_SIZE); - SetPageUptodate(page); + chunknr = map->m_la >> vi->chunkbits; + pos = ALIGN(iloc(EROFS_SB(sb), vi->nid) + vi->inode_isize + + vi->xattr_isize, unit) + unit * chunknr; - /* imply err = 0, see erofs_map_blocks */ - goto has_updated; + kaddr = erofs_read_metabuf(&buf, sb, erofs_blknr(pos), EROFS_KMAP); + if (IS_ERR(kaddr)) { + err = PTR_ERR(kaddr); + goto out; + } + map->m_la = chunknr << vi->chunkbits; + map->m_plen = min_t(erofs_off_t, 1UL << vi->chunkbits, + roundup(inode->i_size - map->m_la, EROFS_BLKSIZ)); + + /* handle block map */ + if (!(vi->chunkformat & EROFS_CHUNK_FORMAT_INDEXES)) { + __le32 *blkaddr = kaddr + erofs_blkoff(pos); + + if (le32_to_cpu(*blkaddr) == EROFS_NULL_ADDR) { + map->m_flags = 0; + } else { + map->m_pa = blknr_to_addr(le32_to_cpu(*blkaddr)); + map->m_flags = EROFS_MAP_MAPPED; } + goto out_unlock; + } + /* parse chunk indexes */ + idx = kaddr + erofs_blkoff(pos); + switch (le32_to_cpu(idx->blkaddr)) { + case EROFS_NULL_ADDR: + map->m_flags = 0; + break; + default: + map->m_deviceid = le16_to_cpu(idx->device_id) & + EROFS_SB(sb)->device_id_mask; + map->m_pa = blknr_to_addr(le32_to_cpu(idx->blkaddr)); + map->m_flags = EROFS_MAP_MAPPED; + break; + } +out_unlock: + erofs_put_metabuf(&buf); +out: + if (!err) + map->m_llen = map->m_plen; + trace_erofs_map_blocks_exit(inode, map, flags, 0); + return err; +} - /* for RAW access mode, m_plen must be equal to m_llen */ - DBG_BUGON(map.m_plen != map.m_llen); - - blknr = erofs_blknr(map.m_pa); - blkoff = erofs_blkoff(map.m_pa); - - /* deal with inline page */ - if (map.m_flags & EROFS_MAP_META) { - void *vsrc, *vto; - struct page *ipage; - - DBG_BUGON(map.m_plen > PAGE_SIZE); - - ipage = erofs_get_meta_page(inode->i_sb, blknr); - - if (IS_ERR(ipage)) { - err = PTR_ERR(ipage); - goto err_out; +int erofs_map_dev(struct super_block *sb, struct erofs_map_dev *map) +{ + struct erofs_dev_context *devs = EROFS_SB(sb)->devs; + struct erofs_device_info *dif; + int id; + + /* primary device by default */ + map->m_bdev = sb->s_bdev; + map->m_daxdev = EROFS_SB(sb)->dax_dev; + map->m_dax_part_off = EROFS_SB(sb)->dax_part_off; + map->m_fscache = EROFS_SB(sb)->s_fscache; + + if (map->m_deviceid) { + down_read(&devs->rwsem); + dif = idr_find(&devs->tree, map->m_deviceid - 1); + if (!dif) { + up_read(&devs->rwsem); + return -ENODEV; + } + map->m_bdev = dif->bdev; + map->m_daxdev = dif->dax_dev; + map->m_dax_part_off = dif->dax_part_off; + map->m_fscache = dif->fscache; + up_read(&devs->rwsem); + } else if (devs->extra_devices) { + down_read(&devs->rwsem); + idr_for_each_entry(&devs->tree, dif, id) { + erofs_off_t startoff, length; + + if (!dif->mapped_blkaddr) + continue; + startoff = blknr_to_addr(dif->mapped_blkaddr); + length = blknr_to_addr(dif->blocks); + + if (map->m_pa >= startoff && + map->m_pa < startoff + length) { + map->m_pa -= startoff; + map->m_bdev = dif->bdev; + map->m_daxdev = dif->dax_dev; + map->m_dax_part_off = dif->dax_part_off; + map->m_fscache = dif->fscache; + break; } - - vsrc = kmap_atomic(ipage); - vto = kmap_atomic(page); - memcpy(vto, vsrc + blkoff, map.m_plen); - memset(vto + map.m_plen, 0, PAGE_SIZE - map.m_plen); - kunmap_atomic(vto); - kunmap_atomic(vsrc); - flush_dcache_page(page); - - SetPageUptodate(page); - /* TODO: could we unlock the page earlier? */ - unlock_page(ipage); - put_page(ipage); - - /* imply err = 0, see erofs_map_blocks */ - goto has_updated; } + up_read(&devs->rwsem); + } + return 0; +} - /* pa must be block-aligned for raw reading */ - DBG_BUGON(erofs_blkoff(map.m_pa)); +static int erofs_iomap_begin(struct inode *inode, loff_t offset, loff_t length, + unsigned int flags, struct iomap *iomap, struct iomap *srcmap) +{ + int ret; + struct erofs_map_blocks map; + struct erofs_map_dev mdev; - /* max # of continuous pages */ - if (nblocks > DIV_ROUND_UP(map.m_plen, PAGE_SIZE)) - nblocks = DIV_ROUND_UP(map.m_plen, PAGE_SIZE); - if (nblocks > BIO_MAX_PAGES) - nblocks = BIO_MAX_PAGES; + map.m_la = offset; + map.m_llen = length; - bio = bio_alloc(GFP_NOIO, nblocks); + ret = erofs_map_blocks(inode, &map, EROFS_GET_BLOCKS_RAW); + if (ret < 0) + return ret; - bio->bi_end_io = erofs_readendio; - bio_set_dev(bio, sb->s_bdev); - bio->bi_iter.bi_sector = (sector_t)blknr << - LOG_SECTORS_PER_BLOCK; - bio->bi_opf = REQ_OP_READ; + mdev = (struct erofs_map_dev) { + .m_deviceid = map.m_deviceid, + .m_pa = map.m_pa, + }; + ret = erofs_map_dev(inode->i_sb, &mdev); + if (ret) + return ret; + + iomap->offset = map.m_la; + if (flags & IOMAP_DAX) + iomap->dax_dev = mdev.m_daxdev; + else + iomap->bdev = mdev.m_bdev; + iomap->length = map.m_llen; + iomap->flags = 0; + iomap->private = NULL; + + if (!(map.m_flags & EROFS_MAP_MAPPED)) { + iomap->type = IOMAP_HOLE; + iomap->addr = IOMAP_NULL_ADDR; + if (!iomap->length) + iomap->length = length; + return 0; } - err = bio_add_page(bio, page, PAGE_SIZE, 0); - /* out of the extent or bio is full */ - if (err < PAGE_SIZE) - goto submit_bio_retry; + if (map.m_flags & EROFS_MAP_META) { + void *ptr; + struct erofs_buf buf = __EROFS_BUF_INITIALIZER; + + iomap->type = IOMAP_INLINE; + ptr = erofs_read_metabuf(&buf, inode->i_sb, + erofs_blknr(mdev.m_pa), EROFS_KMAP); + if (IS_ERR(ptr)) + return PTR_ERR(ptr); + iomap->inline_data = ptr + erofs_blkoff(mdev.m_pa); + iomap->private = buf.base; + } else { + iomap->type = IOMAP_MAPPED; + iomap->addr = mdev.m_pa; + if (flags & IOMAP_DAX) + iomap->addr += mdev.m_dax_part_off; + } + return 0; +} - *last_block = current_block; +static int erofs_iomap_end(struct inode *inode, loff_t pos, loff_t length, + ssize_t written, unsigned int flags, struct iomap *iomap) +{ + void *ptr = iomap->private; - /* shift in advance in case of it followed by too many gaps */ - if (bio->bi_iter.bi_size >= bio->bi_max_vecs * PAGE_SIZE) { - /* err should reassign to 0 after submitting */ - err = 0; - goto submit_bio_out; + if (ptr) { + struct erofs_buf buf = { + .page = kmap_to_page(ptr), + .base = ptr, + .kmap_type = EROFS_KMAP, + }; + + DBG_BUGON(iomap->type != IOMAP_INLINE); + erofs_put_metabuf(&buf); + } else { + DBG_BUGON(iomap->type == IOMAP_INLINE); } + return written; +} - return bio; +static const struct iomap_ops erofs_iomap_ops = { + .iomap_begin = erofs_iomap_begin, + .iomap_end = erofs_iomap_end, +}; -err_out: - /* for sync reading, set page error immediately */ - if (!ra) { - SetPageError(page); - ClearPageUptodate(page); +int erofs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, + u64 start, u64 len) +{ + if (erofs_inode_is_data_compressed(EROFS_I(inode)->datalayout)) { +#ifdef CONFIG_EROFS_FS_ZIP + return iomap_fiemap(inode, fieinfo, start, len, + &z_erofs_iomap_report_ops); +#else + return -EOPNOTSUPP; +#endif } -has_updated: - unlock_page(page); - - /* if updated manually, continuous pages has a gap */ - if (bio) -submit_bio_out: - submit_bio(bio); - return err ? ERR_PTR(err) : NULL; + return iomap_fiemap(inode, fieinfo, start, len, &erofs_iomap_ops); } /* * since we dont have write or truncate flows, so no inode * locking needs to be held at the moment. */ -static int erofs_raw_access_readpage(struct file *file, struct page *page) +static int erofs_read_folio(struct file *file, struct folio *folio) { - erofs_off_t last_block; - struct bio *bio; - - trace_erofs_readpage(page, true); - - bio = erofs_read_raw_page(NULL, page->mapping, - page, &last_block, 1, false); - - if (IS_ERR(bio)) - return PTR_ERR(bio); - - DBG_BUGON(bio); /* since we have only one bio -- must be NULL */ - return 0; + return iomap_read_folio(folio, &erofs_iomap_ops); } -static int erofs_raw_access_readpages(struct file *filp, - struct address_space *mapping, - struct list_head *pages, - unsigned int nr_pages) +static void erofs_readahead(struct readahead_control *rac) { - erofs_off_t last_block; - struct bio *bio = NULL; - gfp_t gfp = readahead_gfp_mask(mapping); - struct page *page = list_last_entry(pages, struct page, lru); - - trace_erofs_readpages(mapping->host, page, nr_pages, true); - - for (; nr_pages; --nr_pages) { - page = list_entry(pages->prev, struct page, lru); - - prefetchw(&page->flags); - list_del(&page->lru); - - if (!add_to_page_cache_lru(page, mapping, page->index, gfp)) { - bio = erofs_read_raw_page(bio, mapping, page, - &last_block, nr_pages, true); - - /* all the page errors are ignored when readahead */ - if (IS_ERR(bio)) { - pr_err("%s, readahead error at page %lu of nid %llu\n", - __func__, page->index, - EROFS_I(mapping->host)->nid); - - bio = NULL; - } - } - - /* pages could still be locked */ - put_page(page); - } - DBG_BUGON(!list_empty(pages)); - - /* the rare case (end in gaps) */ - if (bio) - submit_bio(bio); - return 0; + return iomap_readahead(rac, &erofs_iomap_ops); } -static int erofs_get_block(struct inode *inode, sector_t iblock, - struct buffer_head *bh, int create) +static sector_t erofs_bmap(struct address_space *mapping, sector_t block) { - struct erofs_map_blocks map = { - .m_la = iblock << 9, - }; - int err; - - err = erofs_map_blocks(inode, &map, EROFS_GET_BLOCKS_RAW); - if (err) - return err; - - if (map.m_flags & EROFS_MAP_MAPPED) - bh->b_blocknr = erofs_blknr(map.m_pa); - - return err; + return iomap_bmap(mapping, block, &erofs_iomap_ops); } -static sector_t erofs_bmap(struct address_space *mapping, sector_t block) +static ssize_t erofs_file_read_iter(struct kiocb *iocb, struct iov_iter *to) { - struct inode *inode = mapping->host; + struct inode *inode = file_inode(iocb->ki_filp); + + /* no need taking (shared) inode lock since it's a ro filesystem */ + if (!iov_iter_count(to)) + return 0; + +#ifdef CONFIG_FS_DAX + if (IS_DAX(inode)) + return dax_iomap_rw(iocb, to, &erofs_iomap_ops); +#endif + if (iocb->ki_flags & IOCB_DIRECT) { + struct block_device *bdev = inode->i_sb->s_bdev; + unsigned int blksize_mask; + + if (bdev) + blksize_mask = bdev_logical_block_size(bdev) - 1; + else + blksize_mask = (1 << inode->i_blkbits) - 1; - if (EROFS_I(inode)->datalayout == EROFS_INODE_FLAT_INLINE) { - erofs_blk_t blks = i_size_read(inode) >> LOG_BLOCK_SIZE; + if ((iocb->ki_pos | iov_iter_count(to) | + iov_iter_alignment(to)) & blksize_mask) + return -EINVAL; - if (block >> LOG_SECTORS_PER_BLOCK >= blks) - return 0; + return iomap_dio_rw(iocb, to, &erofs_iomap_ops, + NULL, 0, NULL, 0); } - - return generic_block_bmap(mapping, block, erofs_get_block); + return filemap_read(iocb, to, 0); } /* for uncompressed (aligned) files and raw access for other files */ const struct address_space_operations erofs_raw_access_aops = { - .readpage = erofs_raw_access_readpage, - .readpages = erofs_raw_access_readpages, + .read_folio = erofs_read_folio, + .readahead = erofs_readahead, .bmap = erofs_bmap, + .direct_IO = noop_direct_IO, }; +#ifdef CONFIG_FS_DAX +static vm_fault_t erofs_dax_huge_fault(struct vm_fault *vmf, + enum page_entry_size pe_size) +{ + return dax_iomap_fault(vmf, pe_size, NULL, NULL, &erofs_iomap_ops); +} + +static vm_fault_t erofs_dax_fault(struct vm_fault *vmf) +{ + return erofs_dax_huge_fault(vmf, PE_SIZE_PTE); +} + +static const struct vm_operations_struct erofs_dax_vm_ops = { + .fault = erofs_dax_fault, + .huge_fault = erofs_dax_huge_fault, +}; + +static int erofs_file_mmap(struct file *file, struct vm_area_struct *vma) +{ + if (!IS_DAX(file_inode(file))) + return generic_file_readonly_mmap(file, vma); + + if ((vma->vm_flags & VM_SHARED) && (vma->vm_flags & VM_MAYWRITE)) + return -EINVAL; + + vma->vm_ops = &erofs_dax_vm_ops; + vma->vm_flags |= VM_HUGEPAGE; + return 0; +} +#else +#define erofs_file_mmap generic_file_readonly_mmap +#endif + +const struct file_operations erofs_file_fops = { + .llseek = generic_file_llseek, + .read_iter = erofs_file_read_iter, + .mmap = erofs_file_mmap, + .splice_read = generic_file_splice_read, +}; diff --git a/fs/erofs/decompressor.c b/fs/erofs/decompressor.c index 5779a15c2cd6..51b7ac7166d9 100644 --- a/fs/erofs/decompressor.c +++ b/fs/erofs/decompressor.c @@ -1,8 +1,7 @@ // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2019 HUAWEI, Inc. - * http://www.huawei.com/ - * Created by Gao Xiang <gaoxiang25@huawei.com> + * https://www.huawei.com/ */ #include "compress.h" #include <linux/module.h> @@ -17,53 +16,93 @@ #define LZ4_DECOMPRESS_INPLACE_MARGIN(srcsize) (((srcsize) >> 8) + 32) #endif -struct z_erofs_decompressor { - /* - * if destpages have sparsed pages, fill them with bounce pages. - * it also check whether destpages indicate continuous physical memory. - */ - int (*prepare_destpages)(struct z_erofs_decompress_req *rq, - struct list_head *pagepool); - int (*decompress)(struct z_erofs_decompress_req *rq, u8 *out); - char *name; +struct z_erofs_lz4_decompress_ctx { + struct z_erofs_decompress_req *rq; + /* # of encoded, decoded pages */ + unsigned int inpages, outpages; + /* decoded block total length (used for in-place decompression) */ + unsigned int oend; }; -static int z_erofs_lz4_prepare_destpages(struct z_erofs_decompress_req *rq, - struct list_head *pagepool) +int z_erofs_load_lz4_config(struct super_block *sb, + struct erofs_super_block *dsb, + struct z_erofs_lz4_cfgs *lz4, int size) { - const unsigned int nr = - PAGE_ALIGN(rq->pageofs_out + rq->outputsize) >> PAGE_SHIFT; + struct erofs_sb_info *sbi = EROFS_SB(sb); + u16 distance; + + if (lz4) { + if (size < sizeof(struct z_erofs_lz4_cfgs)) { + erofs_err(sb, "invalid lz4 cfgs, size=%u", size); + return -EINVAL; + } + distance = le16_to_cpu(lz4->max_distance); + + sbi->lz4.max_pclusterblks = le16_to_cpu(lz4->max_pclusterblks); + if (!sbi->lz4.max_pclusterblks) { + sbi->lz4.max_pclusterblks = 1; /* reserved case */ + } else if (sbi->lz4.max_pclusterblks > + Z_EROFS_PCLUSTER_MAX_SIZE / EROFS_BLKSIZ) { + erofs_err(sb, "too large lz4 pclusterblks %u", + sbi->lz4.max_pclusterblks); + return -EINVAL; + } + } else { + distance = le16_to_cpu(dsb->u1.lz4_max_distance); + sbi->lz4.max_pclusterblks = 1; + } + + sbi->lz4.max_distance_pages = distance ? + DIV_ROUND_UP(distance, PAGE_SIZE) + 1 : + LZ4_MAX_DISTANCE_PAGES; + return erofs_pcpubuf_growsize(sbi->lz4.max_pclusterblks); +} + +/* + * Fill all gaps with bounce pages if it's a sparse page list. Also check if + * all physical pages are consecutive, which can be seen for moderate CR. + */ +static int z_erofs_lz4_prepare_dstpages(struct z_erofs_lz4_decompress_ctx *ctx, + struct page **pagepool) +{ + struct z_erofs_decompress_req *rq = ctx->rq; struct page *availables[LZ4_MAX_DISTANCE_PAGES] = { NULL }; unsigned long bounced[DIV_ROUND_UP(LZ4_MAX_DISTANCE_PAGES, BITS_PER_LONG)] = { 0 }; + unsigned int lz4_max_distance_pages = + EROFS_SB(rq->sb)->lz4.max_distance_pages; void *kaddr = NULL; unsigned int i, j, top; top = 0; - for (i = j = 0; i < nr; ++i, ++j) { + for (i = j = 0; i < ctx->outpages; ++i, ++j) { struct page *const page = rq->out[i]; struct page *victim; - if (j >= LZ4_MAX_DISTANCE_PAGES) + if (j >= lz4_max_distance_pages) j = 0; /* 'valid' bounced can only be tested after a complete round */ - if (test_bit(j, bounced)) { - DBG_BUGON(i < LZ4_MAX_DISTANCE_PAGES); - DBG_BUGON(top >= LZ4_MAX_DISTANCE_PAGES); - availables[top++] = rq->out[i - LZ4_MAX_DISTANCE_PAGES]; + if (!rq->fillgaps && test_bit(j, bounced)) { + DBG_BUGON(i < lz4_max_distance_pages); + DBG_BUGON(top >= lz4_max_distance_pages); + availables[top++] = rq->out[i - lz4_max_distance_pages]; } if (page) { __clear_bit(j, bounced); - if (kaddr) { - if (kaddr + PAGE_SIZE == page_address(page)) + if (!PageHighMem(page)) { + if (!i) { + kaddr = page_address(page); + continue; + } + if (kaddr && + kaddr + PAGE_SIZE == page_address(page)) { kaddr += PAGE_SIZE; - else - kaddr = NULL; - } else if (!i) { - kaddr = page_address(page); + continue; + } } + kaddr = NULL; continue; } kaddr = NULL; @@ -73,264 +112,280 @@ static int z_erofs_lz4_prepare_destpages(struct z_erofs_decompress_req *rq, victim = availables[--top]; get_page(victim); } else { - victim = erofs_allocpage(pagepool, GFP_KERNEL); - if (!victim) - return -ENOMEM; - victim->mapping = Z_EROFS_MAPPING_STAGING; + victim = erofs_allocpage(pagepool, + GFP_KERNEL | __GFP_NOFAIL); + set_page_private(victim, Z_EROFS_SHORTLIVED_PAGE); } rq->out[i] = victim; } return kaddr ? 1 : 0; } -static void *generic_copy_inplace_data(struct z_erofs_decompress_req *rq, - u8 *src, unsigned int pageofs_in) +static void *z_erofs_lz4_handle_overlap(struct z_erofs_lz4_decompress_ctx *ctx, + void *inpage, unsigned int *inputmargin, int *maptype, + bool may_inplace) { - /* - * if in-place decompression is ongoing, those decompressed - * pages should be copied in order to avoid being overlapped. - */ - struct page **in = rq->in; - u8 *const tmp = erofs_get_pcpubuf(0); - u8 *tmpp = tmp; - unsigned int inlen = rq->inputsize - pageofs_in; - unsigned int count = min_t(uint, inlen, PAGE_SIZE - pageofs_in); - - while (tmpp < tmp + inlen) { - if (!src) - src = kmap_atomic(*in); - memcpy(tmpp, src + pageofs_in, count); - kunmap_atomic(src); - src = NULL; - tmpp += count; - pageofs_in = 0; - count = PAGE_SIZE; + struct z_erofs_decompress_req *rq = ctx->rq; + unsigned int omargin, total, i, j; + struct page **in; + void *src, *tmp; + + if (rq->inplace_io) { + omargin = PAGE_ALIGN(ctx->oend) - ctx->oend; + if (rq->partial_decoding || !may_inplace || + omargin < LZ4_DECOMPRESS_INPLACE_MARGIN(rq->inputsize)) + goto docopy; + + for (i = 0; i < ctx->inpages; ++i) { + DBG_BUGON(rq->in[i] == NULL); + for (j = 0; j < ctx->outpages - ctx->inpages + i; ++j) + if (rq->out[j] == rq->in[i]) + goto docopy; + } + } + + if (ctx->inpages <= 1) { + *maptype = 0; + return inpage; + } + kunmap_atomic(inpage); + might_sleep(); + src = erofs_vm_map_ram(rq->in, ctx->inpages); + if (!src) + return ERR_PTR(-ENOMEM); + *maptype = 1; + return src; + +docopy: + /* Or copy compressed data which can be overlapped to per-CPU buffer */ + in = rq->in; + src = erofs_get_pcpubuf(ctx->inpages); + if (!src) { + DBG_BUGON(1); + kunmap_atomic(inpage); + return ERR_PTR(-EFAULT); + } + + tmp = src; + total = rq->inputsize; + while (total) { + unsigned int page_copycnt = + min_t(unsigned int, total, PAGE_SIZE - *inputmargin); + + if (!inpage) + inpage = kmap_atomic(*in); + memcpy(tmp, inpage + *inputmargin, page_copycnt); + kunmap_atomic(inpage); + inpage = NULL; + tmp += page_copycnt; + total -= page_copycnt; ++in; + *inputmargin = 0; } - return tmp; + *maptype = 2; + return src; } -static int z_erofs_lz4_decompress(struct z_erofs_decompress_req *rq, u8 *out) +/* + * Get the exact inputsize with zero_padding feature. + * - For LZ4, it should work if zero_padding feature is on (5.3+); + * - For MicroLZMA, it'd be enabled all the time. + */ +int z_erofs_fixup_insize(struct z_erofs_decompress_req *rq, const char *padbuf, + unsigned int padbufsize) { - unsigned int inputmargin, inlen; - u8 *src; - bool copied, support_0padding; - int ret; - - if (rq->inputsize > PAGE_SIZE) - return -EOPNOTSUPP; + const char *padend; - src = kmap_atomic(*rq->in); - inputmargin = 0; - support_0padding = false; + padend = memchr_inv(padbuf, 0, padbufsize); + if (!padend) + return -EFSCORRUPTED; + rq->inputsize -= padend - padbuf; + rq->pageofs_in += padend - padbuf; + return 0; +} - /* decompression inplace is only safe when 0padding is enabled */ - if (EROFS_SB(rq->sb)->feature_incompat & - EROFS_FEATURE_INCOMPAT_LZ4_0PADDING) { - support_0padding = true; +static int z_erofs_lz4_decompress_mem(struct z_erofs_lz4_decompress_ctx *ctx, + u8 *out) +{ + struct z_erofs_decompress_req *rq = ctx->rq; + bool support_0padding = false, may_inplace = false; + unsigned int inputmargin; + u8 *headpage, *src; + int ret, maptype; - while (!src[inputmargin & ~PAGE_MASK]) - if (!(++inputmargin & ~PAGE_MASK)) - break; + DBG_BUGON(*rq->in == NULL); + headpage = kmap_atomic(*rq->in); - if (inputmargin >= rq->inputsize) { - kunmap_atomic(src); - return -EIO; + /* LZ4 decompression inplace is only safe if zero_padding is enabled */ + if (erofs_sb_has_zero_padding(EROFS_SB(rq->sb))) { + support_0padding = true; + ret = z_erofs_fixup_insize(rq, headpage + rq->pageofs_in, + min_t(unsigned int, rq->inputsize, + EROFS_BLKSIZ - rq->pageofs_in)); + if (ret) { + kunmap_atomic(headpage); + return ret; } + may_inplace = !((rq->pageofs_in + rq->inputsize) & + (EROFS_BLKSIZ - 1)); } - copied = false; - inlen = rq->inputsize - inputmargin; - if (rq->inplace_io) { - const uint oend = (rq->pageofs_out + - rq->outputsize) & ~PAGE_MASK; - const uint nr = PAGE_ALIGN(rq->pageofs_out + - rq->outputsize) >> PAGE_SHIFT; - - if (rq->partial_decoding || !support_0padding || - rq->out[nr - 1] != rq->in[0] || - rq->inputsize - oend < - LZ4_DECOMPRESS_INPLACE_MARGIN(inlen)) { - src = generic_copy_inplace_data(rq, src, inputmargin); - inputmargin = 0; - copied = true; - } - } + inputmargin = rq->pageofs_in; + src = z_erofs_lz4_handle_overlap(ctx, headpage, &inputmargin, + &maptype, may_inplace); + if (IS_ERR(src)) + return PTR_ERR(src); + + /* legacy format could compress extra data in a pcluster. */ + if (rq->partial_decoding || !support_0padding) + ret = LZ4_decompress_safe_partial(src + inputmargin, out, + rq->inputsize, rq->outputsize, rq->outputsize); + else + ret = LZ4_decompress_safe(src + inputmargin, out, + rq->inputsize, rq->outputsize); + + if (ret != rq->outputsize) { + erofs_err(rq->sb, "failed to decompress %d in[%u, %u] out[%u]", + ret, rq->inputsize, inputmargin, rq->outputsize); - ret = LZ4_decompress_safe_partial(src + inputmargin, out, - inlen, rq->outputsize, - rq->outputsize); - if (ret < 0) { - erofs_err(rq->sb, "failed to decompress, in[%u, %u] out[%u]", - inlen, inputmargin, rq->outputsize); - WARN_ON(1); print_hex_dump(KERN_DEBUG, "[ in]: ", DUMP_PREFIX_OFFSET, - 16, 1, src + inputmargin, inlen, true); + 16, 1, src + inputmargin, rq->inputsize, true); print_hex_dump(KERN_DEBUG, "[out]: ", DUMP_PREFIX_OFFSET, 16, 1, out, rq->outputsize, true); + + if (ret >= 0) + memset(out + ret, 0, rq->outputsize - ret); ret = -EIO; + } else { + ret = 0; } - if (copied) + if (maptype == 0) { + kunmap_atomic(headpage); + } else if (maptype == 1) { + vm_unmap_ram(src, ctx->inpages); + } else if (maptype == 2) { erofs_put_pcpubuf(src); - else - kunmap_atomic(src); - return ret; -} - -static struct z_erofs_decompressor decompressors[] = { - [Z_EROFS_COMPRESSION_SHIFTED] = { - .name = "shifted" - }, - [Z_EROFS_COMPRESSION_LZ4] = { - .prepare_destpages = z_erofs_lz4_prepare_destpages, - .decompress = z_erofs_lz4_decompress, - .name = "lz4" - }, -}; - -static void copy_from_pcpubuf(struct page **out, const char *dst, - unsigned short pageofs_out, - unsigned int outputsize) -{ - const char *end = dst + outputsize; - const unsigned int righthalf = PAGE_SIZE - pageofs_out; - const char *cur = dst - pageofs_out; - - while (cur < end) { - struct page *const page = *out++; - - if (page) { - char *buf = kmap_atomic(page); - - if (cur >= dst) { - memcpy(buf, cur, min_t(uint, PAGE_SIZE, - end - cur)); - } else { - memcpy(buf + pageofs_out, cur + pageofs_out, - min_t(uint, righthalf, end - cur)); - } - kunmap_atomic(buf); - } - cur += PAGE_SIZE; + } else { + DBG_BUGON(1); + return -EFAULT; } + return ret; } -static int z_erofs_decompress_generic(struct z_erofs_decompress_req *rq, - struct list_head *pagepool) +static int z_erofs_lz4_decompress(struct z_erofs_decompress_req *rq, + struct page **pagepool) { - const unsigned int nrpages_out = - PAGE_ALIGN(rq->pageofs_out + rq->outputsize) >> PAGE_SHIFT; - const struct z_erofs_decompressor *alg = decompressors + rq->alg; + struct z_erofs_lz4_decompress_ctx ctx; unsigned int dst_maptype; void *dst; - int ret, i; + int ret; - if (nrpages_out == 1 && !rq->inplace_io) { + ctx.rq = rq; + ctx.oend = rq->pageofs_out + rq->outputsize; + ctx.outpages = PAGE_ALIGN(ctx.oend) >> PAGE_SHIFT; + ctx.inpages = PAGE_ALIGN(rq->inputsize) >> PAGE_SHIFT; + + /* one optimized fast path only for non bigpcluster cases yet */ + if (ctx.inpages == 1 && ctx.outpages == 1 && !rq->inplace_io) { DBG_BUGON(!*rq->out); dst = kmap_atomic(*rq->out); dst_maptype = 0; goto dstmap_out; } - /* - * For the case of small output size (especially much less - * than PAGE_SIZE), memcpy the decompressed data rather than - * compressed data is preferred. - */ - if (rq->outputsize <= PAGE_SIZE * 7 / 8) { - dst = erofs_get_pcpubuf(0); - if (IS_ERR(dst)) - return PTR_ERR(dst); - - rq->inplace_io = false; - ret = alg->decompress(rq, dst); - if (!ret) - copy_from_pcpubuf(rq->out, dst, rq->pageofs_out, - rq->outputsize); - - erofs_put_pcpubuf(dst); - return ret; - } - - ret = alg->prepare_destpages(rq, pagepool); + /* general decoding path which can be used for all cases */ + ret = z_erofs_lz4_prepare_dstpages(&ctx, pagepool); if (ret < 0) { return ret; - } else if (ret) { + } else if (ret > 0) { dst = page_address(*rq->out); dst_maptype = 1; - goto dstmap_out; + } else { + dst = erofs_vm_map_ram(rq->out, ctx.outpages); + if (!dst) + return -ENOMEM; + dst_maptype = 2; } - i = 0; - while (1) { - dst = vm_map_ram(rq->out, nrpages_out, -1, PAGE_KERNEL); - - /* retry two more times (totally 3 times) */ - if (dst || ++i >= 3) - break; - vm_unmap_aliases(); - } - - if (!dst) - return -ENOMEM; - - dst_maptype = 2; - dstmap_out: - ret = alg->decompress(rq, dst + rq->pageofs_out); - + ret = z_erofs_lz4_decompress_mem(&ctx, dst + rq->pageofs_out); if (!dst_maptype) kunmap_atomic(dst); else if (dst_maptype == 2) - vm_unmap_ram(dst, nrpages_out); + vm_unmap_ram(dst, ctx.outpages); return ret; } -static int z_erofs_shifted_transform(const struct z_erofs_decompress_req *rq, - struct list_head *pagepool) +static int z_erofs_transform_plain(struct z_erofs_decompress_req *rq, + struct page **pagepool) { - const unsigned int nrpages_out = + const unsigned int inpages = PAGE_ALIGN(rq->inputsize) >> PAGE_SHIFT; + const unsigned int outpages = PAGE_ALIGN(rq->pageofs_out + rq->outputsize) >> PAGE_SHIFT; - const unsigned int righthalf = PAGE_SIZE - rq->pageofs_out; + const unsigned int righthalf = min_t(unsigned int, rq->outputsize, + PAGE_SIZE - rq->pageofs_out); + const unsigned int lefthalf = rq->outputsize - righthalf; + const unsigned int interlaced_offset = + rq->alg == Z_EROFS_COMPRESSION_SHIFTED ? 0 : rq->pageofs_out; unsigned char *src, *dst; - if (nrpages_out > 2) { + if (outpages > 2 && rq->alg == Z_EROFS_COMPRESSION_SHIFTED) { DBG_BUGON(1); - return -EIO; + return -EFSCORRUPTED; } if (rq->out[0] == *rq->in) { - DBG_BUGON(nrpages_out != 1); + DBG_BUGON(rq->pageofs_out); return 0; } - src = kmap_atomic(*rq->in); + src = kmap_local_page(rq->in[inpages - 1]) + rq->pageofs_in; if (rq->out[0]) { - dst = kmap_atomic(rq->out[0]); - memcpy(dst + rq->pageofs_out, src, righthalf); - kunmap_atomic(dst); + dst = kmap_local_page(rq->out[0]); + memcpy(dst + rq->pageofs_out, src + interlaced_offset, + righthalf); + kunmap_local(dst); } - if (nrpages_out == 2) { - DBG_BUGON(!rq->out[1]); - if (rq->out[1] == *rq->in) { - memmove(src, src + righthalf, rq->pageofs_out); - } else { - dst = kmap_atomic(rq->out[1]); - memcpy(dst, src + righthalf, rq->pageofs_out); - kunmap_atomic(dst); + if (outpages > inpages) { + DBG_BUGON(!rq->out[outpages - 1]); + if (rq->out[outpages - 1] != rq->in[inpages - 1]) { + dst = kmap_local_page(rq->out[outpages - 1]); + memcpy(dst, interlaced_offset ? src : + (src + righthalf), lefthalf); + kunmap_local(dst); + } else if (!interlaced_offset) { + memmove(src, src + righthalf, lefthalf); } } - kunmap_atomic(src); + kunmap_local(src); return 0; } +static struct z_erofs_decompressor decompressors[] = { + [Z_EROFS_COMPRESSION_SHIFTED] = { + .decompress = z_erofs_transform_plain, + .name = "shifted" + }, + [Z_EROFS_COMPRESSION_INTERLACED] = { + .decompress = z_erofs_transform_plain, + .name = "interlaced" + }, + [Z_EROFS_COMPRESSION_LZ4] = { + .decompress = z_erofs_lz4_decompress, + .name = "lz4" + }, +#ifdef CONFIG_EROFS_FS_ZIP_LZMA + [Z_EROFS_COMPRESSION_LZMA] = { + .decompress = z_erofs_lzma_decompress, + .name = "lzma" + }, +#endif +}; + int z_erofs_decompress(struct z_erofs_decompress_req *rq, - struct list_head *pagepool) + struct page **pagepool) { - if (rq->alg == Z_EROFS_COMPRESSION_SHIFTED) - return z_erofs_shifted_transform(rq, pagepool); - return z_erofs_decompress_generic(rq, pagepool); + return decompressors[rq->alg].decompress(rq, pagepool); } - diff --git a/fs/erofs/decompressor_lzma.c b/fs/erofs/decompressor_lzma.c new file mode 100644 index 000000000000..091fd5adf818 --- /dev/null +++ b/fs/erofs/decompressor_lzma.c @@ -0,0 +1,291 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +#include <linux/xz.h> +#include <linux/module.h> +#include "compress.h" + +struct z_erofs_lzma { + struct z_erofs_lzma *next; + struct xz_dec_microlzma *state; + struct xz_buf buf; + u8 bounce[PAGE_SIZE]; +}; + +/* considering the LZMA performance, no need to use a lockless list for now */ +static DEFINE_SPINLOCK(z_erofs_lzma_lock); +static unsigned int z_erofs_lzma_max_dictsize; +static unsigned int z_erofs_lzma_nstrms, z_erofs_lzma_avail_strms; +static struct z_erofs_lzma *z_erofs_lzma_head; +static DECLARE_WAIT_QUEUE_HEAD(z_erofs_lzma_wq); + +module_param_named(lzma_streams, z_erofs_lzma_nstrms, uint, 0444); + +void z_erofs_lzma_exit(void) +{ + /* there should be no running fs instance */ + while (z_erofs_lzma_avail_strms) { + struct z_erofs_lzma *strm; + + spin_lock(&z_erofs_lzma_lock); + strm = z_erofs_lzma_head; + if (!strm) { + spin_unlock(&z_erofs_lzma_lock); + DBG_BUGON(1); + return; + } + z_erofs_lzma_head = NULL; + spin_unlock(&z_erofs_lzma_lock); + + while (strm) { + struct z_erofs_lzma *n = strm->next; + + if (strm->state) + xz_dec_microlzma_end(strm->state); + kfree(strm); + --z_erofs_lzma_avail_strms; + strm = n; + } + } +} + +int z_erofs_lzma_init(void) +{ + unsigned int i; + + /* by default, use # of possible CPUs instead */ + if (!z_erofs_lzma_nstrms) + z_erofs_lzma_nstrms = num_possible_cpus(); + + for (i = 0; i < z_erofs_lzma_nstrms; ++i) { + struct z_erofs_lzma *strm = kzalloc(sizeof(*strm), GFP_KERNEL); + + if (!strm) { + z_erofs_lzma_exit(); + return -ENOMEM; + } + spin_lock(&z_erofs_lzma_lock); + strm->next = z_erofs_lzma_head; + z_erofs_lzma_head = strm; + spin_unlock(&z_erofs_lzma_lock); + ++z_erofs_lzma_avail_strms; + } + return 0; +} + +int z_erofs_load_lzma_config(struct super_block *sb, + struct erofs_super_block *dsb, + struct z_erofs_lzma_cfgs *lzma, int size) +{ + static DEFINE_MUTEX(lzma_resize_mutex); + unsigned int dict_size, i; + struct z_erofs_lzma *strm, *head = NULL; + int err; + + if (!lzma || size < sizeof(struct z_erofs_lzma_cfgs)) { + erofs_err(sb, "invalid lzma cfgs, size=%u", size); + return -EINVAL; + } + if (lzma->format) { + erofs_err(sb, "unidentified lzma format %x, please check kernel version", + le16_to_cpu(lzma->format)); + return -EINVAL; + } + dict_size = le32_to_cpu(lzma->dict_size); + if (dict_size > Z_EROFS_LZMA_MAX_DICT_SIZE || dict_size < 4096) { + erofs_err(sb, "unsupported lzma dictionary size %u", + dict_size); + return -EINVAL; + } + + erofs_info(sb, "EXPERIMENTAL MicroLZMA in use. Use at your own risk!"); + + /* in case 2 z_erofs_load_lzma_config() race to avoid deadlock */ + mutex_lock(&lzma_resize_mutex); + + if (z_erofs_lzma_max_dictsize >= dict_size) { + mutex_unlock(&lzma_resize_mutex); + return 0; + } + + /* 1. collect/isolate all streams for the following check */ + for (i = 0; i < z_erofs_lzma_avail_strms; ++i) { + struct z_erofs_lzma *last; + +again: + spin_lock(&z_erofs_lzma_lock); + strm = z_erofs_lzma_head; + if (!strm) { + spin_unlock(&z_erofs_lzma_lock); + wait_event(z_erofs_lzma_wq, + READ_ONCE(z_erofs_lzma_head)); + goto again; + } + z_erofs_lzma_head = NULL; + spin_unlock(&z_erofs_lzma_lock); + + for (last = strm; last->next; last = last->next) + ++i; + last->next = head; + head = strm; + } + + err = 0; + /* 2. walk each isolated stream and grow max dict_size if needed */ + for (strm = head; strm; strm = strm->next) { + if (strm->state) + xz_dec_microlzma_end(strm->state); + strm->state = xz_dec_microlzma_alloc(XZ_PREALLOC, dict_size); + if (!strm->state) + err = -ENOMEM; + } + + /* 3. push back all to the global list and update max dict_size */ + spin_lock(&z_erofs_lzma_lock); + DBG_BUGON(z_erofs_lzma_head); + z_erofs_lzma_head = head; + spin_unlock(&z_erofs_lzma_lock); + wake_up_all(&z_erofs_lzma_wq); + + z_erofs_lzma_max_dictsize = dict_size; + mutex_unlock(&lzma_resize_mutex); + return err; +} + +int z_erofs_lzma_decompress(struct z_erofs_decompress_req *rq, + struct page **pagepool) +{ + const unsigned int nrpages_out = + PAGE_ALIGN(rq->pageofs_out + rq->outputsize) >> PAGE_SHIFT; + const unsigned int nrpages_in = + PAGE_ALIGN(rq->inputsize) >> PAGE_SHIFT; + unsigned int inlen, outlen, pageofs; + struct z_erofs_lzma *strm; + u8 *kin; + bool bounced = false; + int no, ni, j, err = 0; + + /* 1. get the exact LZMA compressed size */ + kin = kmap(*rq->in); + err = z_erofs_fixup_insize(rq, kin + rq->pageofs_in, + min_t(unsigned int, rq->inputsize, + EROFS_BLKSIZ - rq->pageofs_in)); + if (err) { + kunmap(*rq->in); + return err; + } + + /* 2. get an available lzma context */ +again: + spin_lock(&z_erofs_lzma_lock); + strm = z_erofs_lzma_head; + if (!strm) { + spin_unlock(&z_erofs_lzma_lock); + wait_event(z_erofs_lzma_wq, READ_ONCE(z_erofs_lzma_head)); + goto again; + } + z_erofs_lzma_head = strm->next; + spin_unlock(&z_erofs_lzma_lock); + + /* 3. multi-call decompress */ + inlen = rq->inputsize; + outlen = rq->outputsize; + xz_dec_microlzma_reset(strm->state, inlen, outlen, + !rq->partial_decoding); + pageofs = rq->pageofs_out; + strm->buf.in = kin + rq->pageofs_in; + strm->buf.in_pos = 0; + strm->buf.in_size = min_t(u32, inlen, PAGE_SIZE - rq->pageofs_in); + inlen -= strm->buf.in_size; + strm->buf.out = NULL; + strm->buf.out_pos = 0; + strm->buf.out_size = 0; + + for (ni = 0, no = -1;;) { + enum xz_ret xz_err; + + if (strm->buf.out_pos == strm->buf.out_size) { + if (strm->buf.out) { + kunmap(rq->out[no]); + strm->buf.out = NULL; + } + + if (++no >= nrpages_out || !outlen) { + erofs_err(rq->sb, "decompressed buf out of bound"); + err = -EFSCORRUPTED; + break; + } + strm->buf.out_pos = 0; + strm->buf.out_size = min_t(u32, outlen, + PAGE_SIZE - pageofs); + outlen -= strm->buf.out_size; + if (!rq->out[no] && rq->fillgaps) /* deduped */ + rq->out[no] = erofs_allocpage(pagepool, + GFP_KERNEL | __GFP_NOFAIL); + if (rq->out[no]) + strm->buf.out = kmap(rq->out[no]) + pageofs; + pageofs = 0; + } else if (strm->buf.in_pos == strm->buf.in_size) { + kunmap(rq->in[ni]); + + if (++ni >= nrpages_in || !inlen) { + erofs_err(rq->sb, "compressed buf out of bound"); + err = -EFSCORRUPTED; + break; + } + strm->buf.in_pos = 0; + strm->buf.in_size = min_t(u32, inlen, PAGE_SIZE); + inlen -= strm->buf.in_size; + kin = kmap(rq->in[ni]); + strm->buf.in = kin; + bounced = false; + } + + /* + * Handle overlapping: Use bounced buffer if the compressed + * data is under processing; Otherwise, Use short-lived pages + * from the on-stack pagepool where pages share with the same + * request. + */ + if (!bounced && rq->out[no] == rq->in[ni]) { + memcpy(strm->bounce, strm->buf.in, strm->buf.in_size); + strm->buf.in = strm->bounce; + bounced = true; + } + for (j = ni + 1; j < nrpages_in; ++j) { + struct page *tmppage; + + if (rq->out[no] != rq->in[j]) + continue; + + DBG_BUGON(erofs_page_is_managed(EROFS_SB(rq->sb), + rq->in[j])); + tmppage = erofs_allocpage(pagepool, + GFP_KERNEL | __GFP_NOFAIL); + set_page_private(tmppage, Z_EROFS_SHORTLIVED_PAGE); + copy_highpage(tmppage, rq->in[j]); + rq->in[j] = tmppage; + } + xz_err = xz_dec_microlzma_run(strm->state, &strm->buf); + DBG_BUGON(strm->buf.out_pos > strm->buf.out_size); + DBG_BUGON(strm->buf.in_pos > strm->buf.in_size); + + if (xz_err != XZ_OK) { + if (xz_err == XZ_STREAM_END && !outlen) + break; + erofs_err(rq->sb, "failed to decompress %d in[%u] out[%u]", + xz_err, rq->inputsize, rq->outputsize); + err = -EFSCORRUPTED; + break; + } + } + if (no < nrpages_out && strm->buf.out) + kunmap(rq->in[no]); + if (ni < nrpages_in) + kunmap(rq->in[ni]); + /* 4. push back LZMA stream context to the global list */ + spin_lock(&z_erofs_lzma_lock); + strm->next = z_erofs_lzma_head; + z_erofs_lzma_head = strm; + spin_unlock(&z_erofs_lzma_lock); + wake_up(&z_erofs_lzma_wq); + return err; +} diff --git a/fs/erofs/dir.c b/fs/erofs/dir.c index d28c623dfef9..ecf28f66b97d 100644 --- a/fs/erofs/dir.c +++ b/fs/erofs/dir.c @@ -1,8 +1,8 @@ // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2017-2018 HUAWEI, Inc. - * http://www.huawei.com/ - * Created by Gao Xiang <gaoxiang25@huawei.com> + * https://www.huawei.com/ + * Copyright (C) 2022, Alibaba Cloud */ #include "internal.h" @@ -22,10 +22,9 @@ static void debug_one_dentry(unsigned char d_type, const char *de_name, } static int erofs_fill_dentries(struct inode *dir, struct dir_context *ctx, - void *dentry_blk, unsigned int *ofs, + void *dentry_blk, struct erofs_dirent *de, unsigned int nameoff, unsigned int maxsize) { - struct erofs_dirent *de = dentry_blk + *ofs; const struct erofs_dirent *end = dentry_blk + nameoff; while (de < end) { @@ -59,16 +58,15 @@ static int erofs_fill_dentries(struct inode *dir, struct dir_context *ctx, /* stopped by some reason */ return 1; ++de; - *ofs += sizeof(struct erofs_dirent); + ctx->pos += sizeof(struct erofs_dirent); } - *ofs = maxsize; return 0; } static int erofs_readdir(struct file *f, struct dir_context *ctx) { struct inode *dir = file_inode(f); - struct address_space *mapping = dir->i_mapping; + struct erofs_buf buf = __EROFS_BUF_INITIALIZER; const size_t dirsize = i_size_read(dir); unsigned int i = ctx->pos / EROFS_BLKSIZ; unsigned int ofs = ctx->pos % EROFS_BLKSIZ; @@ -76,61 +74,51 @@ static int erofs_readdir(struct file *f, struct dir_context *ctx) bool initial = true; while (ctx->pos < dirsize) { - struct page *dentry_page; struct erofs_dirent *de; unsigned int nameoff, maxsize; - dentry_page = read_mapping_page(mapping, i, NULL); - if (dentry_page == ERR_PTR(-ENOMEM)) { - err = -ENOMEM; - break; - } else if (IS_ERR(dentry_page)) { + de = erofs_bread(&buf, dir, i, EROFS_KMAP); + if (IS_ERR(de)) { erofs_err(dir->i_sb, "fail to readdir of logical block %u of nid %llu", i, EROFS_I(dir)->nid); - err = -EFSCORRUPTED; + err = PTR_ERR(de); break; } - de = (struct erofs_dirent *)kmap(dentry_page); - nameoff = le16_to_cpu(de->nameoff); - if (nameoff < sizeof(struct erofs_dirent) || - nameoff >= PAGE_SIZE) { + nameoff >= EROFS_BLKSIZ) { erofs_err(dir->i_sb, "invalid de[0].nameoff %u @ nid %llu", nameoff, EROFS_I(dir)->nid); err = -EFSCORRUPTED; - goto skip_this; + break; } maxsize = min_t(unsigned int, - dirsize - ctx->pos + ofs, PAGE_SIZE); + dirsize - ctx->pos + ofs, EROFS_BLKSIZ); /* search dirents at the arbitrary position */ if (initial) { initial = false; ofs = roundup(ofs, sizeof(struct erofs_dirent)); + ctx->pos = blknr_to_addr(i) + ofs; if (ofs >= nameoff) goto skip_this; } - err = erofs_fill_dentries(dir, ctx, de, &ofs, + err = erofs_fill_dentries(dir, ctx, de, (void *)de + ofs, nameoff, maxsize); -skip_this: - kunmap(dentry_page); - - put_page(dentry_page); - - ctx->pos = blknr_to_addr(i) + ofs; - if (err) break; +skip_this: + ctx->pos = blknr_to_addr(i) + maxsize; ++i; ofs = 0; } + erofs_put_metabuf(&buf); return err < 0 ? err : 0; } @@ -139,4 +127,3 @@ const struct file_operations erofs_dir_fops = { .read = generic_read_dir, .iterate_shared = erofs_readdir, }; - diff --git a/fs/erofs/erofs_fs.h b/fs/erofs/erofs_fs.h index 385fa49c7749..dbcd24371002 100644 --- a/fs/erofs/erofs_fs.h +++ b/fs/erofs/erofs_fs.h @@ -3,8 +3,8 @@ * EROFS (Enhanced ROM File System) on-disk format definition * * Copyright (C) 2017-2018 HUAWEI, Inc. - * http://www.huawei.com/ - * Created by Gao Xiang <gaoxiang25@huawei.com> + * https://www.huawei.com/ + * Copyright (C) 2021, Alibaba Cloud */ #ifndef __EROFS_FS_H #define __EROFS_FS_H @@ -12,53 +12,94 @@ #define EROFS_SUPER_OFFSET 1024 #define EROFS_FEATURE_COMPAT_SB_CHKSUM 0x00000001 +#define EROFS_FEATURE_COMPAT_MTIME 0x00000002 /* * Any bits that aren't in EROFS_ALL_FEATURE_INCOMPAT should * be incompatible with this kernel version. */ -#define EROFS_FEATURE_INCOMPAT_LZ4_0PADDING 0x00000001 -#define EROFS_ALL_FEATURE_INCOMPAT EROFS_FEATURE_INCOMPAT_LZ4_0PADDING +#define EROFS_FEATURE_INCOMPAT_ZERO_PADDING 0x00000001 +#define EROFS_FEATURE_INCOMPAT_COMPR_CFGS 0x00000002 +#define EROFS_FEATURE_INCOMPAT_BIG_PCLUSTER 0x00000002 +#define EROFS_FEATURE_INCOMPAT_CHUNKED_FILE 0x00000004 +#define EROFS_FEATURE_INCOMPAT_DEVICE_TABLE 0x00000008 +#define EROFS_FEATURE_INCOMPAT_COMPR_HEAD2 0x00000008 +#define EROFS_FEATURE_INCOMPAT_ZTAILPACKING 0x00000010 +#define EROFS_FEATURE_INCOMPAT_FRAGMENTS 0x00000020 +#define EROFS_FEATURE_INCOMPAT_DEDUPE 0x00000020 +#define EROFS_ALL_FEATURE_INCOMPAT \ + (EROFS_FEATURE_INCOMPAT_ZERO_PADDING | \ + EROFS_FEATURE_INCOMPAT_COMPR_CFGS | \ + EROFS_FEATURE_INCOMPAT_BIG_PCLUSTER | \ + EROFS_FEATURE_INCOMPAT_CHUNKED_FILE | \ + EROFS_FEATURE_INCOMPAT_DEVICE_TABLE | \ + EROFS_FEATURE_INCOMPAT_COMPR_HEAD2 | \ + EROFS_FEATURE_INCOMPAT_ZTAILPACKING | \ + EROFS_FEATURE_INCOMPAT_FRAGMENTS | \ + EROFS_FEATURE_INCOMPAT_DEDUPE) + +#define EROFS_SB_EXTSLOT_SIZE 16 + +struct erofs_deviceslot { + u8 tag[64]; /* digest(sha256), etc. */ + __le32 blocks; /* total fs blocks of this device */ + __le32 mapped_blkaddr; /* map starting at mapped_blkaddr */ + u8 reserved[56]; +}; +#define EROFS_DEVT_SLOT_SIZE sizeof(struct erofs_deviceslot) -/* 128-byte erofs on-disk super block */ +/* erofs on-disk super block (currently 128 bytes) */ struct erofs_super_block { __le32 magic; /* file system magic number */ __le32 checksum; /* crc32c(super_block) */ __le32 feature_compat; __u8 blkszbits; /* support block_size == PAGE_SIZE only */ - __u8 reserved; + __u8 sb_extslots; /* superblock size = 128 + sb_extslots * 16 */ __le16 root_nid; /* nid of root directory */ __le64 inos; /* total valid ino # (== f_files - f_favail) */ - __le64 build_time; /* inode v1 time derivation */ - __le32 build_time_nsec; /* inode v1 time derivation in nano scale */ + __le64 build_time; /* compact inode time derivation */ + __le32 build_time_nsec; /* compact inode time derivation in ns scale */ __le32 blocks; /* used for statfs */ __le32 meta_blkaddr; /* start block address of metadata area */ __le32 xattr_blkaddr; /* start block address of shared xattr area */ __u8 uuid[16]; /* 128-bit uuid for volume */ __u8 volume_name[16]; /* volume name */ __le32 feature_incompat; - __u8 reserved2[44]; + union { + /* bitmap for available compression algorithms */ + __le16 available_compr_algs; + /* customized sliding window size instead of 64k by default */ + __le16 lz4_max_distance; + } __packed u1; + __le16 extra_devices; /* # of devices besides the primary device */ + __le16 devt_slotoff; /* startoff = devt_slotoff * devt_slotsize */ + __u8 reserved[6]; + __le64 packed_nid; /* nid of the special packed inode */ + __u8 reserved2[24]; }; /* * erofs inode datalayout (i_format in on-disk inode): - * 0 - inode plain without inline data A: + * 0 - uncompressed flat inode without tail-packing inline data: * inode, [xattrs], ... | ... | no-holed data - * 1 - inode VLE compression B (legacy): - * inode, [xattrs], extents ... | ... - * 2 - inode plain with inline data C: - * inode, [xattrs], last_inline_data, ... | ... | no-holed data - * 3 - inode compression D: + * 1 - compressed inode with non-compact indexes: + * inode, [xattrs], [map_header], extents ... | ... + * 2 - uncompressed flat inode with tail-packing inline data: + * inode, [xattrs], tailpacking data, ... | ... | no-holed data + * 3 - compressed inode with compact indexes: * inode, [xattrs], map_header, extents ... | ... - * 4~7 - reserved + * 4 - chunk-based inode with (optional) multi-device support: + * inode, [xattrs], chunk indexes ... | ... + * 5~7 - reserved */ enum { EROFS_INODE_FLAT_PLAIN = 0, EROFS_INODE_FLAT_COMPRESSION_LEGACY = 1, EROFS_INODE_FLAT_INLINE = 2, EROFS_INODE_FLAT_COMPRESSION = 3, + EROFS_INODE_CHUNK_BASED = 4, EROFS_INODE_DATALAYOUT_MAX }; @@ -68,13 +109,29 @@ static inline bool erofs_inode_is_data_compressed(unsigned int datamode) datamode == EROFS_INODE_FLAT_COMPRESSION_LEGACY; } -/* bit definitions of inode i_advise */ +/* bit definitions of inode i_format */ #define EROFS_I_VERSION_BITS 1 #define EROFS_I_DATALAYOUT_BITS 3 #define EROFS_I_VERSION_BIT 0 #define EROFS_I_DATALAYOUT_BIT 1 +#define EROFS_I_ALL \ + ((1 << (EROFS_I_DATALAYOUT_BIT + EROFS_I_DATALAYOUT_BITS)) - 1) + +/* indicate chunk blkbits, thus 'chunksize = blocksize << chunk blkbits' */ +#define EROFS_CHUNK_FORMAT_BLKBITS_MASK 0x001F +/* with chunk indexes or just a 4-byte blkaddr array */ +#define EROFS_CHUNK_FORMAT_INDEXES 0x0020 + +#define EROFS_CHUNK_FORMAT_ALL \ + (EROFS_CHUNK_FORMAT_BLKBITS_MASK | EROFS_CHUNK_FORMAT_INDEXES) + +struct erofs_inode_chunk_info { + __le16 format; /* chunk blkbits, etc. */ + __le16 reserved; +}; + /* 32-byte reduced form of an ondisk inode */ struct erofs_inode_compact { __le16 i_format; /* inode format hints */ @@ -86,12 +143,16 @@ struct erofs_inode_compact { __le32 i_size; __le32 i_reserved; union { - /* file total compressed blocks for data mapping 1 */ + /* total compressed blocks for compressed inodes */ __le32 compressed_blocks; + /* block address for uncompressed flat inodes */ __le32 raw_blkaddr; /* for device files, used to indicate old/new device # */ __le32 rdev; + + /* for chunk-based files, it contains the summary info */ + struct erofs_inode_chunk_info c; } i_u; __le32 i_ino; /* only used for 32-bit stat compatibility */ __le16 i_uid; @@ -99,9 +160,9 @@ struct erofs_inode_compact { __le32 i_reserved2; }; -/* 32 bytes on-disk inode */ +/* 32-byte on-disk inode */ #define EROFS_INODE_LAYOUT_COMPACT 0 -/* 64 bytes on-disk inode */ +/* 64-byte on-disk inode */ #define EROFS_INODE_LAYOUT_EXTENDED 1 /* 64-byte complete form of an ondisk inode */ @@ -114,12 +175,16 @@ struct erofs_inode_extended { __le16 i_reserved; __le64 i_size; union { - /* file total compressed blocks for data mapping 1 */ + /* total compressed blocks for compressed inodes */ __le32 compressed_blocks; + /* block address for uncompressed flat inodes */ __le32 raw_blkaddr; /* for device files, used to indicate old/new device # */ __le32 rdev; + + /* for chunk-based files, it contains the summary info */ + struct erofs_inode_chunk_info c; } i_u; /* only used for 32-bit stat compatibility */ @@ -127,8 +192,8 @@ struct erofs_inode_extended { __le32 i_uid; __le32 i_gid; - __le64 i_ctime; - __le32 i_ctime_nsec; + __le64 i_mtime; + __le32 i_mtime_nsec; __le32 i_nlink; __u8 i_reserved2[16]; }; @@ -152,7 +217,7 @@ struct erofs_xattr_ibody_header { __le32 h_reserved; __u8 h_shared_count; __u8 h_reserved2[7]; - __le32 h_shared_xattrs[0]; /* shared xattr id array */ + __le32 h_shared_xattrs[]; /* shared xattr id array */ }; /* Name indexes */ @@ -169,7 +234,7 @@ struct erofs_xattr_entry { __u8 e_name_index; /* attribute name index */ __le16 e_value_size; /* size of attribute value */ /* followed by e_name and e_value */ - char e_name[0]; /* attribute name */ + char e_name[]; /* attribute name */ }; static inline unsigned int erofs_xattr_ibody_size(__le16 i_xattr_icount) @@ -189,23 +254,74 @@ static inline unsigned int erofs_xattr_entry_size(struct erofs_xattr_entry *e) e->e_name_len + le16_to_cpu(e->e_value_size)); } +/* represent a zeroed chunk (hole) */ +#define EROFS_NULL_ADDR -1 + +/* 4-byte block address array */ +#define EROFS_BLOCK_MAP_ENTRY_SIZE sizeof(__le32) + +/* 8-byte inode chunk indexes */ +struct erofs_inode_chunk_index { + __le16 advise; /* always 0, don't care for now */ + __le16 device_id; /* back-end storage id (with bits masked) */ + __le32 blkaddr; /* start block address of this inode chunk */ +}; + +/* maximum supported size of a physical compression cluster */ +#define Z_EROFS_PCLUSTER_MAX_SIZE (1024 * 1024) + /* available compression algorithm types (for h_algorithmtype) */ enum { - Z_EROFS_COMPRESSION_LZ4 = 0, + Z_EROFS_COMPRESSION_LZ4 = 0, + Z_EROFS_COMPRESSION_LZMA = 1, Z_EROFS_COMPRESSION_MAX }; +#define Z_EROFS_ALL_COMPR_ALGS ((1 << Z_EROFS_COMPRESSION_MAX) - 1) + +/* 14 bytes (+ length field = 16 bytes) */ +struct z_erofs_lz4_cfgs { + __le16 max_distance; + __le16 max_pclusterblks; + u8 reserved[10]; +} __packed; + +/* 14 bytes (+ length field = 16 bytes) */ +struct z_erofs_lzma_cfgs { + __le32 dict_size; + __le16 format; + u8 reserved[8]; +} __packed; + +#define Z_EROFS_LZMA_MAX_DICT_SIZE (8 * Z_EROFS_PCLUSTER_MAX_SIZE) /* * bit 0 : COMPACTED_2B indexes (0 - off; 1 - on) * e.g. for 4k logical cluster size, 4B if compacted 2B is off; * (4B) + 2B + (4B) if compacted 2B is on. + * bit 1 : HEAD1 big pcluster (0 - off; 1 - on) + * bit 2 : HEAD2 big pcluster (0 - off; 1 - on) + * bit 3 : tailpacking inline pcluster (0 - off; 1 - on) + * bit 4 : interlaced plain pcluster (0 - off; 1 - on) + * bit 5 : fragment pcluster (0 - off; 1 - on) */ -#define Z_EROFS_ADVISE_COMPACTED_2B_BIT 0 - -#define Z_EROFS_ADVISE_COMPACTED_2B (1 << Z_EROFS_ADVISE_COMPACTED_2B_BIT) - +#define Z_EROFS_ADVISE_COMPACTED_2B 0x0001 +#define Z_EROFS_ADVISE_BIG_PCLUSTER_1 0x0002 +#define Z_EROFS_ADVISE_BIG_PCLUSTER_2 0x0004 +#define Z_EROFS_ADVISE_INLINE_PCLUSTER 0x0008 +#define Z_EROFS_ADVISE_INTERLACED_PCLUSTER 0x0010 +#define Z_EROFS_ADVISE_FRAGMENT_PCLUSTER 0x0020 + +#define Z_EROFS_FRAGMENT_INODE_BIT 7 struct z_erofs_map_header { - __le32 h_reserved1; + union { + /* fragment data offset in the packed inode */ + __le32 h_fragmentoff; + struct { + __le16 h_reserved1; + /* indicates the encoded size of tailpacking data */ + __le16 h_idata_size; + }; + }; __le16 h_advise; /* * bit 0-3 : algorithm type of head 1 (logical cluster type 01); @@ -214,9 +330,8 @@ struct z_erofs_map_header { __u8 h_algorithmtype; /* * bit 0-2 : logical cluster bits - 12, e.g. 0 for 4096; - * bit 3-4 : (physical - logical) cluster bits of head 1: - * For example, if logical clustersize = 4096, 1 for 8192. - * bit 5-7 : (physical - logical) cluster bits of head 2. + * bit 3-6 : reserved; + * bit 7 : move the whole file into packed inode or not. */ __u8 h_clusterbits; }; @@ -224,54 +339,62 @@ struct z_erofs_map_header { #define Z_EROFS_VLE_LEGACY_HEADER_PADDING 8 /* - * Fixed-sized output compression ondisk Logical Extent cluster type: - * 0 - literal (uncompressed) cluster - * 1 - compressed cluster (for the head logical cluster) - * 2 - compressed cluster (for the other logical clusters) + * Fixed-sized output compression on-disk logical cluster type: + * 0 - literal (uncompressed) lcluster + * 1,3 - compressed lcluster (for HEAD lclusters) + * 2 - compressed lcluster (for NONHEAD lclusters) * * In detail, - * 0 - literal (uncompressed) cluster, + * 0 - literal (uncompressed) lcluster, * di_advise = 0 - * di_clusterofs = the literal data offset of the cluster - * di_blkaddr = the blkaddr of the literal cluster + * di_clusterofs = the literal data offset of the lcluster + * di_blkaddr = the blkaddr of the literal pcluster * - * 1 - compressed cluster (for the head logical cluster) - * di_advise = 1 - * di_clusterofs = the decompressed data offset of the cluster - * di_blkaddr = the blkaddr of the compressed cluster + * 1,3 - compressed lcluster (for HEAD lclusters) + * di_advise = 1 or 3 + * di_clusterofs = the decompressed data offset of the lcluster + * di_blkaddr = the blkaddr of the compressed pcluster * - * 2 - compressed cluster (for the other logical clusters) + * 2 - compressed lcluster (for NONHEAD lclusters) * di_advise = 2 * di_clusterofs = - * the decompressed data offset in its own head cluster - * di_u.delta[0] = distance to its corresponding head cluster - * di_u.delta[1] = distance to its corresponding tail cluster - * (di_advise could be 0, 1 or 2) + * the decompressed data offset in its own HEAD lcluster + * di_u.delta[0] = distance to this HEAD lcluster + * di_u.delta[1] = distance to the next HEAD lcluster */ enum { Z_EROFS_VLE_CLUSTER_TYPE_PLAIN = 0, - Z_EROFS_VLE_CLUSTER_TYPE_HEAD = 1, + Z_EROFS_VLE_CLUSTER_TYPE_HEAD1 = 1, Z_EROFS_VLE_CLUSTER_TYPE_NONHEAD = 2, - Z_EROFS_VLE_CLUSTER_TYPE_RESERVED = 3, + Z_EROFS_VLE_CLUSTER_TYPE_HEAD2 = 3, Z_EROFS_VLE_CLUSTER_TYPE_MAX }; #define Z_EROFS_VLE_DI_CLUSTER_TYPE_BITS 2 #define Z_EROFS_VLE_DI_CLUSTER_TYPE_BIT 0 +/* (noncompact only, HEAD) This pcluster refers to partial decompressed data */ +#define Z_EROFS_VLE_DI_PARTIAL_REF (1 << 15) + +/* + * D0_CBLKCNT will be marked _only_ at the 1st non-head lcluster to store the + * compressed block count of a compressed extent (in logical clusters, aka. + * block count of a pcluster). + */ +#define Z_EROFS_VLE_DI_D0_CBLKCNT (1 << 11) + struct z_erofs_vle_decompressed_index { __le16 di_advise; - /* where to decompress in the head cluster */ + /* where to decompress in the head lcluster */ __le16 di_clusterofs; union { - /* for the head cluster */ + /* for the HEAD lclusters */ __le32 blkaddr; /* - * for the rest clusters - * eg. for 4k page-sized cluster, maximum 4K*64k = 256M) - * [0] - pointing to the head cluster - * [1] - pointing to the tail cluster + * for the NONHEAD lclusters + * [0] - distance to its HEAD lcluster + * [1] - distance to the next HEAD lcluster */ __le16 delta[2]; } di_u; @@ -300,18 +423,30 @@ struct erofs_dirent { /* check the EROFS on-disk layout strictly at compile time */ static inline void erofs_check_ondisk_layout_definitions(void) { + const __le64 fmh = *(__le64 *)&(struct z_erofs_map_header) { + .h_clusterbits = 1 << Z_EROFS_FRAGMENT_INODE_BIT + }; + BUILD_BUG_ON(sizeof(struct erofs_super_block) != 128); BUILD_BUG_ON(sizeof(struct erofs_inode_compact) != 32); BUILD_BUG_ON(sizeof(struct erofs_inode_extended) != 64); BUILD_BUG_ON(sizeof(struct erofs_xattr_ibody_header) != 12); BUILD_BUG_ON(sizeof(struct erofs_xattr_entry) != 4); + BUILD_BUG_ON(sizeof(struct erofs_inode_chunk_info) != 4); + BUILD_BUG_ON(sizeof(struct erofs_inode_chunk_index) != 8); BUILD_BUG_ON(sizeof(struct z_erofs_map_header) != 8); BUILD_BUG_ON(sizeof(struct z_erofs_vle_decompressed_index) != 8); BUILD_BUG_ON(sizeof(struct erofs_dirent) != 12); + /* keep in sync between 2 index structures for better extendibility */ + BUILD_BUG_ON(sizeof(struct erofs_inode_chunk_index) != + sizeof(struct z_erofs_vle_decompressed_index)); + BUILD_BUG_ON(sizeof(struct erofs_deviceslot) != 128); BUILD_BUG_ON(BIT(Z_EROFS_VLE_DI_CLUSTER_TYPE_BITS) < Z_EROFS_VLE_CLUSTER_TYPE_MAX - 1); + /* exclude old compiler versions like gcc 7.5.0 */ + BUILD_BUG_ON(__builtin_constant_p(fmh) ? + fmh != cpu_to_le64(1ULL << 63) : 0); } #endif - diff --git a/fs/erofs/fscache.c b/fs/erofs/fscache.c new file mode 100644 index 000000000000..fe05bc51f9f2 --- /dev/null +++ b/fs/erofs/fscache.c @@ -0,0 +1,674 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Copyright (C) 2022, Alibaba Cloud + * Copyright (C) 2022, Bytedance Inc. All rights reserved. + */ +#include <linux/fscache.h> +#include "internal.h" + +static DEFINE_MUTEX(erofs_domain_list_lock); +static DEFINE_MUTEX(erofs_domain_cookies_lock); +static LIST_HEAD(erofs_domain_list); +static struct vfsmount *erofs_pseudo_mnt; + +static struct netfs_io_request *erofs_fscache_alloc_request(struct address_space *mapping, + loff_t start, size_t len) +{ + struct netfs_io_request *rreq; + + rreq = kzalloc(sizeof(struct netfs_io_request), GFP_KERNEL); + if (!rreq) + return ERR_PTR(-ENOMEM); + + rreq->start = start; + rreq->len = len; + rreq->mapping = mapping; + rreq->inode = mapping->host; + INIT_LIST_HEAD(&rreq->subrequests); + refcount_set(&rreq->ref, 1); + return rreq; +} + +static void erofs_fscache_put_request(struct netfs_io_request *rreq) +{ + if (!refcount_dec_and_test(&rreq->ref)) + return; + if (rreq->cache_resources.ops) + rreq->cache_resources.ops->end_operation(&rreq->cache_resources); + kfree(rreq); +} + +static void erofs_fscache_put_subrequest(struct netfs_io_subrequest *subreq) +{ + if (!refcount_dec_and_test(&subreq->ref)) + return; + erofs_fscache_put_request(subreq->rreq); + kfree(subreq); +} + +static void erofs_fscache_clear_subrequests(struct netfs_io_request *rreq) +{ + struct netfs_io_subrequest *subreq; + + while (!list_empty(&rreq->subrequests)) { + subreq = list_first_entry(&rreq->subrequests, + struct netfs_io_subrequest, rreq_link); + list_del(&subreq->rreq_link); + erofs_fscache_put_subrequest(subreq); + } +} + +static void erofs_fscache_rreq_unlock_folios(struct netfs_io_request *rreq) +{ + struct netfs_io_subrequest *subreq; + struct folio *folio; + unsigned int iopos = 0; + pgoff_t start_page = rreq->start / PAGE_SIZE; + pgoff_t last_page = ((rreq->start + rreq->len) / PAGE_SIZE) - 1; + bool subreq_failed = false; + + XA_STATE(xas, &rreq->mapping->i_pages, start_page); + + subreq = list_first_entry(&rreq->subrequests, + struct netfs_io_subrequest, rreq_link); + subreq_failed = (subreq->error < 0); + + rcu_read_lock(); + xas_for_each(&xas, folio, last_page) { + unsigned int pgpos = + (folio_index(folio) - start_page) * PAGE_SIZE; + unsigned int pgend = pgpos + folio_size(folio); + bool pg_failed = false; + + for (;;) { + if (!subreq) { + pg_failed = true; + break; + } + + pg_failed |= subreq_failed; + if (pgend < iopos + subreq->len) + break; + + iopos += subreq->len; + if (!list_is_last(&subreq->rreq_link, + &rreq->subrequests)) { + subreq = list_next_entry(subreq, rreq_link); + subreq_failed = (subreq->error < 0); + } else { + subreq = NULL; + subreq_failed = false; + } + if (pgend == iopos) + break; + } + + if (!pg_failed) + folio_mark_uptodate(folio); + + folio_unlock(folio); + } + rcu_read_unlock(); +} + +static void erofs_fscache_rreq_complete(struct netfs_io_request *rreq) +{ + erofs_fscache_rreq_unlock_folios(rreq); + erofs_fscache_clear_subrequests(rreq); + erofs_fscache_put_request(rreq); +} + +static void erofc_fscache_subreq_complete(void *priv, + ssize_t transferred_or_error, bool was_async) +{ + struct netfs_io_subrequest *subreq = priv; + struct netfs_io_request *rreq = subreq->rreq; + + if (IS_ERR_VALUE(transferred_or_error)) + subreq->error = transferred_or_error; + + if (atomic_dec_and_test(&rreq->nr_outstanding)) + erofs_fscache_rreq_complete(rreq); + + erofs_fscache_put_subrequest(subreq); +} + +/* + * Read data from fscache and fill the read data into page cache described by + * @rreq, which shall be both aligned with PAGE_SIZE. @pstart describes + * the start physical address in the cache file. + */ +static int erofs_fscache_read_folios_async(struct fscache_cookie *cookie, + struct netfs_io_request *rreq, loff_t pstart) +{ + enum netfs_io_source source; + struct super_block *sb = rreq->mapping->host->i_sb; + struct netfs_io_subrequest *subreq; + struct netfs_cache_resources *cres = &rreq->cache_resources; + struct iov_iter iter; + loff_t start = rreq->start; + size_t len = rreq->len; + size_t done = 0; + int ret; + + atomic_set(&rreq->nr_outstanding, 1); + + ret = fscache_begin_read_operation(cres, cookie); + if (ret) + goto out; + + while (done < len) { + subreq = kzalloc(sizeof(struct netfs_io_subrequest), + GFP_KERNEL); + if (subreq) { + INIT_LIST_HEAD(&subreq->rreq_link); + refcount_set(&subreq->ref, 2); + subreq->rreq = rreq; + refcount_inc(&rreq->ref); + } else { + ret = -ENOMEM; + goto out; + } + + subreq->start = pstart + done; + subreq->len = len - done; + subreq->flags = 1 << NETFS_SREQ_ONDEMAND; + + list_add_tail(&subreq->rreq_link, &rreq->subrequests); + + source = cres->ops->prepare_read(subreq, LLONG_MAX); + if (WARN_ON(subreq->len == 0)) + source = NETFS_INVALID_READ; + if (source != NETFS_READ_FROM_CACHE) { + erofs_err(sb, "failed to fscache prepare_read (source %d)", + source); + ret = -EIO; + subreq->error = ret; + erofs_fscache_put_subrequest(subreq); + goto out; + } + + atomic_inc(&rreq->nr_outstanding); + + iov_iter_xarray(&iter, READ, &rreq->mapping->i_pages, + start + done, subreq->len); + + ret = fscache_read(cres, subreq->start, &iter, + NETFS_READ_HOLE_FAIL, + erofc_fscache_subreq_complete, subreq); + if (ret == -EIOCBQUEUED) + ret = 0; + if (ret) { + erofs_err(sb, "failed to fscache_read (ret %d)", ret); + goto out; + } + + done += subreq->len; + } +out: + if (atomic_dec_and_test(&rreq->nr_outstanding)) + erofs_fscache_rreq_complete(rreq); + + return ret; +} + +static int erofs_fscache_meta_read_folio(struct file *data, struct folio *folio) +{ + int ret; + struct super_block *sb = folio_mapping(folio)->host->i_sb; + struct netfs_io_request *rreq; + struct erofs_map_dev mdev = { + .m_deviceid = 0, + .m_pa = folio_pos(folio), + }; + + ret = erofs_map_dev(sb, &mdev); + if (ret) + goto out; + + rreq = erofs_fscache_alloc_request(folio_mapping(folio), + folio_pos(folio), folio_size(folio)); + if (IS_ERR(rreq)) { + ret = PTR_ERR(rreq); + goto out; + } + + return erofs_fscache_read_folios_async(mdev.m_fscache->cookie, + rreq, mdev.m_pa); +out: + folio_unlock(folio); + return ret; +} + +/* + * Read into page cache in the range described by (@pos, @len). + * + * On return, the caller is responsible for page unlocking if the output @unlock + * is true, or the callee will take this responsibility through netfs_io_request + * interface. + * + * The return value is the number of bytes successfully handled, or negative + * error code on failure. The only exception is that, the length of the range + * instead of the error code is returned on failure after netfs_io_request is + * allocated, so that .readahead() could advance rac accordingly. + */ +static int erofs_fscache_data_read(struct address_space *mapping, + loff_t pos, size_t len, bool *unlock) +{ + struct inode *inode = mapping->host; + struct super_block *sb = inode->i_sb; + struct netfs_io_request *rreq; + struct erofs_map_blocks map; + struct erofs_map_dev mdev; + struct iov_iter iter; + size_t count; + int ret; + + *unlock = true; + + map.m_la = pos; + ret = erofs_map_blocks(inode, &map, EROFS_GET_BLOCKS_RAW); + if (ret) + return ret; + + if (map.m_flags & EROFS_MAP_META) { + struct erofs_buf buf = __EROFS_BUF_INITIALIZER; + erofs_blk_t blknr; + size_t offset, size; + void *src; + + /* For tail packing layout, the offset may be non-zero. */ + offset = erofs_blkoff(map.m_pa); + blknr = erofs_blknr(map.m_pa); + size = map.m_llen; + + src = erofs_read_metabuf(&buf, sb, blknr, EROFS_KMAP); + if (IS_ERR(src)) + return PTR_ERR(src); + + iov_iter_xarray(&iter, READ, &mapping->i_pages, pos, PAGE_SIZE); + if (copy_to_iter(src + offset, size, &iter) != size) + return -EFAULT; + iov_iter_zero(PAGE_SIZE - size, &iter); + erofs_put_metabuf(&buf); + return PAGE_SIZE; + } + + count = min_t(size_t, map.m_llen - (pos - map.m_la), len); + DBG_BUGON(!count || count % PAGE_SIZE); + + if (!(map.m_flags & EROFS_MAP_MAPPED)) { + iov_iter_xarray(&iter, READ, &mapping->i_pages, pos, count); + iov_iter_zero(count, &iter); + return count; + } + + mdev = (struct erofs_map_dev) { + .m_deviceid = map.m_deviceid, + .m_pa = map.m_pa, + }; + ret = erofs_map_dev(sb, &mdev); + if (ret) + return ret; + + rreq = erofs_fscache_alloc_request(mapping, pos, count); + if (IS_ERR(rreq)) + return PTR_ERR(rreq); + + *unlock = false; + erofs_fscache_read_folios_async(mdev.m_fscache->cookie, + rreq, mdev.m_pa + (pos - map.m_la)); + return count; +} + +static int erofs_fscache_read_folio(struct file *file, struct folio *folio) +{ + bool unlock; + int ret; + + DBG_BUGON(folio_size(folio) != EROFS_BLKSIZ); + + ret = erofs_fscache_data_read(folio_mapping(folio), folio_pos(folio), + folio_size(folio), &unlock); + if (unlock) { + if (ret > 0) + folio_mark_uptodate(folio); + folio_unlock(folio); + } + return ret < 0 ? ret : 0; +} + +static void erofs_fscache_readahead(struct readahead_control *rac) +{ + struct folio *folio; + size_t len, done = 0; + loff_t start, pos; + bool unlock; + int ret, size; + + if (!readahead_count(rac)) + return; + + start = readahead_pos(rac); + len = readahead_length(rac); + + do { + pos = start + done; + ret = erofs_fscache_data_read(rac->mapping, pos, + len - done, &unlock); + if (ret <= 0) + return; + + size = ret; + while (size) { + folio = readahead_folio(rac); + size -= folio_size(folio); + if (unlock) { + folio_mark_uptodate(folio); + folio_unlock(folio); + } + } + } while ((done += ret) < len); +} + +static const struct address_space_operations erofs_fscache_meta_aops = { + .read_folio = erofs_fscache_meta_read_folio, +}; + +const struct address_space_operations erofs_fscache_access_aops = { + .read_folio = erofs_fscache_read_folio, + .readahead = erofs_fscache_readahead, +}; + +static void erofs_fscache_domain_put(struct erofs_domain *domain) +{ + if (!domain) + return; + mutex_lock(&erofs_domain_list_lock); + if (refcount_dec_and_test(&domain->ref)) { + list_del(&domain->list); + if (list_empty(&erofs_domain_list)) { + kern_unmount(erofs_pseudo_mnt); + erofs_pseudo_mnt = NULL; + } + mutex_unlock(&erofs_domain_list_lock); + fscache_relinquish_volume(domain->volume, NULL, false); + kfree(domain->domain_id); + kfree(domain); + return; + } + mutex_unlock(&erofs_domain_list_lock); +} + +static int erofs_fscache_register_volume(struct super_block *sb) +{ + struct erofs_sb_info *sbi = EROFS_SB(sb); + char *domain_id = sbi->opt.domain_id; + struct fscache_volume *volume; + char *name; + int ret = 0; + + name = kasprintf(GFP_KERNEL, "erofs,%s", + domain_id ? domain_id : sbi->opt.fsid); + if (!name) + return -ENOMEM; + + volume = fscache_acquire_volume(name, NULL, NULL, 0); + if (IS_ERR_OR_NULL(volume)) { + erofs_err(sb, "failed to register volume for %s", name); + ret = volume ? PTR_ERR(volume) : -EOPNOTSUPP; + volume = NULL; + } + + sbi->volume = volume; + kfree(name); + return ret; +} + +static int erofs_fscache_init_domain(struct super_block *sb) +{ + int err; + struct erofs_domain *domain; + struct erofs_sb_info *sbi = EROFS_SB(sb); + + domain = kzalloc(sizeof(struct erofs_domain), GFP_KERNEL); + if (!domain) + return -ENOMEM; + + domain->domain_id = kstrdup(sbi->opt.domain_id, GFP_KERNEL); + if (!domain->domain_id) { + kfree(domain); + return -ENOMEM; + } + + err = erofs_fscache_register_volume(sb); + if (err) + goto out; + + if (!erofs_pseudo_mnt) { + erofs_pseudo_mnt = kern_mount(&erofs_fs_type); + if (IS_ERR(erofs_pseudo_mnt)) { + err = PTR_ERR(erofs_pseudo_mnt); + goto out; + } + } + + domain->volume = sbi->volume; + refcount_set(&domain->ref, 1); + list_add(&domain->list, &erofs_domain_list); + sbi->domain = domain; + return 0; +out: + kfree(domain->domain_id); + kfree(domain); + return err; +} + +static int erofs_fscache_register_domain(struct super_block *sb) +{ + int err; + struct erofs_domain *domain; + struct erofs_sb_info *sbi = EROFS_SB(sb); + + mutex_lock(&erofs_domain_list_lock); + list_for_each_entry(domain, &erofs_domain_list, list) { + if (!strcmp(domain->domain_id, sbi->opt.domain_id)) { + sbi->domain = domain; + sbi->volume = domain->volume; + refcount_inc(&domain->ref); + mutex_unlock(&erofs_domain_list_lock); + return 0; + } + } + err = erofs_fscache_init_domain(sb); + mutex_unlock(&erofs_domain_list_lock); + return err; +} + +static +struct erofs_fscache *erofs_fscache_acquire_cookie(struct super_block *sb, + char *name, bool need_inode) +{ + struct fscache_volume *volume = EROFS_SB(sb)->volume; + struct erofs_fscache *ctx; + struct fscache_cookie *cookie; + int ret; + + ctx = kzalloc(sizeof(*ctx), GFP_KERNEL); + if (!ctx) + return ERR_PTR(-ENOMEM); + + cookie = fscache_acquire_cookie(volume, FSCACHE_ADV_WANT_CACHE_SIZE, + name, strlen(name), NULL, 0, 0); + if (!cookie) { + erofs_err(sb, "failed to get cookie for %s", name); + ret = -EINVAL; + goto err; + } + + fscache_use_cookie(cookie, false); + ctx->cookie = cookie; + + if (need_inode) { + struct inode *const inode = new_inode(sb); + + if (!inode) { + erofs_err(sb, "failed to get anon inode for %s", name); + ret = -ENOMEM; + goto err_cookie; + } + + set_nlink(inode, 1); + inode->i_size = OFFSET_MAX; + inode->i_mapping->a_ops = &erofs_fscache_meta_aops; + mapping_set_gfp_mask(inode->i_mapping, GFP_NOFS); + + ctx->inode = inode; + } + + return ctx; + +err_cookie: + fscache_unuse_cookie(ctx->cookie, NULL, NULL); + fscache_relinquish_cookie(ctx->cookie, false); +err: + kfree(ctx); + return ERR_PTR(ret); +} + +static void erofs_fscache_relinquish_cookie(struct erofs_fscache *ctx) +{ + fscache_unuse_cookie(ctx->cookie, NULL, NULL); + fscache_relinquish_cookie(ctx->cookie, false); + iput(ctx->inode); + kfree(ctx->name); + kfree(ctx); +} + +static +struct erofs_fscache *erofs_fscache_domain_init_cookie(struct super_block *sb, + char *name, bool need_inode) +{ + int err; + struct inode *inode; + struct erofs_fscache *ctx; + struct erofs_domain *domain = EROFS_SB(sb)->domain; + + ctx = erofs_fscache_acquire_cookie(sb, name, need_inode); + if (IS_ERR(ctx)) + return ctx; + + ctx->name = kstrdup(name, GFP_KERNEL); + if (!ctx->name) { + err = -ENOMEM; + goto out; + } + + inode = new_inode(erofs_pseudo_mnt->mnt_sb); + if (!inode) { + err = -ENOMEM; + goto out; + } + + ctx->domain = domain; + ctx->anon_inode = inode; + inode->i_private = ctx; + refcount_inc(&domain->ref); + return ctx; +out: + erofs_fscache_relinquish_cookie(ctx); + return ERR_PTR(err); +} + +static +struct erofs_fscache *erofs_domain_register_cookie(struct super_block *sb, + char *name, bool need_inode) +{ + struct inode *inode; + struct erofs_fscache *ctx; + struct erofs_domain *domain = EROFS_SB(sb)->domain; + struct super_block *psb = erofs_pseudo_mnt->mnt_sb; + + mutex_lock(&erofs_domain_cookies_lock); + spin_lock(&psb->s_inode_list_lock); + list_for_each_entry(inode, &psb->s_inodes, i_sb_list) { + ctx = inode->i_private; + if (!ctx || ctx->domain != domain || strcmp(ctx->name, name)) + continue; + igrab(inode); + spin_unlock(&psb->s_inode_list_lock); + mutex_unlock(&erofs_domain_cookies_lock); + return ctx; + } + spin_unlock(&psb->s_inode_list_lock); + ctx = erofs_fscache_domain_init_cookie(sb, name, need_inode); + mutex_unlock(&erofs_domain_cookies_lock); + return ctx; +} + +struct erofs_fscache *erofs_fscache_register_cookie(struct super_block *sb, + char *name, bool need_inode) +{ + if (EROFS_SB(sb)->opt.domain_id) + return erofs_domain_register_cookie(sb, name, need_inode); + return erofs_fscache_acquire_cookie(sb, name, need_inode); +} + +void erofs_fscache_unregister_cookie(struct erofs_fscache *ctx) +{ + bool drop; + struct erofs_domain *domain; + + if (!ctx) + return; + domain = ctx->domain; + if (domain) { + mutex_lock(&erofs_domain_cookies_lock); + drop = atomic_read(&ctx->anon_inode->i_count) == 1; + iput(ctx->anon_inode); + mutex_unlock(&erofs_domain_cookies_lock); + if (!drop) + return; + } + + erofs_fscache_relinquish_cookie(ctx); + erofs_fscache_domain_put(domain); +} + +int erofs_fscache_register_fs(struct super_block *sb) +{ + int ret; + struct erofs_sb_info *sbi = EROFS_SB(sb); + struct erofs_fscache *fscache; + + if (sbi->opt.domain_id) + ret = erofs_fscache_register_domain(sb); + else + ret = erofs_fscache_register_volume(sb); + if (ret) + return ret; + + /* acquired domain/volume will be relinquished in kill_sb() on error */ + fscache = erofs_fscache_register_cookie(sb, sbi->opt.fsid, true); + if (IS_ERR(fscache)) + return PTR_ERR(fscache); + + sbi->s_fscache = fscache; + return 0; +} + +void erofs_fscache_unregister_fs(struct super_block *sb) +{ + struct erofs_sb_info *sbi = EROFS_SB(sb); + + erofs_fscache_unregister_cookie(sbi->s_fscache); + + if (sbi->domain) + erofs_fscache_domain_put(sbi->domain); + else + fscache_relinquish_volume(sbi->volume, NULL, false); + + sbi->s_fscache = NULL; + sbi->volume = NULL; + sbi->domain = NULL; +} diff --git a/fs/erofs/inode.c b/fs/erofs/inode.c index 3350ab65d892..ad2a82f2eb4c 100644 --- a/fs/erofs/inode.c +++ b/fs/erofs/inode.c @@ -1,38 +1,87 @@ // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2017-2018 HUAWEI, Inc. - * http://www.huawei.com/ - * Created by Gao Xiang <gaoxiang25@huawei.com> + * https://www.huawei.com/ + * Copyright (C) 2021, Alibaba Cloud */ #include "xattr.h" #include <trace/events/erofs.h> -/* no locking */ -static int erofs_read_inode(struct inode *inode, void *data) +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); - struct erofs_inode_compact *dic = data; - struct erofs_inode_extended *die; + const erofs_off_t inode_loc = iloc(sbi, vi->nid); - const unsigned int ifmt = le16_to_cpu(dic->i_format); - struct erofs_sb_info *sbi = EROFS_SB(inode->i_sb); - erofs_blk_t nblks = 0; + 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; - vi->datalayout = erofs_inode_datalayout(ifmt); + 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); + 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); - DBG_BUGON(1); - return -EOPNOTSUPP; + err = -EOPNOTSUPP; + goto err_out; } switch (erofs_inode_version(ifmt)) { case EROFS_INODE_LAYOUT_EXTENDED: - die = data; - vi->inode_isize = sizeof(struct erofs_inode_extended); + /* check if the extended inode acrosses block boundary */ + if (*ofs + vi->inode_isize <= EROFS_BLKSIZ) { + *ofs += vi->inode_isize; + die = (struct erofs_inode_extended *)dic; + } else { + const unsigned int gotten = EROFS_BLKSIZ - *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); @@ -58,20 +107,24 @@ static int erofs_read_inode(struct inode *inode, void *data) i_gid_write(inode, le32_to_cpu(die->i_gid)); set_nlink(inode, le32_to_cpu(die->i_nlink)); - /* ns timestamp */ - inode->i_mtime.tv_sec = inode->i_ctime.tv_sec = - le64_to_cpu(die->i_ctime); - inode->i_mtime.tv_nsec = inode->i_ctime.tv_nsec = - le32_to_cpu(die->i_ctime_nsec); + /* 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); @@ -97,39 +150,63 @@ static int erofs_read_inode(struct inode *inode, void *data) i_gid_write(inode, le16_to_cpu(dic->i_gid)); set_nlink(inode, le16_to_cpu(dic->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; + /* 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); - DBG_BUGON(1); - return -EOPNOTSUPP; + 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; + } + vi->chunkbits = LOG_BLOCK_SIZE + + (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; 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; + 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); - return -EFSCORRUPTED; + kfree(copied); + erofs_put_metabuf(buf); + return ERR_PTR(err); } -static int erofs_fill_symlink(struct inode *inode, void *data, +static int erofs_fill_symlink(struct inode *inode, void *kaddr, unsigned int m_pofs) { struct erofs_inode *vi = EROFS_I(inode); @@ -137,7 +214,7 @@ static int erofs_fill_symlink(struct inode *inode, void *data, /* if it cannot be handled with fast symlink scheme */ if (vi->datalayout != EROFS_INODE_FLAT_INLINE || - inode->i_size >= PAGE_SIZE) { + inode->i_size >= EROFS_BLKSIZ || inode->i_size < 0) { inode->i_op = &erofs_symlink_iops; return 0; } @@ -146,9 +223,9 @@ static int erofs_fill_symlink(struct inode *inode, void *data, if (!lnk) return -ENOMEM; - m_pofs += vi->inode_isize + vi->xattr_isize; - /* inline symlink data shouldn't cross page boundary as well */ - if (m_pofs + inode->i_size > PAGE_SIZE) { + m_pofs += vi->xattr_isize; + /* inline symlink data shouldn't cross block boundary */ + if (m_pofs + inode->i_size > EROFS_BLKSIZ) { kfree(lnk); erofs_err(inode->i_sb, "inline data cross block boundary @ nid %llu", @@ -156,8 +233,7 @@ static int erofs_fill_symlink(struct inode *inode, void *data, DBG_BUGON(1); return -EFSCORRUPTED; } - - memcpy(lnk, data + m_pofs, inode->i_size); + memcpy(lnk, kaddr + m_pofs, inode->i_size); lnk[inode->i_size] = '\0'; inode->i_link = lnk; @@ -165,52 +241,36 @@ static int erofs_fill_symlink(struct inode *inode, void *data, return 0; } -static int erofs_fill_inode(struct inode *inode, int isdir) +static int erofs_fill_inode(struct inode *inode) { - struct super_block *sb = inode->i_sb; struct erofs_inode *vi = EROFS_I(inode); - struct page *page; - void *data; - int err; - erofs_blk_t blkaddr; + struct erofs_buf buf = __EROFS_BUF_INITIALIZER; + void *kaddr; unsigned int ofs; - erofs_off_t inode_loc; - - trace_erofs_fill_inode(inode, isdir); - inode_loc = iloc(EROFS_SB(sb), vi->nid); - 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); + int err = 0; - page = erofs_get_meta_page(sb, blkaddr); + trace_erofs_fill_inode(inode); - if (IS_ERR(page)) { - erofs_err(sb, "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 = erofs_read_inode(inode, data + ofs); - if (err) - goto out_unlock; + /* 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; - inode->i_fop = &generic_ro_fops; + 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; break; case S_IFLNK: - err = erofs_fill_symlink(inode, data, ofs); + err = erofs_fill_symlink(inode, kaddr, ofs); if (err) goto out_unlock; inode_nohighmem(inode); @@ -228,14 +288,20 @@ static int erofs_fill_inode(struct inode *inode, int isdir) } if (erofs_inode_is_data_compressed(vi->datalayout)) { - err = z_erofs_fill_inode(inode); + if (!erofs_is_fscache_mode(inode->i_sb)) + err = z_erofs_fill_inode(inode); + else + err = -EOPNOTSUPP; goto out_unlock; } inode->i_mapping->a_ops = &erofs_raw_access_aops; +#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: - unlock_page(page); - put_page(page); + erofs_put_metabuf(&buf); return err; } @@ -258,21 +324,13 @@ static int erofs_iget_set_actor(struct inode *inode, void *opaque) return 0; } -static inline struct inode *erofs_iget_locked(struct super_block *sb, - erofs_nid_t nid) +struct inode *erofs_iget(struct super_block *sb, erofs_nid_t nid) { const unsigned long hashval = erofs_inode_hash(nid); + struct inode *inode; - return iget5_locked(sb, hashval, erofs_ilookup_test_actor, + inode = 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); @@ -282,10 +340,10 @@ struct inode *erofs_iget(struct super_block *sb, vi->nid = nid; - err = erofs_fill_inode(inode, isdir); - if (!err) + err = erofs_fill_inode(inode); + if (!err) { unlock_new_inode(inode); - else { + } else { iget_failed(inode); inode = ERR_PTR(err); } @@ -293,8 +351,9 @@ struct inode *erofs_iget(struct super_block *sb, return inode; } -int erofs_getattr(const struct path *path, struct kstat *stat, - u32 request_mask, unsigned int query_flags) +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); @@ -305,33 +364,27 @@ int erofs_getattr(const struct path *path, struct kstat *stat, stat->attributes_mask |= (STATX_ATTR_COMPRESSED | STATX_ATTR_IMMUTABLE); - generic_fillattr(inode, stat); + generic_fillattr(mnt_userns, inode, stat); return 0; } const struct inode_operations erofs_generic_iops = { .getattr = erofs_getattr, -#ifdef CONFIG_EROFS_FS_XATTR .listxattr = erofs_listxattr, -#endif .get_acl = erofs_get_acl, + .fiemap = erofs_fiemap, }; const struct inode_operations erofs_symlink_iops = { .get_link = page_get_link, .getattr = erofs_getattr, -#ifdef CONFIG_EROFS_FS_XATTR .listxattr = erofs_listxattr, -#endif .get_acl = erofs_get_acl, }; const struct inode_operations erofs_fast_symlink_iops = { .get_link = simple_get_link, .getattr = erofs_getattr, -#ifdef CONFIG_EROFS_FS_XATTR .listxattr = erofs_listxattr, -#endif .get_acl = erofs_get_acl, }; - diff --git a/fs/erofs/internal.h b/fs/erofs/internal.h index c4c6dcdc89ad..1701df48c446 100644 --- a/fs/erofs/internal.h +++ b/fs/erofs/internal.h @@ -1,8 +1,8 @@ /* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (C) 2017-2018 HUAWEI, Inc. - * http://www.huawei.com/ - * Created by Gao Xiang <gaoxiang25@huawei.com> + * https://www.huawei.com/ + * Copyright (C) 2021, Alibaba Cloud */ #ifndef __EROFS_INTERNAL_H #define __EROFS_INTERNAL_H @@ -16,6 +16,7 @@ #include <linux/magic.h> #include <linux/slab.h> #include <linux/vmalloc.h> +#include <linux/iomap.h> #include "erofs_fs.h" /* redefine pr_fmt "erofs: " */ @@ -46,35 +47,108 @@ typedef u64 erofs_off_t; /* data type for filesystem-wide blocks number */ typedef u32 erofs_blk_t; +struct erofs_device_info { + char *path; + struct erofs_fscache *fscache; + struct block_device *bdev; + struct dax_device *dax_dev; + u64 dax_part_off; + + u32 blocks; + u32 mapped_blkaddr; +}; + +enum { + EROFS_SYNC_DECOMPRESS_AUTO, + EROFS_SYNC_DECOMPRESS_FORCE_ON, + EROFS_SYNC_DECOMPRESS_FORCE_OFF +}; + +struct erofs_mount_opts { +#ifdef CONFIG_EROFS_FS_ZIP + /* current strategy of how to use managed cache */ + unsigned char cache_strategy; + /* strategy of sync decompression (0 - auto, 1 - force on, 2 - force off) */ + unsigned int sync_decompress; + + /* threshold for decompression synchronously */ + unsigned int max_sync_decompress_pages; +#endif + unsigned int mount_opt; + char *fsid; + char *domain_id; +}; + +struct erofs_dev_context { + struct idr tree; + struct rw_semaphore rwsem; + + unsigned int extra_devices; +}; + +struct erofs_fs_context { + struct erofs_mount_opts opt; + struct erofs_dev_context *devs; +}; + +/* all filesystem-wide lz4 configurations */ +struct erofs_sb_lz4_info { + /* # of pages needed for EROFS lz4 rolling decompression */ + u16 max_distance_pages; + /* maximum possible blocks for pclusters in the filesystem */ + u16 max_pclusterblks; +}; + +struct erofs_domain { + refcount_t ref; + struct list_head list; + struct fscache_volume *volume; + char *domain_id; +}; + +struct erofs_fscache { + struct fscache_cookie *cookie; + struct inode *inode; + struct inode *anon_inode; + struct erofs_domain *domain; + char *name; +}; + struct erofs_sb_info { + struct erofs_mount_opts opt; /* options */ #ifdef CONFIG_EROFS_FS_ZIP /* list for all registered superblocks, mainly for shrinker */ struct list_head list; struct mutex umount_mutex; - /* the dedicated workstation for compression */ - struct radix_tree_root workstn_tree; - - /* threshold for decompression synchronously */ - unsigned int max_sync_decompress_pages; + /* managed XArray arranged in physical block number */ + struct xarray managed_pslots; unsigned int shrinker_run_no; - - /* current strategy of how to use managed cache */ - unsigned char cache_strategy; + u16 available_compr_algs; /* pseudo inode to manage cached pages */ struct inode *managed_cache; + + struct erofs_sb_lz4_info lz4; + struct inode *packed_inode; #endif /* CONFIG_EROFS_FS_ZIP */ - u32 blocks; + struct erofs_dev_context *devs; + struct dax_device *dax_dev; + u64 dax_part_off; + u64 total_blocks; + u32 primarydevice_blocks; + u32 meta_blkaddr; #ifdef CONFIG_EROFS_FS_XATTR u32 xattr_blkaddr; #endif + u16 device_id_mask; /* valid bits of device id to be used */ /* inode slot unit size in bit shift */ unsigned char islotbits; + u32 sb_size; /* total superblock size */ u32 build_time_nsec; u64 build_time; @@ -88,7 +162,14 @@ struct erofs_sb_info { u32 feature_compat; u32 feature_incompat; - unsigned int mount_opt; + /* sysfs support */ + struct kobject s_kobj; /* /sys/fs/erofs/<devname> */ + struct completion s_kobj_unregister; + + /* fscache support */ + struct fscache_volume *volume; + struct erofs_fscache *s_fscache; + struct erofs_domain *domain; }; #define EROFS_SB(sb) ((struct erofs_sb_info *)(sb)->s_fs_info) @@ -97,12 +178,18 @@ struct erofs_sb_info { /* Mount flags set via mount options or defaults */ #define EROFS_MOUNT_XATTR_USER 0x00000010 #define EROFS_MOUNT_POSIX_ACL 0x00000020 +#define EROFS_MOUNT_DAX_ALWAYS 0x00000040 +#define EROFS_MOUNT_DAX_NEVER 0x00000080 -#define clear_opt(sbi, option) ((sbi)->mount_opt &= ~EROFS_MOUNT_##option) -#define set_opt(sbi, option) ((sbi)->mount_opt |= EROFS_MOUNT_##option) -#define test_opt(sbi, option) ((sbi)->mount_opt & EROFS_MOUNT_##option) +#define clear_opt(opt, option) ((opt)->mount_opt &= ~EROFS_MOUNT_##option) +#define set_opt(opt, option) ((opt)->mount_opt |= EROFS_MOUNT_##option) +#define test_opt(opt, option) ((opt)->mount_opt & EROFS_MOUNT_##option) + +static inline bool erofs_is_fscache_mode(struct super_block *sb) +{ + return IS_ENABLED(CONFIG_EROFS_FS_ONDEMAND) && !sb->s_bdev; +} -#ifdef CONFIG_EROFS_FS_ZIP enum { EROFS_ZIP_CACHE_DISABLED, EROFS_ZIP_CACHE_READAHEAD, @@ -120,7 +207,6 @@ struct erofs_workgroup { atomic_t refcount; }; -#if defined(CONFIG_SMP) static inline bool erofs_workgroup_try_to_freeze(struct erofs_workgroup *grp, int val) { @@ -149,41 +235,6 @@ static inline int erofs_wait_on_workgroup_freezed(struct erofs_workgroup *grp) return atomic_cond_read_relaxed(&grp->refcount, VAL != EROFS_LOCKED_MAGIC); } -#else -static inline bool erofs_workgroup_try_to_freeze(struct erofs_workgroup *grp, - int val) -{ - preempt_disable(); - /* no need to spin on UP platforms, let's just disable preemption. */ - if (val != atomic_read(&grp->refcount)) { - preempt_enable(); - return false; - } - return true; -} - -static inline void erofs_workgroup_unfreeze(struct erofs_workgroup *grp, - int orig_val) -{ - preempt_enable(); -} - -static inline int erofs_wait_on_workgroup_freezed(struct erofs_workgroup *grp) -{ - int v = atomic_read(&grp->refcount); - - /* workgroup is never freezed on uniprocessor systems */ - DBG_BUGON(v == EROFS_LOCKED_MAGIC); - return v; -} -#endif /* !CONFIG_SMP */ - -/* hard limit of pages per compressed cluster */ -#define Z_EROFS_CLUSTER_MAX_PAGES (CONFIG_EROFS_FS_CLUSTER_PAGE_LIMIT) -#define EROFS_PCPUBUF_NR_PAGES Z_EROFS_CLUSTER_MAX_PAGES -#else -#define EROFS_PCPUBUF_NR_PAGES 0 -#endif /* !CONFIG_EROFS_FS_ZIP */ /* we strictly follow PAGE_SIZE and no buffer head yet */ #define LOG_BLOCK_SIZE PAGE_SHIFT @@ -200,6 +251,19 @@ static inline int erofs_wait_on_workgroup_freezed(struct erofs_workgroup *grp) #error erofs cannot be used in this platform #endif +enum erofs_kmap_type { + EROFS_NO_KMAP, /* don't map the buffer */ + EROFS_KMAP, /* use kmap() to map the buffer */ + EROFS_KMAP_ATOMIC, /* use kmap_atomic() to map the buffer */ +}; + +struct erofs_buf { + struct page *page; + void *base; + enum erofs_kmap_type kmap_type; +}; +#define __EROFS_BUF_INITIALIZER ((struct erofs_buf){ .page = NULL }) + #define ROOT_NID(sb) ((sb)->root_nid) #define erofs_blknr(addr) ((addr) / EROFS_BLKSIZ) @@ -211,6 +275,23 @@ static inline erofs_off_t iloc(struct erofs_sb_info *sbi, erofs_nid_t nid) return blknr_to_addr(sbi->meta_blkaddr) + (nid << sbi->islotbits); } +#define EROFS_FEATURE_FUNCS(name, compat, feature) \ +static inline bool erofs_sb_has_##name(struct erofs_sb_info *sbi) \ +{ \ + return sbi->feature_##compat & EROFS_FEATURE_##feature; \ +} + +EROFS_FEATURE_FUNCS(zero_padding, incompat, INCOMPAT_ZERO_PADDING) +EROFS_FEATURE_FUNCS(compr_cfgs, incompat, INCOMPAT_COMPR_CFGS) +EROFS_FEATURE_FUNCS(big_pcluster, incompat, INCOMPAT_BIG_PCLUSTER) +EROFS_FEATURE_FUNCS(chunked_file, incompat, INCOMPAT_CHUNKED_FILE) +EROFS_FEATURE_FUNCS(device_table, incompat, INCOMPAT_DEVICE_TABLE) +EROFS_FEATURE_FUNCS(compr_head2, incompat, INCOMPAT_COMPR_HEAD2) +EROFS_FEATURE_FUNCS(ztailpacking, incompat, INCOMPAT_ZTAILPACKING) +EROFS_FEATURE_FUNCS(fragments, incompat, INCOMPAT_FRAGMENTS) +EROFS_FEATURE_FUNCS(dedupe, incompat, INCOMPAT_DEDUPE) +EROFS_FEATURE_FUNCS(sb_chksum, compat, COMPAT_SB_CHKSUM) + /* atomic flag definitions */ #define EROFS_I_EA_INITED_BIT 0 #define EROFS_I_Z_INITED_BIT 1 @@ -234,12 +315,23 @@ struct erofs_inode { union { erofs_blk_t raw_blkaddr; + struct { + unsigned short chunkformat; + unsigned char chunkbits; + }; #ifdef CONFIG_EROFS_FS_ZIP struct { unsigned short z_advise; unsigned char z_algorithmtype[2]; unsigned char z_logical_clusterbits; - unsigned char z_physical_clusterbits[2]; + unsigned long z_tailextent_headlcn; + union { + struct { + erofs_off_t z_idataoff; + unsigned short z_idata_size; + }; + erofs_off_t z_fragmentoff; + }; }; #endif /* CONFIG_EROFS_FS_ZIP */ }; @@ -276,63 +368,77 @@ static inline unsigned int erofs_inode_datalayout(unsigned int value) EROFS_I_DATALAYOUT_BITS); } +/* + * Different from grab_cache_page_nowait(), reclaiming is never triggered + * when allocating new pages. + */ +static inline +struct page *erofs_grab_cache_page_nowait(struct address_space *mapping, + pgoff_t index) +{ + return pagecache_get_page(mapping, index, + FGP_LOCK|FGP_CREAT|FGP_NOFS|FGP_NOWAIT, + readahead_gfp_mask(mapping) & ~__GFP_RECLAIM); +} + extern const struct super_operations erofs_sops; +extern struct file_system_type erofs_fs_type; extern const struct address_space_operations erofs_raw_access_aops; extern const struct address_space_operations z_erofs_aops; -/* - * Logical to physical block mapping, used by erofs_map_blocks() - * - * Different with other file systems, it is used for 2 access modes: - * - * 1) RAW access mode: - * - * Users pass a valid (m_lblk, m_lofs -- usually 0) pair, - * and get the valid m_pblk, m_pofs and the longest m_len(in bytes). - * - * Note that m_lblk in the RAW access mode refers to the number of - * the compressed ondisk block rather than the uncompressed - * in-memory block for the compressed file. - * - * m_pofs equals to m_lofs except for the inline data page. - * - * 2) Normal access mode: - * - * If the inode is not compressed, it has no difference with - * the RAW access mode. However, if the inode is compressed, - * users should pass a valid (m_lblk, m_lofs) pair, and get - * the needed m_pblk, m_pofs, m_len to get the compressed data - * and the updated m_lblk, m_lofs which indicates the start - * of the corresponding uncompressed data in the file. - */ enum { - BH_Zipped = BH_PrivateStart, + BH_Encoded = BH_PrivateStart, BH_FullMapped, + BH_Fragment, + BH_Partialref, }; /* Has a disk mapping */ #define EROFS_MAP_MAPPED (1 << BH_Mapped) /* Located in metadata (could be copied from bd_inode) */ #define EROFS_MAP_META (1 << BH_Meta) -/* The extent has been compressed */ -#define EROFS_MAP_ZIPPED (1 << BH_Zipped) +/* The extent is encoded */ +#define EROFS_MAP_ENCODED (1 << BH_Encoded) /* The length of extent is full */ #define EROFS_MAP_FULL_MAPPED (1 << BH_FullMapped) +/* Located in the special packed inode */ +#define EROFS_MAP_FRAGMENT (1 << BH_Fragment) +/* The extent refers to partial decompressed data */ +#define EROFS_MAP_PARTIAL_REF (1 << BH_Partialref) struct erofs_map_blocks { + struct erofs_buf buf; + erofs_off_t m_pa, m_la; u64 m_plen, m_llen; + unsigned short m_deviceid; + char m_algorithmformat; unsigned int m_flags; - - struct page *mpage; }; -/* Flags used by erofs_map_blocks() */ +/* Flags used by erofs_map_blocks_flatmode() */ #define EROFS_GET_BLOCKS_RAW 0x0001 +/* + * Used to get the exact decompressed length, e.g. fiemap (consider lookback + * approach instead if possible since it's more metadata lightweight.) + */ +#define EROFS_GET_BLOCKS_FIEMAP 0x0002 +/* Used to map the whole extent if non-negligible data is requested for LZMA */ +#define EROFS_GET_BLOCKS_READMORE 0x0004 +/* Used to map tail extent for tailpacking inline or fragment pcluster */ +#define EROFS_GET_BLOCKS_FINDTAIL 0x0008 + +enum { + Z_EROFS_COMPRESSION_SHIFTED = Z_EROFS_COMPRESSION_MAX, + Z_EROFS_COMPRESSION_INTERLACED, + Z_EROFS_COMPRESSION_RUNTIME_MAX +}; /* zmap.c */ +extern const struct iomap_ops z_erofs_iomap_report_ops; + #ifdef CONFIG_EROFS_FS_ZIP int z_erofs_fill_inode(struct inode *inode); int z_erofs_map_blocks_iter(struct inode *inode, @@ -348,10 +454,29 @@ static inline int z_erofs_map_blocks_iter(struct inode *inode, } #endif /* !CONFIG_EROFS_FS_ZIP */ -/* data.c */ -struct page *erofs_get_meta_page(struct super_block *sb, erofs_blk_t blkaddr); +struct erofs_map_dev { + struct erofs_fscache *m_fscache; + struct block_device *m_bdev; + struct dax_device *m_daxdev; + u64 m_dax_part_off; + + erofs_off_t m_pa; + unsigned int m_deviceid; +}; -int erofs_map_blocks(struct inode *, struct erofs_map_blocks *, int); +/* data.c */ +extern const struct file_operations erofs_file_fops; +void erofs_unmap_metabuf(struct erofs_buf *buf); +void erofs_put_metabuf(struct erofs_buf *buf); +void *erofs_bread(struct erofs_buf *buf, struct inode *inode, + erofs_blk_t blkaddr, enum erofs_kmap_type type); +void *erofs_read_metabuf(struct erofs_buf *buf, struct super_block *sb, + erofs_blk_t blkaddr, enum erofs_kmap_type type); +int erofs_map_dev(struct super_block *sb, struct erofs_map_dev *dev); +int erofs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, + u64 start, u64 len); +int erofs_map_blocks(struct inode *inode, + struct erofs_map_blocks *map, int flags); /* inode.c */ static inline unsigned long erofs_inode_hash(erofs_nid_t nid) @@ -367,43 +492,64 @@ extern const struct inode_operations erofs_generic_iops; extern const struct inode_operations erofs_symlink_iops; extern const struct inode_operations erofs_fast_symlink_iops; -struct inode *erofs_iget(struct super_block *sb, erofs_nid_t nid, bool dir); -int erofs_getattr(const struct path *path, struct kstat *stat, - u32 request_mask, unsigned int query_flags); +struct inode *erofs_iget(struct super_block *sb, erofs_nid_t nid); +int erofs_getattr(struct user_namespace *mnt_userns, const struct path *path, + struct kstat *stat, u32 request_mask, + unsigned int query_flags); /* namei.c */ extern const struct inode_operations erofs_dir_iops; -int erofs_namei(struct inode *dir, struct qstr *name, +int erofs_namei(struct inode *dir, const struct qstr *name, erofs_nid_t *nid, unsigned int *d_type); /* dir.c */ extern const struct file_operations erofs_dir_fops; -/* utils.c / zdata.c */ -struct page *erofs_allocpage(struct list_head *pool, gfp_t gfp); - -#if (EROFS_PCPUBUF_NR_PAGES > 0) -void *erofs_get_pcpubuf(unsigned int pagenr); -#define erofs_put_pcpubuf(buf) do { \ - (void)&(buf); \ - preempt_enable(); \ -} while (0) -#else -static inline void *erofs_get_pcpubuf(unsigned int pagenr) +static inline void *erofs_vm_map_ram(struct page **pages, unsigned int count) { - return ERR_PTR(-EOPNOTSUPP); + int retried = 0; + + while (1) { + void *p = vm_map_ram(pages, count, -1); + + /* retry two more times (totally 3 times) */ + if (p || ++retried >= 3) + return p; + vm_unmap_aliases(); + } + return NULL; } -#define erofs_put_pcpubuf(buf) do {} while (0) -#endif +/* pcpubuf.c */ +void *erofs_get_pcpubuf(unsigned int requiredpages); +void erofs_put_pcpubuf(void *ptr); +int erofs_pcpubuf_growsize(unsigned int nrpages); +void erofs_pcpubuf_init(void); +void erofs_pcpubuf_exit(void); + +/* sysfs.c */ +int erofs_register_sysfs(struct super_block *sb); +void erofs_unregister_sysfs(struct super_block *sb); +int __init erofs_init_sysfs(void); +void erofs_exit_sysfs(void); + +/* utils.c / zdata.c */ +struct page *erofs_allocpage(struct page **pagepool, gfp_t gfp); +static inline void erofs_pagepool_add(struct page **pagepool, + struct page *page) +{ + set_page_private(page, (unsigned long)*pagepool); + *pagepool = page; +} +void erofs_release_pages(struct page **pagepool); #ifdef CONFIG_EROFS_FS_ZIP int erofs_workgroup_put(struct erofs_workgroup *grp); struct erofs_workgroup *erofs_find_workgroup(struct super_block *sb, pgoff_t index); -int erofs_register_workgroup(struct super_block *sb, - struct erofs_workgroup *grp); +struct erofs_workgroup *erofs_insert_workgroup(struct super_block *sb, + struct erofs_workgroup *grp); void erofs_workgroup_free_rcu(struct erofs_workgroup *grp); void erofs_shrinker_register(struct super_block *sb); void erofs_shrinker_unregister(struct super_block *sb); @@ -413,8 +559,10 @@ int __init z_erofs_init_zip_subsystem(void); void z_erofs_exit_zip_subsystem(void); int erofs_try_to_free_all_cached_pages(struct erofs_sb_info *sbi, struct erofs_workgroup *egrp); -int erofs_try_to_free_cached_page(struct address_space *mapping, - struct page *page); +int erofs_try_to_free_cached_page(struct page *page); +int z_erofs_load_lz4_config(struct super_block *sb, + struct erofs_super_block *dsb, + struct z_erofs_lz4_cfgs *lz4, int len); #else static inline void erofs_shrinker_register(struct super_block *sb) {} static inline void erofs_shrinker_unregister(struct super_block *sb) {} @@ -422,9 +570,67 @@ static inline int erofs_init_shrinker(void) { return 0; } static inline void erofs_exit_shrinker(void) {} static inline int z_erofs_init_zip_subsystem(void) { return 0; } static inline void z_erofs_exit_zip_subsystem(void) {} +static inline int z_erofs_load_lz4_config(struct super_block *sb, + struct erofs_super_block *dsb, + struct z_erofs_lz4_cfgs *lz4, int len) +{ + if (lz4 || dsb->u1.lz4_max_distance) { + erofs_err(sb, "lz4 algorithm isn't enabled"); + return -EINVAL; + } + return 0; +} +#endif /* !CONFIG_EROFS_FS_ZIP */ + +#ifdef CONFIG_EROFS_FS_ZIP_LZMA +int z_erofs_lzma_init(void); +void z_erofs_lzma_exit(void); +int z_erofs_load_lzma_config(struct super_block *sb, + struct erofs_super_block *dsb, + struct z_erofs_lzma_cfgs *lzma, int size); +#else +static inline int z_erofs_lzma_init(void) { return 0; } +static inline int z_erofs_lzma_exit(void) { return 0; } +static inline int z_erofs_load_lzma_config(struct super_block *sb, + struct erofs_super_block *dsb, + struct z_erofs_lzma_cfgs *lzma, int size) { + if (lzma) { + erofs_err(sb, "lzma algorithm isn't enabled"); + return -EINVAL; + } + return 0; +} #endif /* !CONFIG_EROFS_FS_ZIP */ +/* fscache.c */ +#ifdef CONFIG_EROFS_FS_ONDEMAND +int erofs_fscache_register_fs(struct super_block *sb); +void erofs_fscache_unregister_fs(struct super_block *sb); + +struct erofs_fscache *erofs_fscache_register_cookie(struct super_block *sb, + char *name, bool need_inode); +void erofs_fscache_unregister_cookie(struct erofs_fscache *fscache); + +extern const struct address_space_operations erofs_fscache_access_aops; +#else +static inline int erofs_fscache_register_fs(struct super_block *sb) +{ + return -EOPNOTSUPP; +} +static inline void erofs_fscache_unregister_fs(struct super_block *sb) {} + +static inline +struct erofs_fscache *erofs_fscache_register_cookie(struct super_block *sb, + char *name, bool need_inode) +{ + return ERR_PTR(-EOPNOTSUPP); +} + +static inline void erofs_fscache_unregister_cookie(struct erofs_fscache *fscache) +{ +} +#endif + #define EFSCORRUPTED EUCLEAN /* Filesystem is corrupted */ #endif /* __EROFS_INTERNAL_H */ - diff --git a/fs/erofs/namei.c b/fs/erofs/namei.c index 3abbecbf73de..0dc34721080c 100644 --- a/fs/erofs/namei.c +++ b/fs/erofs/namei.c @@ -1,8 +1,8 @@ // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2017-2018 HUAWEI, Inc. - * http://www.huawei.com/ - * Created by Gao Xiang <gaoxiang25@huawei.com> + * https://www.huawei.com/ + * Copyright (C) 2022, Alibaba Cloud */ #include "xattr.h" @@ -87,14 +87,14 @@ static struct erofs_dirent *find_target_dirent(struct erofs_qstr *name, return ERR_PTR(-ENOENT); } -static struct page *find_target_block_classic(struct inode *dir, - struct erofs_qstr *name, - int *_ndirents) +static void *find_target_block_classic(struct erofs_buf *target, + struct inode *dir, + struct erofs_qstr *name, + int *_ndirents) { unsigned int startprfx, endprfx; int head, back; - struct address_space *const mapping = dir->i_mapping; - struct page *candidate = ERR_PTR(-ENOENT); + void *candidate = ERR_PTR(-ENOENT); startprfx = endprfx = 0; head = 0; @@ -102,10 +102,11 @@ static struct page *find_target_block_classic(struct inode *dir, while (head <= back) { const int mid = head + (back - head) / 2; - struct page *page = read_mapping_page(mapping, mid, NULL); + struct erofs_buf buf = __EROFS_BUF_INITIALIZER; + struct erofs_dirent *de; - if (!IS_ERR(page)) { - struct erofs_dirent *de = kmap_atomic(page); + de = erofs_bread(&buf, dir, mid, EROFS_KMAP); + if (!IS_ERR(de)) { const int nameoff = nameoff_from_disk(de->nameoff, EROFS_BLKSIZ); const int ndirents = nameoff / sizeof(*de); @@ -114,13 +115,12 @@ static struct page *find_target_block_classic(struct inode *dir, struct erofs_qstr dname; if (!ndirents) { - kunmap_atomic(de); - put_page(page); + erofs_put_metabuf(&buf); erofs_err(dir->i_sb, "corrupted dir block %d @ nid %llu", mid, EROFS_I(dir)->nid); DBG_BUGON(1); - page = ERR_PTR(-EFSCORRUPTED); + de = ERR_PTR(-EFSCORRUPTED); goto out; } @@ -136,7 +136,6 @@ static struct page *find_target_block_classic(struct inode *dir, /* string comparison without already matched prefix */ diff = erofs_dirnamecmp(name, &dname, &matched); - kunmap_atomic(de); if (!diff) { *_ndirents = 0; @@ -146,11 +145,12 @@ static struct page *find_target_block_classic(struct inode *dir, startprfx = matched; if (!IS_ERR(candidate)) - put_page(candidate); - candidate = page; + erofs_put_metabuf(target); + *target = buf; + candidate = de; *_ndirents = ndirents; } else { - put_page(page); + erofs_put_metabuf(&buf); back = mid - 1; endprfx = matched; @@ -159,19 +159,17 @@ static struct page *find_target_block_classic(struct inode *dir, } out: /* free if the candidate is valid */ if (!IS_ERR(candidate)) - put_page(candidate); - return page; + erofs_put_metabuf(target); + return de; } return candidate; } -int erofs_namei(struct inode *dir, - struct qstr *name, - erofs_nid_t *nid, unsigned int *d_type) +int erofs_namei(struct inode *dir, const struct qstr *name, erofs_nid_t *nid, + unsigned int *d_type) { int ndirents; - struct page *page; - void *data; + struct erofs_buf buf = __EROFS_BUF_INITIALIZER; struct erofs_dirent *de; struct erofs_qstr qn; @@ -182,32 +180,23 @@ int erofs_namei(struct inode *dir, qn.end = name->name + name->len; ndirents = 0; - page = find_target_block_classic(dir, &qn, &ndirents); - if (IS_ERR(page)) - return PTR_ERR(page); + de = find_target_block_classic(&buf, dir, &qn, &ndirents); + if (IS_ERR(de)) + return PTR_ERR(de); - data = kmap_atomic(page); - /* the target page has been mapped */ if (ndirents) - de = find_target_dirent(&qn, data, EROFS_BLKSIZ, ndirents); - else - de = (struct erofs_dirent *)data; + de = find_target_dirent(&qn, (u8 *)de, EROFS_BLKSIZ, ndirents); if (!IS_ERR(de)) { *nid = le64_to_cpu(de->nid); *d_type = de->file_type; } - - kunmap_atomic(data); - put_page(page); - + erofs_put_metabuf(&buf); return PTR_ERR_OR_ZERO(de); } -/* NOTE: i_mutex is already held by vfs */ -static struct dentry *erofs_lookup(struct inode *dir, - struct dentry *dentry, +static struct dentry *erofs_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) { int err; @@ -215,17 +204,11 @@ static struct dentry *erofs_lookup(struct inode *dir, unsigned int d_type; struct inode *inode; - DBG_BUGON(!d_really_is_negative(dentry)); - /* dentry must be unhashed in lookup, no need to worry about */ - DBG_BUGON(!d_unhashed(dentry)); - trace_erofs_lookup(dir, dentry, flags); - /* file name exceeds fs limit */ if (dentry->d_name.len > EROFS_NAME_LEN) return ERR_PTR(-ENAMETOOLONG); - /* false uninitialized warnings on gcc 4.8.x */ err = erofs_namei(dir, &dentry->d_name, &nid, &d_type); if (err == -ENOENT) { @@ -234,9 +217,9 @@ static struct dentry *erofs_lookup(struct inode *dir, } else if (err) { inode = ERR_PTR(err); } else { - erofs_dbg("%s, %s (nid %llu) found, d_type %u", __func__, - dentry->d_name.name, nid, d_type); - inode = erofs_iget(dir->i_sb, nid, d_type == FT_DIR); + erofs_dbg("%s, %pd (nid %llu) found, d_type %u", __func__, + dentry, nid, d_type); + inode = erofs_iget(dir->i_sb, nid); } return d_splice_alias(inode, dentry); } @@ -244,9 +227,7 @@ static struct dentry *erofs_lookup(struct inode *dir, const struct inode_operations erofs_dir_iops = { .lookup = erofs_lookup, .getattr = erofs_getattr, -#ifdef CONFIG_EROFS_FS_XATTR .listxattr = erofs_listxattr, -#endif .get_acl = erofs_get_acl, + .fiemap = erofs_fiemap, }; - diff --git a/fs/erofs/pcpubuf.c b/fs/erofs/pcpubuf.c new file mode 100644 index 000000000000..a2efd833d1b6 --- /dev/null +++ b/fs/erofs/pcpubuf.c @@ -0,0 +1,148 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) Gao Xiang <xiang@kernel.org> + * + * For low-latency decompression algorithms (e.g. lz4), reserve consecutive + * per-CPU virtual memory (in pages) in advance to store such inplace I/O + * data if inplace decompression is failed (due to unmet inplace margin for + * example). + */ +#include "internal.h" + +struct erofs_pcpubuf { + raw_spinlock_t lock; + void *ptr; + struct page **pages; + unsigned int nrpages; +}; + +static DEFINE_PER_CPU(struct erofs_pcpubuf, erofs_pcb); + +void *erofs_get_pcpubuf(unsigned int requiredpages) + __acquires(pcb->lock) +{ + struct erofs_pcpubuf *pcb = &get_cpu_var(erofs_pcb); + + raw_spin_lock(&pcb->lock); + /* check if the per-CPU buffer is too small */ + if (requiredpages > pcb->nrpages) { + raw_spin_unlock(&pcb->lock); + put_cpu_var(erofs_pcb); + /* (for sparse checker) pretend pcb->lock is still taken */ + __acquire(pcb->lock); + return NULL; + } + return pcb->ptr; +} + +void erofs_put_pcpubuf(void *ptr) __releases(pcb->lock) +{ + struct erofs_pcpubuf *pcb = &per_cpu(erofs_pcb, smp_processor_id()); + + DBG_BUGON(pcb->ptr != ptr); + raw_spin_unlock(&pcb->lock); + put_cpu_var(erofs_pcb); +} + +/* the next step: support per-CPU page buffers hotplug */ +int erofs_pcpubuf_growsize(unsigned int nrpages) +{ + static DEFINE_MUTEX(pcb_resize_mutex); + static unsigned int pcb_nrpages; + struct page *pagepool = NULL; + int delta, cpu, ret, i; + + mutex_lock(&pcb_resize_mutex); + delta = nrpages - pcb_nrpages; + ret = 0; + /* avoid shrinking pcpubuf, since no idea how many fses rely on */ + if (delta <= 0) + goto out; + + for_each_possible_cpu(cpu) { + struct erofs_pcpubuf *pcb = &per_cpu(erofs_pcb, cpu); + struct page **pages, **oldpages; + void *ptr, *old_ptr; + + pages = kmalloc_array(nrpages, sizeof(*pages), GFP_KERNEL); + if (!pages) { + ret = -ENOMEM; + break; + } + + for (i = 0; i < nrpages; ++i) { + pages[i] = erofs_allocpage(&pagepool, GFP_KERNEL); + if (!pages[i]) { + ret = -ENOMEM; + oldpages = pages; + goto free_pagearray; + } + } + ptr = vmap(pages, nrpages, VM_MAP, PAGE_KERNEL); + if (!ptr) { + ret = -ENOMEM; + oldpages = pages; + goto free_pagearray; + } + raw_spin_lock(&pcb->lock); + old_ptr = pcb->ptr; + pcb->ptr = ptr; + oldpages = pcb->pages; + pcb->pages = pages; + i = pcb->nrpages; + pcb->nrpages = nrpages; + raw_spin_unlock(&pcb->lock); + + if (!oldpages) { + DBG_BUGON(old_ptr); + continue; + } + + if (old_ptr) + vunmap(old_ptr); +free_pagearray: + while (i) + erofs_pagepool_add(&pagepool, oldpages[--i]); + kfree(oldpages); + if (ret) + break; + } + pcb_nrpages = nrpages; + erofs_release_pages(&pagepool); +out: + mutex_unlock(&pcb_resize_mutex); + return ret; +} + +void erofs_pcpubuf_init(void) +{ + int cpu; + + for_each_possible_cpu(cpu) { + struct erofs_pcpubuf *pcb = &per_cpu(erofs_pcb, cpu); + + raw_spin_lock_init(&pcb->lock); + } +} + +void erofs_pcpubuf_exit(void) +{ + int cpu, i; + + for_each_possible_cpu(cpu) { + struct erofs_pcpubuf *pcb = &per_cpu(erofs_pcb, cpu); + + if (pcb->ptr) { + vunmap(pcb->ptr); + pcb->ptr = NULL; + } + if (!pcb->pages) + continue; + + for (i = 0; i < pcb->nrpages; ++i) + if (pcb->pages[i]) + put_page(pcb->pages[i]); + kfree(pcb->pages); + pcb->pages = NULL; + } +} diff --git a/fs/erofs/super.c b/fs/erofs/super.c index 057e6d7b5b7f..2cf96ce1c32e 100644 --- a/fs/erofs/super.c +++ b/fs/erofs/super.c @@ -1,8 +1,8 @@ // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2017-2018 HUAWEI, Inc. - * http://www.huawei.com/ - * Created by Gao Xiang <gaoxiang25@huawei.com> + * https://www.huawei.com/ + * Copyright (C) 2021, Alibaba Cloud */ #include <linux/module.h> #include <linux/buffer_head.h> @@ -10,6 +10,10 @@ #include <linux/parser.h> #include <linux/seq_file.h> #include <linux/crc32c.h> +#include <linux/fs_context.h> +#include <linux/fs_parser.h> +#include <linux/dax.h> +#include <linux/exportfs.h> #include "xattr.h" #define CREATE_TRACE_POINTS @@ -81,7 +85,7 @@ static void erofs_inode_init_once(void *ptr) static struct inode *erofs_alloc_inode(struct super_block *sb) { struct erofs_inode *vi = - kmem_cache_alloc(erofs_inode_cachep, GFP_KERNEL); + alloc_inode_sb(sb, erofs_inode_cachep, GFP_KERNEL); if (!vi) return NULL; @@ -120,24 +124,223 @@ static bool check_layout_compatibility(struct super_block *sb, return true; } +#ifdef CONFIG_EROFS_FS_ZIP +/* read variable-sized metadata, offset will be aligned by 4-byte */ +static void *erofs_read_metadata(struct super_block *sb, struct erofs_buf *buf, + erofs_off_t *offset, int *lengthp) +{ + u8 *buffer, *ptr; + int len, i, cnt; + + *offset = round_up(*offset, 4); + ptr = erofs_read_metabuf(buf, sb, erofs_blknr(*offset), EROFS_KMAP); + if (IS_ERR(ptr)) + return ptr; + + len = le16_to_cpu(*(__le16 *)&ptr[erofs_blkoff(*offset)]); + if (!len) + len = U16_MAX + 1; + buffer = kmalloc(len, GFP_KERNEL); + if (!buffer) + return ERR_PTR(-ENOMEM); + *offset += sizeof(__le16); + *lengthp = len; + + for (i = 0; i < len; i += cnt) { + cnt = min(EROFS_BLKSIZ - (int)erofs_blkoff(*offset), len - i); + ptr = erofs_read_metabuf(buf, sb, erofs_blknr(*offset), + EROFS_KMAP); + if (IS_ERR(ptr)) { + kfree(buffer); + return ptr; + } + memcpy(buffer + i, ptr + erofs_blkoff(*offset), cnt); + *offset += cnt; + } + return buffer; +} + +static int erofs_load_compr_cfgs(struct super_block *sb, + struct erofs_super_block *dsb) +{ + struct erofs_sb_info *sbi = EROFS_SB(sb); + struct erofs_buf buf = __EROFS_BUF_INITIALIZER; + unsigned int algs, alg; + erofs_off_t offset; + int size, ret = 0; + + sbi->available_compr_algs = le16_to_cpu(dsb->u1.available_compr_algs); + if (sbi->available_compr_algs & ~Z_EROFS_ALL_COMPR_ALGS) { + erofs_err(sb, "try to load compressed fs with unsupported algorithms %x", + sbi->available_compr_algs & ~Z_EROFS_ALL_COMPR_ALGS); + return -EINVAL; + } + + offset = EROFS_SUPER_OFFSET + sbi->sb_size; + alg = 0; + for (algs = sbi->available_compr_algs; algs; algs >>= 1, ++alg) { + void *data; + + if (!(algs & 1)) + continue; + + data = erofs_read_metadata(sb, &buf, &offset, &size); + if (IS_ERR(data)) { + ret = PTR_ERR(data); + break; + } + + switch (alg) { + case Z_EROFS_COMPRESSION_LZ4: + ret = z_erofs_load_lz4_config(sb, dsb, data, size); + break; + case Z_EROFS_COMPRESSION_LZMA: + ret = z_erofs_load_lzma_config(sb, dsb, data, size); + break; + default: + DBG_BUGON(1); + ret = -EFAULT; + } + kfree(data); + if (ret) + break; + } + erofs_put_metabuf(&buf); + return ret; +} +#else +static int erofs_load_compr_cfgs(struct super_block *sb, + struct erofs_super_block *dsb) +{ + if (dsb->u1.available_compr_algs) { + erofs_err(sb, "try to load compressed fs when compression is disabled"); + return -EINVAL; + } + return 0; +} +#endif + +static int erofs_init_device(struct erofs_buf *buf, struct super_block *sb, + struct erofs_device_info *dif, erofs_off_t *pos) +{ + struct erofs_sb_info *sbi = EROFS_SB(sb); + struct erofs_fscache *fscache; + struct erofs_deviceslot *dis; + struct block_device *bdev; + void *ptr; + + ptr = erofs_read_metabuf(buf, sb, erofs_blknr(*pos), EROFS_KMAP); + if (IS_ERR(ptr)) + return PTR_ERR(ptr); + dis = ptr + erofs_blkoff(*pos); + + if (!dif->path) { + if (!dis->tag[0]) { + erofs_err(sb, "empty device tag @ pos %llu", *pos); + return -EINVAL; + } + dif->path = kmemdup_nul(dis->tag, sizeof(dis->tag), GFP_KERNEL); + if (!dif->path) + return -ENOMEM; + } + + if (erofs_is_fscache_mode(sb)) { + fscache = erofs_fscache_register_cookie(sb, dif->path, false); + if (IS_ERR(fscache)) + return PTR_ERR(fscache); + dif->fscache = fscache; + } else { + bdev = blkdev_get_by_path(dif->path, FMODE_READ | FMODE_EXCL, + sb->s_type); + if (IS_ERR(bdev)) + return PTR_ERR(bdev); + dif->bdev = bdev; + dif->dax_dev = fs_dax_get_by_bdev(bdev, &dif->dax_part_off, + NULL, NULL); + } + + dif->blocks = le32_to_cpu(dis->blocks); + dif->mapped_blkaddr = le32_to_cpu(dis->mapped_blkaddr); + sbi->total_blocks += dif->blocks; + *pos += EROFS_DEVT_SLOT_SIZE; + return 0; +} + +static int erofs_scan_devices(struct super_block *sb, + struct erofs_super_block *dsb) +{ + struct erofs_sb_info *sbi = EROFS_SB(sb); + unsigned int ondisk_extradevs; + erofs_off_t pos; + struct erofs_buf buf = __EROFS_BUF_INITIALIZER; + struct erofs_device_info *dif; + int id, err = 0; + + sbi->total_blocks = sbi->primarydevice_blocks; + if (!erofs_sb_has_device_table(sbi)) + ondisk_extradevs = 0; + else + ondisk_extradevs = le16_to_cpu(dsb->extra_devices); + + if (sbi->devs->extra_devices && + ondisk_extradevs != sbi->devs->extra_devices) { + erofs_err(sb, "extra devices don't match (ondisk %u, given %u)", + ondisk_extradevs, sbi->devs->extra_devices); + return -EINVAL; + } + if (!ondisk_extradevs) + return 0; + + sbi->device_id_mask = roundup_pow_of_two(ondisk_extradevs + 1) - 1; + pos = le16_to_cpu(dsb->devt_slotoff) * EROFS_DEVT_SLOT_SIZE; + down_read(&sbi->devs->rwsem); + if (sbi->devs->extra_devices) { + idr_for_each_entry(&sbi->devs->tree, dif, id) { + err = erofs_init_device(&buf, sb, dif, &pos); + if (err) + break; + } + } else { + for (id = 0; id < ondisk_extradevs; id++) { + dif = kzalloc(sizeof(*dif), GFP_KERNEL); + if (!dif) { + err = -ENOMEM; + break; + } + + err = idr_alloc(&sbi->devs->tree, dif, 0, 0, GFP_KERNEL); + if (err < 0) { + kfree(dif); + break; + } + ++sbi->devs->extra_devices; + + err = erofs_init_device(&buf, sb, dif, &pos); + if (err) + break; + } + } + up_read(&sbi->devs->rwsem); + erofs_put_metabuf(&buf); + return err; +} + static int erofs_read_superblock(struct super_block *sb) { struct erofs_sb_info *sbi; - struct page *page; + struct erofs_buf buf = __EROFS_BUF_INITIALIZER; struct erofs_super_block *dsb; unsigned int blkszbits; void *data; int ret; - page = read_mapping_page(sb->s_bdev->bd_inode->i_mapping, 0, NULL); - if (IS_ERR(page)) { + data = erofs_read_metabuf(&buf, sb, 0, EROFS_KMAP); + if (IS_ERR(data)) { erofs_err(sb, "cannot read erofs superblock"); - return PTR_ERR(page); + return PTR_ERR(data); } sbi = EROFS_SB(sb); - - data = kmap(page); dsb = (struct erofs_super_block *)(data + EROFS_SUPER_OFFSET); ret = -EINVAL; @@ -147,30 +350,48 @@ static int erofs_read_superblock(struct super_block *sb) } sbi->feature_compat = le32_to_cpu(dsb->feature_compat); - if (sbi->feature_compat & EROFS_FEATURE_COMPAT_SB_CHKSUM) { + if (erofs_sb_has_sb_chksum(sbi)) { ret = erofs_superblock_csum_verify(sb, data); if (ret) goto out; } + ret = -EINVAL; blkszbits = dsb->blkszbits; /* 9(512 bytes) + LOG_SECTORS_PER_BLOCK == LOG_BLOCK_SIZE */ if (blkszbits != LOG_BLOCK_SIZE) { - erofs_err(sb, "blksize %u isn't supported on this platform", - 1 << blkszbits); + erofs_err(sb, "blkszbits %u isn't supported on this platform", + blkszbits); goto out; } if (!check_layout_compatibility(sb, dsb)) goto out; - sbi->blocks = le32_to_cpu(dsb->blocks); + sbi->sb_size = 128 + dsb->sb_extslots * EROFS_SB_EXTSLOT_SIZE; + if (sbi->sb_size > EROFS_BLKSIZ) { + erofs_err(sb, "invalid sb_extslots %u (more than a fs block)", + sbi->sb_size); + goto out; + } + sbi->primarydevice_blocks = le32_to_cpu(dsb->blocks); sbi->meta_blkaddr = le32_to_cpu(dsb->meta_blkaddr); #ifdef CONFIG_EROFS_FS_XATTR sbi->xattr_blkaddr = le32_to_cpu(dsb->xattr_blkaddr); #endif sbi->islotbits = ilog2(sizeof(struct erofs_inode_compact)); sbi->root_nid = le16_to_cpu(dsb->root_nid); +#ifdef CONFIG_EROFS_FS_ZIP + sbi->packed_inode = NULL; + if (erofs_sb_has_fragments(sbi) && dsb->packed_nid) { + sbi->packed_inode = + erofs_iget(sb, le64_to_cpu(dsb->packed_nid)); + if (IS_ERR(sbi->packed_inode)) { + ret = PTR_ERR(sbi->packed_inode); + goto out; + } + } +#endif sbi->inos = le64_to_cpu(dsb->inos); sbi->build_time = le64_to_cpu(dsb->build_time); @@ -185,139 +406,199 @@ static int erofs_read_superblock(struct super_block *sb) ret = -EFSCORRUPTED; goto out; } - ret = 0; -out: - kunmap(page); - put_page(page); - return ret; -} - -#ifdef CONFIG_EROFS_FS_ZIP -static int erofs_build_cache_strategy(struct super_block *sb, - substring_t *args) -{ - struct erofs_sb_info *sbi = EROFS_SB(sb); - const char *cs = match_strdup(args); - int err = 0; - if (!cs) { - erofs_err(sb, "Not enough memory to store cache strategy"); - return -ENOMEM; - } + /* parse on-disk compression configurations */ + if (erofs_sb_has_compr_cfgs(sbi)) + ret = erofs_load_compr_cfgs(sb, dsb); + else + ret = z_erofs_load_lz4_config(sb, dsb, NULL, 0); + if (ret < 0) + goto out; - if (!strcmp(cs, "disabled")) { - sbi->cache_strategy = EROFS_ZIP_CACHE_DISABLED; - } else if (!strcmp(cs, "readahead")) { - sbi->cache_strategy = EROFS_ZIP_CACHE_READAHEAD; - } else if (!strcmp(cs, "readaround")) { - sbi->cache_strategy = EROFS_ZIP_CACHE_READAROUND; - } else { - erofs_err(sb, "Unrecognized cache strategy \"%s\"", cs); - err = -EINVAL; - } - kfree(cs); - return err; -} -#else -static int erofs_build_cache_strategy(struct super_block *sb, - substring_t *args) -{ - erofs_info(sb, "EROFS compression is disabled, so cache strategy is ignored"); - return 0; + /* handle multiple devices */ + ret = erofs_scan_devices(sb, dsb); + + if (erofs_sb_has_ztailpacking(sbi)) + erofs_info(sb, "EXPERIMENTAL compressed inline data feature in use. Use at your own risk!"); + if (erofs_is_fscache_mode(sb)) + erofs_info(sb, "EXPERIMENTAL fscache-based on-demand read feature in use. Use at your own risk!"); + if (erofs_sb_has_fragments(sbi)) + erofs_info(sb, "EXPERIMENTAL compressed fragments feature in use. Use at your own risk!"); + if (erofs_sb_has_dedupe(sbi)) + erofs_info(sb, "EXPERIMENTAL global deduplication feature in use. Use at your own risk!"); +out: + erofs_put_metabuf(&buf); + return ret; } -#endif /* set up default EROFS parameters */ -static void erofs_default_options(struct erofs_sb_info *sbi) +static void erofs_default_options(struct erofs_fs_context *ctx) { #ifdef CONFIG_EROFS_FS_ZIP - sbi->cache_strategy = EROFS_ZIP_CACHE_READAROUND; - sbi->max_sync_decompress_pages = 3; + ctx->opt.cache_strategy = EROFS_ZIP_CACHE_READAROUND; + ctx->opt.max_sync_decompress_pages = 3; + ctx->opt.sync_decompress = EROFS_SYNC_DECOMPRESS_AUTO; #endif #ifdef CONFIG_EROFS_FS_XATTR - set_opt(sbi, XATTR_USER); + set_opt(&ctx->opt, XATTR_USER); #endif #ifdef CONFIG_EROFS_FS_POSIX_ACL - set_opt(sbi, POSIX_ACL); + set_opt(&ctx->opt, POSIX_ACL); #endif } enum { Opt_user_xattr, - Opt_nouser_xattr, Opt_acl, - Opt_noacl, Opt_cache_strategy, + Opt_dax, + Opt_dax_enum, + Opt_device, + Opt_fsid, + Opt_domain_id, Opt_err }; -static match_table_t erofs_tokens = { - {Opt_user_xattr, "user_xattr"}, - {Opt_nouser_xattr, "nouser_xattr"}, - {Opt_acl, "acl"}, - {Opt_noacl, "noacl"}, - {Opt_cache_strategy, "cache_strategy=%s"}, - {Opt_err, NULL} +static const struct constant_table erofs_param_cache_strategy[] = { + {"disabled", EROFS_ZIP_CACHE_DISABLED}, + {"readahead", EROFS_ZIP_CACHE_READAHEAD}, + {"readaround", EROFS_ZIP_CACHE_READAROUND}, + {} }; -static int erofs_parse_options(struct super_block *sb, char *options) -{ - substring_t args[MAX_OPT_ARGS]; - char *p; - int err; +static const struct constant_table erofs_dax_param_enums[] = { + {"always", EROFS_MOUNT_DAX_ALWAYS}, + {"never", EROFS_MOUNT_DAX_NEVER}, + {} +}; - if (!options) - return 0; +static const struct fs_parameter_spec erofs_fs_parameters[] = { + fsparam_flag_no("user_xattr", Opt_user_xattr), + fsparam_flag_no("acl", Opt_acl), + fsparam_enum("cache_strategy", Opt_cache_strategy, + erofs_param_cache_strategy), + fsparam_flag("dax", Opt_dax), + fsparam_enum("dax", Opt_dax_enum, erofs_dax_param_enums), + fsparam_string("device", Opt_device), + fsparam_string("fsid", Opt_fsid), + fsparam_string("domain_id", Opt_domain_id), + {} +}; - while ((p = strsep(&options, ","))) { - int token; +static bool erofs_fc_set_dax_mode(struct fs_context *fc, unsigned int mode) +{ +#ifdef CONFIG_FS_DAX + struct erofs_fs_context *ctx = fc->fs_private; + + switch (mode) { + case EROFS_MOUNT_DAX_ALWAYS: + warnfc(fc, "DAX enabled. Warning: EXPERIMENTAL, use at your own risk"); + set_opt(&ctx->opt, DAX_ALWAYS); + clear_opt(&ctx->opt, DAX_NEVER); + return true; + case EROFS_MOUNT_DAX_NEVER: + set_opt(&ctx->opt, DAX_NEVER); + clear_opt(&ctx->opt, DAX_ALWAYS); + return true; + default: + DBG_BUGON(1); + return false; + } +#else + errorfc(fc, "dax options not supported"); + return false; +#endif +} - if (!*p) - continue; +static int erofs_fc_parse_param(struct fs_context *fc, + struct fs_parameter *param) +{ + struct erofs_fs_context *ctx = fc->fs_private; + struct fs_parse_result result; + struct erofs_device_info *dif; + int opt, ret; - args[0].to = args[0].from = NULL; - token = match_token(p, erofs_tokens, args); + opt = fs_parse(fc, erofs_fs_parameters, param, &result); + if (opt < 0) + return opt; - switch (token) { + switch (opt) { + case Opt_user_xattr: #ifdef CONFIG_EROFS_FS_XATTR - case Opt_user_xattr: - set_opt(EROFS_SB(sb), XATTR_USER); - break; - case Opt_nouser_xattr: - clear_opt(EROFS_SB(sb), XATTR_USER); - break; + if (result.boolean) + set_opt(&ctx->opt, XATTR_USER); + else + clear_opt(&ctx->opt, XATTR_USER); #else - case Opt_user_xattr: - erofs_info(sb, "user_xattr options not supported"); - break; - case Opt_nouser_xattr: - erofs_info(sb, "nouser_xattr options not supported"); - break; + errorfc(fc, "{,no}user_xattr options not supported"); #endif + break; + case Opt_acl: #ifdef CONFIG_EROFS_FS_POSIX_ACL - case Opt_acl: - set_opt(EROFS_SB(sb), POSIX_ACL); - break; - case Opt_noacl: - clear_opt(EROFS_SB(sb), POSIX_ACL); - break; + if (result.boolean) + set_opt(&ctx->opt, POSIX_ACL); + else + clear_opt(&ctx->opt, POSIX_ACL); #else - case Opt_acl: - erofs_info(sb, "acl options not supported"); - break; - case Opt_noacl: - erofs_info(sb, "noacl options not supported"); - break; + errorfc(fc, "{,no}acl options not supported"); #endif - case Opt_cache_strategy: - err = erofs_build_cache_strategy(sb, args); - if (err) - return err; - break; - default: - erofs_err(sb, "Unrecognized mount option \"%s\" or missing value", p); + break; + case Opt_cache_strategy: +#ifdef CONFIG_EROFS_FS_ZIP + ctx->opt.cache_strategy = result.uint_32; +#else + errorfc(fc, "compression not supported, cache_strategy ignored"); +#endif + break; + case Opt_dax: + if (!erofs_fc_set_dax_mode(fc, EROFS_MOUNT_DAX_ALWAYS)) return -EINVAL; + break; + case Opt_dax_enum: + if (!erofs_fc_set_dax_mode(fc, result.uint_32)) + return -EINVAL; + break; + case Opt_device: + dif = kzalloc(sizeof(*dif), GFP_KERNEL); + if (!dif) + return -ENOMEM; + dif->path = kstrdup(param->string, GFP_KERNEL); + if (!dif->path) { + kfree(dif); + return -ENOMEM; + } + down_write(&ctx->devs->rwsem); + ret = idr_alloc(&ctx->devs->tree, dif, 0, 0, GFP_KERNEL); + up_write(&ctx->devs->rwsem); + if (ret < 0) { + kfree(dif->path); + kfree(dif); + return ret; } + ++ctx->devs->extra_devices; + break; + case Opt_fsid: +#ifdef CONFIG_EROFS_FS_ONDEMAND + kfree(ctx->opt.fsid); + ctx->opt.fsid = kstrdup(param->string, GFP_KERNEL); + if (!ctx->opt.fsid) + return -ENOMEM; +#else + errorfc(fc, "fsid option not supported"); +#endif + break; + case Opt_domain_id: +#ifdef CONFIG_EROFS_FS_ONDEMAND + kfree(ctx->opt.domain_id); + ctx->opt.domain_id = kstrdup(param->string, GFP_KERNEL); + if (!ctx->opt.domain_id) + return -ENOMEM; +#else + errorfc(fc, "domain_id option not supported"); +#endif + break; + default: + return -ENOPARAM; } return 0; } @@ -325,39 +606,43 @@ static int erofs_parse_options(struct super_block *sb, char *options) #ifdef CONFIG_EROFS_FS_ZIP static const struct address_space_operations managed_cache_aops; -static int erofs_managed_cache_releasepage(struct page *page, gfp_t gfp_mask) +static bool erofs_managed_cache_release_folio(struct folio *folio, gfp_t gfp) { - int ret = 1; /* 0 - busy */ - struct address_space *const mapping = page->mapping; + bool ret = true; + struct address_space *const mapping = folio->mapping; - DBG_BUGON(!PageLocked(page)); + DBG_BUGON(!folio_test_locked(folio)); DBG_BUGON(mapping->a_ops != &managed_cache_aops); - if (PagePrivate(page)) - ret = erofs_try_to_free_cached_page(mapping, page); + if (folio_test_private(folio)) + ret = erofs_try_to_free_cached_page(&folio->page); return ret; } -static void erofs_managed_cache_invalidatepage(struct page *page, - unsigned int offset, - unsigned int length) +/* + * It will be called only on inode eviction. In case that there are still some + * decompression requests in progress, wait with rescheduling for a bit here. + * We could introduce an extra locking instead but it seems unnecessary. + */ +static void erofs_managed_cache_invalidate_folio(struct folio *folio, + size_t offset, size_t length) { - const unsigned int stop = length + offset; + const size_t stop = length + offset; - DBG_BUGON(!PageLocked(page)); + DBG_BUGON(!folio_test_locked(folio)); /* Check for potential overflow in debug mode */ - DBG_BUGON(stop > PAGE_SIZE || stop < length); + DBG_BUGON(stop > folio_size(folio) || stop < length); - if (offset == 0 && stop == PAGE_SIZE) - while (!erofs_managed_cache_releasepage(page, GFP_NOFS)) + if (offset == 0 && stop == folio_size(folio)) + while (!erofs_managed_cache_release_folio(folio, GFP_NOFS)) cond_resched(); } static const struct address_space_operations managed_cache_aops = { - .releasepage = erofs_managed_cache_releasepage, - .invalidatepage = erofs_managed_cache_invalidatepage, + .release_folio = erofs_managed_cache_release_folio, + .invalidate_folio = erofs_managed_cache_invalidate_folio, }; static int erofs_init_managed_cache(struct super_block *sb) @@ -372,8 +657,7 @@ static int erofs_init_managed_cache(struct super_block *sb) inode->i_size = OFFSET_MAX; inode->i_mapping->a_ops = &managed_cache_aops; - mapping_set_gfp_mask(inode->i_mapping, - GFP_NOFS | __GFP_HIGHMEM | __GFP_MOVABLE); + mapping_set_gfp_mask(inode->i_mapping, GFP_NOFS); sbi->managed_cache = inode; return 0; } @@ -381,55 +665,124 @@ static int erofs_init_managed_cache(struct super_block *sb) static int erofs_init_managed_cache(struct super_block *sb) { return 0; } #endif -static int erofs_fill_super(struct super_block *sb, void *data, int silent) +static struct inode *erofs_nfs_get_inode(struct super_block *sb, + u64 ino, u32 generation) +{ + return erofs_iget(sb, ino); +} + +static struct dentry *erofs_fh_to_dentry(struct super_block *sb, + struct fid *fid, int fh_len, int fh_type) +{ + return generic_fh_to_dentry(sb, fid, fh_len, fh_type, + erofs_nfs_get_inode); +} + +static struct dentry *erofs_fh_to_parent(struct super_block *sb, + struct fid *fid, int fh_len, int fh_type) +{ + return generic_fh_to_parent(sb, fid, fh_len, fh_type, + erofs_nfs_get_inode); +} + +static struct dentry *erofs_get_parent(struct dentry *child) +{ + erofs_nid_t nid; + unsigned int d_type; + int err; + + err = erofs_namei(d_inode(child), &dotdot_name, &nid, &d_type); + if (err) + return ERR_PTR(err); + return d_obtain_alias(erofs_iget(child->d_sb, nid)); +} + +static const struct export_operations erofs_export_ops = { + .fh_to_dentry = erofs_fh_to_dentry, + .fh_to_parent = erofs_fh_to_parent, + .get_parent = erofs_get_parent, +}; + +static int erofs_fc_fill_pseudo_super(struct super_block *sb, struct fs_context *fc) +{ + static const struct tree_descr empty_descr = {""}; + + return simple_fill_super(sb, EROFS_SUPER_MAGIC, &empty_descr); +} + +static int erofs_fc_fill_super(struct super_block *sb, struct fs_context *fc) { struct inode *inode; struct erofs_sb_info *sbi; + struct erofs_fs_context *ctx = fc->fs_private; int err; sb->s_magic = EROFS_SUPER_MAGIC; - - if (!sb_set_blocksize(sb, EROFS_BLKSIZ)) { - erofs_err(sb, "failed to set erofs blksize"); - return -EINVAL; - } + sb->s_flags |= SB_RDONLY | SB_NOATIME; + sb->s_maxbytes = MAX_LFS_FILESIZE; + sb->s_op = &erofs_sops; sbi = kzalloc(sizeof(*sbi), GFP_KERNEL); if (!sbi) return -ENOMEM; sb->s_fs_info = sbi; + sbi->opt = ctx->opt; + ctx->opt.fsid = NULL; + ctx->opt.domain_id = NULL; + sbi->devs = ctx->devs; + ctx->devs = NULL; + + if (erofs_is_fscache_mode(sb)) { + sb->s_blocksize = EROFS_BLKSIZ; + sb->s_blocksize_bits = LOG_BLOCK_SIZE; + + err = erofs_fscache_register_fs(sb); + if (err) + return err; + + err = super_setup_bdi(sb); + if (err) + return err; + } else { + if (!sb_set_blocksize(sb, EROFS_BLKSIZ)) { + erofs_err(sb, "failed to set erofs blksize"); + return -EINVAL; + } + + sbi->dax_dev = fs_dax_get_by_bdev(sb->s_bdev, + &sbi->dax_part_off, + NULL, NULL); + } + err = erofs_read_superblock(sb); if (err) return err; - sb->s_flags |= SB_RDONLY | SB_NOATIME; - sb->s_maxbytes = MAX_LFS_FILESIZE; - sb->s_time_gran = 1; + if (test_opt(&sbi->opt, DAX_ALWAYS)) { + BUILD_BUG_ON(EROFS_BLKSIZ != PAGE_SIZE); - sb->s_op = &erofs_sops; + if (!sbi->dax_dev) { + errorfc(fc, "DAX unsupported by block device. Turning off DAX."); + clear_opt(&sbi->opt, DAX_ALWAYS); + } + } -#ifdef CONFIG_EROFS_FS_XATTR + sb->s_time_gran = 1; sb->s_xattr = erofs_xattr_handlers; -#endif - /* set erofs default mount options */ - erofs_default_options(sbi); - - err = erofs_parse_options(sb, data); - if (err) - return err; + sb->s_export_op = &erofs_export_ops; - if (test_opt(sbi, POSIX_ACL)) + if (test_opt(&sbi->opt, POSIX_ACL)) sb->s_flags |= SB_POSIXACL; else sb->s_flags &= ~SB_POSIXACL; #ifdef CONFIG_EROFS_FS_ZIP - INIT_RADIX_TREE(&sbi->workstn_tree, GFP_ATOMIC); + xa_init(&sbi->managed_pslots); #endif /* get the root inode */ - inode = erofs_iget(sb, ROOT_NID(sbi), true); + inode = erofs_iget(sb, ROOT_NID(sbi)); if (IS_ERR(inode)) return PTR_ERR(inode); @@ -450,15 +803,117 @@ static int erofs_fill_super(struct super_block *sb, void *data, int silent) if (err) return err; - erofs_info(sb, "mounted with opts: %s, root inode @ nid %llu.", - (char *)data, ROOT_NID(sbi)); + err = erofs_register_sysfs(sb); + if (err) + return err; + + erofs_info(sb, "mounted with root inode @ nid %llu.", ROOT_NID(sbi)); return 0; } -static struct dentry *erofs_mount(struct file_system_type *fs_type, int flags, - const char *dev_name, void *data) +static int erofs_fc_anon_get_tree(struct fs_context *fc) { - return mount_bdev(fs_type, flags, dev_name, data, erofs_fill_super); + return get_tree_nodev(fc, erofs_fc_fill_pseudo_super); +} + +static int erofs_fc_get_tree(struct fs_context *fc) +{ + struct erofs_fs_context *ctx = fc->fs_private; + + if (IS_ENABLED(CONFIG_EROFS_FS_ONDEMAND) && ctx->opt.fsid) + return get_tree_nodev(fc, erofs_fc_fill_super); + + return get_tree_bdev(fc, erofs_fc_fill_super); +} + +static int erofs_fc_reconfigure(struct fs_context *fc) +{ + struct super_block *sb = fc->root->d_sb; + struct erofs_sb_info *sbi = EROFS_SB(sb); + struct erofs_fs_context *ctx = fc->fs_private; + + DBG_BUGON(!sb_rdonly(sb)); + + if (test_opt(&ctx->opt, POSIX_ACL)) + fc->sb_flags |= SB_POSIXACL; + else + fc->sb_flags &= ~SB_POSIXACL; + + sbi->opt = ctx->opt; + + fc->sb_flags |= SB_RDONLY; + return 0; +} + +static int erofs_release_device_info(int id, void *ptr, void *data) +{ + struct erofs_device_info *dif = ptr; + + fs_put_dax(dif->dax_dev, NULL); + if (dif->bdev) + blkdev_put(dif->bdev, FMODE_READ | FMODE_EXCL); + erofs_fscache_unregister_cookie(dif->fscache); + dif->fscache = NULL; + kfree(dif->path); + kfree(dif); + return 0; +} + +static void erofs_free_dev_context(struct erofs_dev_context *devs) +{ + if (!devs) + return; + idr_for_each(&devs->tree, &erofs_release_device_info, NULL); + idr_destroy(&devs->tree); + kfree(devs); +} + +static void erofs_fc_free(struct fs_context *fc) +{ + struct erofs_fs_context *ctx = fc->fs_private; + + erofs_free_dev_context(ctx->devs); + kfree(ctx->opt.fsid); + kfree(ctx->opt.domain_id); + kfree(ctx); +} + +static const struct fs_context_operations erofs_context_ops = { + .parse_param = erofs_fc_parse_param, + .get_tree = erofs_fc_get_tree, + .reconfigure = erofs_fc_reconfigure, + .free = erofs_fc_free, +}; + +static const struct fs_context_operations erofs_anon_context_ops = { + .get_tree = erofs_fc_anon_get_tree, +}; + +static int erofs_init_fs_context(struct fs_context *fc) +{ + struct erofs_fs_context *ctx; + + /* pseudo mount for anon inodes */ + if (fc->sb_flags & SB_KERNMOUNT) { + fc->ops = &erofs_anon_context_ops; + return 0; + } + + ctx = kzalloc(sizeof(*ctx), GFP_KERNEL); + if (!ctx) + return -ENOMEM; + ctx->devs = kzalloc(sizeof(struct erofs_dev_context), GFP_KERNEL); + if (!ctx->devs) { + kfree(ctx); + return -ENOMEM; + } + fc->fs_private = ctx; + + idr_init(&ctx->devs->tree); + init_rwsem(&ctx->devs->rwsem); + erofs_default_options(ctx); + fc->ops = &erofs_context_ops; + return 0; } /* @@ -471,11 +926,26 @@ static void erofs_kill_sb(struct super_block *sb) WARN_ON(sb->s_magic != EROFS_SUPER_MAGIC); - kill_block_super(sb); + /* pseudo mount for anon inodes */ + if (sb->s_flags & SB_KERNMOUNT) { + kill_anon_super(sb); + return; + } + + if (erofs_is_fscache_mode(sb)) + kill_anon_super(sb); + else + kill_block_super(sb); sbi = EROFS_SB(sb); if (!sbi) return; + + erofs_free_dev_context(sbi->devs); + fs_put_dax(sbi->dax_dev, NULL); + erofs_fscache_unregister_fs(sb); + kfree(sbi->opt.fsid); + kfree(sbi->opt.domain_id); kfree(sbi); sb->s_fs_info = NULL; } @@ -487,19 +957,23 @@ static void erofs_put_super(struct super_block *sb) DBG_BUGON(!sbi); + erofs_unregister_sysfs(sb); erofs_shrinker_unregister(sb); #ifdef CONFIG_EROFS_FS_ZIP iput(sbi->managed_cache); sbi->managed_cache = NULL; + iput(sbi->packed_inode); + sbi->packed_inode = NULL; #endif + erofs_fscache_unregister_fs(sb); } -static struct file_system_type erofs_fs_type = { +struct file_system_type erofs_fs_type = { .owner = THIS_MODULE, .name = "erofs", - .mount = erofs_mount, + .init_fs_context = erofs_init_fs_context, .kill_sb = erofs_kill_sb, - .fs_flags = FS_REQUIRES_DEV, + .fs_flags = FS_REQUIRES_DEV | FS_ALLOW_IDMAP, }; MODULE_ALIAS_FS("erofs"); @@ -522,10 +996,19 @@ static int __init erofs_module_init(void) if (err) goto shrinker_err; + err = z_erofs_lzma_init(); + if (err) + goto lzma_err; + + erofs_pcpubuf_init(); err = z_erofs_init_zip_subsystem(); if (err) goto zip_err; + err = erofs_init_sysfs(); + if (err) + goto sysfs_err; + err = register_filesystem(&erofs_fs_type); if (err) goto fs_err; @@ -533,8 +1016,12 @@ static int __init erofs_module_init(void) return 0; fs_err: + erofs_exit_sysfs(); +sysfs_err: z_erofs_exit_zip_subsystem(); zip_err: + z_erofs_lzma_exit(); +lzma_err: erofs_exit_shrinker(); shrinker_err: kmem_cache_destroy(erofs_inode_cachep); @@ -545,12 +1032,16 @@ icache_err: static void __exit erofs_module_exit(void) { unregister_filesystem(&erofs_fs_type); - z_erofs_exit_zip_subsystem(); - erofs_exit_shrinker(); - /* Ensure all RCU free inodes are safe before cache is destroyed. */ + /* Ensure all RCU free inodes / pclusters are safe to be destroyed. */ rcu_barrier(); + + erofs_exit_sysfs(); + z_erofs_exit_zip_subsystem(); + z_erofs_lzma_exit(); + erofs_exit_shrinker(); kmem_cache_destroy(erofs_inode_cachep); + erofs_pcpubuf_exit(); } /* get filesystem statistics */ @@ -558,11 +1049,14 @@ static int erofs_statfs(struct dentry *dentry, struct kstatfs *buf) { struct super_block *sb = dentry->d_sb; struct erofs_sb_info *sbi = EROFS_SB(sb); - u64 id = huge_encode_dev(sb->s_bdev->bd_dev); + u64 id = 0; + + if (!erofs_is_fscache_mode(sb)) + id = huge_encode_dev(sb->s_bdev->bd_dev); buf->f_type = sb->s_magic; buf->f_bsize = EROFS_BLKSIZ; - buf->f_blocks = sbi->blocks; + buf->f_blocks = sbi->total_blocks; buf->f_bfree = buf->f_bavail = 0; buf->f_files = ULLONG_MAX; @@ -570,69 +1064,54 @@ static int erofs_statfs(struct dentry *dentry, struct kstatfs *buf) buf->f_namelen = EROFS_NAME_LEN; - buf->f_fsid.val[0] = (u32)id; - buf->f_fsid.val[1] = (u32)(id >> 32); + buf->f_fsid = u64_to_fsid(id); return 0; } static int erofs_show_options(struct seq_file *seq, struct dentry *root) { - struct erofs_sb_info *sbi __maybe_unused = EROFS_SB(root->d_sb); + struct erofs_sb_info *sbi = EROFS_SB(root->d_sb); + struct erofs_mount_opts *opt = &sbi->opt; #ifdef CONFIG_EROFS_FS_XATTR - if (test_opt(sbi, XATTR_USER)) + if (test_opt(opt, XATTR_USER)) seq_puts(seq, ",user_xattr"); else seq_puts(seq, ",nouser_xattr"); #endif #ifdef CONFIG_EROFS_FS_POSIX_ACL - if (test_opt(sbi, POSIX_ACL)) + if (test_opt(opt, POSIX_ACL)) seq_puts(seq, ",acl"); else seq_puts(seq, ",noacl"); #endif #ifdef CONFIG_EROFS_FS_ZIP - if (sbi->cache_strategy == EROFS_ZIP_CACHE_DISABLED) { + if (opt->cache_strategy == EROFS_ZIP_CACHE_DISABLED) seq_puts(seq, ",cache_strategy=disabled"); - } else if (sbi->cache_strategy == EROFS_ZIP_CACHE_READAHEAD) { + else if (opt->cache_strategy == EROFS_ZIP_CACHE_READAHEAD) seq_puts(seq, ",cache_strategy=readahead"); - } else if (sbi->cache_strategy == EROFS_ZIP_CACHE_READAROUND) { + else if (opt->cache_strategy == EROFS_ZIP_CACHE_READAROUND) seq_puts(seq, ",cache_strategy=readaround"); - } +#endif + if (test_opt(opt, DAX_ALWAYS)) + seq_puts(seq, ",dax=always"); + if (test_opt(opt, DAX_NEVER)) + seq_puts(seq, ",dax=never"); +#ifdef CONFIG_EROFS_FS_ONDEMAND + if (opt->fsid) + seq_printf(seq, ",fsid=%s", opt->fsid); + if (opt->domain_id) + seq_printf(seq, ",domain_id=%s", opt->domain_id); #endif return 0; } -static int erofs_remount(struct super_block *sb, int *flags, char *data) -{ - struct erofs_sb_info *sbi = EROFS_SB(sb); - unsigned int org_mnt_opt = sbi->mount_opt; - int err; - - DBG_BUGON(!sb_rdonly(sb)); - err = erofs_parse_options(sb, data); - if (err) - goto out; - - if (test_opt(sbi, POSIX_ACL)) - sb->s_flags |= SB_POSIXACL; - else - sb->s_flags &= ~SB_POSIXACL; - - *flags |= SB_RDONLY; - return 0; -out: - sbi->mount_opt = org_mnt_opt; - return err; -} - const struct super_operations erofs_sops = { .put_super = erofs_put_super, .alloc_inode = erofs_alloc_inode, .free_inode = erofs_free_inode, .statfs = erofs_statfs, .show_options = erofs_show_options, - .remount_fs = erofs_remount, }; module_init(erofs_module_init); @@ -641,4 +1120,3 @@ module_exit(erofs_module_exit); MODULE_DESCRIPTION("Enhanced ROM File System"); MODULE_AUTHOR("Gao Xiang, Chao Yu, Miao Xie, CONSUMER BG, HUAWEI Inc."); MODULE_LICENSE("GPL"); - diff --git a/fs/erofs/sysfs.c b/fs/erofs/sysfs.c new file mode 100644 index 000000000000..783bb7b21b51 --- /dev/null +++ b/fs/erofs/sysfs.c @@ -0,0 +1,277 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Copyright (C), 2008-2021, OPPO Mobile Comm Corp., Ltd. + * https://www.oppo.com/ + */ +#include <linux/sysfs.h> +#include <linux/kobject.h> + +#include "internal.h" + +enum { + attr_feature, + attr_pointer_ui, + attr_pointer_bool, +}; + +enum { + struct_erofs_sb_info, + struct_erofs_mount_opts, +}; + +struct erofs_attr { + struct attribute attr; + short attr_id; + int struct_type, offset; +}; + +#define EROFS_ATTR(_name, _mode, _id) \ +static struct erofs_attr erofs_attr_##_name = { \ + .attr = {.name = __stringify(_name), .mode = _mode }, \ + .attr_id = attr_##_id, \ +} +#define EROFS_ATTR_FUNC(_name, _mode) EROFS_ATTR(_name, _mode, _name) +#define EROFS_ATTR_FEATURE(_name) EROFS_ATTR(_name, 0444, feature) + +#define EROFS_ATTR_OFFSET(_name, _mode, _id, _struct) \ +static struct erofs_attr erofs_attr_##_name = { \ + .attr = {.name = __stringify(_name), .mode = _mode }, \ + .attr_id = attr_##_id, \ + .struct_type = struct_##_struct, \ + .offset = offsetof(struct _struct, _name),\ +} + +#define EROFS_ATTR_RW(_name, _id, _struct) \ + EROFS_ATTR_OFFSET(_name, 0644, _id, _struct) + +#define EROFS_RO_ATTR(_name, _id, _struct) \ + EROFS_ATTR_OFFSET(_name, 0444, _id, _struct) + +#define EROFS_ATTR_RW_UI(_name, _struct) \ + EROFS_ATTR_RW(_name, pointer_ui, _struct) + +#define EROFS_ATTR_RW_BOOL(_name, _struct) \ + EROFS_ATTR_RW(_name, pointer_bool, _struct) + +#define ATTR_LIST(name) (&erofs_attr_##name.attr) + +#ifdef CONFIG_EROFS_FS_ZIP +EROFS_ATTR_RW_UI(sync_decompress, erofs_mount_opts); +#endif + +static struct attribute *erofs_attrs[] = { +#ifdef CONFIG_EROFS_FS_ZIP + ATTR_LIST(sync_decompress), +#endif + NULL, +}; +ATTRIBUTE_GROUPS(erofs); + +/* Features this copy of erofs supports */ +EROFS_ATTR_FEATURE(zero_padding); +EROFS_ATTR_FEATURE(compr_cfgs); +EROFS_ATTR_FEATURE(big_pcluster); +EROFS_ATTR_FEATURE(chunked_file); +EROFS_ATTR_FEATURE(device_table); +EROFS_ATTR_FEATURE(compr_head2); +EROFS_ATTR_FEATURE(sb_chksum); +EROFS_ATTR_FEATURE(ztailpacking); +EROFS_ATTR_FEATURE(fragments); +EROFS_ATTR_FEATURE(dedupe); + +static struct attribute *erofs_feat_attrs[] = { + ATTR_LIST(zero_padding), + ATTR_LIST(compr_cfgs), + ATTR_LIST(big_pcluster), + ATTR_LIST(chunked_file), + ATTR_LIST(device_table), + ATTR_LIST(compr_head2), + ATTR_LIST(sb_chksum), + ATTR_LIST(ztailpacking), + ATTR_LIST(fragments), + ATTR_LIST(dedupe), + NULL, +}; +ATTRIBUTE_GROUPS(erofs_feat); + +static unsigned char *__struct_ptr(struct erofs_sb_info *sbi, + int struct_type, int offset) +{ + if (struct_type == struct_erofs_sb_info) + return (unsigned char *)sbi + offset; + if (struct_type == struct_erofs_mount_opts) + return (unsigned char *)&sbi->opt + offset; + return NULL; +} + +static ssize_t erofs_attr_show(struct kobject *kobj, + struct attribute *attr, char *buf) +{ + struct erofs_sb_info *sbi = container_of(kobj, struct erofs_sb_info, + s_kobj); + struct erofs_attr *a = container_of(attr, struct erofs_attr, attr); + unsigned char *ptr = __struct_ptr(sbi, a->struct_type, a->offset); + + switch (a->attr_id) { + case attr_feature: + return sysfs_emit(buf, "supported\n"); + case attr_pointer_ui: + if (!ptr) + return 0; + return sysfs_emit(buf, "%u\n", *(unsigned int *)ptr); + case attr_pointer_bool: + if (!ptr) + return 0; + return sysfs_emit(buf, "%d\n", *(bool *)ptr); + } + return 0; +} + +static ssize_t erofs_attr_store(struct kobject *kobj, struct attribute *attr, + const char *buf, size_t len) +{ + struct erofs_sb_info *sbi = container_of(kobj, struct erofs_sb_info, + s_kobj); + struct erofs_attr *a = container_of(attr, struct erofs_attr, attr); + unsigned char *ptr = __struct_ptr(sbi, a->struct_type, a->offset); + unsigned long t; + int ret; + + switch (a->attr_id) { + case attr_pointer_ui: + if (!ptr) + return 0; + ret = kstrtoul(skip_spaces(buf), 0, &t); + if (ret) + return ret; + if (t != (unsigned int)t) + return -ERANGE; +#ifdef CONFIG_EROFS_FS_ZIP + if (!strcmp(a->attr.name, "sync_decompress") && + (t > EROFS_SYNC_DECOMPRESS_FORCE_OFF)) + return -EINVAL; +#endif + *(unsigned int *)ptr = t; + return len; + case attr_pointer_bool: + if (!ptr) + return 0; + ret = kstrtoul(skip_spaces(buf), 0, &t); + if (ret) + return ret; + if (t != 0 && t != 1) + return -EINVAL; + *(bool *)ptr = !!t; + return len; + } + return 0; +} + +static void erofs_sb_release(struct kobject *kobj) +{ + struct erofs_sb_info *sbi = container_of(kobj, struct erofs_sb_info, + s_kobj); + complete(&sbi->s_kobj_unregister); +} + +static const struct sysfs_ops erofs_attr_ops = { + .show = erofs_attr_show, + .store = erofs_attr_store, +}; + +static struct kobj_type erofs_sb_ktype = { + .default_groups = erofs_groups, + .sysfs_ops = &erofs_attr_ops, + .release = erofs_sb_release, +}; + +static struct kobj_type erofs_ktype = { + .sysfs_ops = &erofs_attr_ops, +}; + +static struct kset erofs_root = { + .kobj = {.ktype = &erofs_ktype}, +}; + +static struct kobj_type erofs_feat_ktype = { + .default_groups = erofs_feat_groups, + .sysfs_ops = &erofs_attr_ops, +}; + +static struct kobject erofs_feat = { + .kset = &erofs_root, +}; + +int erofs_register_sysfs(struct super_block *sb) +{ + struct erofs_sb_info *sbi = EROFS_SB(sb); + char *name; + char *str = NULL; + int err; + + if (erofs_is_fscache_mode(sb)) { + if (sbi->opt.domain_id) { + str = kasprintf(GFP_KERNEL, "%s,%s", sbi->opt.domain_id, + sbi->opt.fsid); + if (!str) + return -ENOMEM; + name = str; + } else { + name = sbi->opt.fsid; + } + } else { + name = sb->s_id; + } + sbi->s_kobj.kset = &erofs_root; + init_completion(&sbi->s_kobj_unregister); + err = kobject_init_and_add(&sbi->s_kobj, &erofs_sb_ktype, NULL, "%s", name); + kfree(str); + if (err) + goto put_sb_kobj; + return 0; + +put_sb_kobj: + kobject_put(&sbi->s_kobj); + wait_for_completion(&sbi->s_kobj_unregister); + return err; +} + +void erofs_unregister_sysfs(struct super_block *sb) +{ + struct erofs_sb_info *sbi = EROFS_SB(sb); + + if (sbi->s_kobj.state_in_sysfs) { + kobject_del(&sbi->s_kobj); + kobject_put(&sbi->s_kobj); + wait_for_completion(&sbi->s_kobj_unregister); + } +} + +int __init erofs_init_sysfs(void) +{ + int ret; + + kobject_set_name(&erofs_root.kobj, "erofs"); + erofs_root.kobj.parent = fs_kobj; + ret = kset_register(&erofs_root); + if (ret) + goto root_err; + + ret = kobject_init_and_add(&erofs_feat, &erofs_feat_ktype, + NULL, "features"); + if (ret) + goto feat_err; + return ret; + +feat_err: + kobject_put(&erofs_feat); + kset_unregister(&erofs_root); +root_err: + return ret; +} + +void erofs_exit_sysfs(void) +{ + kobject_put(&erofs_feat); + kset_unregister(&erofs_root); +} diff --git a/fs/erofs/tagptr.h b/fs/erofs/tagptr.h index a72897c86744..64ceb7270b5c 100644 --- a/fs/erofs/tagptr.h +++ b/fs/erofs/tagptr.h @@ -1,8 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0-only */ /* * A tagged pointer implementation - * - * Copyright (C) 2018 Gao Xiang <gaoxiang25@huawei.com> */ #ifndef __EROFS_FS_TAGPTR_H #define __EROFS_FS_TAGPTR_H @@ -107,4 +105,3 @@ tagptr_init(o, cmpxchg(&ptptr->v, o.v, n.v)); }) *ptptr; }) #endif /* __EROFS_FS_TAGPTR_H */ - diff --git a/fs/erofs/utils.c b/fs/erofs/utils.c index fddc5059c930..46627cb69abe 100644 --- a/fs/erofs/utils.c +++ b/fs/erofs/utils.c @@ -1,45 +1,38 @@ // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2018 HUAWEI, Inc. - * http://www.huawei.com/ - * Created by Gao Xiang <gaoxiang25@huawei.com> + * https://www.huawei.com/ */ #include "internal.h" #include <linux/pagevec.h> -struct page *erofs_allocpage(struct list_head *pool, gfp_t gfp) +struct page *erofs_allocpage(struct page **pagepool, gfp_t gfp) { - struct page *page; + struct page *page = *pagepool; - if (!list_empty(pool)) { - page = lru_to_page(pool); + if (page) { DBG_BUGON(page_ref_count(page) != 1); - list_del(&page->lru); + *pagepool = (struct page *)page_private(page); } else { page = alloc_page(gfp); } return page; } -#if (EROFS_PCPUBUF_NR_PAGES > 0) -static struct { - u8 data[PAGE_SIZE * EROFS_PCPUBUF_NR_PAGES]; -} ____cacheline_aligned_in_smp erofs_pcpubuf[NR_CPUS]; - -void *erofs_get_pcpubuf(unsigned int pagenr) +void erofs_release_pages(struct page **pagepool) { - preempt_disable(); - return &erofs_pcpubuf[smp_processor_id()].data[pagenr * PAGE_SIZE]; + while (*pagepool) { + struct page *page = *pagepool; + + *pagepool = (struct page *)page_private(page); + put_page(page); + } } -#endif #ifdef CONFIG_EROFS_FS_ZIP /* global shrink count (for all mounted EROFS instances) */ static atomic_long_t erofs_global_shrink_cnt; -#define __erofs_workgroup_get(grp) atomic_inc(&(grp)->refcount) -#define __erofs_workgroup_put(grp) atomic_dec(&(grp)->refcount) - static int erofs_workgroup_get(struct erofs_workgroup *grp) { int o; @@ -66,7 +59,7 @@ struct erofs_workgroup *erofs_find_workgroup(struct super_block *sb, repeat: rcu_read_lock(); - grp = radix_tree_lookup(&sbi->workstn_tree, index); + grp = xa_load(&sbi->managed_pslots, index); if (grp) { if (erofs_workgroup_get(grp)) { /* prefer to relax rcu read side */ @@ -80,43 +73,37 @@ repeat: return grp; } -int erofs_register_workgroup(struct super_block *sb, - struct erofs_workgroup *grp) +struct erofs_workgroup *erofs_insert_workgroup(struct super_block *sb, + struct erofs_workgroup *grp) { - struct erofs_sb_info *sbi; - int err; - - /* grp shouldn't be broken or used before */ - if (atomic_read(&grp->refcount) != 1) { - DBG_BUGON(1); - return -EINVAL; - } - - err = radix_tree_preload(GFP_NOFS); - if (err) - return err; - - sbi = EROFS_SB(sb); - xa_lock(&sbi->workstn_tree); + struct erofs_sb_info *const sbi = EROFS_SB(sb); + struct erofs_workgroup *pre; /* - * Bump up reference count before making this workgroup - * visible to other users in order to avoid potential UAF - * without serialized by workstn_lock. + * Bump up a reference count before making this visible + * to others for the XArray in order to avoid potential + * UAF without serialized by xa_lock. */ - __erofs_workgroup_get(grp); + atomic_inc(&grp->refcount); - err = radix_tree_insert(&sbi->workstn_tree, grp->index, grp); - if (err) - /* - * it's safe to decrease since the workgroup isn't visible - * and refcount >= 2 (cannot be freezed). - */ - __erofs_workgroup_put(grp); - - xa_unlock(&sbi->workstn_tree); - radix_tree_preload_end(); - return err; +repeat: + xa_lock(&sbi->managed_pslots); + pre = __xa_cmpxchg(&sbi->managed_pslots, grp->index, + NULL, grp, GFP_NOFS); + if (pre) { + if (xa_is_err(pre)) { + pre = ERR_PTR(xa_err(pre)); + } else if (erofs_workgroup_get(pre)) { + /* try to legitimize the current in-tree one */ + xa_unlock(&sbi->managed_pslots); + cond_resched(); + goto repeat; + } + atomic_dec(&grp->refcount); + grp = pre; + } + xa_unlock(&sbi->managed_pslots); + return grp; } static void __erofs_workgroup_free(struct erofs_workgroup *grp) @@ -136,12 +123,6 @@ int erofs_workgroup_put(struct erofs_workgroup *grp) return count; } -static void erofs_workgroup_unfreeze_final(struct erofs_workgroup *grp) -{ - erofs_workgroup_unfreeze(grp, 0); - __erofs_workgroup_free(grp); -} - static bool erofs_try_to_release_workgroup(struct erofs_sb_info *sbi, struct erofs_workgroup *grp) { @@ -155,7 +136,7 @@ static bool erofs_try_to_release_workgroup(struct erofs_sb_info *sbi, /* * Note that all cached pages should be unattached - * before deleted from the radix tree. Otherwise some + * before deleted from the XArray. Otherwise some * cached pages could be still attached to the orphan * old workgroup when the new one is available in the tree. */ @@ -169,47 +150,34 @@ static bool erofs_try_to_release_workgroup(struct erofs_sb_info *sbi, * however in order to avoid some race conditions, add a * DBG_BUGON to observe this in advance. */ - DBG_BUGON(radix_tree_delete(&sbi->workstn_tree, grp->index) != grp); + DBG_BUGON(__xa_erase(&sbi->managed_pslots, grp->index) != grp); - /* - * If managed cache is on, last refcount should indicate - * the related workstation. - */ - erofs_workgroup_unfreeze_final(grp); + /* last refcount should be connected with its managed pslot. */ + erofs_workgroup_unfreeze(grp, 0); + __erofs_workgroup_free(grp); return true; } static unsigned long erofs_shrink_workstation(struct erofs_sb_info *sbi, unsigned long nr_shrink) { - pgoff_t first_index = 0; - void *batch[PAGEVEC_SIZE]; + struct erofs_workgroup *grp; unsigned int freed = 0; + unsigned long index; - int i, found; -repeat: - xa_lock(&sbi->workstn_tree); - - found = radix_tree_gang_lookup(&sbi->workstn_tree, - batch, first_index, PAGEVEC_SIZE); - - for (i = 0; i < found; ++i) { - struct erofs_workgroup *grp = batch[i]; - - first_index = grp->index + 1; - + xa_lock(&sbi->managed_pslots); + xa_for_each(&sbi->managed_pslots, index, grp) { /* try to shrink each valid workgroup */ if (!erofs_try_to_release_workgroup(sbi, grp)) continue; + xa_unlock(&sbi->managed_pslots); ++freed; if (!--nr_shrink) - break; + return freed; + xa_lock(&sbi->managed_pslots); } - xa_unlock(&sbi->workstn_tree); - - if (i && nr_shrink) - goto repeat; + xa_unlock(&sbi->managed_pslots); return freed; } @@ -286,7 +254,7 @@ static unsigned long erofs_shrink_scan(struct shrinker *shrink, spin_unlock(&erofs_sb_list_lock); sbi->shrinker_run_no = run_no; - freed += erofs_shrink_workstation(sbi, nr); + freed += erofs_shrink_workstation(sbi, nr - freed); spin_lock(&erofs_sb_list_lock); /* Get the next list element before we move this one */ @@ -314,7 +282,7 @@ static struct shrinker erofs_shrinker_info = { int __init erofs_init_shrinker(void) { - return register_shrinker(&erofs_shrinker_info); + return register_shrinker(&erofs_shrinker_info, "erofs-shrinker"); } void erofs_exit_shrinker(void) @@ -322,4 +290,3 @@ void erofs_exit_shrinker(void) unregister_shrinker(&erofs_shrinker_info); } #endif /* !CONFIG_EROFS_FS_ZIP */ - diff --git a/fs/erofs/xattr.c b/fs/erofs/xattr.c index b766c3ee5fa8..8106bcb5a38d 100644 --- a/fs/erofs/xattr.c +++ b/fs/erofs/xattr.c @@ -1,41 +1,21 @@ // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2017-2018 HUAWEI, Inc. - * http://www.huawei.com/ - * Created by Gao Xiang <gaoxiang25@huawei.com> + * https://www.huawei.com/ + * Copyright (C) 2021-2022, Alibaba Cloud */ #include <linux/security.h> #include "xattr.h" struct xattr_iter { struct super_block *sb; - struct page *page; + struct erofs_buf buf; void *kaddr; erofs_blk_t blkaddr; unsigned int ofs; }; -static inline void xattr_iter_end(struct xattr_iter *it, bool atomic) -{ - /* the only user of kunmap() is 'init_inode_xattrs' */ - if (!atomic) - kunmap(it->page); - else - kunmap_atomic(it->kaddr); - - unlock_page(it->page); - put_page(it->page); -} - -static inline void xattr_iter_end_final(struct xattr_iter *it) -{ - if (!it->page) - return; - - xattr_iter_end(it, true); -} - static int init_inode_xattrs(struct inode *inode) { struct erofs_inode *const vi = EROFS_I(inode); @@ -44,12 +24,17 @@ static int init_inode_xattrs(struct inode *inode) struct erofs_xattr_ibody_header *ih; struct super_block *sb; struct erofs_sb_info *sbi; - bool atomic_map; int ret = 0; /* the most case is that xattrs of this inode are initialized. */ - if (test_bit(EROFS_I_EA_INITED_BIT, &vi->flags)) + if (test_bit(EROFS_I_EA_INITED_BIT, &vi->flags)) { + /* + * paired with smp_mb() at the end of the function to ensure + * fields will only be observed after the bit is set. + */ + smp_mb(); return 0; + } if (wait_on_bit_lock(&vi->flags, EROFS_I_BL_XATTR_BIT, TASK_KILLABLE)) return -ERESTARTSYS; @@ -86,26 +71,23 @@ static int init_inode_xattrs(struct inode *inode) sb = inode->i_sb; sbi = EROFS_SB(sb); + it.buf = __EROFS_BUF_INITIALIZER; it.blkaddr = erofs_blknr(iloc(sbi, vi->nid) + vi->inode_isize); it.ofs = erofs_blkoff(iloc(sbi, vi->nid) + vi->inode_isize); - it.page = erofs_get_meta_page(sb, it.blkaddr); - if (IS_ERR(it.page)) { - ret = PTR_ERR(it.page); + /* read in shared xattr array (non-atomic, see kmalloc below) */ + it.kaddr = erofs_read_metabuf(&it.buf, sb, it.blkaddr, EROFS_KMAP); + if (IS_ERR(it.kaddr)) { + ret = PTR_ERR(it.kaddr); goto out_unlock; } - /* read in shared xattr array (non-atomic, see kmalloc below) */ - it.kaddr = kmap(it.page); - atomic_map = false; - ih = (struct erofs_xattr_ibody_header *)(it.kaddr + it.ofs); - vi->xattr_shared_count = ih->h_shared_count; vi->xattr_shared_xattrs = kmalloc_array(vi->xattr_shared_count, sizeof(uint), GFP_KERNEL); if (!vi->xattr_shared_xattrs) { - xattr_iter_end(&it, atomic_map); + erofs_put_metabuf(&it.buf); ret = -ENOMEM; goto out_unlock; } @@ -117,26 +99,25 @@ static int init_inode_xattrs(struct inode *inode) if (it.ofs >= EROFS_BLKSIZ) { /* cannot be unaligned */ DBG_BUGON(it.ofs != EROFS_BLKSIZ); - xattr_iter_end(&it, atomic_map); - it.page = erofs_get_meta_page(sb, ++it.blkaddr); - if (IS_ERR(it.page)) { + it.kaddr = erofs_read_metabuf(&it.buf, sb, ++it.blkaddr, + EROFS_KMAP); + if (IS_ERR(it.kaddr)) { kfree(vi->xattr_shared_xattrs); vi->xattr_shared_xattrs = NULL; - ret = PTR_ERR(it.page); + ret = PTR_ERR(it.kaddr); goto out_unlock; } - - it.kaddr = kmap_atomic(it.page); - atomic_map = true; it.ofs = 0; } vi->xattr_shared_xattrs[i] = le32_to_cpu(*(__le32 *)(it.kaddr + it.ofs)); it.ofs += sizeof(__le32); } - xattr_iter_end(&it, atomic_map); + erofs_put_metabuf(&it.buf); + /* paired with smp_mb() at the beginning of the function. */ + smp_mb(); set_bit(EROFS_I_EA_INITED_BIT, &vi->flags); out_unlock: @@ -165,19 +146,11 @@ static inline int xattr_iter_fixup(struct xattr_iter *it) if (it->ofs < EROFS_BLKSIZ) return 0; - xattr_iter_end(it, true); - it->blkaddr += erofs_blknr(it->ofs); - - it->page = erofs_get_meta_page(it->sb, it->blkaddr); - if (IS_ERR(it->page)) { - int err = PTR_ERR(it->page); - - it->page = NULL; - return err; - } - - it->kaddr = kmap_atomic(it->page); + it->kaddr = erofs_read_metabuf(&it->buf, it->sb, it->blkaddr, + EROFS_KMAP_ATOMIC); + if (IS_ERR(it->kaddr)) + return PTR_ERR(it->kaddr); it->ofs = erofs_blkoff(it->ofs); return 0; } @@ -200,11 +173,10 @@ static int inline_xattr_iter_begin(struct xattr_iter *it, it->blkaddr = erofs_blknr(iloc(sbi, vi->nid) + inline_xattr_ofs); it->ofs = erofs_blkoff(iloc(sbi, vi->nid) + inline_xattr_ofs); - it->page = erofs_get_meta_page(inode->i_sb, it->blkaddr); - if (IS_ERR(it->page)) - return PTR_ERR(it->page); - - it->kaddr = kmap_atomic(it->page); + it->kaddr = erofs_read_metabuf(&it->buf, inode->i_sb, it->blkaddr, + EROFS_KMAP_ATOMIC); + if (IS_ERR(it->kaddr)) + return PTR_ERR(it->kaddr); return vi->xattr_isize - xattr_header_sz; } @@ -265,7 +237,7 @@ static int xattr_foreach(struct xattr_iter *it, it->ofs = 0; } - slice = min_t(unsigned int, PAGE_SIZE - it->ofs, + slice = min_t(unsigned int, EROFS_BLKSIZ - it->ofs, entry.e_name_len - processed); /* handle name */ @@ -300,7 +272,7 @@ static int xattr_foreach(struct xattr_iter *it, it->ofs = 0; } - slice = min_t(unsigned int, PAGE_SIZE - it->ofs, + slice = min_t(unsigned int, EROFS_BLKSIZ - it->ofs, value_sz - processed); op->value(it, processed, it->kaddr + it->ofs, slice); it->ofs += slice; @@ -379,8 +351,6 @@ static int inline_getxattr(struct inode *inode, struct getxattr_iter *it) if (ret != -ENOATTR) break; } - xattr_iter_end_final(&it->it); - return ret ? ret : it->buffer_size; } @@ -397,32 +367,22 @@ static int shared_getxattr(struct inode *inode, struct getxattr_iter *it) xattrblock_addr(sbi, vi->xattr_shared_xattrs[i]); it->it.ofs = xattrblock_offset(sbi, vi->xattr_shared_xattrs[i]); - - if (!i || blkaddr != it->it.blkaddr) { - if (i) - xattr_iter_end(&it->it, true); - - it->it.page = erofs_get_meta_page(sb, blkaddr); - if (IS_ERR(it->it.page)) - return PTR_ERR(it->it.page); - - it->it.kaddr = kmap_atomic(it->it.page); - it->it.blkaddr = blkaddr; - } + it->it.kaddr = erofs_read_metabuf(&it->it.buf, sb, blkaddr, + EROFS_KMAP_ATOMIC); + if (IS_ERR(it->it.kaddr)) + return PTR_ERR(it->it.kaddr); + it->it.blkaddr = blkaddr; ret = xattr_foreach(&it->it, &find_xattr_handlers, NULL); if (ret != -ENOATTR) break; } - if (vi->xattr_shared_count) - xattr_iter_end_final(&it->it); - return ret ? ret : it->buffer_size; } static bool erofs_xattr_user_list(struct dentry *dentry) { - return test_opt(EROFS_SB(dentry->d_sb), XATTR_USER); + return test_opt(&EROFS_SB(dentry->d_sb)->opt, XATTR_USER); } static bool erofs_xattr_trusted_list(struct dentry *dentry) @@ -445,10 +405,11 @@ int erofs_getxattr(struct inode *inode, int index, return ret; it.index = index; - it.name.len = strlen(name); if (it.name.len > EROFS_NAME_LEN) return -ERANGE; + + it.it.buf = __EROFS_BUF_INITIALIZER; it.name.name = name; it.buffer = buffer; @@ -458,6 +419,7 @@ int erofs_getxattr(struct inode *inode, int index, ret = inline_getxattr(inode, &it); if (ret == -ENOATTR) ret = shared_getxattr(inode, &it); + erofs_put_metabuf(&it.it.buf); return ret; } @@ -469,12 +431,10 @@ static int erofs_xattr_generic_get(const struct xattr_handler *handler, switch (handler->flags) { case EROFS_XATTR_INDEX_USER: - if (!test_opt(sbi, XATTR_USER)) + if (!test_opt(&sbi->opt, XATTR_USER)) return -EOPNOTSUPP; break; case EROFS_XATTR_INDEX_TRUSTED: - if (!capable(CAP_SYS_ADMIN)) - return -EPERM; break; case EROFS_XATTR_INDEX_SECURITY: break; @@ -602,7 +562,6 @@ static int inline_listxattr(struct listxattr_iter *it) if (ret) break; } - xattr_iter_end_final(&it->it); return ret ? ret : it->buffer_ofs; } @@ -620,25 +579,16 @@ static int shared_listxattr(struct listxattr_iter *it) xattrblock_addr(sbi, vi->xattr_shared_xattrs[i]); it->it.ofs = xattrblock_offset(sbi, vi->xattr_shared_xattrs[i]); - if (!i || blkaddr != it->it.blkaddr) { - if (i) - xattr_iter_end(&it->it, true); - - it->it.page = erofs_get_meta_page(sb, blkaddr); - if (IS_ERR(it->it.page)) - return PTR_ERR(it->it.page); - - it->it.kaddr = kmap_atomic(it->it.page); - it->it.blkaddr = blkaddr; - } + it->it.kaddr = erofs_read_metabuf(&it->it.buf, sb, blkaddr, + EROFS_KMAP_ATOMIC); + if (IS_ERR(it->it.kaddr)) + return PTR_ERR(it->it.kaddr); + it->it.blkaddr = blkaddr; ret = xattr_foreach(&it->it, &list_xattr_handlers, NULL); if (ret) break; } - if (vi->xattr_shared_count) - xattr_iter_end_final(&it->it); - return ret ? ret : it->buffer_ofs; } @@ -654,6 +604,7 @@ ssize_t erofs_listxattr(struct dentry *dentry, if (ret) return ret; + it.it.buf = __EROFS_BUF_INITIALIZER; it.dentry = dentry; it.buffer = buffer; it.buffer_size = buffer_size; @@ -662,18 +613,22 @@ ssize_t erofs_listxattr(struct dentry *dentry, it.it.sb = dentry->d_sb; ret = inline_listxattr(&it); - if (ret < 0 && ret != -ENOATTR) - return ret; - return shared_listxattr(&it); + if (ret >= 0 || ret == -ENOATTR) + ret = shared_listxattr(&it); + erofs_put_metabuf(&it.it.buf); + return ret; } #ifdef CONFIG_EROFS_FS_POSIX_ACL -struct posix_acl *erofs_get_acl(struct inode *inode, int type) +struct posix_acl *erofs_get_acl(struct inode *inode, int type, bool rcu) { struct posix_acl *acl; int prefix, rc; char *value = NULL; + if (rcu) + return ERR_PTR(-ECHILD); + switch (type) { case ACL_TYPE_ACCESS: prefix = EROFS_XATTR_INDEX_POSIX_ACL_ACCESS; @@ -703,4 +658,3 @@ struct posix_acl *erofs_get_acl(struct inode *inode, int type) return acl; } #endif - diff --git a/fs/erofs/xattr.h b/fs/erofs/xattr.h index 50966f1c676e..0a43c9ee9f8f 100644 --- a/fs/erofs/xattr.h +++ b/fs/erofs/xattr.h @@ -1,8 +1,7 @@ /* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (C) 2017-2018 HUAWEI, Inc. - * http://www.huawei.com/ - * Created by Gao Xiang <gaoxiang25@huawei.com> + * https://www.huawei.com/ */ #ifndef __EROFS_XATTR_H #define __EROFS_XATTR_H @@ -40,9 +39,7 @@ static inline unsigned int xattrblock_offset(struct erofs_sb_info *sbi, #ifdef CONFIG_EROFS_FS_XATTR extern const struct xattr_handler erofs_xattr_user_handler; extern const struct xattr_handler erofs_xattr_trusted_handler; -#ifdef CONFIG_EROFS_FS_SECURITY extern const struct xattr_handler erofs_xattr_security_handler; -#endif static inline const struct xattr_handler *erofs_xattr_handler(unsigned int idx) { @@ -76,18 +73,14 @@ static inline int erofs_getxattr(struct inode *inode, int index, return -EOPNOTSUPP; } -static inline ssize_t erofs_listxattr(struct dentry *dentry, - char *buffer, size_t buffer_size) -{ - return -EOPNOTSUPP; -} +#define erofs_listxattr (NULL) +#define erofs_xattr_handlers (NULL) #endif /* !CONFIG_EROFS_FS_XATTR */ #ifdef CONFIG_EROFS_FS_POSIX_ACL -struct posix_acl *erofs_get_acl(struct inode *inode, int type); +struct posix_acl *erofs_get_acl(struct inode *inode, int type, bool rcu); #else #define erofs_get_acl (NULL) #endif #endif - diff --git a/fs/erofs/zdata.c b/fs/erofs/zdata.c index 80e47f07d946..064a166324a7 100644 --- a/fs/erofs/zdata.c +++ b/fs/erofs/zdata.c @@ -1,25 +1,188 @@ // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2018 HUAWEI, Inc. - * http://www.huawei.com/ - * Created by Gao Xiang <gaoxiang25@huawei.com> + * https://www.huawei.com/ + * Copyright (C) 2022 Alibaba Cloud */ #include "zdata.h" #include "compress.h" #include <linux/prefetch.h> +#include <linux/psi.h> #include <trace/events/erofs.h> /* - * a compressed_pages[] placeholder in order to avoid - * being filled with file pages for in-place decompression. + * since pclustersize is variable for big pcluster feature, introduce slab + * pools implementation for different pcluster sizes. */ -#define PAGE_UNALLOCATED ((void *)0x5F0E4B1D) +struct z_erofs_pcluster_slab { + struct kmem_cache *slab; + unsigned int maxpages; + char name[48]; +}; + +#define _PCLP(n) { .maxpages = n } + +static struct z_erofs_pcluster_slab pcluster_pool[] __read_mostly = { + _PCLP(1), _PCLP(4), _PCLP(16), _PCLP(64), _PCLP(128), + _PCLP(Z_EROFS_PCLUSTER_MAX_PAGES) +}; + +struct z_erofs_bvec_iter { + struct page *bvpage; + struct z_erofs_bvset *bvset; + unsigned int nr, cur; +}; + +static struct page *z_erofs_bvec_iter_end(struct z_erofs_bvec_iter *iter) +{ + if (iter->bvpage) + kunmap_local(iter->bvset); + return iter->bvpage; +} + +static struct page *z_erofs_bvset_flip(struct z_erofs_bvec_iter *iter) +{ + unsigned long base = (unsigned long)((struct z_erofs_bvset *)0)->bvec; + /* have to access nextpage in advance, otherwise it will be unmapped */ + struct page *nextpage = iter->bvset->nextpage; + struct page *oldpage; + + DBG_BUGON(!nextpage); + oldpage = z_erofs_bvec_iter_end(iter); + iter->bvpage = nextpage; + iter->bvset = kmap_local_page(nextpage); + iter->nr = (PAGE_SIZE - base) / sizeof(struct z_erofs_bvec); + iter->cur = 0; + return oldpage; +} + +static void z_erofs_bvec_iter_begin(struct z_erofs_bvec_iter *iter, + struct z_erofs_bvset_inline *bvset, + unsigned int bootstrap_nr, + unsigned int cur) +{ + *iter = (struct z_erofs_bvec_iter) { + .nr = bootstrap_nr, + .bvset = (struct z_erofs_bvset *)bvset, + }; + + while (cur > iter->nr) { + cur -= iter->nr; + z_erofs_bvset_flip(iter); + } + iter->cur = cur; +} + +static int z_erofs_bvec_enqueue(struct z_erofs_bvec_iter *iter, + struct z_erofs_bvec *bvec, + struct page **candidate_bvpage) +{ + if (iter->cur == iter->nr) { + if (!*candidate_bvpage) + return -EAGAIN; + + DBG_BUGON(iter->bvset->nextpage); + iter->bvset->nextpage = *candidate_bvpage; + z_erofs_bvset_flip(iter); + + iter->bvset->nextpage = NULL; + *candidate_bvpage = NULL; + } + iter->bvset->bvec[iter->cur++] = *bvec; + return 0; +} + +static void z_erofs_bvec_dequeue(struct z_erofs_bvec_iter *iter, + struct z_erofs_bvec *bvec, + struct page **old_bvpage) +{ + if (iter->cur == iter->nr) + *old_bvpage = z_erofs_bvset_flip(iter); + else + *old_bvpage = NULL; + *bvec = iter->bvset->bvec[iter->cur++]; +} + +static void z_erofs_destroy_pcluster_pool(void) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(pcluster_pool); ++i) { + if (!pcluster_pool[i].slab) + continue; + kmem_cache_destroy(pcluster_pool[i].slab); + pcluster_pool[i].slab = NULL; + } +} + +static int z_erofs_create_pcluster_pool(void) +{ + struct z_erofs_pcluster_slab *pcs; + struct z_erofs_pcluster *a; + unsigned int size; + + for (pcs = pcluster_pool; + pcs < pcluster_pool + ARRAY_SIZE(pcluster_pool); ++pcs) { + size = struct_size(a, compressed_bvecs, pcs->maxpages); + + sprintf(pcs->name, "erofs_pcluster-%u", pcs->maxpages); + pcs->slab = kmem_cache_create(pcs->name, size, 0, + SLAB_RECLAIM_ACCOUNT, NULL); + if (pcs->slab) + continue; + + z_erofs_destroy_pcluster_pool(); + return -ENOMEM; + } + return 0; +} + +static struct z_erofs_pcluster *z_erofs_alloc_pcluster(unsigned int nrpages) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(pcluster_pool); ++i) { + struct z_erofs_pcluster_slab *pcs = pcluster_pool + i; + struct z_erofs_pcluster *pcl; + + if (nrpages > pcs->maxpages) + continue; + + pcl = kmem_cache_zalloc(pcs->slab, GFP_NOFS); + if (!pcl) + return ERR_PTR(-ENOMEM); + pcl->pclusterpages = nrpages; + return pcl; + } + return ERR_PTR(-EINVAL); +} + +static void z_erofs_free_pcluster(struct z_erofs_pcluster *pcl) +{ + unsigned int pclusterpages = z_erofs_pclusterpages(pcl); + int i; + + for (i = 0; i < ARRAY_SIZE(pcluster_pool); ++i) { + struct z_erofs_pcluster_slab *pcs = pcluster_pool + i; + + if (pclusterpages > pcs->maxpages) + continue; + + kmem_cache_free(pcs->slab, pcl); + return; + } + DBG_BUGON(1); +} /* how to allocate cached pages for a pcluster */ enum z_erofs_cache_alloctype { DONTALLOC, /* don't allocate any cached pages */ - DELAYEDALLOC, /* delayed allocation (at the time of submitting io) */ + /* + * try to use cached I/O if page allocation succeeds or fallback + * to in-place I/O instead to avoid any direct reclaim. + */ + TRYALLOC, }; /* @@ -32,84 +195,62 @@ typedef tagptr1_t compressed_page_t; tagptr_fold(compressed_page_t, page, 1) static struct workqueue_struct *z_erofs_workqueue __read_mostly; -static struct kmem_cache *pcluster_cachep __read_mostly; void z_erofs_exit_zip_subsystem(void) { destroy_workqueue(z_erofs_workqueue); - kmem_cache_destroy(pcluster_cachep); + z_erofs_destroy_pcluster_pool(); } static inline int z_erofs_init_workqueue(void) { const unsigned int onlinecpus = num_possible_cpus(); - const unsigned int flags = WQ_UNBOUND | WQ_HIGHPRI | WQ_CPU_INTENSIVE; /* * no need to spawn too many threads, limiting threads could minimum * scheduling overhead, perhaps per-CPU threads should be better? */ - z_erofs_workqueue = alloc_workqueue("erofs_unzipd", flags, + z_erofs_workqueue = alloc_workqueue("erofs_unzipd", + WQ_UNBOUND | WQ_HIGHPRI, onlinecpus + onlinecpus / 4); return z_erofs_workqueue ? 0 : -ENOMEM; } -static void z_erofs_pcluster_init_once(void *ptr) -{ - struct z_erofs_pcluster *pcl = ptr; - struct z_erofs_collection *cl = z_erofs_primarycollection(pcl); - unsigned int i; - - mutex_init(&cl->lock); - cl->nr_pages = 0; - cl->vcnt = 0; - for (i = 0; i < Z_EROFS_CLUSTER_MAX_PAGES; ++i) - pcl->compressed_pages[i] = NULL; -} - -static void z_erofs_pcluster_init_always(struct z_erofs_pcluster *pcl) -{ - struct z_erofs_collection *cl = z_erofs_primarycollection(pcl); - - atomic_set(&pcl->obj.refcount, 1); - - DBG_BUGON(cl->nr_pages); - DBG_BUGON(cl->vcnt); -} - int __init z_erofs_init_zip_subsystem(void) { - pcluster_cachep = kmem_cache_create("erofs_compress", - Z_EROFS_WORKGROUP_SIZE, 0, - SLAB_RECLAIM_ACCOUNT, - z_erofs_pcluster_init_once); - if (pcluster_cachep) { - if (!z_erofs_init_workqueue()) - return 0; + int err = z_erofs_create_pcluster_pool(); - kmem_cache_destroy(pcluster_cachep); - } - return -ENOMEM; + if (err) + return err; + err = z_erofs_init_workqueue(); + if (err) + z_erofs_destroy_pcluster_pool(); + return err; } -enum z_erofs_collectmode { - COLLECT_SECONDARY, - COLLECT_PRIMARY, +enum z_erofs_pclustermode { + Z_EROFS_PCLUSTER_INFLIGHT, /* - * The current collection was the tail of an exist chain, in addition - * that the previous processed chained collections are all decided to + * The current pclusters was the tail of an exist chain, in addition + * that the previous processed chained pclusters are all decided to * be hooked up to it. - * A new chain will be created for the remaining collections which are - * not processed yet, therefore different from COLLECT_PRIMARY_FOLLOWED, - * the next collection cannot reuse the whole page safely in - * the following scenario: + * A new chain will be created for the remaining pclusters which are + * not processed yet, so different from Z_EROFS_PCLUSTER_FOLLOWED, + * the next pcluster cannot reuse the whole page safely for inplace I/O + * in the following scenario: * ________________________________________________________________ * | tail (partial) page | head (partial) page | - * | (belongs to the next cl) | (belongs to the current cl) | - * |_______PRIMARY_FOLLOWED_______|________PRIMARY_HOOKED___________| + * | (belongs to the next pcl) | (belongs to the current pcl) | + * |_______PCLUSTER_FOLLOWED______|________PCLUSTER_HOOKED__________| + */ + Z_EROFS_PCLUSTER_HOOKED, + /* + * a weak form of Z_EROFS_PCLUSTER_FOLLOWED, the difference is that it + * could be dispatched into bypass queue later due to uptodated managed + * pages. All related online pages cannot be reused for inplace I/O (or + * bvpage) since it can be directly decoded without I/O submission. */ - COLLECT_PRIMARY_HOOKED, - COLLECT_PRIMARY_FOLLOWED_NOINPLACE, + Z_EROFS_PCLUSTER_FOLLOWED_NOINPLACE, /* * The current collection has been linked with the owned chain, and * could also be linked with the remaining collections, which means @@ -120,91 +261,101 @@ enum z_erofs_collectmode { * ________________________________________________________________ * | tail (partial) page | head (partial) page | * | (of the current cl) | (of the previous collection) | - * | PRIMARY_FOLLOWED or | | - * |_____PRIMARY_HOOKED___|____________PRIMARY_FOLLOWED____________| + * | PCLUSTER_FOLLOWED or | | + * |_____PCLUSTER_HOOKED__|___________PCLUSTER_FOLLOWED____________| * * [ (*) the above page can be used as inplace I/O. ] */ - COLLECT_PRIMARY_FOLLOWED, -}; - -struct z_erofs_collector { - struct z_erofs_pagevec_ctor vector; - - struct z_erofs_pcluster *pcl, *tailpcl; - struct z_erofs_collection *cl; - struct page **compressedpages; - z_erofs_next_pcluster_t owned_head; - - enum z_erofs_collectmode mode; + Z_EROFS_PCLUSTER_FOLLOWED, }; struct z_erofs_decompress_frontend { struct inode *const inode; - - struct z_erofs_collector clt; struct erofs_map_blocks map; + struct z_erofs_bvec_iter biter; + struct page *candidate_bvpage; + struct z_erofs_pcluster *pcl, *tailpcl; + z_erofs_next_pcluster_t owned_head; + enum z_erofs_pclustermode mode; + + bool readahead; /* used for applying cache strategy on the fly */ bool backmost; erofs_off_t headoffset; -}; -#define COLLECTOR_INIT() { \ - .owned_head = Z_EROFS_PCLUSTER_TAIL, \ - .mode = COLLECT_PRIMARY_FOLLOWED } + /* a pointer used to pick up inplace I/O pages */ + unsigned int icur; +}; #define DECOMPRESS_FRONTEND_INIT(__i) { \ - .inode = __i, .clt = COLLECTOR_INIT(), \ - .backmost = true, } - -static struct page *z_pagemap_global[Z_EROFS_VMAP_GLOBAL_PAGES]; -static DEFINE_MUTEX(z_pagemap_global_lock); + .inode = __i, .owned_head = Z_EROFS_PCLUSTER_TAIL, \ + .mode = Z_EROFS_PCLUSTER_FOLLOWED, .backmost = true } -static void preload_compressed_pages(struct z_erofs_collector *clt, - struct address_space *mc, - enum z_erofs_cache_alloctype type, - struct list_head *pagepool) +static void z_erofs_bind_cache(struct z_erofs_decompress_frontend *fe, + enum z_erofs_cache_alloctype type, + struct page **pagepool) { - const struct z_erofs_pcluster *pcl = clt->pcl; - const unsigned int clusterpages = BIT(pcl->clusterbits); - struct page **pages = clt->compressedpages; - pgoff_t index = pcl->obj.index + (pages - pcl->compressed_pages); + struct address_space *mc = MNGD_MAPPING(EROFS_I_SB(fe->inode)); + struct z_erofs_pcluster *pcl = fe->pcl; bool standalone = true; + /* + * optimistic allocation without direct reclaim since inplace I/O + * can be used if low memory otherwise. + */ + gfp_t gfp = (mapping_gfp_mask(mc) & ~__GFP_DIRECT_RECLAIM) | + __GFP_NOMEMALLOC | __GFP_NORETRY | __GFP_NOWARN; + unsigned int i; - if (clt->mode < COLLECT_PRIMARY_FOLLOWED) + if (fe->mode < Z_EROFS_PCLUSTER_FOLLOWED) return; - for (; pages < pcl->compressed_pages + clusterpages; ++pages) { + for (i = 0; i < pcl->pclusterpages; ++i) { struct page *page; compressed_page_t t; + struct page *newpage = NULL; /* the compressed page was loaded before */ - if (READ_ONCE(*pages)) + if (READ_ONCE(pcl->compressed_bvecs[i].page)) continue; - page = find_get_page(mc, index); + page = find_get_page(mc, pcl->obj.index + i); if (page) { t = tag_compressed_page_justfound(page); - } else if (type == DELAYEDALLOC) { - t = tagptr_init(compressed_page_t, PAGE_UNALLOCATED); - } else { /* DONTALLOC */ - if (standalone) - clt->compressedpages = pages; + } else { + /* I/O is needed, no possible to decompress directly */ standalone = false; - continue; + switch (type) { + case TRYALLOC: + newpage = erofs_allocpage(pagepool, gfp); + if (!newpage) + continue; + set_page_private(newpage, + Z_EROFS_PREALLOCATED_PAGE); + t = tag_compressed_page_justfound(newpage); + break; + default: /* DONTALLOC */ + continue; + } } - if (!cmpxchg_relaxed(pages, NULL, tagptr_cast_ptr(t))) + if (!cmpxchg_relaxed(&pcl->compressed_bvecs[i].page, NULL, + tagptr_cast_ptr(t))) continue; if (page) put_page(page); + else if (newpage) + erofs_pagepool_add(pagepool, newpage); } - if (standalone) /* downgrade to PRIMARY_FOLLOWED_NOINPLACE */ - clt->mode = COLLECT_PRIMARY_FOLLOWED_NOINPLACE; + /* + * don't do inplace I/O if all compressed pages are available in + * managed cache since it can be moved to the bypass queue instead. + */ + if (standalone) + fe->mode = Z_EROFS_PCLUSTER_FOLLOWED_NOINPLACE; } /* called by erofs_shrinker to get rid of all compressed_pages */ @@ -213,16 +364,15 @@ int erofs_try_to_free_all_cached_pages(struct erofs_sb_info *sbi, { struct z_erofs_pcluster *const pcl = container_of(grp, struct z_erofs_pcluster, obj); - struct address_space *const mapping = MNGD_MAPPING(sbi); - const unsigned int clusterpages = BIT(pcl->clusterbits); int i; + DBG_BUGON(z_erofs_is_inline_pcluster(pcl)); /* * refcount of workgroup is now freezed as 1, * therefore no need to worry about available decompression users. */ - for (i = 0; i < clusterpages; ++i) { - struct page *page = pcl->compressed_pages[i]; + for (i = 0; i < pcl->pclusterpages; ++i) { + struct page *page = pcl->compressed_bvecs[i].page; if (!page) continue; @@ -231,265 +381,215 @@ int erofs_try_to_free_all_cached_pages(struct erofs_sb_info *sbi, if (!trylock_page(page)) return -EBUSY; - if (page->mapping != mapping) + if (!erofs_page_is_managed(sbi, page)) continue; /* barrier is implied in the following 'unlock_page' */ - WRITE_ONCE(pcl->compressed_pages[i], NULL); - set_page_private(page, 0); - ClearPagePrivate(page); - + WRITE_ONCE(pcl->compressed_bvecs[i].page, NULL); + detach_page_private(page); unlock_page(page); - put_page(page); } return 0; } -int erofs_try_to_free_cached_page(struct address_space *mapping, - struct page *page) +int erofs_try_to_free_cached_page(struct page *page) { struct z_erofs_pcluster *const pcl = (void *)page_private(page); - const unsigned int clusterpages = BIT(pcl->clusterbits); - int ret = 0; /* 0 - busy */ - - if (erofs_workgroup_try_to_freeze(&pcl->obj, 1)) { - unsigned int i; + int ret, i; - for (i = 0; i < clusterpages; ++i) { - if (pcl->compressed_pages[i] == page) { - WRITE_ONCE(pcl->compressed_pages[i], NULL); - ret = 1; - break; - } - } - erofs_workgroup_unfreeze(&pcl->obj, 1); + if (!erofs_workgroup_try_to_freeze(&pcl->obj, 1)) + return 0; - if (ret) { - ClearPagePrivate(page); - put_page(page); + ret = 0; + DBG_BUGON(z_erofs_is_inline_pcluster(pcl)); + for (i = 0; i < pcl->pclusterpages; ++i) { + if (pcl->compressed_bvecs[i].page == page) { + WRITE_ONCE(pcl->compressed_bvecs[i].page, NULL); + ret = 1; + break; } } + erofs_workgroup_unfreeze(&pcl->obj, 1); + if (ret) + detach_page_private(page); return ret; } -/* page_type must be Z_EROFS_PAGE_TYPE_EXCLUSIVE */ -static inline bool z_erofs_try_inplace_io(struct z_erofs_collector *clt, - struct page *page) +static bool z_erofs_try_inplace_io(struct z_erofs_decompress_frontend *fe, + struct z_erofs_bvec *bvec) { - struct z_erofs_pcluster *const pcl = clt->pcl; - const unsigned int clusterpages = BIT(pcl->clusterbits); + struct z_erofs_pcluster *const pcl = fe->pcl; - while (clt->compressedpages < pcl->compressed_pages + clusterpages) { - if (!cmpxchg(clt->compressedpages++, NULL, page)) + while (fe->icur > 0) { + if (!cmpxchg(&pcl->compressed_bvecs[--fe->icur].page, + NULL, bvec->page)) { + pcl->compressed_bvecs[fe->icur] = *bvec; return true; + } } return false; } -/* callers must be with collection lock held */ -static int z_erofs_attach_page(struct z_erofs_collector *clt, - struct page *page, - enum z_erofs_page_type type) +/* callers must be with pcluster lock held */ +static int z_erofs_attach_page(struct z_erofs_decompress_frontend *fe, + struct z_erofs_bvec *bvec, bool exclusive) { int ret; - bool occupied; - /* give priority for inplaceio */ - if (clt->mode >= COLLECT_PRIMARY && - type == Z_EROFS_PAGE_TYPE_EXCLUSIVE && - z_erofs_try_inplace_io(clt, page)) - return 0; - - ret = z_erofs_pagevec_enqueue(&clt->vector, - page, type, &occupied); - clt->cl->vcnt += (unsigned int)ret; - - return ret ? 0 : -EAGAIN; + if (exclusive) { + /* give priority for inplaceio to use file pages first */ + if (z_erofs_try_inplace_io(fe, bvec)) + return 0; + /* otherwise, check if it can be used as a bvpage */ + if (fe->mode >= Z_EROFS_PCLUSTER_FOLLOWED && + !fe->candidate_bvpage) + fe->candidate_bvpage = bvec->page; + } + ret = z_erofs_bvec_enqueue(&fe->biter, bvec, &fe->candidate_bvpage); + fe->pcl->vcnt += (ret >= 0); + return ret; } -static enum z_erofs_collectmode -try_to_claim_pcluster(struct z_erofs_pcluster *pcl, - z_erofs_next_pcluster_t *owned_head) +static void z_erofs_try_to_claim_pcluster(struct z_erofs_decompress_frontend *f) { - /* let's claim these following types of pclusters */ -retry: - if (pcl->next == Z_EROFS_PCLUSTER_NIL) { - /* type 1, nil pcluster */ - if (cmpxchg(&pcl->next, Z_EROFS_PCLUSTER_NIL, - *owned_head) != Z_EROFS_PCLUSTER_NIL) - goto retry; + struct z_erofs_pcluster *pcl = f->pcl; + z_erofs_next_pcluster_t *owned_head = &f->owned_head; + /* type 1, nil pcluster (this pcluster doesn't belong to any chain.) */ + if (cmpxchg(&pcl->next, Z_EROFS_PCLUSTER_NIL, + *owned_head) == Z_EROFS_PCLUSTER_NIL) { *owned_head = &pcl->next; - /* lucky, I am the followee :) */ - return COLLECT_PRIMARY_FOLLOWED; - } else if (pcl->next == Z_EROFS_PCLUSTER_TAIL) { - /* - * type 2, link to the end of a existing open chain, - * be careful that its submission itself is governed - * by the original owned chain. - */ - if (cmpxchg(&pcl->next, Z_EROFS_PCLUSTER_TAIL, - *owned_head) != Z_EROFS_PCLUSTER_TAIL) - goto retry; + /* so we can attach this pcluster to our submission chain. */ + f->mode = Z_EROFS_PCLUSTER_FOLLOWED; + return; + } + + /* + * type 2, link to the end of an existing open chain, be careful + * that its submission is controlled by the original attached chain. + */ + if (*owned_head != &pcl->next && pcl != f->tailpcl && + cmpxchg(&pcl->next, Z_EROFS_PCLUSTER_TAIL, + *owned_head) == Z_EROFS_PCLUSTER_TAIL) { *owned_head = Z_EROFS_PCLUSTER_TAIL; - return COLLECT_PRIMARY_HOOKED; + f->mode = Z_EROFS_PCLUSTER_HOOKED; + f->tailpcl = NULL; + return; } - return COLLECT_PRIMARY; /* :( better luck next time */ + /* type 3, it belongs to a chain, but it isn't the end of the chain */ + f->mode = Z_EROFS_PCLUSTER_INFLIGHT; } -static int z_erofs_lookup_collection(struct z_erofs_collector *clt, - struct inode *inode, - struct erofs_map_blocks *map) +static int z_erofs_register_pcluster(struct z_erofs_decompress_frontend *fe) { - struct erofs_workgroup *grp; + struct erofs_map_blocks *map = &fe->map; + bool ztailpacking = map->m_flags & EROFS_MAP_META; struct z_erofs_pcluster *pcl; - struct z_erofs_collection *cl; - unsigned int length; - - grp = erofs_find_workgroup(inode->i_sb, map->m_pa >> PAGE_SHIFT); - if (!grp) - return -ENOENT; - - pcl = container_of(grp, struct z_erofs_pcluster, obj); - if (clt->owned_head == &pcl->next || pcl == clt->tailpcl) { - DBG_BUGON(1); - erofs_workgroup_put(grp); - return -EFSCORRUPTED; - } + struct erofs_workgroup *grp; + int err; - cl = z_erofs_primarycollection(pcl); - if (cl->pageofs != (map->m_la & ~PAGE_MASK)) { + if (!(map->m_flags & EROFS_MAP_ENCODED)) { DBG_BUGON(1); - erofs_workgroup_put(grp); return -EFSCORRUPTED; } - length = READ_ONCE(pcl->length); - if (length & Z_EROFS_PCLUSTER_FULL_LENGTH) { - if ((map->m_llen << Z_EROFS_PCLUSTER_LENGTH_BIT) > length) { - DBG_BUGON(1); - erofs_workgroup_put(grp); - return -EFSCORRUPTED; - } - } else { - unsigned int llen = map->m_llen << Z_EROFS_PCLUSTER_LENGTH_BIT; - - if (map->m_flags & EROFS_MAP_FULL_MAPPED) - llen |= Z_EROFS_PCLUSTER_FULL_LENGTH; - - while (llen > length && - length != cmpxchg_relaxed(&pcl->length, length, llen)) { - cpu_relax(); - length = READ_ONCE(pcl->length); - } - } - mutex_lock(&cl->lock); - /* used to check tail merging loop due to corrupted images */ - if (clt->owned_head == Z_EROFS_PCLUSTER_TAIL) - clt->tailpcl = pcl; - clt->mode = try_to_claim_pcluster(pcl, &clt->owned_head); - /* clean tailpcl if the current owned_head is Z_EROFS_PCLUSTER_TAIL */ - if (clt->owned_head == Z_EROFS_PCLUSTER_TAIL) - clt->tailpcl = NULL; - clt->pcl = pcl; - clt->cl = cl; - return 0; -} + /* no available pcluster, let's allocate one */ + pcl = z_erofs_alloc_pcluster(ztailpacking ? 1 : + map->m_plen >> PAGE_SHIFT); + if (IS_ERR(pcl)) + return PTR_ERR(pcl); -static int z_erofs_register_collection(struct z_erofs_collector *clt, - struct inode *inode, - struct erofs_map_blocks *map) -{ - struct z_erofs_pcluster *pcl; - struct z_erofs_collection *cl; - int err; - - /* no available workgroup, let's allocate one */ - pcl = kmem_cache_alloc(pcluster_cachep, GFP_NOFS); - if (!pcl) - return -ENOMEM; - - z_erofs_pcluster_init_always(pcl); - pcl->obj.index = map->m_pa >> PAGE_SHIFT; - - pcl->length = (map->m_llen << Z_EROFS_PCLUSTER_LENGTH_BIT) | - (map->m_flags & EROFS_MAP_FULL_MAPPED ? - Z_EROFS_PCLUSTER_FULL_LENGTH : 0); - - if (map->m_flags & EROFS_MAP_ZIPPED) - pcl->algorithmformat = Z_EROFS_COMPRESSION_LZ4; - else - pcl->algorithmformat = Z_EROFS_COMPRESSION_SHIFTED; - - pcl->clusterbits = EROFS_I(inode)->z_physical_clusterbits[0]; - pcl->clusterbits -= PAGE_SHIFT; + atomic_set(&pcl->obj.refcount, 1); + pcl->algorithmformat = map->m_algorithmformat; + pcl->length = 0; + pcl->partial = true; /* new pclusters should be claimed as type 1, primary and followed */ - pcl->next = clt->owned_head; - clt->mode = COLLECT_PRIMARY_FOLLOWED; - - cl = z_erofs_primarycollection(pcl); - cl->pageofs = map->m_la & ~PAGE_MASK; + pcl->next = fe->owned_head; + pcl->pageofs_out = map->m_la & ~PAGE_MASK; + fe->mode = Z_EROFS_PCLUSTER_FOLLOWED; /* * lock all primary followed works before visible to others * and mutex_trylock *never* fails for a new pcluster. */ - mutex_trylock(&cl->lock); + mutex_init(&pcl->lock); + DBG_BUGON(!mutex_trylock(&pcl->lock)); - err = erofs_register_workgroup(inode->i_sb, &pcl->obj); - if (err) { - mutex_unlock(&cl->lock); - kmem_cache_free(pcluster_cachep, pcl); - return -EAGAIN; + if (ztailpacking) { + pcl->obj.index = 0; /* which indicates ztailpacking */ + pcl->pageofs_in = erofs_blkoff(map->m_pa); + pcl->tailpacking_size = map->m_plen; + } else { + pcl->obj.index = map->m_pa >> PAGE_SHIFT; + + grp = erofs_insert_workgroup(fe->inode->i_sb, &pcl->obj); + if (IS_ERR(grp)) { + err = PTR_ERR(grp); + goto err_out; + } + + if (grp != &pcl->obj) { + fe->pcl = container_of(grp, + struct z_erofs_pcluster, obj); + err = -EEXIST; + goto err_out; + } } /* used to check tail merging loop due to corrupted images */ - if (clt->owned_head == Z_EROFS_PCLUSTER_TAIL) - clt->tailpcl = pcl; - clt->owned_head = &pcl->next; - clt->pcl = pcl; - clt->cl = cl; + if (fe->owned_head == Z_EROFS_PCLUSTER_TAIL) + fe->tailpcl = pcl; + fe->owned_head = &pcl->next; + fe->pcl = pcl; return 0; + +err_out: + mutex_unlock(&pcl->lock); + z_erofs_free_pcluster(pcl); + return err; } -static int z_erofs_collector_begin(struct z_erofs_collector *clt, - struct inode *inode, - struct erofs_map_blocks *map) +static int z_erofs_collector_begin(struct z_erofs_decompress_frontend *fe) { + struct erofs_map_blocks *map = &fe->map; + struct erofs_workgroup *grp = NULL; int ret; - DBG_BUGON(clt->cl); + DBG_BUGON(fe->pcl); - /* must be Z_EROFS_PCLUSTER_TAIL or pointed to previous collection */ - DBG_BUGON(clt->owned_head == Z_EROFS_PCLUSTER_NIL); - DBG_BUGON(clt->owned_head == Z_EROFS_PCLUSTER_TAIL_CLOSED); + /* must be Z_EROFS_PCLUSTER_TAIL or pointed to previous pcluster */ + DBG_BUGON(fe->owned_head == Z_EROFS_PCLUSTER_NIL); + DBG_BUGON(fe->owned_head == Z_EROFS_PCLUSTER_TAIL_CLOSED); - if (!PAGE_ALIGNED(map->m_pa)) { + if (!(map->m_flags & EROFS_MAP_META)) { + grp = erofs_find_workgroup(fe->inode->i_sb, + map->m_pa >> PAGE_SHIFT); + } else if ((map->m_pa & ~PAGE_MASK) + map->m_plen > PAGE_SIZE) { DBG_BUGON(1); - return -EINVAL; + return -EFSCORRUPTED; } -repeat: - ret = z_erofs_lookup_collection(clt, inode, map); - if (ret == -ENOENT) { - ret = z_erofs_register_collection(clt, inode, map); - - /* someone registered at the same time, give another try */ - if (ret == -EAGAIN) { - cond_resched(); - goto repeat; - } + if (grp) { + fe->pcl = container_of(grp, struct z_erofs_pcluster, obj); + ret = -EEXIST; + } else { + ret = z_erofs_register_pcluster(fe); } - if (ret) - return ret; - - z_erofs_pagevec_ctor_init(&clt->vector, Z_EROFS_NR_INLINE_PAGEVECS, - clt->cl->pagevec, clt->cl->vcnt); + if (ret == -EEXIST) { + mutex_lock(&fe->pcl->lock); + /* used to check tail merging loop due to corrupted images */ + if (fe->owned_head == Z_EROFS_PCLUSTER_TAIL) + fe->tailpcl = fe->pcl; - clt->compressedpages = clt->pcl->compressed_pages; - if (clt->mode <= COLLECT_PRIMARY) /* cannot do in-place I/O */ - clt->compressedpages += Z_EROFS_CLUSTER_MAX_PAGES; + z_erofs_try_to_claim_pcluster(fe); + } else if (ret) { + return ret; + } + z_erofs_bvec_iter_begin(&fe->biter, &fe->pcl->bvset, + Z_EROFS_INLINE_BVECS, fe->pcl->vcnt); + /* since file-backed online pages are traversed in reverse order */ + fe->icur = z_erofs_pclusterpages(fe->pcl); return 0; } @@ -499,49 +599,41 @@ repeat: */ static void z_erofs_rcu_callback(struct rcu_head *head) { - struct z_erofs_collection *const cl = - container_of(head, struct z_erofs_collection, rcu); - - kmem_cache_free(pcluster_cachep, - container_of(cl, struct z_erofs_pcluster, - primary_collection)); + z_erofs_free_pcluster(container_of(head, + struct z_erofs_pcluster, rcu)); } void erofs_workgroup_free_rcu(struct erofs_workgroup *grp) { struct z_erofs_pcluster *const pcl = container_of(grp, struct z_erofs_pcluster, obj); - struct z_erofs_collection *const cl = z_erofs_primarycollection(pcl); - - call_rcu(&cl->rcu, z_erofs_rcu_callback); -} - -static void z_erofs_collection_put(struct z_erofs_collection *cl) -{ - struct z_erofs_pcluster *const pcl = - container_of(cl, struct z_erofs_pcluster, primary_collection); - erofs_workgroup_put(&pcl->obj); + call_rcu(&pcl->rcu, z_erofs_rcu_callback); } -static bool z_erofs_collector_end(struct z_erofs_collector *clt) +static bool z_erofs_collector_end(struct z_erofs_decompress_frontend *fe) { - struct z_erofs_collection *cl = clt->cl; + struct z_erofs_pcluster *pcl = fe->pcl; - if (!cl) + if (!pcl) return false; - z_erofs_pagevec_ctor_exit(&clt->vector, false); - mutex_unlock(&cl->lock); + z_erofs_bvec_iter_end(&fe->biter); + mutex_unlock(&pcl->lock); + + if (fe->candidate_bvpage) { + DBG_BUGON(z_erofs_is_shortlived_page(fe->candidate_bvpage)); + fe->candidate_bvpage = NULL; + } /* * if all pending pages are added, don't hold its reference * any longer if the pcluster isn't hosted by ourselves. */ - if (clt->mode < COLLECT_PRIMARY_FOLLOWED_NOINPLACE) - z_erofs_collection_put(cl); + if (fe->mode < Z_EROFS_PCLUSTER_FOLLOWED_NOINPLACE) + erofs_workgroup_put(&pcl->obj); - clt->cl = NULL; + fe->pcl = NULL; return true; } @@ -559,20 +651,46 @@ static bool should_alloc_managed_pages(struct z_erofs_decompress_frontend *fe, la < fe->headoffset; } +static int z_erofs_read_fragment(struct inode *inode, erofs_off_t pos, + struct page *page, unsigned int pageofs, + unsigned int len) +{ + struct inode *packed_inode = EROFS_I_SB(inode)->packed_inode; + struct erofs_buf buf = __EROFS_BUF_INITIALIZER; + u8 *src, *dst; + unsigned int i, cnt; + + pos += EROFS_I(inode)->z_fragmentoff; + for (i = 0; i < len; i += cnt) { + cnt = min_t(unsigned int, len - i, + EROFS_BLKSIZ - erofs_blkoff(pos)); + src = erofs_bread(&buf, packed_inode, + erofs_blknr(pos), EROFS_KMAP); + if (IS_ERR(src)) { + erofs_put_metabuf(&buf); + return PTR_ERR(src); + } + + dst = kmap_local_page(page); + memcpy(dst + pageofs + i, src + erofs_blkoff(pos), cnt); + kunmap_local(dst); + pos += cnt; + } + erofs_put_metabuf(&buf); + return 0; +} + static int z_erofs_do_read_page(struct z_erofs_decompress_frontend *fe, - struct page *page, - struct list_head *pagepool) + struct page *page, struct page **pagepool) { struct inode *const inode = fe->inode; struct erofs_sb_info *const sbi = EROFS_I_SB(inode); struct erofs_map_blocks *const map = &fe->map; - struct z_erofs_collector *const clt = &fe->clt; const loff_t offset = page_offset(page); - bool tight = true; + bool tight = true, exclusive; enum z_erofs_cache_alloctype cache_strategy; - enum z_erofs_page_type page_type; - unsigned int cur, end, spiltted, index; + unsigned int cur, end, spiltted; int err = 0; /* register locked file pages as online pages in pack */ @@ -583,379 +701,456 @@ static int z_erofs_do_read_page(struct z_erofs_decompress_frontend *fe, repeat: cur = end - 1; - /* lucky, within the range of the current map_blocks */ - if (offset + cur >= map->m_la && - offset + cur < map->m_la + map->m_llen) { - /* didn't get a valid collection previously (very rare) */ - if (!clt->cl) - goto restart_now; - goto hitted; - } - - /* go ahead the next map_blocks */ - erofs_dbg("%s: [out-of-range] pos %llu", __func__, offset + cur); + if (offset + cur < map->m_la || + offset + cur >= map->m_la + map->m_llen) { + erofs_dbg("out-of-range map @ pos %llu", offset + cur); - if (z_erofs_collector_end(clt)) - fe->backmost = false; - - map->m_la = offset + cur; - map->m_llen = 0; - err = z_erofs_map_blocks_iter(inode, map, 0); - if (err) - goto err_out; + if (z_erofs_collector_end(fe)) + fe->backmost = false; + map->m_la = offset + cur; + map->m_llen = 0; + err = z_erofs_map_blocks_iter(inode, map, 0); + if (err) + goto out; + } else { + if (fe->pcl) + goto hitted; + /* didn't get a valid pcluster previously (very rare) */ + } -restart_now: - if (!(map->m_flags & EROFS_MAP_MAPPED)) + if (!(map->m_flags & EROFS_MAP_MAPPED) || + map->m_flags & EROFS_MAP_FRAGMENT) goto hitted; - err = z_erofs_collector_begin(clt, inode, map); + err = z_erofs_collector_begin(fe); if (err) - goto err_out; + goto out; - /* preload all compressed pages (maybe downgrade role if necessary) */ - if (should_alloc_managed_pages(fe, sbi->cache_strategy, map->m_la)) - cache_strategy = DELAYEDALLOC; - else - cache_strategy = DONTALLOC; + if (z_erofs_is_inline_pcluster(fe->pcl)) { + void *mp; - preload_compressed_pages(clt, MNGD_MAPPING(sbi), - cache_strategy, pagepool); + mp = erofs_read_metabuf(&fe->map.buf, inode->i_sb, + erofs_blknr(map->m_pa), EROFS_NO_KMAP); + if (IS_ERR(mp)) { + err = PTR_ERR(mp); + erofs_err(inode->i_sb, + "failed to get inline page, err %d", err); + goto out; + } + get_page(fe->map.buf.page); + WRITE_ONCE(fe->pcl->compressed_bvecs[0].page, + fe->map.buf.page); + fe->mode = Z_EROFS_PCLUSTER_FOLLOWED_NOINPLACE; + } else { + /* bind cache first when cached decompression is preferred */ + if (should_alloc_managed_pages(fe, sbi->opt.cache_strategy, + map->m_la)) + cache_strategy = TRYALLOC; + else + cache_strategy = DONTALLOC; + z_erofs_bind_cache(fe, cache_strategy, pagepool); + } hitted: /* * Ensure the current partial page belongs to this submit chain rather * than other concurrent submit chains or the noio(bypass) chain since * those chains are handled asynchronously thus the page cannot be used - * for inplace I/O or pagevec (should be processed in strict order.) + * for inplace I/O or bvpage (should be processed in a strict order.) */ - tight &= (clt->mode >= COLLECT_PRIMARY_HOOKED && - clt->mode != COLLECT_PRIMARY_FOLLOWED_NOINPLACE); + tight &= (fe->mode >= Z_EROFS_PCLUSTER_HOOKED && + fe->mode != Z_EROFS_PCLUSTER_FOLLOWED_NOINPLACE); cur = end - min_t(unsigned int, offset + end - map->m_la, end); if (!(map->m_flags & EROFS_MAP_MAPPED)) { zero_user_segment(page, cur, end); goto next_part; } + if (map->m_flags & EROFS_MAP_FRAGMENT) { + unsigned int pageofs, skip, len; - /* let's derive page type */ - page_type = cur ? Z_EROFS_VLE_PAGE_TYPE_HEAD : - (!spiltted ? Z_EROFS_PAGE_TYPE_EXCLUSIVE : - (tight ? Z_EROFS_PAGE_TYPE_EXCLUSIVE : - Z_EROFS_VLE_PAGE_TYPE_TAIL_SHARED)); + if (offset > map->m_la) { + pageofs = 0; + skip = offset - map->m_la; + } else { + pageofs = map->m_la & ~PAGE_MASK; + skip = 0; + } + len = min_t(unsigned int, map->m_llen - skip, end - cur); + err = z_erofs_read_fragment(inode, skip, page, pageofs, len); + if (err) + goto out; + ++spiltted; + tight = false; + goto next_part; + } + exclusive = (!cur && (!spiltted || tight)); if (cur) - tight &= (clt->mode >= COLLECT_PRIMARY_FOLLOWED); + tight &= (fe->mode >= Z_EROFS_PCLUSTER_FOLLOWED); retry: - err = z_erofs_attach_page(clt, page, page_type); - /* should allocate an additional staging page for pagevec */ - if (err == -EAGAIN) { - struct page *const newpage = - erofs_allocpage(pagepool, GFP_NOFS | __GFP_NOFAIL); - - newpage->mapping = Z_EROFS_MAPPING_STAGING; - err = z_erofs_attach_page(clt, newpage, - Z_EROFS_PAGE_TYPE_EXCLUSIVE); - if (!err) - goto retry; + err = z_erofs_attach_page(fe, &((struct z_erofs_bvec) { + .page = page, + .offset = offset - map->m_la, + .end = end, + }), exclusive); + /* should allocate an additional short-lived page for bvset */ + if (err == -EAGAIN && !fe->candidate_bvpage) { + fe->candidate_bvpage = alloc_page(GFP_NOFS | __GFP_NOFAIL); + set_page_private(fe->candidate_bvpage, + Z_EROFS_SHORTLIVED_PAGE); + goto retry; } - if (err) - goto err_out; - - index = page->index - (map->m_la >> PAGE_SHIFT); - - z_erofs_onlinepage_fixup(page, index, true); + if (err) { + DBG_BUGON(err == -EAGAIN && fe->candidate_bvpage); + goto out; + } + z_erofs_onlinepage_split(page); /* bump up the number of spiltted parts of a page */ ++spiltted; - /* also update nr_pages */ - clt->cl->nr_pages = max_t(pgoff_t, clt->cl->nr_pages, index + 1); + if (fe->pcl->pageofs_out != (map->m_la & ~PAGE_MASK)) + fe->pcl->multibases = true; + if (fe->pcl->length < offset + end - map->m_la) { + fe->pcl->length = offset + end - map->m_la; + fe->pcl->pageofs_out = map->m_la & ~PAGE_MASK; + } + if ((map->m_flags & EROFS_MAP_FULL_MAPPED) && + !(map->m_flags & EROFS_MAP_PARTIAL_REF) && + fe->pcl->length == map->m_llen) + fe->pcl->partial = false; next_part: - /* can be used for verification */ + /* shorten the remaining extent to update progress */ map->m_llen = offset + cur - map->m_la; + map->m_flags &= ~EROFS_MAP_FULL_MAPPED; end = cur; if (end > 0) goto repeat; out: + if (err) + z_erofs_page_mark_eio(page); z_erofs_onlinepage_endio(page); erofs_dbg("%s, finish page: %pK spiltted: %u map->m_llen %llu", __func__, page, spiltted, map->m_llen); return err; - - /* if some error occurred while processing this page */ -err_out: - SetPageError(page); - goto out; } -static void z_erofs_decompress_kickoff(struct z_erofs_decompressqueue *io, - bool sync, int bios) +static bool z_erofs_get_sync_decompress_policy(struct erofs_sb_info *sbi, + unsigned int readahead_pages) { - /* wake up the caller thread for sync decompression */ - if (sync) { - unsigned long flags; + /* auto: enable for read_folio, disable for readahead */ + if ((sbi->opt.sync_decompress == EROFS_SYNC_DECOMPRESS_AUTO) && + !readahead_pages) + return true; - spin_lock_irqsave(&io->u.wait.lock, flags); - if (!atomic_add_return(bios, &io->pending_bios)) - wake_up_locked(&io->u.wait); - spin_unlock_irqrestore(&io->u.wait.lock, flags); - return; - } + if ((sbi->opt.sync_decompress == EROFS_SYNC_DECOMPRESS_FORCE_ON) && + (readahead_pages <= sbi->opt.max_sync_decompress_pages)) + return true; - if (!atomic_add_return(bios, &io->pending_bios)) - queue_work(z_erofs_workqueue, &io->u.work); + return false; } -static void z_erofs_decompressqueue_endio(struct bio *bio) +static bool z_erofs_page_is_invalidated(struct page *page) { - tagptr1_t t = tagptr_init(tagptr1_t, bio->bi_private); - struct z_erofs_decompressqueue *q = tagptr_unfold_ptr(t); - blk_status_t err = bio->bi_status; - struct bio_vec *bvec; - struct bvec_iter_all iter_all; + return !page->mapping && !z_erofs_is_shortlived_page(page); +} - bio_for_each_segment_all(bvec, bio, iter_all) { - struct page *page = bvec->bv_page; +struct z_erofs_decompress_backend { + struct page *onstack_pages[Z_EROFS_ONSTACK_PAGES]; + struct super_block *sb; + struct z_erofs_pcluster *pcl; - DBG_BUGON(PageUptodate(page)); - DBG_BUGON(!page->mapping); + /* pages with the longest decompressed length for deduplication */ + struct page **decompressed_pages; + /* pages to keep the compressed data */ + struct page **compressed_pages; - if (err) - SetPageError(page); + struct list_head decompressed_secondary_bvecs; + struct page **pagepool; + unsigned int onstack_used, nr_pages; +}; - if (erofs_page_is_managed(EROFS_SB(q->sb), page)) { - if (!err) - SetPageUptodate(page); - unlock_page(page); - } - } - z_erofs_decompress_kickoff(q, tagptr_unfold_tags(t), -1); - bio_put(bio); -} +struct z_erofs_bvec_item { + struct z_erofs_bvec bvec; + struct list_head list; +}; -static int z_erofs_decompress_pcluster(struct super_block *sb, - struct z_erofs_pcluster *pcl, - struct list_head *pagepool) +static void z_erofs_do_decompressed_bvec(struct z_erofs_decompress_backend *be, + struct z_erofs_bvec *bvec) { - struct erofs_sb_info *const sbi = EROFS_SB(sb); - const unsigned int clusterpages = BIT(pcl->clusterbits); - struct z_erofs_pagevec_ctor ctor; - unsigned int i, outputsize, llen, nr_pages; - struct page *pages_onstack[Z_EROFS_VMAP_ONSTACK_PAGES]; - struct page **pages, **compressed_pages, *page; - - enum z_erofs_page_type page_type; - bool overlapped, partial; - struct z_erofs_collection *cl; - int err; + struct z_erofs_bvec_item *item; - might_sleep(); - cl = z_erofs_primarycollection(pcl); - DBG_BUGON(!READ_ONCE(cl->nr_pages)); + if (!((bvec->offset + be->pcl->pageofs_out) & ~PAGE_MASK)) { + unsigned int pgnr; - mutex_lock(&cl->lock); - nr_pages = cl->nr_pages; - - if (nr_pages <= Z_EROFS_VMAP_ONSTACK_PAGES) { - pages = pages_onstack; - } else if (nr_pages <= Z_EROFS_VMAP_GLOBAL_PAGES && - mutex_trylock(&z_pagemap_global_lock)) { - pages = z_pagemap_global; - } else { - gfp_t gfp_flags = GFP_KERNEL; - - if (nr_pages > Z_EROFS_VMAP_GLOBAL_PAGES) - gfp_flags |= __GFP_NOFAIL; + pgnr = (bvec->offset + be->pcl->pageofs_out) >> PAGE_SHIFT; + DBG_BUGON(pgnr >= be->nr_pages); + if (!be->decompressed_pages[pgnr]) { + be->decompressed_pages[pgnr] = bvec->page; + return; + } + } - pages = kvmalloc_array(nr_pages, sizeof(struct page *), - gfp_flags); + /* (cold path) one pcluster is requested multiple times */ + item = kmalloc(sizeof(*item), GFP_KERNEL | __GFP_NOFAIL); + item->bvec = *bvec; + list_add(&item->list, &be->decompressed_secondary_bvecs); +} - /* fallback to global pagemap for the lowmem scenario */ - if (!pages) { - mutex_lock(&z_pagemap_global_lock); - pages = z_pagemap_global; +static void z_erofs_fill_other_copies(struct z_erofs_decompress_backend *be, + int err) +{ + unsigned int off0 = be->pcl->pageofs_out; + struct list_head *p, *n; + + list_for_each_safe(p, n, &be->decompressed_secondary_bvecs) { + struct z_erofs_bvec_item *bvi; + unsigned int end, cur; + void *dst, *src; + + bvi = container_of(p, struct z_erofs_bvec_item, list); + cur = bvi->bvec.offset < 0 ? -bvi->bvec.offset : 0; + end = min_t(unsigned int, be->pcl->length - bvi->bvec.offset, + bvi->bvec.end); + dst = kmap_local_page(bvi->bvec.page); + while (cur < end) { + unsigned int pgnr, scur, len; + + pgnr = (bvi->bvec.offset + cur + off0) >> PAGE_SHIFT; + DBG_BUGON(pgnr >= be->nr_pages); + + scur = bvi->bvec.offset + cur - + ((pgnr << PAGE_SHIFT) - off0); + len = min_t(unsigned int, end - cur, PAGE_SIZE - scur); + if (!be->decompressed_pages[pgnr]) { + err = -EFSCORRUPTED; + cur += len; + continue; + } + src = kmap_local_page(be->decompressed_pages[pgnr]); + memcpy(dst + cur, src + scur, len); + kunmap_local(src); + cur += len; } + kunmap_local(dst); + if (err) + z_erofs_page_mark_eio(bvi->bvec.page); + z_erofs_onlinepage_endio(bvi->bvec.page); + list_del(p); + kfree(bvi); } +} - for (i = 0; i < nr_pages; ++i) - pages[i] = NULL; +static void z_erofs_parse_out_bvecs(struct z_erofs_decompress_backend *be) +{ + struct z_erofs_pcluster *pcl = be->pcl; + struct z_erofs_bvec_iter biter; + struct page *old_bvpage; + int i; - err = 0; - z_erofs_pagevec_ctor_init(&ctor, Z_EROFS_NR_INLINE_PAGEVECS, - cl->pagevec, 0); + z_erofs_bvec_iter_begin(&biter, &pcl->bvset, Z_EROFS_INLINE_BVECS, 0); + for (i = 0; i < pcl->vcnt; ++i) { + struct z_erofs_bvec bvec; - for (i = 0; i < cl->vcnt; ++i) { - unsigned int pagenr; + z_erofs_bvec_dequeue(&biter, &bvec, &old_bvpage); - page = z_erofs_pagevec_dequeue(&ctor, &page_type); + if (old_bvpage) + z_erofs_put_shortlivedpage(be->pagepool, old_bvpage); - /* all pages in pagevec ought to be valid */ - DBG_BUGON(!page); - DBG_BUGON(!page->mapping); + DBG_BUGON(z_erofs_page_is_invalidated(bvec.page)); + z_erofs_do_decompressed_bvec(be, &bvec); + } - if (z_erofs_put_stagingpage(pagepool, page)) - continue; + old_bvpage = z_erofs_bvec_iter_end(&biter); + if (old_bvpage) + z_erofs_put_shortlivedpage(be->pagepool, old_bvpage); +} - if (page_type == Z_EROFS_VLE_PAGE_TYPE_HEAD) - pagenr = 0; - else - pagenr = z_erofs_onlinepage_index(page); +static int z_erofs_parse_in_bvecs(struct z_erofs_decompress_backend *be, + bool *overlapped) +{ + struct z_erofs_pcluster *pcl = be->pcl; + unsigned int pclusterpages = z_erofs_pclusterpages(pcl); + int i, err = 0; - DBG_BUGON(pagenr >= nr_pages); + *overlapped = false; + for (i = 0; i < pclusterpages; ++i) { + struct z_erofs_bvec *bvec = &pcl->compressed_bvecs[i]; + struct page *page = bvec->page; - /* - * currently EROFS doesn't support multiref(dedup), - * so here erroring out one multiref page. - */ - if (pages[pagenr]) { + /* compressed pages ought to be present before decompressing */ + if (!page) { DBG_BUGON(1); - SetPageError(pages[pagenr]); - z_erofs_onlinepage_endio(pages[pagenr]); - err = -EFSCORRUPTED; + continue; } - pages[pagenr] = page; - } - z_erofs_pagevec_ctor_exit(&ctor, true); - - overlapped = false; - compressed_pages = pcl->compressed_pages; - - for (i = 0; i < clusterpages; ++i) { - unsigned int pagenr; - - page = compressed_pages[i]; + be->compressed_pages[i] = page; - /* all compressed pages ought to be valid */ - DBG_BUGON(!page); - DBG_BUGON(!page->mapping); + if (z_erofs_is_inline_pcluster(pcl)) { + if (!PageUptodate(page)) + err = -EIO; + continue; + } - if (!z_erofs_page_is_staging(page)) { - if (erofs_page_is_managed(sbi, page)) { + DBG_BUGON(z_erofs_page_is_invalidated(page)); + if (!z_erofs_is_shortlived_page(page)) { + if (erofs_page_is_managed(EROFS_SB(be->sb), page)) { if (!PageUptodate(page)) err = -EIO; continue; } - - /* - * only if non-head page can be selected - * for inplace decompression - */ - pagenr = z_erofs_onlinepage_index(page); - - DBG_BUGON(pagenr >= nr_pages); - if (pages[pagenr]) { - DBG_BUGON(1); - SetPageError(pages[pagenr]); - z_erofs_onlinepage_endio(pages[pagenr]); - err = -EFSCORRUPTED; - } - pages[pagenr] = page; - - overlapped = true; + z_erofs_do_decompressed_bvec(be, bvec); + *overlapped = true; } + } - /* PG_error needs checking for inplaced and staging pages */ - if (PageError(page)) { - DBG_BUGON(PageUptodate(page)); - err = -EIO; - } + if (err) + return err; + return 0; +} + +static int z_erofs_decompress_pcluster(struct z_erofs_decompress_backend *be, + int err) +{ + struct erofs_sb_info *const sbi = EROFS_SB(be->sb); + struct z_erofs_pcluster *pcl = be->pcl; + unsigned int pclusterpages = z_erofs_pclusterpages(pcl); + unsigned int i, inputsize; + int err2; + struct page *page; + bool overlapped; + + mutex_lock(&pcl->lock); + be->nr_pages = PAGE_ALIGN(pcl->length + pcl->pageofs_out) >> PAGE_SHIFT; + + /* allocate (de)compressed page arrays if cannot be kept on stack */ + be->decompressed_pages = NULL; + be->compressed_pages = NULL; + be->onstack_used = 0; + if (be->nr_pages <= Z_EROFS_ONSTACK_PAGES) { + be->decompressed_pages = be->onstack_pages; + be->onstack_used = be->nr_pages; + memset(be->decompressed_pages, 0, + sizeof(struct page *) * be->nr_pages); } + if (pclusterpages + be->onstack_used <= Z_EROFS_ONSTACK_PAGES) + be->compressed_pages = be->onstack_pages + be->onstack_used; + + if (!be->decompressed_pages) + be->decompressed_pages = + kvcalloc(be->nr_pages, sizeof(struct page *), + GFP_KERNEL | __GFP_NOFAIL); + if (!be->compressed_pages) + be->compressed_pages = + kvcalloc(pclusterpages, sizeof(struct page *), + GFP_KERNEL | __GFP_NOFAIL); + + z_erofs_parse_out_bvecs(be); + err2 = z_erofs_parse_in_bvecs(be, &overlapped); + if (err2) + err = err2; if (err) goto out; - llen = pcl->length >> Z_EROFS_PCLUSTER_LENGTH_BIT; - if (nr_pages << PAGE_SHIFT >= cl->pageofs + llen) { - outputsize = llen; - partial = !(pcl->length & Z_EROFS_PCLUSTER_FULL_LENGTH); - } else { - outputsize = (nr_pages << PAGE_SHIFT) - cl->pageofs; - partial = true; - } + if (z_erofs_is_inline_pcluster(pcl)) + inputsize = pcl->tailpacking_size; + else + inputsize = pclusterpages * PAGE_SIZE; err = z_erofs_decompress(&(struct z_erofs_decompress_req) { - .sb = sb, - .in = compressed_pages, - .out = pages, - .pageofs_out = cl->pageofs, - .inputsize = PAGE_SIZE, - .outputsize = outputsize, + .sb = be->sb, + .in = be->compressed_pages, + .out = be->decompressed_pages, + .pageofs_in = pcl->pageofs_in, + .pageofs_out = pcl->pageofs_out, + .inputsize = inputsize, + .outputsize = pcl->length, .alg = pcl->algorithmformat, .inplace_io = overlapped, - .partial_decoding = partial - }, pagepool); + .partial_decoding = pcl->partial, + .fillgaps = pcl->multibases, + }, be->pagepool); out: - /* must handle all compressed pages before endding pages */ - for (i = 0; i < clusterpages; ++i) { - page = compressed_pages[i]; - - if (erofs_page_is_managed(sbi, page)) - continue; + /* must handle all compressed pages before actual file pages */ + if (z_erofs_is_inline_pcluster(pcl)) { + page = pcl->compressed_bvecs[0].page; + WRITE_ONCE(pcl->compressed_bvecs[0].page, NULL); + put_page(page); + } else { + for (i = 0; i < pclusterpages; ++i) { + page = pcl->compressed_bvecs[i].page; - /* recycle all individual staging pages */ - (void)z_erofs_put_stagingpage(pagepool, page); + if (erofs_page_is_managed(sbi, page)) + continue; - WRITE_ONCE(compressed_pages[i], NULL); + /* recycle all individual short-lived pages */ + (void)z_erofs_put_shortlivedpage(be->pagepool, page); + WRITE_ONCE(pcl->compressed_bvecs[i].page, NULL); + } } + if (be->compressed_pages < be->onstack_pages || + be->compressed_pages >= be->onstack_pages + Z_EROFS_ONSTACK_PAGES) + kvfree(be->compressed_pages); + z_erofs_fill_other_copies(be, err); - for (i = 0; i < nr_pages; ++i) { - page = pages[i]; + for (i = 0; i < be->nr_pages; ++i) { + page = be->decompressed_pages[i]; if (!page) continue; - DBG_BUGON(!page->mapping); + DBG_BUGON(z_erofs_page_is_invalidated(page)); - /* recycle all individual staging pages */ - if (z_erofs_put_stagingpage(pagepool, page)) + /* recycle all individual short-lived pages */ + if (z_erofs_put_shortlivedpage(be->pagepool, page)) continue; - - if (err < 0) - SetPageError(page); - + if (err) + z_erofs_page_mark_eio(page); z_erofs_onlinepage_endio(page); } - if (pages == z_pagemap_global) - mutex_unlock(&z_pagemap_global_lock); - else if (pages != pages_onstack) - kvfree(pages); + if (be->decompressed_pages != be->onstack_pages) + kvfree(be->decompressed_pages); - cl->nr_pages = 0; - cl->vcnt = 0; + pcl->length = 0; + pcl->partial = true; + pcl->multibases = false; + pcl->bvset.nextpage = NULL; + pcl->vcnt = 0; - /* all cl locks MUST be taken before the following line */ + /* pcluster lock MUST be taken before the following line */ WRITE_ONCE(pcl->next, Z_EROFS_PCLUSTER_NIL); - - /* all cl locks SHOULD be released right now */ - mutex_unlock(&cl->lock); - - z_erofs_collection_put(cl); + mutex_unlock(&pcl->lock); return err; } static void z_erofs_decompress_queue(const struct z_erofs_decompressqueue *io, - struct list_head *pagepool) + struct page **pagepool) { + struct z_erofs_decompress_backend be = { + .sb = io->sb, + .pagepool = pagepool, + .decompressed_secondary_bvecs = + LIST_HEAD_INIT(be.decompressed_secondary_bvecs), + }; z_erofs_next_pcluster_t owned = io->head; while (owned != Z_EROFS_PCLUSTER_TAIL_CLOSED) { - struct z_erofs_pcluster *pcl; - - /* no possible that 'owned' equals Z_EROFS_WORK_TPTR_TAIL */ + /* impossible that 'owned' equals Z_EROFS_WORK_TPTR_TAIL */ DBG_BUGON(owned == Z_EROFS_PCLUSTER_TAIL); - - /* no possible that 'owned' equals NULL */ + /* impossible that 'owned' equals Z_EROFS_PCLUSTER_NIL */ DBG_BUGON(owned == Z_EROFS_PCLUSTER_NIL); - pcl = container_of(owned, struct z_erofs_pcluster, next); - owned = READ_ONCE(pcl->next); + be.pcl = container_of(owned, struct z_erofs_pcluster, next); + owned = READ_ONCE(be.pcl->next); - z_erofs_decompress_pcluster(io->sb, pcl, pagepool); + z_erofs_decompress_pcluster(&be, io->eio ? -EIO : 0); + erofs_workgroup_put(&be.pcl->obj); } } @@ -963,22 +1158,47 @@ static void z_erofs_decompressqueue_work(struct work_struct *work) { struct z_erofs_decompressqueue *bgq = container_of(work, struct z_erofs_decompressqueue, u.work); - LIST_HEAD(pagepool); + struct page *pagepool = NULL; DBG_BUGON(bgq->head == Z_EROFS_PCLUSTER_TAIL_CLOSED); z_erofs_decompress_queue(bgq, &pagepool); - put_pages_list(&pagepool); + erofs_release_pages(&pagepool); kvfree(bgq); } +static void z_erofs_decompress_kickoff(struct z_erofs_decompressqueue *io, + bool sync, int bios) +{ + struct erofs_sb_info *const sbi = EROFS_SB(io->sb); + + /* wake up the caller thread for sync decompression */ + if (sync) { + if (!atomic_add_return(bios, &io->pending_bios)) + complete(&io->u.done); + return; + } + + if (atomic_add_return(bios, &io->pending_bios)) + return; + /* Use workqueue and sync decompression for atomic contexts only */ + if (in_atomic() || irqs_disabled()) { + queue_work(z_erofs_workqueue, &io->u.work); + /* enable sync decompression for readahead */ + if (sbi->opt.sync_decompress == EROFS_SYNC_DECOMPRESS_AUTO) + sbi->opt.sync_decompress = EROFS_SYNC_DECOMPRESS_FORCE_ON; + return; + } + z_erofs_decompressqueue_work(&io->u.work); +} + static struct page *pickup_page_for_submission(struct z_erofs_pcluster *pcl, unsigned int nr, - struct list_head *pagepool, - struct address_space *mc, - gfp_t gfp) + struct page **pagepool, + struct address_space *mc) { const pgoff_t index = pcl->obj.index; + gfp_t gfp = mapping_gfp_mask(mc); bool tocache = false; struct address_space *mapping; @@ -988,36 +1208,41 @@ static struct page *pickup_page_for_submission(struct z_erofs_pcluster *pcl, int justfound; repeat: - page = READ_ONCE(pcl->compressed_pages[nr]); + page = READ_ONCE(pcl->compressed_bvecs[nr].page); oldpage = page; if (!page) goto out_allocpage; - /* - * the cached page has not been allocated and - * an placeholder is out there, prepare it now. - */ - if (page == PAGE_UNALLOCATED) { - tocache = true; - goto out_allocpage; - } - /* process the target tagged pointer */ t = tagptr_init(compressed_page_t, page); justfound = tagptr_unfold_tags(t); page = tagptr_unfold_ptr(t); + /* + * preallocated cached pages, which is used to avoid direct reclaim + * otherwise, it will go inplace I/O path instead. + */ + if (page->private == Z_EROFS_PREALLOCATED_PAGE) { + WRITE_ONCE(pcl->compressed_bvecs[nr].page, page); + set_page_private(page, 0); + tocache = true; + goto out_tocache; + } mapping = READ_ONCE(page->mapping); /* - * unmanaged (file) pages are all locked solidly, + * file-backed online pages in plcuster are all locked steady, * therefore it is impossible for `mapping' to be NULL. */ if (mapping && mapping != mc) /* ought to be unmanaged pages */ goto out; + /* directly return for shortlived page as well */ + if (z_erofs_is_shortlived_page(page)) + goto out; + lock_page(page); /* only true if page reclaim goes wrong, should never happen */ @@ -1025,14 +1250,13 @@ repeat: /* the page is still in manage cache */ if (page->mapping == mc) { - WRITE_ONCE(pcl->compressed_pages[nr], page); + WRITE_ONCE(pcl->compressed_bvecs[nr].page, page); - ClearPageError(page); if (!PagePrivate(page)) { /* * impossible to be !PagePrivate(page) for * the current restriction as well if - * the page is already in compressed_pages[]. + * the page is already in compressed_bvecs[]. */ DBG_BUGON(!justfound); @@ -1061,25 +1285,22 @@ repeat: put_page(page); out_allocpage: page = erofs_allocpage(pagepool, gfp | __GFP_NOFAIL); - if (!tocache || add_to_page_cache_lru(page, mc, index + nr, gfp)) { - /* non-LRU / non-movable temporary page is needed */ - page->mapping = Z_EROFS_MAPPING_STAGING; - tocache = false; - } - - if (oldpage != cmpxchg(&pcl->compressed_pages[nr], oldpage, page)) { - if (tocache) { - /* since it added to managed cache successfully */ - unlock_page(page); - put_page(page); - } else { - list_add(&page->lru, pagepool); - } + if (oldpage != cmpxchg(&pcl->compressed_bvecs[nr].page, + oldpage, page)) { + erofs_pagepool_add(pagepool, page); cond_resched(); goto repeat; } - set_page_private(page, (unsigned long)pcl); - SetPagePrivate(page); +out_tocache: + if (!tocache || add_to_page_cache_lru(page, mc, index + nr, gfp)) { + /* turn into temporary page if fails (1 ref) */ + set_page_private(page, Z_EROFS_SHORTLIVED_PAGE); + goto out; + } + attach_page_private(page, pcl); + /* drop a refcount added by allocpage (then we have 2 refs here) */ + put_page(page); + out: /* the only exit (for tracing and debugging) */ return page; } @@ -1100,8 +1321,9 @@ jobqueue_init(struct super_block *sb, } else { fg_out: q = fgq; - init_waitqueue_head(&fgq->u.wait); + init_completion(&fgq->u.done); atomic_set(&fgq->pending_bios, 0); + q->eio = false; } q->sb = sb; q->head = Z_EROFS_PCLUSTER_TAIL_CLOSED; @@ -1148,20 +1370,50 @@ static void move_to_bypass_jobqueue(struct z_erofs_pcluster *pcl, qtail[JQ_BYPASS] = &pcl->next; } -static void z_erofs_submit_queue(struct super_block *sb, - z_erofs_next_pcluster_t owned_head, - struct list_head *pagepool, +static void z_erofs_decompressqueue_endio(struct bio *bio) +{ + tagptr1_t t = tagptr_init(tagptr1_t, bio->bi_private); + struct z_erofs_decompressqueue *q = tagptr_unfold_ptr(t); + blk_status_t err = bio->bi_status; + struct bio_vec *bvec; + struct bvec_iter_all iter_all; + + bio_for_each_segment_all(bvec, bio, iter_all) { + struct page *page = bvec->bv_page; + + DBG_BUGON(PageUptodate(page)); + DBG_BUGON(z_erofs_page_is_invalidated(page)); + + if (erofs_page_is_managed(EROFS_SB(q->sb), page)) { + if (!err) + SetPageUptodate(page); + unlock_page(page); + } + } + if (err) + q->eio = true; + z_erofs_decompress_kickoff(q, tagptr_unfold_tags(t), -1); + bio_put(bio); +} + +static void z_erofs_submit_queue(struct z_erofs_decompress_frontend *f, + struct page **pagepool, struct z_erofs_decompressqueue *fgq, bool *force_fg) { - struct erofs_sb_info *const sbi = EROFS_SB(sb); + struct super_block *sb = f->inode->i_sb; + struct address_space *mc = MNGD_MAPPING(EROFS_SB(sb)); z_erofs_next_pcluster_t qtail[NR_JOBQUEUES]; struct z_erofs_decompressqueue *q[NR_JOBQUEUES]; void *bi_private; - /* since bio will be NULL, no need to initialize last_index */ - pgoff_t uninitialized_var(last_index); + z_erofs_next_pcluster_t owned_head = f->owned_head; + /* bio is NULL initially, so no need to initialize last_{index,bdev} */ + pgoff_t last_index; + struct block_device *last_bdev; unsigned int nr_bios = 0; struct bio *bio = NULL; + unsigned long pflags; + int memstall = 0; bi_private = jobqueueset_init(sb, q, fgq, force_fg); qtail[JQ_BYPASS] = &q[JQ_BYPASS]->head; @@ -1171,6 +1423,7 @@ static void z_erofs_submit_queue(struct super_block *sb, q[JQ_SUBMIT]->head = owned_head; do { + struct erofs_map_dev mdev; struct z_erofs_pcluster *pcl; pgoff_t cur, end; unsigned int i = 0; @@ -1182,43 +1435,62 @@ static void z_erofs_submit_queue(struct super_block *sb, pcl = container_of(owned_head, struct z_erofs_pcluster, next); - cur = pcl->obj.index; - end = cur + BIT(pcl->clusterbits); - /* close the main owned chain at first */ owned_head = cmpxchg(&pcl->next, Z_EROFS_PCLUSTER_TAIL, Z_EROFS_PCLUSTER_TAIL_CLOSED); + if (z_erofs_is_inline_pcluster(pcl)) { + move_to_bypass_jobqueue(pcl, qtail, owned_head); + continue; + } + + /* no device id here, thus it will always succeed */ + mdev = (struct erofs_map_dev) { + .m_pa = blknr_to_addr(pcl->obj.index), + }; + (void)erofs_map_dev(sb, &mdev); + + cur = erofs_blknr(mdev.m_pa); + end = cur + pcl->pclusterpages; do { struct page *page; - int err; page = pickup_page_for_submission(pcl, i++, pagepool, - MNGD_MAPPING(sbi), - GFP_NOFS); + mc); if (!page) continue; - if (bio && cur != last_index + 1) { + if (bio && (cur != last_index + 1 || + last_bdev != mdev.m_bdev)) { submit_bio_retry: submit_bio(bio); + if (memstall) { + psi_memstall_leave(&pflags); + memstall = 0; + } bio = NULL; } - if (!bio) { - bio = bio_alloc(GFP_NOIO, BIO_MAX_PAGES); + if (unlikely(PageWorkingset(page)) && !memstall) { + psi_memstall_enter(&pflags); + memstall = 1; + } + if (!bio) { + bio = bio_alloc(mdev.m_bdev, BIO_MAX_VECS, + REQ_OP_READ, GFP_NOIO); bio->bi_end_io = z_erofs_decompressqueue_endio; - bio_set_dev(bio, sb->s_bdev); + + last_bdev = mdev.m_bdev; bio->bi_iter.bi_sector = (sector_t)cur << LOG_SECTORS_PER_BLOCK; bio->bi_private = bi_private; - bio->bi_opf = REQ_OP_READ; + if (f->readahead) + bio->bi_opf |= REQ_RAHEAD; ++nr_bios; } - err = bio_add_page(bio, page, PAGE_SIZE, 0); - if (err < PAGE_SIZE) + if (bio_add_page(bio, page, PAGE_SIZE, 0) < PAGE_SIZE) goto submit_bio_retry; last_index = cur; @@ -1231,8 +1503,11 @@ submit_bio_retry: move_to_bypass_jobqueue(pcl, qtail, owned_head); } while (owned_head != Z_EROFS_PCLUSTER_TAIL); - if (bio) + if (bio) { submit_bio(bio); + if (memstall) + psi_memstall_leave(&pflags); + } /* * although background is preferred, no one is pending for submission. @@ -1245,15 +1520,14 @@ submit_bio_retry: z_erofs_decompress_kickoff(q[JQ_SUBMIT], *force_fg, nr_bios); } -static void z_erofs_runqueue(struct super_block *sb, - struct z_erofs_collector *clt, - struct list_head *pagepool, bool force_fg) +static void z_erofs_runqueue(struct z_erofs_decompress_frontend *f, + struct page **pagepool, bool force_fg) { struct z_erofs_decompressqueue io[NR_JOBQUEUES]; - if (clt->owned_head == Z_EROFS_PCLUSTER_TAIL) + if (f->owned_head == Z_EROFS_PCLUSTER_TAIL) return; - z_erofs_submit_queue(sb, clt->owned_head, pagepool, io, &force_fg); + z_erofs_submit_queue(f, pagepool, io, &force_fg); /* handle bypass queue (no i/o pclusters) immediately */ z_erofs_decompress_queue(&io[JQ_BYPASS], pagepool); @@ -1262,82 +1536,123 @@ static void z_erofs_runqueue(struct super_block *sb, return; /* wait until all bios are completed */ - io_wait_event(io[JQ_SUBMIT].u.wait, - !atomic_read(&io[JQ_SUBMIT].pending_bios)); + wait_for_completion_io(&io[JQ_SUBMIT].u.done); /* handle synchronous decompress queue in the caller context */ z_erofs_decompress_queue(&io[JQ_SUBMIT], pagepool); } -static int z_erofs_readpage(struct file *file, struct page *page) +/* + * Since partial uptodate is still unimplemented for now, we have to use + * approximate readmore strategies as a start. + */ +static void z_erofs_pcluster_readmore(struct z_erofs_decompress_frontend *f, + struct readahead_control *rac, + erofs_off_t end, + struct page **pagepool, + bool backmost) +{ + struct inode *inode = f->inode; + struct erofs_map_blocks *map = &f->map; + erofs_off_t cur; + int err; + + if (backmost) { + map->m_la = end; + err = z_erofs_map_blocks_iter(inode, map, + EROFS_GET_BLOCKS_READMORE); + if (err) + return; + + /* expend ra for the trailing edge if readahead */ + if (rac) { + loff_t newstart = readahead_pos(rac); + + cur = round_up(map->m_la + map->m_llen, PAGE_SIZE); + readahead_expand(rac, newstart, cur - newstart); + return; + } + end = round_up(end, PAGE_SIZE); + } else { + end = round_up(map->m_la, PAGE_SIZE); + + if (!map->m_llen) + return; + } + + cur = map->m_la + map->m_llen - 1; + while (cur >= end) { + pgoff_t index = cur >> PAGE_SHIFT; + struct page *page; + + page = erofs_grab_cache_page_nowait(inode->i_mapping, index); + if (page) { + if (PageUptodate(page)) { + unlock_page(page); + } else { + err = z_erofs_do_read_page(f, page, pagepool); + if (err) + erofs_err(inode->i_sb, + "readmore error at page %lu @ nid %llu", + index, EROFS_I(inode)->nid); + } + put_page(page); + } + + if (cur < PAGE_SIZE) + break; + cur = (index << PAGE_SHIFT) - 1; + } +} + +static int z_erofs_read_folio(struct file *file, struct folio *folio) { + struct page *page = &folio->page; struct inode *const inode = page->mapping->host; + struct erofs_sb_info *const sbi = EROFS_I_SB(inode); struct z_erofs_decompress_frontend f = DECOMPRESS_FRONTEND_INIT(inode); + struct page *pagepool = NULL; int err; - LIST_HEAD(pagepool); trace_erofs_readpage(page, false); - f.headoffset = (erofs_off_t)page->index << PAGE_SHIFT; + z_erofs_pcluster_readmore(&f, NULL, f.headoffset + PAGE_SIZE - 1, + &pagepool, true); err = z_erofs_do_read_page(&f, page, &pagepool); - (void)z_erofs_collector_end(&f.clt); + z_erofs_pcluster_readmore(&f, NULL, 0, &pagepool, false); + + (void)z_erofs_collector_end(&f); /* if some compressed cluster ready, need submit them anyway */ - z_erofs_runqueue(inode->i_sb, &f.clt, &pagepool, true); + z_erofs_runqueue(&f, &pagepool, + z_erofs_get_sync_decompress_policy(sbi, 0)); if (err) erofs_err(inode->i_sb, "failed to read, err [%d]", err); - if (f.map.mpage) - put_page(f.map.mpage); - - /* clean up the remaining free pages */ - put_pages_list(&pagepool); + erofs_put_metabuf(&f.map.buf); + erofs_release_pages(&pagepool); return err; } -static bool should_decompress_synchronously(struct erofs_sb_info *sbi, - unsigned int nr) +static void z_erofs_readahead(struct readahead_control *rac) { - return nr <= sbi->max_sync_decompress_pages; -} - -static int z_erofs_readpages(struct file *filp, struct address_space *mapping, - struct list_head *pages, unsigned int nr_pages) -{ - struct inode *const inode = mapping->host; + struct inode *const inode = rac->mapping->host; struct erofs_sb_info *const sbi = EROFS_I_SB(inode); - - bool sync = should_decompress_synchronously(sbi, nr_pages); struct z_erofs_decompress_frontend f = DECOMPRESS_FRONTEND_INIT(inode); - gfp_t gfp = mapping_gfp_constraint(mapping, GFP_KERNEL); - struct page *head = NULL; - LIST_HEAD(pagepool); - - trace_erofs_readpages(mapping->host, lru_to_page(pages), - nr_pages, false); - - f.headoffset = (erofs_off_t)lru_to_page(pages)->index << PAGE_SHIFT; + struct page *pagepool = NULL, *head = NULL, *page; + unsigned int nr_pages; - for (; nr_pages; --nr_pages) { - struct page *page = lru_to_page(pages); + f.readahead = true; + f.headoffset = readahead_pos(rac); - prefetchw(&page->flags); - list_del(&page->lru); - - /* - * A pure asynchronous readahead is indicated if - * a PG_readahead marked page is hitted at first. - * Let's also do asynchronous decompression for this case. - */ - sync &= !(PageReadahead(page) && !head); - - if (add_to_page_cache_lru(page, mapping, page->index, gfp)) { - list_add(&page->lru, &pagepool); - continue; - } + z_erofs_pcluster_readmore(&f, rac, f.headoffset + + readahead_length(rac) - 1, &pagepool, true); + nr_pages = readahead_count(rac); + trace_erofs_readpages(inode, readahead_index(rac), nr_pages, false); + while ((page = readahead_page(rac))) { set_page_private(page, (unsigned long)head); head = page; } @@ -1356,21 +1671,16 @@ static int z_erofs_readpages(struct file *filp, struct address_space *mapping, page->index, EROFS_I(inode)->nid); put_page(page); } + z_erofs_pcluster_readmore(&f, rac, 0, &pagepool, false); + (void)z_erofs_collector_end(&f); - (void)z_erofs_collector_end(&f.clt); - - z_erofs_runqueue(inode->i_sb, &f.clt, &pagepool, sync); - - if (f.map.mpage) - put_page(f.map.mpage); - - /* clean up the remaining free pages */ - put_pages_list(&pagepool); - return 0; + z_erofs_runqueue(&f, &pagepool, + z_erofs_get_sync_decompress_policy(sbi, nr_pages)); + erofs_put_metabuf(&f.map.buf); + erofs_release_pages(&pagepool); } const struct address_space_operations z_erofs_aops = { - .readpage = z_erofs_readpage, - .readpages = z_erofs_readpages, + .read_folio = z_erofs_read_folio, + .readahead = z_erofs_readahead, }; - diff --git a/fs/erofs/zdata.h b/fs/erofs/zdata.h index 7824f5563a55..d98c95212985 100644 --- a/fs/erofs/zdata.h +++ b/fs/erofs/zdata.h @@ -1,16 +1,37 @@ /* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (C) 2018 HUAWEI, Inc. - * http://www.huawei.com/ - * Created by Gao Xiang <gaoxiang25@huawei.com> + * https://www.huawei.com/ */ #ifndef __EROFS_FS_ZDATA_H #define __EROFS_FS_ZDATA_H #include "internal.h" -#include "zpvec.h" +#include "tagptr.h" -#define Z_EROFS_NR_INLINE_PAGEVECS 3 +#define Z_EROFS_PCLUSTER_MAX_PAGES (Z_EROFS_PCLUSTER_MAX_SIZE / PAGE_SIZE) +#define Z_EROFS_INLINE_BVECS 2 + +/* + * let's leave a type here in case of introducing + * another tagged pointer later. + */ +typedef void *z_erofs_next_pcluster_t; + +struct z_erofs_bvec { + struct page *page; + int offset; + unsigned int end; +}; + +#define __Z_EROFS_BVSET(name, total) \ +struct name { \ + /* point to the next page which contains the following bvecs */ \ + struct page *nextpage; \ + struct z_erofs_bvec bvec[total]; \ +} +__Z_EROFS_BVSET(z_erofs_bvset,); +__Z_EROFS_BVSET(z_erofs_bvset_inline, Z_EROFS_INLINE_BVECS); /* * Structure fields follow one of the following exclusion rules. @@ -18,61 +39,58 @@ * I: Modifiable by initialization/destruction paths and read-only * for everyone else; * - * L: Field should be protected by pageset lock; + * L: Field should be protected by the pcluster lock; * * A: Field should be accessed / updated in atomic for parallelized code. */ -struct z_erofs_collection { +struct z_erofs_pcluster { + struct erofs_workgroup obj; struct mutex lock; - /* I: page offset of start position of decompression */ - unsigned short pageofs; + /* A: point to next chained pcluster or TAILs */ + z_erofs_next_pcluster_t next; - /* L: maximum relative page index in pagevec[] */ - unsigned short nr_pages; + /* L: the maximum decompression size of this round */ + unsigned int length; - /* L: total number of pages in pagevec[] */ + /* L: total number of bvecs */ unsigned int vcnt; + /* I: page offset of start position of decompression */ + unsigned short pageofs_out; + + /* I: page offset of inline compressed data */ + unsigned short pageofs_in; + union { - /* L: inline a certain number of pagevecs for bootstrap */ - erofs_vtptr_t pagevec[Z_EROFS_NR_INLINE_PAGEVECS]; + /* L: inline a certain number of bvec for bootstrap */ + struct z_erofs_bvset_inline bvset; /* 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; + union { + /* I: physical cluster size in pages */ + unsigned short pclusterpages; -struct z_erofs_pcluster { - struct erofs_workgroup obj; - struct z_erofs_collection primary_collection; + /* I: tailpacking inline compressed size */ + unsigned short tailpacking_size; + }; - /* A: point to next chained pcluster or TAILs */ - z_erofs_next_pcluster_t next; + /* I: compression algorithm format */ + unsigned char algorithmformat; - /* A: compressed pages (including multi-usage pages) */ - struct page *compressed_pages[Z_EROFS_CLUSTER_MAX_PAGES]; + /* L: whether partial decompression or not */ + bool partial; - /* A: lower limit of decompressed length and if full length or not */ - unsigned int length; + /* L: indicate several pageofs_outs or not */ + bool multibases; - /* I: compression algorithm format */ - unsigned char algorithmformat; - /* I: bit shift of physical cluster size */ - unsigned char clusterbits; + /* A: compressed bvecs (can be cached or inplaced pages) */ + struct z_erofs_bvec compressed_bvecs[]; }; -#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) */ @@ -82,58 +100,42 @@ struct z_erofs_pcluster { #define Z_EROFS_PCLUSTER_NIL (NULL) -#define Z_EROFS_WORKGROUP_SIZE sizeof(struct z_erofs_pcluster) - struct z_erofs_decompressqueue { struct super_block *sb; atomic_t pending_bios; z_erofs_next_pcluster_t head; union { - wait_queue_head_t wait; + struct completion done; struct work_struct work; } u; + + bool eio; }; -#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) +static inline bool z_erofs_is_inline_pcluster(struct z_erofs_pcluster *pcl) { - return page->mapping == MNGD_MAPPING(sbi); + return !pcl->obj.index; } -#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) +static inline unsigned int z_erofs_pclusterpages(struct z_erofs_pcluster *pcl) +{ + if (z_erofs_is_inline_pcluster(pcl)) + return 1; + return pcl->pclusterpages; +} /* - * waiters (aka. ongoing_packs): # to unlock the page - * sub-index: 0 - for partial page, >= 1 full page sub-index + * bit 30: I/O error occurred on this page + * bit 0 - 29: remaining parts to complete this page */ -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; -} +#define Z_EROFS_PAGE_EIO (1 << 30) static inline void z_erofs_onlinepage_init(struct page *page) { union { - z_erofs_onlinepage_t o; + atomic_t o; unsigned long v; - /* keep from being unlocked in advance */ } u = { .o = ATOMIC_INIT(1) }; set_page_private(page, u.v); @@ -141,49 +143,36 @@ static inline void z_erofs_onlinepage_init(struct page *page) SetPagePrivate(page); } -static inline void z_erofs_onlinepage_fixup(struct page *page, - uintptr_t index, bool down) +static inline void z_erofs_onlinepage_split(struct page *page) { - 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; + atomic_inc((atomic_t *)&page->private); +} - DBG_BUGON(id != index); - } +static inline void z_erofs_page_mark_eio(struct page *page) +{ + int orig; - v = (index << Z_EROFS_ONLINEPAGE_INDEX_SHIFT) | - ((o & Z_EROFS_ONLINEPAGE_COUNT_MASK) + (unsigned int)down); - if (cmpxchg(p, o, v) != o) - goto repeat; + do { + orig = atomic_read((atomic_t *)&page->private); + } while (atomic_cmpxchg((atomic_t *)&page->private, orig, + orig | Z_EROFS_PAGE_EIO) != orig); } 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)) { + v = atomic_dec_return((atomic_t *)&page->private); + if (!(v & ~Z_EROFS_PAGE_EIO)) { + set_page_private(page, 0); ClearPagePrivate(page); - if (!PageError(page)) + if (!(v & Z_EROFS_PAGE_EIO)) SetPageUptodate(page); unlock_page(page); } - erofs_dbg("%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 +#define Z_EROFS_ONSTACK_PAGES 32 #endif - diff --git a/fs/erofs/zmap.c b/fs/erofs/zmap.c index 736db3a4cdef..0bb66927e3d0 100644 --- a/fs/erofs/zmap.c +++ b/fs/erofs/zmap.c @@ -1,27 +1,30 @@ // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2018-2019 HUAWEI, Inc. - * http://www.huawei.com/ - * Created by Gao Xiang <gaoxiang25@huawei.com> + * https://www.huawei.com/ */ #include "internal.h" #include <asm/unaligned.h> #include <trace/events/erofs.h> +static int z_erofs_do_map_blocks(struct inode *inode, + struct erofs_map_blocks *map, + int flags); + int z_erofs_fill_inode(struct inode *inode) { struct erofs_inode *const vi = EROFS_I(inode); + struct erofs_sb_info *sbi = EROFS_SB(inode->i_sb); - if (vi->datalayout == EROFS_INODE_FLAT_COMPRESSION_LEGACY) { + if (!erofs_sb_has_big_pcluster(sbi) && + !erofs_sb_has_ztailpacking(sbi) && !erofs_sb_has_fragments(sbi) && + vi->datalayout == EROFS_INODE_FLAT_COMPRESSION_LEGACY) { vi->z_advise = 0; vi->z_algorithmtype[0] = 0; vi->z_algorithmtype[1] = 0; vi->z_logical_clusterbits = LOG_BLOCK_SIZE; - vi->z_physical_clusterbits[0] = vi->z_logical_clusterbits; - vi->z_physical_clusterbits[1] = vi->z_logical_clusterbits; set_bit(EROFS_I_Z_INITED_BIT, &vi->flags); } - inode->i_mapping->a_ops = &z_erofs_aops; return 0; } @@ -30,14 +33,20 @@ static int z_erofs_fill_inode_lazy(struct inode *inode) { struct erofs_inode *const vi = EROFS_I(inode); struct super_block *const sb = inode->i_sb; - int err; + int err, headnr; erofs_off_t pos; - struct page *page; + struct erofs_buf buf = __EROFS_BUF_INITIALIZER; void *kaddr; struct z_erofs_map_header *h; - if (test_bit(EROFS_I_Z_INITED_BIT, &vi->flags)) + if (test_bit(EROFS_I_Z_INITED_BIT, &vi->flags)) { + /* + * paired with smp_mb() at the end of the function to ensure + * fields will only be observed after the bit is set. + */ + smp_mb(); return 0; + } if (wait_on_bit_lock(&vi->flags, EROFS_I_BL_Z_BIT, TASK_KILLABLE)) return -ERESTARTSYS; @@ -46,48 +55,95 @@ static int z_erofs_fill_inode_lazy(struct inode *inode) if (test_bit(EROFS_I_Z_INITED_BIT, &vi->flags)) goto out_unlock; - DBG_BUGON(vi->datalayout == EROFS_INODE_FLAT_COMPRESSION_LEGACY); - pos = ALIGN(iloc(EROFS_SB(sb), vi->nid) + vi->inode_isize + vi->xattr_isize, 8); - page = erofs_get_meta_page(sb, erofs_blknr(pos)); - if (IS_ERR(page)) { - err = PTR_ERR(page); + kaddr = erofs_read_metabuf(&buf, sb, erofs_blknr(pos), EROFS_KMAP); + if (IS_ERR(kaddr)) { + err = PTR_ERR(kaddr); goto out_unlock; } - kaddr = kmap_atomic(page); - h = kaddr + erofs_blkoff(pos); + /* + * if the highest bit of the 8-byte map header is set, the whole file + * is stored in the packed inode. The rest bits keeps z_fragmentoff. + */ + if (h->h_clusterbits >> Z_EROFS_FRAGMENT_INODE_BIT) { + vi->z_advise = Z_EROFS_ADVISE_FRAGMENT_PCLUSTER; + vi->z_fragmentoff = le64_to_cpu(*(__le64 *)h) ^ (1ULL << 63); + vi->z_tailextent_headlcn = 0; + goto done; + } vi->z_advise = le16_to_cpu(h->h_advise); vi->z_algorithmtype[0] = h->h_algorithmtype & 15; vi->z_algorithmtype[1] = h->h_algorithmtype >> 4; - if (vi->z_algorithmtype[0] >= Z_EROFS_COMPRESSION_MAX) { - erofs_err(sb, "unknown compression format %u for nid %llu, please upgrade kernel", - vi->z_algorithmtype[0], vi->nid); + headnr = 0; + if (vi->z_algorithmtype[0] >= Z_EROFS_COMPRESSION_MAX || + vi->z_algorithmtype[++headnr] >= Z_EROFS_COMPRESSION_MAX) { + erofs_err(sb, "unknown HEAD%u format %u for nid %llu, please upgrade kernel", + headnr + 1, vi->z_algorithmtype[headnr], vi->nid); err = -EOPNOTSUPP; - goto unmap_done; + goto out_put_metabuf; } vi->z_logical_clusterbits = LOG_BLOCK_SIZE + (h->h_clusterbits & 7); - vi->z_physical_clusterbits[0] = vi->z_logical_clusterbits + - ((h->h_clusterbits >> 3) & 3); + if (!erofs_sb_has_big_pcluster(EROFS_SB(sb)) && + vi->z_advise & (Z_EROFS_ADVISE_BIG_PCLUSTER_1 | + Z_EROFS_ADVISE_BIG_PCLUSTER_2)) { + erofs_err(sb, "per-inode big pcluster without sb feature for nid %llu", + vi->nid); + err = -EFSCORRUPTED; + goto out_put_metabuf; + } + if (vi->datalayout == EROFS_INODE_FLAT_COMPRESSION && + !(vi->z_advise & Z_EROFS_ADVISE_BIG_PCLUSTER_1) ^ + !(vi->z_advise & Z_EROFS_ADVISE_BIG_PCLUSTER_2)) { + erofs_err(sb, "big pcluster head1/2 of compact indexes should be consistent for nid %llu", + vi->nid); + err = -EFSCORRUPTED; + goto out_put_metabuf; + } - if (vi->z_physical_clusterbits[0] != LOG_BLOCK_SIZE) { - erofs_err(sb, "unsupported physical clusterbits %u for nid %llu, please upgrade kernel", - vi->z_physical_clusterbits[0], vi->nid); - err = -EOPNOTSUPP; - goto unmap_done; + if (vi->z_advise & Z_EROFS_ADVISE_INLINE_PCLUSTER) { + struct erofs_map_blocks map = { + .buf = __EROFS_BUF_INITIALIZER + }; + + vi->z_idata_size = le16_to_cpu(h->h_idata_size); + err = z_erofs_do_map_blocks(inode, &map, + EROFS_GET_BLOCKS_FINDTAIL); + erofs_put_metabuf(&map.buf); + + if (!map.m_plen || + erofs_blkoff(map.m_pa) + map.m_plen > EROFS_BLKSIZ) { + erofs_err(sb, "invalid tail-packing pclustersize %llu", + map.m_plen); + err = -EFSCORRUPTED; + } + if (err < 0) + goto out_put_metabuf; } - vi->z_physical_clusterbits[1] = vi->z_logical_clusterbits + - ((h->h_clusterbits >> 5) & 7); + if (vi->z_advise & Z_EROFS_ADVISE_FRAGMENT_PCLUSTER && + !(h->h_clusterbits >> Z_EROFS_FRAGMENT_INODE_BIT)) { + struct erofs_map_blocks map = { + .buf = __EROFS_BUF_INITIALIZER + }; + + vi->z_fragmentoff = le32_to_cpu(h->h_fragmentoff); + err = z_erofs_do_map_blocks(inode, &map, + EROFS_GET_BLOCKS_FINDTAIL); + erofs_put_metabuf(&map.buf); + if (err < 0) + goto out_put_metabuf; + } +done: + /* paired with smp_mb() at the beginning of the function */ + smp_mb(); set_bit(EROFS_I_Z_INITED_BIT, &vi->flags); -unmap_done: - kunmap_atomic(kaddr); - unlock_page(page); - put_page(page); +out_put_metabuf: + erofs_put_metabuf(&buf); out_unlock: clear_and_wake_up_bit(EROFS_I_BL_Z_BIT, &vi->flags); return err; @@ -100,44 +156,14 @@ struct z_erofs_maprecorder { unsigned long lcn; /* compression extent information gathered */ - u8 type; + u8 type, headtype; u16 clusterofs; u16 delta[2]; - erofs_blk_t pblk; + erofs_blk_t pblk, compressedblks; + erofs_off_t nextpackoff; + bool partialref; }; -static int z_erofs_reload_indexes(struct z_erofs_maprecorder *m, - erofs_blk_t eblk) -{ - struct super_block *const sb = m->inode->i_sb; - struct erofs_map_blocks *const map = m->map; - struct page *mpage = map->mpage; - - if (mpage) { - if (mpage->index == eblk) { - if (!m->kaddr) - m->kaddr = kmap_atomic(mpage); - return 0; - } - - if (m->kaddr) { - kunmap_atomic(m->kaddr); - m->kaddr = NULL; - } - put_page(mpage); - } - - mpage = erofs_get_meta_page(sb, eblk); - if (IS_ERR(mpage)) { - map->mpage = NULL; - return PTR_ERR(mpage); - } - m->kaddr = kmap_atomic(mpage); - unlock_page(mpage); - map->mpage = mpage; - return 0; -} - static int legacy_load_cluster_from_disk(struct z_erofs_maprecorder *m, unsigned long lcn) { @@ -150,12 +176,13 @@ static int legacy_load_cluster_from_disk(struct z_erofs_maprecorder *m, lcn * sizeof(struct z_erofs_vle_decompressed_index); struct z_erofs_vle_decompressed_index *di; unsigned int advise, type; - int err; - err = z_erofs_reload_indexes(m, erofs_blknr(pos)); - if (err) - return err; + m->kaddr = erofs_read_metabuf(&m->map->buf, inode->i_sb, + erofs_blknr(pos), EROFS_KMAP_ATOMIC); + if (IS_ERR(m->kaddr)) + return PTR_ERR(m->kaddr); + m->nextpackoff = pos + sizeof(struct z_erofs_vle_decompressed_index); m->lcn = lcn; di = m->kaddr + erofs_blkoff(pos); @@ -166,10 +193,23 @@ static int legacy_load_cluster_from_disk(struct z_erofs_maprecorder *m, case Z_EROFS_VLE_CLUSTER_TYPE_NONHEAD: m->clusterofs = 1 << vi->z_logical_clusterbits; m->delta[0] = le16_to_cpu(di->di_u.delta[0]); + if (m->delta[0] & Z_EROFS_VLE_DI_D0_CBLKCNT) { + if (!(vi->z_advise & (Z_EROFS_ADVISE_BIG_PCLUSTER_1 | + Z_EROFS_ADVISE_BIG_PCLUSTER_2))) { + DBG_BUGON(1); + return -EFSCORRUPTED; + } + m->compressedblks = m->delta[0] & + ~Z_EROFS_VLE_DI_D0_CBLKCNT; + m->delta[0] = 1; + } m->delta[1] = le16_to_cpu(di->di_u.delta[1]); break; case Z_EROFS_VLE_CLUSTER_TYPE_PLAIN: - case Z_EROFS_VLE_CLUSTER_TYPE_HEAD: + case Z_EROFS_VLE_CLUSTER_TYPE_HEAD1: + case Z_EROFS_VLE_CLUSTER_TYPE_HEAD2: + if (advise & Z_EROFS_VLE_DI_PARTIAL_REF) + m->partialref = true; m->clusterofs = le16_to_cpu(di->di_clusterofs); m->pblk = le32_to_cpu(di->di_u.blkaddr); break; @@ -192,16 +232,42 @@ static unsigned int decode_compactedbits(unsigned int lobits, return lo; } +static int get_compacted_la_distance(unsigned int lclusterbits, + unsigned int encodebits, + unsigned int vcnt, u8 *in, int i) +{ + const unsigned int lomask = (1 << lclusterbits) - 1; + unsigned int lo, d1 = 0; + u8 type; + + DBG_BUGON(i >= vcnt); + + do { + lo = decode_compactedbits(lclusterbits, lomask, + in, encodebits * i, &type); + + if (type != Z_EROFS_VLE_CLUSTER_TYPE_NONHEAD) + return d1; + ++d1; + } while (++i < vcnt); + + /* vcnt - 1 (Z_EROFS_VLE_CLUSTER_TYPE_NONHEAD) item */ + if (!(lo & Z_EROFS_VLE_DI_D0_CBLKCNT)) + d1 += lo - 1; + return d1; +} + static int unpack_compacted_index(struct z_erofs_maprecorder *m, unsigned int amortizedshift, - unsigned int eofs) + erofs_off_t pos, bool lookahead) { struct erofs_inode *const vi = EROFS_I(m->inode); const unsigned int lclusterbits = vi->z_logical_clusterbits; const unsigned int lomask = (1 << lclusterbits) - 1; - unsigned int vcnt, base, lo, encodebits, nblk; + unsigned int vcnt, base, lo, encodebits, nblk, eofs; int i; u8 *in, type; + bool big_pcluster; if (1 << amortizedshift == 4) vcnt = 2; @@ -210,7 +276,12 @@ static int unpack_compacted_index(struct z_erofs_maprecorder *m, else return -EOPNOTSUPP; + /* it doesn't equal to round_up(..) */ + m->nextpackoff = round_down(pos, vcnt << amortizedshift) + + (vcnt << amortizedshift); + big_pcluster = vi->z_advise & Z_EROFS_ADVISE_BIG_PCLUSTER_1; encodebits = ((vcnt << amortizedshift) - sizeof(__le32)) * 8 / vcnt; + eofs = erofs_blkoff(pos); base = round_down(eofs, vcnt << amortizedshift); in = m->kaddr + base; @@ -221,7 +292,20 @@ static int unpack_compacted_index(struct z_erofs_maprecorder *m, m->type = type; if (type == Z_EROFS_VLE_CLUSTER_TYPE_NONHEAD) { m->clusterofs = 1 << lclusterbits; - if (i + 1 != vcnt) { + + /* figure out lookahead_distance: delta[1] if needed */ + if (lookahead) + m->delta[1] = get_compacted_la_distance(lclusterbits, + encodebits, vcnt, in, i); + if (lo & Z_EROFS_VLE_DI_D0_CBLKCNT) { + if (!big_pcluster) { + DBG_BUGON(1); + return -EFSCORRUPTED; + } + m->compressedblks = lo & ~Z_EROFS_VLE_DI_D0_CBLKCNT; + m->delta[0] = 1; + return 0; + } else if (i + 1 != (int)vcnt) { m->delta[0] = lo; return 0; } @@ -234,22 +318,48 @@ static int unpack_compacted_index(struct z_erofs_maprecorder *m, in, encodebits * (i - 1), &type); if (type != Z_EROFS_VLE_CLUSTER_TYPE_NONHEAD) lo = 0; + else if (lo & Z_EROFS_VLE_DI_D0_CBLKCNT) + lo = 1; m->delta[0] = lo + 1; return 0; } m->clusterofs = lo; m->delta[0] = 0; /* figout out blkaddr (pblk) for HEAD lclusters */ - nblk = 1; - while (i > 0) { - --i; - lo = decode_compactedbits(lclusterbits, lomask, - in, encodebits * i, &type); - if (type == Z_EROFS_VLE_CLUSTER_TYPE_NONHEAD) - i -= lo; - - if (i >= 0) + if (!big_pcluster) { + nblk = 1; + while (i > 0) { + --i; + lo = decode_compactedbits(lclusterbits, lomask, + in, encodebits * i, &type); + if (type == Z_EROFS_VLE_CLUSTER_TYPE_NONHEAD) + i -= lo; + + if (i >= 0) + ++nblk; + } + } else { + nblk = 0; + while (i > 0) { + --i; + lo = decode_compactedbits(lclusterbits, lomask, + in, encodebits * i, &type); + if (type == Z_EROFS_VLE_CLUSTER_TYPE_NONHEAD) { + if (lo & Z_EROFS_VLE_DI_D0_CBLKCNT) { + --i; + nblk += lo & ~Z_EROFS_VLE_DI_D0_CBLKCNT; + continue; + } + /* bigpcluster shouldn't have plain d0 == 1 */ + if (lo <= 1) { + DBG_BUGON(1); + return -EFSCORRUPTED; + } + i -= lo - 2; + continue; + } ++nblk; + } } in += (vcnt << amortizedshift) - sizeof(__le32); m->pblk = le32_to_cpu(*(__le32 *)in) + nblk; @@ -257,7 +367,7 @@ static int unpack_compacted_index(struct z_erofs_maprecorder *m, } static int compacted_load_cluster_from_disk(struct z_erofs_maprecorder *m, - unsigned long lcn) + unsigned long lcn, bool lookahead) { struct inode *const inode = m->inode; struct erofs_inode *const vi = EROFS_I(inode); @@ -269,7 +379,6 @@ static int compacted_load_cluster_from_disk(struct z_erofs_maprecorder *m, unsigned int compacted_4b_initial, compacted_2b; unsigned int amortizedshift; erofs_off_t pos; - int err; if (lclusterbits != 12) return -EOPNOTSUPP; @@ -283,7 +392,8 @@ static int compacted_load_cluster_from_disk(struct z_erofs_maprecorder *m, if (compacted_4b_initial == 32 / 4) compacted_4b_initial = 0; - if (vi->z_advise & Z_EROFS_ADVISE_COMPACTED_2B) + if ((vi->z_advise & Z_EROFS_ADVISE_COMPACTED_2B) && + compacted_4b_initial < totalidx) compacted_2b = rounddown(totalidx - compacted_4b_initial, 16); else compacted_2b = 0; @@ -305,14 +415,15 @@ static int compacted_load_cluster_from_disk(struct z_erofs_maprecorder *m, amortizedshift = 2; out: pos += lcn * (1 << amortizedshift); - err = z_erofs_reload_indexes(m, erofs_blknr(pos)); - if (err) - return err; - return unpack_compacted_index(m, amortizedshift, erofs_blkoff(pos)); + m->kaddr = erofs_read_metabuf(&m->map->buf, inode->i_sb, + erofs_blknr(pos), EROFS_KMAP_ATOMIC); + if (IS_ERR(m->kaddr)) + return PTR_ERR(m->kaddr); + return unpack_compacted_index(m, amortizedshift, pos, lookahead); } static int z_erofs_load_cluster_from_disk(struct z_erofs_maprecorder *m, - unsigned int lcn) + unsigned int lcn, bool lookahead) { const unsigned int datamode = EROFS_I(m->inode)->datalayout; @@ -320,7 +431,7 @@ static int z_erofs_load_cluster_from_disk(struct z_erofs_maprecorder *m, return legacy_load_cluster_from_disk(m, lcn); if (datamode == EROFS_INODE_FLAT_COMPRESSION) - return compacted_load_cluster_from_disk(m, lcn); + return compacted_load_cluster_from_disk(m, lcn, lookahead); return -EINVAL; } @@ -329,97 +440,212 @@ static int z_erofs_extent_lookback(struct z_erofs_maprecorder *m, unsigned int lookback_distance) { struct erofs_inode *const vi = EROFS_I(m->inode); + const unsigned int lclusterbits = vi->z_logical_clusterbits; + + while (m->lcn >= lookback_distance) { + unsigned long lcn = m->lcn - lookback_distance; + int err; + + /* load extent head logical cluster if needed */ + err = z_erofs_load_cluster_from_disk(m, lcn, false); + if (err) + return err; + + switch (m->type) { + case Z_EROFS_VLE_CLUSTER_TYPE_NONHEAD: + if (!m->delta[0]) { + erofs_err(m->inode->i_sb, + "invalid lookback distance 0 @ nid %llu", + vi->nid); + DBG_BUGON(1); + return -EFSCORRUPTED; + } + lookback_distance = m->delta[0]; + continue; + case Z_EROFS_VLE_CLUSTER_TYPE_PLAIN: + case Z_EROFS_VLE_CLUSTER_TYPE_HEAD1: + case Z_EROFS_VLE_CLUSTER_TYPE_HEAD2: + m->headtype = m->type; + m->map->m_la = (lcn << lclusterbits) | m->clusterofs; + return 0; + default: + erofs_err(m->inode->i_sb, + "unknown type %u @ lcn %lu of nid %llu", + m->type, lcn, vi->nid); + DBG_BUGON(1); + return -EOPNOTSUPP; + } + } + + erofs_err(m->inode->i_sb, "bogus lookback distance @ nid %llu", + vi->nid); + DBG_BUGON(1); + return -EFSCORRUPTED; +} + +static int z_erofs_get_extent_compressedlen(struct z_erofs_maprecorder *m, + unsigned int initial_lcn) +{ + struct erofs_inode *const vi = EROFS_I(m->inode); struct erofs_map_blocks *const map = m->map; const unsigned int lclusterbits = vi->z_logical_clusterbits; - unsigned long lcn = m->lcn; + unsigned long lcn; int err; - if (lcn < lookback_distance) { - erofs_err(m->inode->i_sb, - "bogus lookback distance @ nid %llu", vi->nid); - DBG_BUGON(1); - return -EFSCORRUPTED; + DBG_BUGON(m->type != Z_EROFS_VLE_CLUSTER_TYPE_PLAIN && + m->type != Z_EROFS_VLE_CLUSTER_TYPE_HEAD1 && + m->type != Z_EROFS_VLE_CLUSTER_TYPE_HEAD2); + DBG_BUGON(m->type != m->headtype); + + if (m->headtype == Z_EROFS_VLE_CLUSTER_TYPE_PLAIN || + ((m->headtype == Z_EROFS_VLE_CLUSTER_TYPE_HEAD1) && + !(vi->z_advise & Z_EROFS_ADVISE_BIG_PCLUSTER_1)) || + ((m->headtype == Z_EROFS_VLE_CLUSTER_TYPE_HEAD2) && + !(vi->z_advise & Z_EROFS_ADVISE_BIG_PCLUSTER_2))) { + map->m_plen = 1ULL << lclusterbits; + return 0; } + lcn = m->lcn + 1; + if (m->compressedblks) + goto out; - /* load extent head logical cluster if needed */ - lcn -= lookback_distance; - err = z_erofs_load_cluster_from_disk(m, lcn); + err = z_erofs_load_cluster_from_disk(m, lcn, false); if (err) return err; + /* + * If the 1st NONHEAD lcluster has already been handled initially w/o + * valid compressedblks, which means at least it mustn't be CBLKCNT, or + * an internal implemenatation error is detected. + * + * The following code can also handle it properly anyway, but let's + * BUG_ON in the debugging mode only for developers to notice that. + */ + DBG_BUGON(lcn == initial_lcn && + m->type == Z_EROFS_VLE_CLUSTER_TYPE_NONHEAD); + switch (m->type) { - case Z_EROFS_VLE_CLUSTER_TYPE_NONHEAD: - if (!m->delta[0]) { - erofs_err(m->inode->i_sb, - "invalid lookback distance 0 @ nid %llu", - vi->nid); - DBG_BUGON(1); - return -EFSCORRUPTED; - } - return z_erofs_extent_lookback(m, m->delta[0]); case Z_EROFS_VLE_CLUSTER_TYPE_PLAIN: - map->m_flags &= ~EROFS_MAP_ZIPPED; - /* fallthrough */ - case Z_EROFS_VLE_CLUSTER_TYPE_HEAD: - map->m_la = (lcn << lclusterbits) | m->clusterofs; + case Z_EROFS_VLE_CLUSTER_TYPE_HEAD1: + case Z_EROFS_VLE_CLUSTER_TYPE_HEAD2: + /* + * if the 1st NONHEAD lcluster is actually PLAIN or HEAD type + * rather than CBLKCNT, it's a 1 lcluster-sized pcluster. + */ + m->compressedblks = 1 << (lclusterbits - LOG_BLOCK_SIZE); break; + case Z_EROFS_VLE_CLUSTER_TYPE_NONHEAD: + if (m->delta[0] != 1) + goto err_bonus_cblkcnt; + if (m->compressedblks) + break; + fallthrough; default: erofs_err(m->inode->i_sb, - "unknown type %u @ lcn %lu of nid %llu", - m->type, lcn, vi->nid); + "cannot found CBLKCNT @ lcn %lu of nid %llu", + lcn, vi->nid); DBG_BUGON(1); - return -EOPNOTSUPP; + return -EFSCORRUPTED; } +out: + map->m_plen = (u64)m->compressedblks << LOG_BLOCK_SIZE; return 0; +err_bonus_cblkcnt: + erofs_err(m->inode->i_sb, + "bogus CBLKCNT @ lcn %lu of nid %llu", + lcn, vi->nid); + DBG_BUGON(1); + return -EFSCORRUPTED; } -int z_erofs_map_blocks_iter(struct inode *inode, - struct erofs_map_blocks *map, - int flags) +static int z_erofs_get_extent_decompressedlen(struct z_erofs_maprecorder *m) +{ + struct inode *inode = m->inode; + struct erofs_inode *vi = EROFS_I(inode); + struct erofs_map_blocks *map = m->map; + unsigned int lclusterbits = vi->z_logical_clusterbits; + u64 lcn = m->lcn, headlcn = map->m_la >> lclusterbits; + int err; + + do { + /* handle the last EOF pcluster (no next HEAD lcluster) */ + if ((lcn << lclusterbits) >= inode->i_size) { + map->m_llen = inode->i_size - map->m_la; + return 0; + } + + err = z_erofs_load_cluster_from_disk(m, lcn, true); + if (err) + return err; + + if (m->type == Z_EROFS_VLE_CLUSTER_TYPE_NONHEAD) { + DBG_BUGON(!m->delta[1] && + m->clusterofs != 1 << lclusterbits); + } else if (m->type == Z_EROFS_VLE_CLUSTER_TYPE_PLAIN || + m->type == Z_EROFS_VLE_CLUSTER_TYPE_HEAD1 || + m->type == Z_EROFS_VLE_CLUSTER_TYPE_HEAD2) { + /* go on until the next HEAD lcluster */ + if (lcn != headlcn) + break; + m->delta[1] = 1; + } else { + erofs_err(inode->i_sb, "unknown type %u @ lcn %llu of nid %llu", + m->type, lcn, vi->nid); + DBG_BUGON(1); + return -EOPNOTSUPP; + } + lcn += m->delta[1]; + } while (m->delta[1]); + + map->m_llen = (lcn << lclusterbits) + m->clusterofs - map->m_la; + return 0; +} + +static int z_erofs_do_map_blocks(struct inode *inode, + struct erofs_map_blocks *map, + int flags) { struct erofs_inode *const vi = EROFS_I(inode); + bool ztailpacking = vi->z_advise & Z_EROFS_ADVISE_INLINE_PCLUSTER; + bool fragment = vi->z_advise & Z_EROFS_ADVISE_FRAGMENT_PCLUSTER; struct z_erofs_maprecorder m = { .inode = inode, .map = map, }; int err = 0; unsigned int lclusterbits, endoff; + unsigned long initial_lcn; unsigned long long ofs, end; - trace_z_erofs_map_blocks_iter_enter(inode, map, flags); - - /* when trying to read beyond EOF, leave it unmapped */ - if (map->m_la >= inode->i_size) { - map->m_llen = map->m_la + 1 - inode->i_size; - map->m_la = inode->i_size; - map->m_flags = 0; - goto out; - } - - err = z_erofs_fill_inode_lazy(inode); - if (err) - goto out; - lclusterbits = vi->z_logical_clusterbits; - ofs = map->m_la; - m.lcn = ofs >> lclusterbits; + ofs = flags & EROFS_GET_BLOCKS_FINDTAIL ? inode->i_size - 1 : map->m_la; + initial_lcn = ofs >> lclusterbits; endoff = ofs & ((1 << lclusterbits) - 1); - err = z_erofs_load_cluster_from_disk(&m, m.lcn); + err = z_erofs_load_cluster_from_disk(&m, initial_lcn, false); if (err) goto unmap_out; - map->m_flags = EROFS_MAP_ZIPPED; /* by default, compressed */ + if (ztailpacking && (flags & EROFS_GET_BLOCKS_FINDTAIL)) + vi->z_idataoff = m.nextpackoff; + + map->m_flags = EROFS_MAP_MAPPED | EROFS_MAP_ENCODED; end = (m.lcn + 1ULL) << lclusterbits; switch (m.type) { case Z_EROFS_VLE_CLUSTER_TYPE_PLAIN: - if (endoff >= m.clusterofs) - map->m_flags &= ~EROFS_MAP_ZIPPED; - /* fallthrough */ - case Z_EROFS_VLE_CLUSTER_TYPE_HEAD: + case Z_EROFS_VLE_CLUSTER_TYPE_HEAD1: + case Z_EROFS_VLE_CLUSTER_TYPE_HEAD2: if (endoff >= m.clusterofs) { + m.headtype = m.type; map->m_la = (m.lcn << lclusterbits) | m.clusterofs; + /* + * For ztailpacking files, in order to inline data more + * effectively, special EOF lclusters are now supported + * which can have three parts at most. + */ + if (ztailpacking && end > inode->i_size) + end = inode->i_size; break; } /* m.lcn should be >= 1 if endoff < m.clusterofs */ @@ -433,9 +659,9 @@ int z_erofs_map_blocks_iter(struct inode *inode, end = (m.lcn << lclusterbits) | m.clusterofs; map->m_flags |= EROFS_MAP_FULL_MAPPED; m.delta[0] = 1; - /* fallthrough */ + fallthrough; case Z_EROFS_VLE_CLUSTER_TYPE_NONHEAD: - /* get the correspoinding first chunk */ + /* get the corresponding first chunk */ err = z_erofs_extent_lookback(&m, m.delta[0]); if (err) goto unmap_out; @@ -447,21 +673,93 @@ int z_erofs_map_blocks_iter(struct inode *inode, err = -EOPNOTSUPP; goto unmap_out; } - + if (m.partialref) + map->m_flags |= EROFS_MAP_PARTIAL_REF; map->m_llen = end - map->m_la; - map->m_plen = 1 << lclusterbits; - map->m_pa = blknr_to_addr(m.pblk); - map->m_flags |= EROFS_MAP_MAPPED; + if (flags & EROFS_GET_BLOCKS_FINDTAIL) { + vi->z_tailextent_headlcn = m.lcn; + /* for non-compact indexes, fragmentoff is 64 bits */ + if (fragment && + vi->datalayout == EROFS_INODE_FLAT_COMPRESSION_LEGACY) + vi->z_fragmentoff |= (u64)m.pblk << 32; + } + if (ztailpacking && m.lcn == vi->z_tailextent_headlcn) { + map->m_flags |= EROFS_MAP_META; + map->m_pa = vi->z_idataoff; + map->m_plen = vi->z_idata_size; + } else if (fragment && m.lcn == vi->z_tailextent_headlcn) { + map->m_flags |= EROFS_MAP_FRAGMENT; + } else { + map->m_pa = blknr_to_addr(m.pblk); + err = z_erofs_get_extent_compressedlen(&m, initial_lcn); + if (err) + goto out; + } + + if (m.headtype == Z_EROFS_VLE_CLUSTER_TYPE_PLAIN) { + if (vi->z_advise & Z_EROFS_ADVISE_INTERLACED_PCLUSTER) + map->m_algorithmformat = + Z_EROFS_COMPRESSION_INTERLACED; + else + map->m_algorithmformat = + Z_EROFS_COMPRESSION_SHIFTED; + } else if (m.headtype == Z_EROFS_VLE_CLUSTER_TYPE_HEAD2) { + map->m_algorithmformat = vi->z_algorithmtype[1]; + } else { + map->m_algorithmformat = vi->z_algorithmtype[0]; + } + + if ((flags & EROFS_GET_BLOCKS_FIEMAP) || + ((flags & EROFS_GET_BLOCKS_READMORE) && + map->m_algorithmformat == Z_EROFS_COMPRESSION_LZMA && + map->m_llen >= EROFS_BLKSIZ)) { + err = z_erofs_get_extent_decompressedlen(&m); + if (!err) + map->m_flags |= EROFS_MAP_FULL_MAPPED; + } unmap_out: - if (m.kaddr) - kunmap_atomic(m.kaddr); + erofs_unmap_metabuf(&m.map->buf); out: erofs_dbg("%s, m_la %llu m_pa %llu m_llen %llu m_plen %llu m_flags 0%o", __func__, map->m_la, map->m_pa, map->m_llen, map->m_plen, map->m_flags); + return err; +} + +int z_erofs_map_blocks_iter(struct inode *inode, struct erofs_map_blocks *map, + int flags) +{ + struct erofs_inode *const vi = EROFS_I(inode); + int err = 0; + + trace_z_erofs_map_blocks_iter_enter(inode, map, flags); + + /* when trying to read beyond EOF, leave it unmapped */ + if (map->m_la >= inode->i_size) { + map->m_llen = map->m_la + 1 - inode->i_size; + map->m_la = inode->i_size; + map->m_flags = 0; + goto out; + } + + err = z_erofs_fill_inode_lazy(inode); + if (err) + goto out; + + if ((vi->z_advise & Z_EROFS_ADVISE_FRAGMENT_PCLUSTER) && + !vi->z_tailextent_headlcn) { + map->m_la = 0; + map->m_llen = inode->i_size; + map->m_flags = EROFS_MAP_MAPPED | EROFS_MAP_FULL_MAPPED | + EROFS_MAP_FRAGMENT; + goto out; + } + + err = z_erofs_do_map_blocks(inode, map, flags); +out: trace_z_erofs_map_blocks_iter_exit(inode, map, flags, err); /* aggressively BUG_ON iff CONFIG_EROFS_FS_DEBUG is on */ @@ -469,3 +767,40 @@ out: return err; } +static int z_erofs_iomap_begin_report(struct inode *inode, loff_t offset, + loff_t length, unsigned int flags, + struct iomap *iomap, struct iomap *srcmap) +{ + int ret; + struct erofs_map_blocks map = { .m_la = offset }; + + ret = z_erofs_map_blocks_iter(inode, &map, EROFS_GET_BLOCKS_FIEMAP); + erofs_put_metabuf(&map.buf); + if (ret < 0) + return ret; + + iomap->bdev = inode->i_sb->s_bdev; + iomap->offset = map.m_la; + iomap->length = map.m_llen; + if (map.m_flags & EROFS_MAP_MAPPED) { + iomap->type = IOMAP_MAPPED; + iomap->addr = map.m_flags & EROFS_MAP_FRAGMENT ? + IOMAP_NULL_ADDR : map.m_pa; + } else { + iomap->type = IOMAP_HOLE; + iomap->addr = IOMAP_NULL_ADDR; + /* + * No strict rule how to describe extents for post EOF, yet + * we need do like below. Otherwise, iomap itself will get + * into an endless loop on post EOF. + */ + if (iomap->offset >= inode->i_size) + iomap->length = length + map.m_la - offset; + } + iomap->flags = 0; + return 0; +} + +const struct iomap_ops z_erofs_iomap_report_ops = { + .iomap_begin = z_erofs_iomap_begin_report, +}; diff --git a/fs/erofs/zpvec.h b/fs/erofs/zpvec.h deleted file mode 100644 index 58556903aa94..000000000000 --- a/fs/erofs/zpvec.h +++ /dev/null @@ -1,157 +0,0 @@ -/* 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_ZPVEC_H -#define __EROFS_FS_ZPVEC_H - -#include "tagptr.h" - -/* page type in pagevec for decompress subsystem */ -enum z_erofs_page_type { - /* including Z_EROFS_VLE_PAGE_TAIL_EXCLUSIVE */ - Z_EROFS_PAGE_TYPE_EXCLUSIVE, - - Z_EROFS_VLE_PAGE_TYPE_TAIL_SHARED, - - Z_EROFS_VLE_PAGE_TYPE_HEAD, - Z_EROFS_VLE_PAGE_TYPE_MAX -}; - -extern void __compiletime_error("Z_EROFS_PAGE_TYPE_EXCLUSIVE != 0") - __bad_page_type_exclusive(void); - -/* pagevec tagged pointer */ -typedef tagptr2_t erofs_vtptr_t; - -/* pagevec collector */ -struct z_erofs_pagevec_ctor { - struct page *curr, *next; - erofs_vtptr_t *pages; - - unsigned int nr, index; -}; - -static inline void z_erofs_pagevec_ctor_exit(struct z_erofs_pagevec_ctor *ctor, - bool atomic) -{ - if (!ctor->curr) - return; - - if (atomic) - kunmap_atomic(ctor->pages); - else - kunmap(ctor->curr); -} - -static inline struct page * -z_erofs_pagevec_ctor_next_page(struct z_erofs_pagevec_ctor *ctor, - unsigned int nr) -{ - unsigned int index; - - /* keep away from occupied pages */ - if (ctor->next) - return ctor->next; - - for (index = 0; index < nr; ++index) { - const erofs_vtptr_t t = ctor->pages[index]; - const unsigned int tags = tagptr_unfold_tags(t); - - if (tags == Z_EROFS_PAGE_TYPE_EXCLUSIVE) - return tagptr_unfold_ptr(t); - } - DBG_BUGON(nr >= ctor->nr); - return NULL; -} - -static inline void -z_erofs_pagevec_ctor_pagedown(struct z_erofs_pagevec_ctor *ctor, - bool atomic) -{ - struct page *next = z_erofs_pagevec_ctor_next_page(ctor, ctor->nr); - - z_erofs_pagevec_ctor_exit(ctor, atomic); - - ctor->curr = next; - ctor->next = NULL; - ctor->pages = atomic ? - kmap_atomic(ctor->curr) : kmap(ctor->curr); - - ctor->nr = PAGE_SIZE / sizeof(struct page *); - ctor->index = 0; -} - -static inline void z_erofs_pagevec_ctor_init(struct z_erofs_pagevec_ctor *ctor, - unsigned int nr, - erofs_vtptr_t *pages, - unsigned int i) -{ - ctor->nr = nr; - ctor->curr = ctor->next = NULL; - ctor->pages = pages; - - if (i >= nr) { - i -= nr; - z_erofs_pagevec_ctor_pagedown(ctor, false); - while (i > ctor->nr) { - i -= ctor->nr; - z_erofs_pagevec_ctor_pagedown(ctor, false); - } - } - ctor->next = z_erofs_pagevec_ctor_next_page(ctor, i); - ctor->index = i; -} - -static inline bool z_erofs_pagevec_enqueue(struct z_erofs_pagevec_ctor *ctor, - struct page *page, - enum z_erofs_page_type type, - bool *occupied) -{ - *occupied = false; - if (!ctor->next && type) - if (ctor->index + 1 == ctor->nr) - return false; - - if (ctor->index >= ctor->nr) - z_erofs_pagevec_ctor_pagedown(ctor, false); - - /* exclusive page type must be 0 */ - if (Z_EROFS_PAGE_TYPE_EXCLUSIVE != (uintptr_t)NULL) - __bad_page_type_exclusive(); - - /* should remind that collector->next never equal to 1, 2 */ - if (type == (uintptr_t)ctor->next) { - ctor->next = page; - *occupied = true; - } - ctor->pages[ctor->index++] = tagptr_fold(erofs_vtptr_t, page, type); - return true; -} - -static inline struct page * -z_erofs_pagevec_dequeue(struct z_erofs_pagevec_ctor *ctor, - enum z_erofs_page_type *type) -{ - erofs_vtptr_t t; - - if (ctor->index >= ctor->nr) { - DBG_BUGON(!ctor->next); - z_erofs_pagevec_ctor_pagedown(ctor, true); - } - - t = ctor->pages[ctor->index]; - - *type = tagptr_unfold_tags(t); - - /* should remind that collector->next never equal to 1, 2 */ - if (*type == (uintptr_t)ctor->next) - ctor->next = tagptr_unfold_ptr(t); - - ctor->pages[ctor->index++] = tagptr_fold(erofs_vtptr_t, NULL, 0); - return tagptr_unfold_ptr(t); -} -#endif - |