diff options
| author | Zeng Chi <zengchi@kylinos.cn> | 2026-09-21 18:24:42 +0800 |
|---|---|---|
| committer | Sean Christopherson <seanjc@google.com> | 2026-09-22 08:36:16 -0700 |
| commit | 119e9db233ad0f4cbd4cfb9f9385a7bca378b37d (patch) | |
| tree | 660d50d4139cb750fbde1ae3432452c20726c99d /fs/squashfs | |
| download | linux-stable-119e9db233ad0f4cbd4cfb9f9385a7bca378b37d.tar.gz linux-stable-119e9db233ad0f4cbd4cfb9f9385a7bca378b37d.zip | |
KVM: Don't pre-reserve xarray entries when storing empty/NULL attributesgrafted
Skip the xarray reservation loop when clearing all memory attributes, as
storing NULL only erases the entry and never needs to allocate, so no
reservation (and no cleanup of a failed one) is required in that case.
Suggested-by: Sean Christopherson <seanjc@google.com>
Cc: David Ballesteros <davimaba.v@proton.me>
Signed-off-by: Zeng Chi <zengchi@kylinos.cn>
Link: https://patch.msgid.link/20260921102442.1232375-1-zeng_chi911@163.com
[sean: split to separate patch]
Signed-off-by: Sean Christopherson <seanjc@google.com>
Diffstat (limited to 'fs/squashfs')
34 files changed, 6997 insertions, 0 deletions
diff --git a/fs/squashfs/Kconfig b/fs/squashfs/Kconfig new file mode 100644 index 000000000..a9602aae2 --- /dev/null +++ b/fs/squashfs/Kconfig @@ -0,0 +1,287 @@ +# SPDX-License-Identifier: GPL-2.0-only +config SQUASHFS + tristate "SquashFS 4.0 - Squashed file system support" + depends on BLOCK + help + Saying Y here includes support for SquashFS 4.0 (a Compressed + Read-Only File System). Squashfs is a highly compressed read-only + filesystem for Linux. It uses zlib, lz4, lzo, xz or zstd compression + to compress both files, inodes and directories. Inodes in the system + are very small and all blocks are packed to minimise data overhead. + Block sizes greater than 4K are supported up to a maximum of 1 Mbytes + (default block size 128K). SquashFS 4.0 supports 64 bit filesystems + and files (larger than 4GB), full uid/gid information, hard links and + timestamps. + + Squashfs is intended for general read-only filesystem use, for + archival use (i.e. in cases where a .tar.gz file may be used), and in + embedded systems where low overhead is needed. Further information + and tools are available from github.com/plougher/squashfs-tools. + + If you want to compile this as a module ( = code which can be + inserted in and removed from the running kernel whenever you want), + say M here. The module will be called squashfs. Note that the root + file system (the one containing the directory /) cannot be compiled + as a module. + + If unsure, say N. + +choice + prompt "File decompression options" + depends on SQUASHFS + help + Squashfs now supports two options for decompressing file + data. Traditionally Squashfs has decompressed into an + intermediate buffer and then memcopied it into the page cache. + Squashfs now supports the ability to decompress directly into + the page cache. + + If unsure, select "Decompress file data into an intermediate buffer" + +config SQUASHFS_FILE_CACHE + bool "Decompress file data into an intermediate buffer" + help + Decompress file data into an intermediate buffer and then + memcopy it into the page cache. + +config SQUASHFS_FILE_DIRECT + bool "Decompress files directly into the page cache" + help + Directly decompress file data into the page cache. + Doing so can significantly improve performance because + it eliminates a memcpy and it also removes the lock contention + on the single buffer. + +endchoice + +config SQUASHFS_DECOMP_SINGLE + depends on SQUASHFS + def_bool n + +config SQUASHFS_DECOMP_MULTI + depends on SQUASHFS + def_bool n + +config SQUASHFS_DECOMP_MULTI_PERCPU + depends on SQUASHFS + def_bool n + +config SQUASHFS_CHOICE_DECOMP_BY_MOUNT + bool "Select the parallel decompression mode during mount" + depends on SQUASHFS + default n + select SQUASHFS_DECOMP_SINGLE + select SQUASHFS_DECOMP_MULTI + select SQUASHFS_DECOMP_MULTI_PERCPU + select SQUASHFS_MOUNT_DECOMP_THREADS + help + Compile all parallel decompression modes and specify the + decompression mode by setting "threads=" during mount. + default Decompressor parallelisation is SQUASHFS_DECOMP_SINGLE + +choice + prompt "Select decompression parallel mode at compile time" + depends on SQUASHFS + depends on !SQUASHFS_CHOICE_DECOMP_BY_MOUNT + help + Squashfs now supports three parallelisation options for + decompression. Each one exhibits various trade-offs between + decompression performance and CPU and memory usage. + + If in doubt, select "Single threaded compression" + +config SQUASHFS_COMPILE_DECOMP_SINGLE + bool "Single threaded compression" + select SQUASHFS_DECOMP_SINGLE + help + Traditionally Squashfs has used single-threaded decompression. + Only one block (data or metadata) can be decompressed at any + one time. This limits CPU and memory usage to a minimum. + +config SQUASHFS_COMPILE_DECOMP_MULTI + bool "Use multiple decompressors for parallel I/O" + select SQUASHFS_DECOMP_MULTI + help + By default Squashfs uses a single decompressor but it gives + poor performance on parallel I/O workloads when using multiple CPU + machines due to waiting on decompressor availability. + + If you have a parallel I/O workload and your system has enough memory, + using this option may improve overall I/O performance. + + This decompressor implementation uses up to two parallel + decompressors per core. It dynamically allocates decompressors + on a demand basis. + +config SQUASHFS_COMPILE_DECOMP_MULTI_PERCPU + bool "Use percpu multiple decompressors for parallel I/O" + select SQUASHFS_DECOMP_MULTI_PERCPU + help + By default Squashfs uses a single decompressor but it gives + poor performance on parallel I/O workloads when using multiple CPU + machines due to waiting on decompressor availability. + + This decompressor implementation uses a maximum of one + decompressor per core. It uses percpu variables to ensure + decompression is load-balanced across the cores. +endchoice + +config SQUASHFS_MOUNT_DECOMP_THREADS + bool "Add the mount parameter 'threads=' for squashfs" + depends on SQUASHFS + depends on SQUASHFS_DECOMP_MULTI + default n + help + Use threads= to set the decompression parallel mode and the number of threads. + If SQUASHFS_CHOICE_DECOMP_BY_MOUNT=y + threads=<single|multi|percpu|1|2|3|...> + else + threads=<2|3|...> + The upper limit is num_online_cpus() * 2. + +config SQUASHFS_XATTR + bool "Squashfs XATTR support" + depends on SQUASHFS + help + Saying Y here includes support for extended attributes (xattrs). + Xattrs are name:value pairs associated with inodes by + the kernel or by users (see the attr(5) manual page). + + If unsure, say N. + +config SQUASHFS_COMP_CACHE_FULL + bool "Enable full caching of compressed blocks" + depends on SQUASHFS + default n + help + This option enables caching of all compressed blocks, Without caching, + repeated reads of the same files trigger excessive disk I/O, significantly + reducinng performance in workloads like fio-based benchmarks. + + For example, fio tests (iodepth=1, numjobs=1, ioengine=psync) show: + With caching: IOPS=2223, BW=278MiB/s (291MB/s) + Without caching: IOPS=815, BW=102MiB/s (107MB/s) + + Enabling this option restores performance to pre-regression levels by + caching all compressed blocks in the page cache, reducing disk I/O for + repeated reads. However, this increases memory usage, which may be a + concern in memory-constrained environments. + + Enable this option if your workload involves frequent repeated reads and + memory usage is not a limiting factor. If unsure, say N. + +config SQUASHFS_ZLIB + bool "Include support for ZLIB compressed file systems" + depends on SQUASHFS + select ZLIB_INFLATE + default y + help + ZLIB compression is the standard compression used by Squashfs + file systems. It offers a good trade-off between compression + achieved and the amount of CPU time and memory necessary to + compress and decompress. + + If unsure, say Y. + +config SQUASHFS_LZ4 + bool "Include support for LZ4 compressed file systems" + depends on SQUASHFS + select LZ4_DECOMPRESS + help + Saying Y here includes support for reading Squashfs file systems + compressed with LZ4 compression. LZ4 compression is mainly + aimed at embedded systems with slower CPUs where the overheads + of zlib are too high. + + LZ4 is not the standard compression used in Squashfs and so most + file systems will be readable without selecting this option. + + If unsure, say N. + +config SQUASHFS_LZO + bool "Include support for LZO compressed file systems" + depends on SQUASHFS + select LZO_DECOMPRESS + help + Saying Y here includes support for reading Squashfs file systems + compressed with LZO compression. LZO compression is mainly + aimed at embedded systems with slower CPUs where the overheads + of zlib are too high. + + LZO is not the standard compression used in Squashfs and so most + file systems will be readable without selecting this option. + + If unsure, say N. + +config SQUASHFS_XZ + bool "Include support for XZ compressed file systems" + depends on SQUASHFS + select XZ_DEC + help + Saying Y here includes support for reading Squashfs file systems + compressed with XZ compression. XZ gives better compression than + the default zlib compression, at the expense of greater CPU and + memory overhead. + + XZ is not the standard compression used in Squashfs and so most + file systems will be readable without selecting this option. + + If unsure, say N. + +config SQUASHFS_ZSTD + bool "Include support for ZSTD compressed file systems" + depends on SQUASHFS + select ZSTD_DECOMPRESS + help + Saying Y here includes support for reading Squashfs file systems + compressed with ZSTD compression. ZSTD gives better compression than + the default ZLIB compression, while using less CPU. + + ZSTD is not the standard compression used in Squashfs and so most + file systems will be readable without selecting this option. + + If unsure, say N. + +config SQUASHFS_4K_DEVBLK_SIZE + bool "Use 4K device block size?" + depends on SQUASHFS + help + By default Squashfs sets the dev block size (sb_min_blocksize) + to 1K or the smallest block size supported by the block device + (if larger). This, because blocks are packed together and + unaligned in Squashfs, should reduce latency. + + This, however, gives poor performance on MTD NAND devices where + the optimal I/O size is 4K (even though the devices can support + smaller block sizes). + + Using a 4K device block size may also improve overall I/O + performance for some file access patterns (e.g. sequential + accesses of files in filesystem order) on all media. + + Setting this option will force Squashfs to use a 4K device block + size by default. + + If unsure, say N. + +config SQUASHFS_EMBEDDED + bool "Additional option for memory-constrained systems" + depends on SQUASHFS + help + Saying Y here allows you to specify cache size. + + If unsure, say N. + +config SQUASHFS_FRAGMENT_CACHE_SIZE + int "Number of fragments cached" if SQUASHFS_EMBEDDED + depends on SQUASHFS + default "3" + help + By default SquashFS caches the last 3 fragments read from + the filesystem. Increasing this amount may mean SquashFS + has to re-read fragments less often from disk, at the expense + of extra system memory. Decreasing this amount will mean + SquashFS uses less memory at the expense of extra reads from disk. + + Note there must be at least one cached fragment. Anything + much more than three will probably not make much difference. diff --git a/fs/squashfs/Makefile b/fs/squashfs/Makefile new file mode 100644 index 000000000..477c89a51 --- /dev/null +++ b/fs/squashfs/Makefile @@ -0,0 +1,19 @@ +# SPDX-License-Identifier: GPL-2.0 +# +# Makefile for the linux squashfs routines. +# + +obj-$(CONFIG_SQUASHFS) += squashfs.o +squashfs-y += block.o cache.o dir.o export.o file.o fragment.o id.o inode.o +squashfs-y += namei.o super.o symlink.o decompressor.o page_actor.o +squashfs-$(CONFIG_SQUASHFS_FILE_CACHE) += file_cache.o +squashfs-$(CONFIG_SQUASHFS_FILE_DIRECT) += file_direct.o +squashfs-$(CONFIG_SQUASHFS_DECOMP_SINGLE) += decompressor_single.o +squashfs-$(CONFIG_SQUASHFS_DECOMP_MULTI) += decompressor_multi.o +squashfs-$(CONFIG_SQUASHFS_DECOMP_MULTI_PERCPU) += decompressor_multi_percpu.o +squashfs-$(CONFIG_SQUASHFS_XATTR) += xattr.o xattr_id.o +squashfs-$(CONFIG_SQUASHFS_LZ4) += lz4_wrapper.o +squashfs-$(CONFIG_SQUASHFS_LZO) += lzo_wrapper.o +squashfs-$(CONFIG_SQUASHFS_XZ) += xz_wrapper.o +squashfs-$(CONFIG_SQUASHFS_ZLIB) += zlib_wrapper.o +squashfs-$(CONFIG_SQUASHFS_ZSTD) += zstd_wrapper.o diff --git a/fs/squashfs/block.c b/fs/squashfs/block.c new file mode 100644 index 000000000..2d5850168 --- /dev/null +++ b/fs/squashfs/block.c @@ -0,0 +1,386 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Squashfs - a compressed read only filesystem for Linux + * + * Copyright (c) 2002, 2003, 2004, 2005, 2006, 2007, 2008 + * Phillip Lougher <phillip@squashfs.org.uk> + * + * block.c + */ + +/* + * This file implements the low-level routines to read and decompress + * datablocks and metadata blocks. + */ + +#include <linux/blkdev.h> +#include <linux/fs.h> +#include <linux/vfs.h> +#include <linux/slab.h> +#include <linux/pagemap.h> +#include <linux/string.h> +#include <linux/bio.h> + +#include "squashfs_fs.h" +#include "squashfs_fs_sb.h" +#include "squashfs.h" +#include "decompressor.h" +#include "page_actor.h" + +/* + * Returns the amount of bytes copied to the page actor. + */ +static int copy_bio_to_actor(struct bio *bio, + struct squashfs_page_actor *actor, + int offset, int req_length) +{ + void *actor_addr; + struct bvec_iter_all iter_all = {}; + struct bio_vec *bvec = bvec_init_iter_all(&iter_all); + int copied_bytes = 0; + int actor_offset = 0; + + squashfs_actor_nobuff(actor); + actor_addr = squashfs_first_page(actor); + + if (WARN_ON_ONCE(!bio_next_segment(bio, &iter_all))) + return 0; + + while (copied_bytes < req_length) { + int bytes_to_copy = min_t(int, bvec->bv_len - offset, + PAGE_SIZE - actor_offset); + + bytes_to_copy = min_t(int, bytes_to_copy, + req_length - copied_bytes); + if (!IS_ERR(actor_addr)) + memcpy(actor_addr + actor_offset, bvec_virt(bvec) + + offset, bytes_to_copy); + + actor_offset += bytes_to_copy; + copied_bytes += bytes_to_copy; + offset += bytes_to_copy; + + if (actor_offset >= PAGE_SIZE) { + actor_addr = squashfs_next_page(actor); + if (!actor_addr) + break; + actor_offset = 0; + } + if (offset >= bvec->bv_len) { + if (!bio_next_segment(bio, &iter_all)) + break; + offset = 0; + } + } + squashfs_finish_page(actor); + return copied_bytes; +} + +static int squashfs_bio_read_cached(struct bio *fullbio, + struct address_space *cache_mapping, u64 index, int length, + u64 read_start, u64 read_end, int page_count) +{ + struct folio *head_to_cache = NULL, *tail_to_cache = NULL; + struct block_device *bdev = fullbio->bi_bdev; + int start_idx = 0, end_idx = 0; + struct folio_iter fi; + struct bio *bio = NULL; + int idx = 0; + int err = 0; +#ifdef CONFIG_SQUASHFS_COMP_CACHE_FULL + struct folio **cache_folios = kmalloc_objs(*cache_folios, page_count, + GFP_KERNEL | __GFP_ZERO); +#endif + + bio_for_each_folio_all(fi, fullbio) { + struct folio *folio = fi.folio; + + if (folio->mapping == cache_mapping) { + idx++; + continue; + } + + /* + * We only use this when the device block size is the same as + * the page size, so read_start and read_end cover full pages. + * + * Compare these to the original required index and length to + * only cache pages which were requested partially, since these + * are the ones which are likely to be needed when reading + * adjacent blocks. + */ + if (idx == 0 && index != read_start) + head_to_cache = folio; + else if (idx == page_count - 1 && index + length != read_end) + tail_to_cache = folio; +#ifdef CONFIG_SQUASHFS_COMP_CACHE_FULL + /* Cache all pages in the BIO for repeated reads */ + else if (cache_folios) + cache_folios[idx] = folio; +#endif + + if (!bio || idx != end_idx) { + struct bio *new = bio_alloc_clone(bdev, fullbio, + GFP_NOIO, &fs_bio_set); + + if (bio) { + bio_trim(bio, start_idx * PAGE_SECTORS, + (end_idx - start_idx) * PAGE_SECTORS); + bio_chain(bio, new); + submit_bio(bio); + } + + bio = new; + start_idx = idx; + } + + idx++; + end_idx = idx; + } + + if (bio) { + bio_trim(bio, start_idx * PAGE_SECTORS, + (end_idx - start_idx) * PAGE_SECTORS); + err = submit_bio_wait(bio); + bio_put(bio); + } + + if (err) + return err; + + if (head_to_cache) { + int ret = filemap_add_folio(cache_mapping, head_to_cache, + read_start >> PAGE_SHIFT, + GFP_NOIO); + + if (!ret) { + folio_mark_uptodate(head_to_cache); + folio_unlock(head_to_cache); + } + + } + + if (tail_to_cache) { + int ret = filemap_add_folio(cache_mapping, tail_to_cache, + (read_end >> PAGE_SHIFT) - 1, + GFP_NOIO); + + if (!ret) { + folio_mark_uptodate(tail_to_cache); + folio_unlock(tail_to_cache); + } + } + +#ifdef CONFIG_SQUASHFS_COMP_CACHE_FULL + if (!cache_folios) + goto out; + + for (idx = 0; idx < page_count; idx++) { + if (!cache_folios[idx]) + continue; + int ret = filemap_add_folio(cache_mapping, cache_folios[idx], + (read_start >> PAGE_SHIFT) + idx, + GFP_NOIO); + + if (!ret) { + folio_mark_uptodate(cache_folios[idx]); + folio_unlock(cache_folios[idx]); + } + } + kfree(cache_folios); +out: +#endif + return 0; +} + +static struct page *squashfs_get_cache_page(struct address_space *mapping, + pgoff_t index) +{ + struct page *page; + + if (!mapping) + return NULL; + + page = find_get_page(mapping, index); + if (!page) + return NULL; + + if (!PageUptodate(page)) { + put_page(page); + return NULL; + } + + return page; +} + +static int squashfs_bio_read(struct super_block *sb, u64 index, int length, + struct bio **biop, int *block_offset) +{ + struct squashfs_sb_info *msblk = sb->s_fs_info; + struct address_space *cache_mapping = msblk->cache_mapping; + const u64 read_start = round_down(index, msblk->devblksize); + const sector_t block = read_start >> msblk->devblksize_log2; + const u64 read_end = round_up(index + length, msblk->devblksize); + const sector_t block_end = read_end >> msblk->devblksize_log2; + int offset = read_start - round_down(index, PAGE_SIZE); + int total_len = (block_end - block) << msblk->devblksize_log2; + const int page_count = DIV_ROUND_UP(total_len + offset, PAGE_SIZE); + int error, i; + struct bio *bio; + + bio = bio_kmalloc(page_count, GFP_NOIO); + if (!bio) + return -ENOMEM; + bio_init_inline(bio, sb->s_bdev, page_count, REQ_OP_READ); + bio->bi_iter.bi_sector = block * (msblk->devblksize >> SECTOR_SHIFT); + + for (i = 0; i < page_count; ++i) { + unsigned int len = + min_t(unsigned int, PAGE_SIZE - offset, total_len); + pgoff_t index = (read_start >> PAGE_SHIFT) + i; + struct page *page; + + page = squashfs_get_cache_page(cache_mapping, index); + if (!page) + page = alloc_page(GFP_NOIO); + + if (!page) { + error = -ENOMEM; + goto out_free_bio; + } + + /* + * Use the __ version to avoid merging since we need each page + * to be separate when we check for and avoid cached pages. + */ + __bio_add_page(bio, page, len, offset); + offset = 0; + total_len -= len; + } + + if (cache_mapping) + error = squashfs_bio_read_cached(bio, cache_mapping, index, + length, read_start, read_end, + page_count); + else + error = submit_bio_wait(bio); + if (error) + goto out_free_bio; + + *biop = bio; + *block_offset = index & ((1 << msblk->devblksize_log2) - 1); + return 0; + +out_free_bio: + bio_free_pages(bio); + bio_uninit(bio); + kfree(bio); + return error; +} + +/* + * Read and decompress a metadata block or datablock. Length is non-zero + * if a datablock is being read (the size is stored elsewhere in the + * filesystem), otherwise the length is obtained from the first two bytes of + * the metadata block. A bit in the length field indicates if the block + * is stored uncompressed in the filesystem (usually because compression + * generated a larger block - this does occasionally happen with compression + * algorithms). + */ +int squashfs_read_data(struct super_block *sb, u64 index, int length, + u64 *next_index, struct squashfs_page_actor *output) +{ + struct squashfs_sb_info *msblk = sb->s_fs_info; + struct bio *bio = NULL; + int compressed; + int res; + int offset; + + if (length) { + /* + * Datablock. + */ + compressed = SQUASHFS_COMPRESSED_BLOCK(length); + length = SQUASHFS_COMPRESSED_SIZE_BLOCK(length); + TRACE("Block @ 0x%llx, %scompressed size %d, src size %d\n", + index, compressed ? "" : "un", length, output->length); + } else { + /* + * Metadata block. + */ + const u8 *data; + struct bvec_iter_all iter_all = {}; + struct bio_vec *bvec = bvec_init_iter_all(&iter_all); + + if (index + 2 > msblk->bytes_used) { + res = -EIO; + goto out; + } + res = squashfs_bio_read(sb, index, 2, &bio, &offset); + if (res) + goto out; + + if (WARN_ON_ONCE(!bio_next_segment(bio, &iter_all))) { + res = -EIO; + goto out_free_bio; + } + /* Extract the length of the metadata block */ + data = bvec_virt(bvec); + length = data[offset]; + if (offset < bvec->bv_len - 1) { + length |= data[offset + 1] << 8; + } else { + if (WARN_ON_ONCE(!bio_next_segment(bio, &iter_all))) { + res = -EIO; + goto out_free_bio; + } + data = bvec_virt(bvec); + length |= data[0] << 8; + } + bio_free_pages(bio); + bio_uninit(bio); + kfree(bio); + + compressed = SQUASHFS_COMPRESSED(length); + length = SQUASHFS_COMPRESSED_SIZE(length); + index += 2; + + TRACE("Block @ 0x%llx, %scompressed size %d\n", index - 2, + compressed ? "" : "un", length); + } + if (length <= 0 || length > output->length || + (index + length) > msblk->bytes_used) { + res = -EIO; + goto out; + } + + if (next_index) + *next_index = index + length; + + res = squashfs_bio_read(sb, index, length, &bio, &offset); + if (res) + goto out; + + if (compressed) { + if (!msblk->stream) { + res = -EIO; + goto out_free_bio; + } + res = msblk->thread_ops->decompress(msblk, bio, offset, length, output); + } else { + res = copy_bio_to_actor(bio, output, offset, length); + } + +out_free_bio: + bio_free_pages(bio); + bio_uninit(bio); + kfree(bio); +out: + if (res < 0) { + ERROR("Failed to read block 0x%llx: %d\n", index, res); + if (msblk->panic_on_errors) + panic("squashfs read failed"); + } + + return res; +} diff --git a/fs/squashfs/cache.c b/fs/squashfs/cache.c new file mode 100644 index 000000000..c1a83bb0e --- /dev/null +++ b/fs/squashfs/cache.c @@ -0,0 +1,557 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Squashfs - a compressed read only filesystem for Linux + * + * Copyright (c) 2002, 2003, 2004, 2005, 2006, 2007, 2008 + * Phillip Lougher <phillip@squashfs.org.uk> + * + * cache.c + */ + +/* + * Blocks in Squashfs are compressed. To avoid repeatedly decompressing + * recently accessed data Squashfs uses two small metadata and fragment caches. + * + * This file implements a generic cache implementation used for both caches, + * plus functions layered ontop of the generic cache implementation to + * access the metadata and fragment caches. + * + * To avoid out of memory and fragmentation issues with vmalloc the cache + * uses sequences of kmalloced PAGE_SIZE buffers. + * + * It should be noted that the cache is not used for file datablocks, these + * are decompressed and cached in the page-cache in the normal way. The + * cache is only used to temporarily cache fragment and metadata blocks + * which have been read as as a result of a metadata (i.e. inode or + * directory) or fragment access. Because metadata and fragments are packed + * together into blocks (to gain greater compression) the read of a particular + * piece of metadata or fragment will retrieve other metadata/fragments which + * have been packed with it, these because of locality-of-reference may be read + * in the near future. Temporarily caching them ensures they are available for + * near future access without requiring an additional read and decompress. + */ + +#include <linux/fs.h> +#include <linux/vfs.h> +#include <linux/slab.h> +#include <linux/vmalloc.h> +#include <linux/sched.h> +#include <linux/spinlock.h> +#include <linux/wait.h> +#include <linux/pagemap.h> + +#include "squashfs_fs.h" +#include "squashfs_fs_sb.h" +#include "squashfs.h" +#include "page_actor.h" + +/* + * Waiters on cache->wait_queue are keyed by the block they want, so a wakeup + * can name who it is for. A NULL key is a capacity wakeup: one entry became + * free, so wake one waiter. A block key is a publication wakeup: that block + * now has an entry, so wake every waiter which can share it. + */ +struct squashfs_cache_wait { + wait_queue_entry_t wait; + u64 block; + bool capacity_wake; +}; + +static int squashfs_cache_wake_function(wait_queue_entry_t *wait, + unsigned int mode, int sync, void *key) +{ + struct squashfs_cache_wait *cache_wait = + container_of(wait, struct squashfs_cache_wait, wait); + u64 *block = key; + + if (block && cache_wait->block != *block) + return 0; + + WRITE_ONCE(cache_wait->capacity_wake, !block); + + /* + * Wake and unlink unconditionally instead of using + * autoremove_wake_function(), which unlinks only when it changed the + * task state. A waiter can be made runnable by something which does + * not go through this queue: wake_up_process() takes TASK_NORMAL, and + * a cgroup v2 thaw calls it on every task in the cgroup, as do + * free_pid() on a pid namespace init and a late rcuwait_wake_up(). + * try_to_wake_up() then fails. Leaving such a waiter queued with a + * reason already recorded would let it act on a freed entry it was not + * given, and the failure would not consume the exclusive budget, so a + * second waiter would be woken for the same entry. + * + * list_del_init_careful() must be the last access to @cache_wait: it + * releases the waiter, whose wait structure lives on its stack, and it + * pairs with list_empty_careful() in finish_wait() to publish the + * store above. __wake_up_common() samples ->flags and the next entry + * before calling here, so it does not touch @wait afterwards either. + */ + default_wake_function(wait, mode, sync, key); + list_del_init_careful(&wait->entry); + + return 1; +} + +static void squashfs_cache_wake_block(struct squashfs_cache *cache, u64 block) +{ + /* nr_exclusive == 0: wake every waiter which matches the key. */ + __wake_up(&cache->wait_queue, TASK_NORMAL, 0, &block); +} + +/* + * Look-up block in cache, and increment usage count. If not in cache, read + * and decompress it from disk. + * + * A caller which finds no free entry sleeps on cache->wait_queue as an + * exclusive waiter, so squashfs_cache_put() releasing one entry wakes exactly + * one task. Because a wakee may find its block published in the meantime and + * share that entry rather than claim the free one, a wakee which shares hands + * its wakeup on to the next waiter. + */ +struct squashfs_cache_entry *squashfs_cache_get(struct super_block *sb, + struct squashfs_cache *cache, u64 block, int length) +{ + int i, n; + struct squashfs_cache_entry *entry; + bool capacity_wake = false; + + spin_lock(&cache->lock); + + while (1) { + bool pending, wake_next, wake_block; + + for (i = cache->curr_blk, n = 0; n < cache->entries; n++) { + if (cache->entry[i].block == block) { + cache->curr_blk = i; + break; + } + i = (i + 1) % cache->entries; + } + + if (n == cache->entries) { + /* + * Block not in cache, if all cache entries are used + * go to sleep waiting for one to become available. + */ + if (cache->unused == 0) { + struct squashfs_cache_wait wait = { + .block = block, + .capacity_wake = false, + }; + + init_wait_func(&wait.wait, + squashfs_cache_wake_function); + cache->num_waiters++; + /* + * Enqueue while still holding cache->lock, so + * that a concurrent lookup either sees us + * queued or we see the block it publishes. + */ + prepare_to_wait_exclusive(&cache->wait_queue, + &wait.wait, TASK_UNINTERRUPTIBLE); + spin_unlock(&cache->lock); + schedule(); + finish_wait(&cache->wait_queue, &wait.wait); + capacity_wake = READ_ONCE(wait.capacity_wake); + spin_lock(&cache->lock); + cache->num_waiters--; + continue; + } + + /* + * At least one unused cache entry. A simple + * round-robin strategy is used to choose the entry to + * be evicted from the cache. + */ + i = cache->next_blk; + for (n = 0; n < cache->entries; n++) { + if (cache->entry[i].refcount == 0) + break; + i = (i + 1) % cache->entries; + } + + cache->next_blk = (i + 1) % cache->entries; + entry = &cache->entry[i]; + + /* + * Initialise chosen cache entry, and fill it in from + * disk. + */ + cache->unused--; + entry->block = block; + entry->refcount = 1; + entry->pending = 1; + entry->num_waiters = 0; + entry->error = 0; + wake_block = cache->num_waiters > 0; + spin_unlock(&cache->lock); + + /* + * The entry is now findable, so release everybody + * queued for this block to share it rather than each + * waiting for an entry of their own. They will block + * on entry->wait_queue below until the read completes. + */ + if (wake_block) + squashfs_cache_wake_block(cache, block); + + entry->length = squashfs_read_data(sb, block, length, + &entry->next_index, entry->actor); + + spin_lock(&cache->lock); + + if (entry->length < 0) + entry->error = entry->length; + + entry->pending = 0; + + /* + * While filling this entry one or more other processes + * have looked it up in the cache, and have slept + * waiting for it to become available. + */ + if (entry->num_waiters) { + spin_unlock(&cache->lock); + wake_up_all(&entry->wait_queue); + } else + spin_unlock(&cache->lock); + + goto out; + } + + /* + * Block already in cache. Increment refcount so it doesn't + * get reused until we're finished with it, if it was + * previously unused there's one less cache entry available + * for reuse. + */ + entry = &cache->entry[i]; + if (entry->refcount == 0) { + cache->unused--; + /* This claims the capacity we were woken for. */ + capacity_wake = false; + } + entry->refcount++; + + /* + * If the entry is currently being filled in by another process + * go to sleep waiting for it to become available. + */ + pending = entry->pending; + if (pending) + entry->num_waiters++; + + /* + * We were woken because an entry became free, but shared a + * block instead of claiming it. Hand the wakeup on, otherwise + * the free entry sits unclaimed while others sleep. + */ + wake_next = capacity_wake && cache->unused && cache->num_waiters; + spin_unlock(&cache->lock); + + if (wake_next) + wake_up(&cache->wait_queue); + if (pending) + wait_event(entry->wait_queue, !entry->pending); + + goto out; + } + +out: + TRACE("Got %s %d, start block %lld, refcount %d, error %d\n", + cache->name, i, entry->block, entry->refcount, entry->error); + + if (entry->error) + ERROR("Unable to read %s cache entry [%llx]\n", cache->name, + block); + return entry; +} + + +/* + * Release cache entry, once usage count is zero it can be reused. + */ +void squashfs_cache_put(struct squashfs_cache_entry *entry) +{ + struct squashfs_cache *cache = entry->cache; + + spin_lock(&cache->lock); + entry->refcount--; + if (entry->refcount == 0) { + cache->unused++; + /* + * If there's any processes waiting for a block to become + * available, wake one up. + */ + if (cache->num_waiters) { + spin_unlock(&cache->lock); + wake_up(&cache->wait_queue); + return; + } + } + spin_unlock(&cache->lock); +} + +/* + * Delete cache reclaiming all kmalloced buffers. + */ +void squashfs_cache_delete(struct squashfs_cache *cache) +{ + int i, j; + + if (IS_ERR(cache) || cache == NULL) + return; + + for (i = 0; i < cache->entries; i++) { + if (cache->entry[i].data) { + for (j = 0; j < cache->pages; j++) + kfree(cache->entry[i].data[j]); + kfree(cache->entry[i].data); + } + kfree(cache->entry[i].actor); + } + + kfree(cache->entry); + kfree(cache); +} + + +/* + * Initialise cache allocating the specified number of entries, each of + * size block_size. To avoid vmalloc fragmentation issues each entry + * is allocated as a sequence of kmalloced PAGE_SIZE buffers. + */ +struct squashfs_cache *squashfs_cache_init(char *name, int entries, + int block_size) +{ + int i, j; + struct squashfs_cache *cache; + + if (entries == 0) + return NULL; + + cache = kzalloc_obj(*cache); + if (cache == NULL) { + ERROR("Failed to allocate %s cache\n", name); + return ERR_PTR(-ENOMEM); + } + + cache->entry = kzalloc_objs(*(cache->entry), entries); + if (cache->entry == NULL) { + ERROR("Failed to allocate %s cache\n", name); + goto cleanup; + } + + cache->curr_blk = 0; + cache->next_blk = 0; + cache->unused = entries; + cache->entries = entries; + cache->block_size = block_size; + cache->pages = block_size >> PAGE_SHIFT; + cache->pages = cache->pages ? cache->pages : 1; + cache->name = name; + cache->num_waiters = 0; + spin_lock_init(&cache->lock); + init_waitqueue_head(&cache->wait_queue); + + for (i = 0; i < entries; i++) { + struct squashfs_cache_entry *entry = &cache->entry[i]; + + init_waitqueue_head(&cache->entry[i].wait_queue); + entry->cache = cache; + entry->block = SQUASHFS_INVALID_BLK; + entry->data = kcalloc(cache->pages, sizeof(void *), GFP_KERNEL); + if (entry->data == NULL) { + ERROR("Failed to allocate %s cache entry\n", name); + goto cleanup; + } + + for (j = 0; j < cache->pages; j++) { + entry->data[j] = kmalloc(PAGE_SIZE, GFP_KERNEL); + if (entry->data[j] == NULL) { + ERROR("Failed to allocate %s buffer\n", name); + goto cleanup; + } + } + + entry->actor = squashfs_page_actor_init(entry->data, + cache->pages, 0); + if (entry->actor == NULL) { + ERROR("Failed to allocate %s cache entry\n", name); + goto cleanup; + } + } + + return cache; + +cleanup: + squashfs_cache_delete(cache); + return ERR_PTR(-ENOMEM); +} + + +/* + * Copy up to length bytes from cache entry to buffer starting at offset bytes + * into the cache entry. If there's not length bytes then copy the number of + * bytes available. In all cases return the number of bytes copied. + */ +int squashfs_copy_data(void *buffer, struct squashfs_cache_entry *entry, + int offset, int length) +{ + int remaining = length; + + if (length == 0 || offset < 0) + return 0; + else if (buffer == NULL) + return min(length, entry->length - offset); + + while (offset < entry->length) { + void *buff = entry->data[offset / PAGE_SIZE] + + (offset % PAGE_SIZE); + int bytes = min_t(int, entry->length - offset, + PAGE_SIZE - (offset % PAGE_SIZE)); + + if (bytes >= remaining) { + memcpy(buffer, buff, remaining); + remaining = 0; + break; + } + + memcpy(buffer, buff, bytes); + buffer += bytes; + remaining -= bytes; + offset += bytes; + } + + return length - remaining; +} + + +/* + * Read length bytes from metadata position <block, offset> (block is the + * start of the compressed block on disk, and offset is the offset into + * the block once decompressed). Data is packed into consecutive blocks, + * and length bytes may require reading more than one block. + */ +int squashfs_read_metadata(struct super_block *sb, void *buffer, + u64 *block, int *offset, int length) +{ + struct squashfs_sb_info *msblk = sb->s_fs_info; + int bytes, res = length; + struct squashfs_cache_entry *entry; + + TRACE("Entered squashfs_read_metadata [%llx:%x]\n", *block, *offset); + + if (unlikely(length < 0)) + return -EIO; + + if (unlikely(*offset < 0 || *offset >= SQUASHFS_METADATA_SIZE)) + return -EIO; + + while (length) { + entry = squashfs_cache_get(sb, msblk->block_cache, *block, 0); + if (entry->error) { + res = entry->error; + goto error; + } else if (*offset >= entry->length) { + res = -EIO; + goto error; + } + + bytes = squashfs_copy_data(buffer, entry, *offset, length); + if (buffer) + buffer += bytes; + length -= bytes; + *offset += bytes; + + if (*offset == entry->length) { + *block = entry->next_index; + *offset = 0; + } + + squashfs_cache_put(entry); + } + + return res; + +error: + squashfs_cache_put(entry); + return res; +} + + +/* + * Look-up in the fragmment cache the fragment located at <start_block> in the + * filesystem. If necessary read and decompress it from disk. + */ +struct squashfs_cache_entry *squashfs_get_fragment(struct super_block *sb, + u64 start_block, int length) +{ + struct squashfs_sb_info *msblk = sb->s_fs_info; + + return squashfs_cache_get(sb, msblk->fragment_cache, start_block, + length); +} + + +/* + * Read and decompress the datablock located at <start_block> in the + * filesystem. The cache is used here to avoid duplicating locking and + * read/decompress code. + */ +struct squashfs_cache_entry *squashfs_get_datablock(struct super_block *sb, + u64 start_block, int length) +{ + struct squashfs_sb_info *msblk = sb->s_fs_info; + + return squashfs_cache_get(sb, msblk->read_page, start_block, length); +} + + +/* + * Read a filesystem table (uncompressed sequence of bytes) from disk + */ +void *squashfs_read_table(struct super_block *sb, u64 block, int length) +{ + int pages = (length + PAGE_SIZE - 1) >> PAGE_SHIFT; + int i, res; + void *table, *buffer, **data; + struct squashfs_page_actor *actor; + + table = buffer = kmalloc(length, GFP_KERNEL); + if (table == NULL) + return ERR_PTR(-ENOMEM); + + data = kcalloc(pages, sizeof(void *), GFP_KERNEL); + if (data == NULL) { + res = -ENOMEM; + goto failed; + } + + actor = squashfs_page_actor_init(data, pages, length); + if (actor == NULL) { + res = -ENOMEM; + goto failed2; + } + + for (i = 0; i < pages; i++, buffer += PAGE_SIZE) + data[i] = buffer; + + res = squashfs_read_data(sb, block, length | + SQUASHFS_COMPRESSED_BIT_BLOCK, NULL, actor); + + kfree(data); + kfree(actor); + + if (res < 0) + goto failed; + + return table; + +failed2: + kfree(data); +failed: + kfree(table); + return ERR_PTR(res); +} diff --git a/fs/squashfs/decompressor.c b/fs/squashfs/decompressor.c new file mode 100644 index 000000000..a676084be --- /dev/null +++ b/fs/squashfs/decompressor.c @@ -0,0 +1,141 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Squashfs - a compressed read only filesystem for Linux + * + * Copyright (c) 2002, 2003, 2004, 2005, 2006, 2007, 2008, 2009 + * Phillip Lougher <phillip@squashfs.org.uk> + * + * decompressor.c + */ + +#include <linux/types.h> +#include <linux/mutex.h> +#include <linux/slab.h> + +#include "squashfs_fs.h" +#include "squashfs_fs_sb.h" +#include "decompressor.h" +#include "squashfs.h" +#include "page_actor.h" + +/* + * This file (and decompressor.h) implements a decompressor framework for + * Squashfs, allowing multiple decompressors to be easily supported + */ + +static const struct squashfs_decompressor squashfs_lzma_unsupported_comp_ops = { + NULL, NULL, NULL, NULL, LZMA_COMPRESSION, "lzma", 0 +}; + +#ifndef CONFIG_SQUASHFS_LZ4 +static const struct squashfs_decompressor squashfs_lz4_comp_ops = { + NULL, NULL, NULL, NULL, LZ4_COMPRESSION, "lz4", 0 +}; +#endif + +#ifndef CONFIG_SQUASHFS_LZO +static const struct squashfs_decompressor squashfs_lzo_comp_ops = { + NULL, NULL, NULL, NULL, LZO_COMPRESSION, "lzo", 0 +}; +#endif + +#ifndef CONFIG_SQUASHFS_XZ +static const struct squashfs_decompressor squashfs_xz_comp_ops = { + NULL, NULL, NULL, NULL, XZ_COMPRESSION, "xz", 0 +}; +#endif + +#ifndef CONFIG_SQUASHFS_ZLIB +static const struct squashfs_decompressor squashfs_zlib_comp_ops = { + NULL, NULL, NULL, NULL, ZLIB_COMPRESSION, "zlib", 0 +}; +#endif + +#ifndef CONFIG_SQUASHFS_ZSTD +static const struct squashfs_decompressor squashfs_zstd_comp_ops = { + NULL, NULL, NULL, NULL, ZSTD_COMPRESSION, "zstd", 0 +}; +#endif + +static const struct squashfs_decompressor squashfs_unknown_comp_ops = { + NULL, NULL, NULL, NULL, 0, "unknown", 0 +}; + +static const struct squashfs_decompressor *decompressor[] = { + &squashfs_zlib_comp_ops, + &squashfs_lz4_comp_ops, + &squashfs_lzo_comp_ops, + &squashfs_xz_comp_ops, + &squashfs_lzma_unsupported_comp_ops, + &squashfs_zstd_comp_ops, + &squashfs_unknown_comp_ops +}; + + +const struct squashfs_decompressor *squashfs_lookup_decompressor(int id) +{ + int i; + + for (i = 0; decompressor[i]->id; i++) + if (id == decompressor[i]->id) + break; + + return decompressor[i]; +} + + +static void *get_comp_opts(struct super_block *sb, unsigned short flags) +{ + struct squashfs_sb_info *msblk = sb->s_fs_info; + void *buffer = NULL, *comp_opts; + struct squashfs_page_actor *actor = NULL; + int length = 0; + + /* + * Read decompressor specific options from file system if present + */ + if (SQUASHFS_COMP_OPTS(flags)) { + buffer = kmalloc(PAGE_SIZE, GFP_KERNEL); + if (buffer == NULL) { + comp_opts = ERR_PTR(-ENOMEM); + goto out; + } + + actor = squashfs_page_actor_init(&buffer, 1, 0); + if (actor == NULL) { + comp_opts = ERR_PTR(-ENOMEM); + goto out; + } + + length = squashfs_read_data(sb, + sizeof(struct squashfs_super_block), 0, NULL, actor); + + if (length < 0) { + comp_opts = ERR_PTR(length); + goto out; + } + } + + comp_opts = squashfs_comp_opts(msblk, buffer, length); + +out: + kfree(actor); + kfree(buffer); + return comp_opts; +} + + +void *squashfs_decompressor_setup(struct super_block *sb, unsigned short flags) +{ + struct squashfs_sb_info *msblk = sb->s_fs_info; + void *stream, *comp_opts = get_comp_opts(sb, flags); + + if (IS_ERR(comp_opts)) + return comp_opts; + + stream = msblk->thread_ops->create(msblk, comp_opts); + if (IS_ERR(stream)) + kfree(comp_opts); + + return stream; +} diff --git a/fs/squashfs/decompressor.h b/fs/squashfs/decompressor.h new file mode 100644 index 000000000..19ab60834 --- /dev/null +++ b/fs/squashfs/decompressor.h @@ -0,0 +1,54 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +#ifndef DECOMPRESSOR_H +#define DECOMPRESSOR_H +/* + * Squashfs - a compressed read only filesystem for Linux + * + * Copyright (c) 2002, 2003, 2004, 2005, 2006, 2007, 2008, 2009 + * Phillip Lougher <phillip@squashfs.org.uk> + * + * decompressor.h + */ + +#include <linux/bio.h> + +struct squashfs_decompressor { + void *(*init)(struct squashfs_sb_info *, void *); + void *(*comp_opts)(struct squashfs_sb_info *, void *, int); + void (*free)(void *); + int (*decompress)(struct squashfs_sb_info *, void *, + struct bio *, int, int, struct squashfs_page_actor *); + int id; + char *name; + int alloc_buffer; + int supported; +}; + +static inline void *squashfs_comp_opts(struct squashfs_sb_info *msblk, + void *buff, int length) +{ + return msblk->decompressor->comp_opts ? + msblk->decompressor->comp_opts(msblk, buff, length) : NULL; +} + +#ifdef CONFIG_SQUASHFS_XZ +extern const struct squashfs_decompressor squashfs_xz_comp_ops; +#endif + +#ifdef CONFIG_SQUASHFS_LZ4 +extern const struct squashfs_decompressor squashfs_lz4_comp_ops; +#endif + +#ifdef CONFIG_SQUASHFS_LZO +extern const struct squashfs_decompressor squashfs_lzo_comp_ops; +#endif + +#ifdef CONFIG_SQUASHFS_ZLIB +extern const struct squashfs_decompressor squashfs_zlib_comp_ops; +#endif + +#ifdef CONFIG_SQUASHFS_ZSTD +extern const struct squashfs_decompressor squashfs_zstd_comp_ops; +#endif + +#endif diff --git a/fs/squashfs/decompressor_multi.c b/fs/squashfs/decompressor_multi.c new file mode 100644 index 000000000..5c1aede1e --- /dev/null +++ b/fs/squashfs/decompressor_multi.c @@ -0,0 +1,203 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (c) 2013 + * Minchan Kim <minchan@kernel.org> + */ +#include <linux/types.h> +#include <linux/mutex.h> +#include <linux/slab.h> +#include <linux/bio.h> +#include <linux/sched.h> +#include <linux/wait.h> +#include <linux/cpumask.h> + +#include "squashfs_fs.h" +#include "squashfs_fs_sb.h" +#include "decompressor.h" +#include "squashfs.h" + +/* + * This file implements multi-threaded decompression in the + * decompressor framework + */ + + +/* + * The reason that multiply two is that a CPU can request new I/O + * while it is waiting previous request. + */ +#define MAX_DECOMPRESSOR (num_online_cpus() * 2) + + +static int squashfs_max_decompressors(void) +{ + return MAX_DECOMPRESSOR; +} + +struct squashfs_stream { + void *comp_opts; + struct list_head strm_list; + struct mutex mutex; + int avail_decomp; + wait_queue_head_t wait; +}; + + +struct decomp_stream { + void *stream; + struct list_head list; +}; + + +static void put_decomp_stream(struct decomp_stream *decomp_strm, + struct squashfs_stream *stream) +{ + mutex_lock(&stream->mutex); + list_add(&decomp_strm->list, &stream->strm_list); + mutex_unlock(&stream->mutex); + wake_up(&stream->wait); +} + +static void *squashfs_decompressor_create(struct squashfs_sb_info *msblk, + void *comp_opts) +{ + struct squashfs_stream *stream; + struct decomp_stream *decomp_strm = NULL; + int err = -ENOMEM; + + stream = kzalloc_obj(*stream); + if (!stream) + goto out; + + stream->comp_opts = comp_opts; + mutex_init(&stream->mutex); + INIT_LIST_HEAD(&stream->strm_list); + init_waitqueue_head(&stream->wait); + + /* + * We should have a decompressor at least as default + * so if we fail to allocate new decompressor dynamically, + * we could always fall back to default decompressor and + * file system works. + */ + decomp_strm = kmalloc_obj(*decomp_strm); + if (!decomp_strm) + goto out; + + decomp_strm->stream = msblk->decompressor->init(msblk, + stream->comp_opts); + if (IS_ERR(decomp_strm->stream)) { + err = PTR_ERR(decomp_strm->stream); + goto out; + } + + list_add(&decomp_strm->list, &stream->strm_list); + stream->avail_decomp = 1; + return stream; + +out: + kfree(decomp_strm); + kfree(stream); + return ERR_PTR(err); +} + + +static void squashfs_decompressor_destroy(struct squashfs_sb_info *msblk) +{ + struct squashfs_stream *stream = msblk->stream; + if (stream) { + struct decomp_stream *decomp_strm; + + while (!list_empty(&stream->strm_list)) { + decomp_strm = list_entry(stream->strm_list.prev, + struct decomp_stream, list); + list_del(&decomp_strm->list); + msblk->decompressor->free(decomp_strm->stream); + kfree(decomp_strm); + stream->avail_decomp--; + } + WARN_ON(stream->avail_decomp); + kfree(stream->comp_opts); + kfree(stream); + } +} + + +static struct decomp_stream *get_decomp_stream(struct squashfs_sb_info *msblk, + struct squashfs_stream *stream) +{ + struct decomp_stream *decomp_strm; + + while (1) { + mutex_lock(&stream->mutex); + + /* There is available decomp_stream */ + if (!list_empty(&stream->strm_list)) { + decomp_strm = list_entry(stream->strm_list.prev, + struct decomp_stream, list); + list_del(&decomp_strm->list); + mutex_unlock(&stream->mutex); + break; + } + + /* + * If there is no available decomp and already full, + * let's wait for releasing decomp from other users. + */ + if (stream->avail_decomp >= msblk->max_thread_num) + goto wait; + + /* Let's allocate new decomp */ + decomp_strm = kmalloc_obj(*decomp_strm); + if (!decomp_strm) + goto wait; + + decomp_strm->stream = msblk->decompressor->init(msblk, + stream->comp_opts); + if (IS_ERR(decomp_strm->stream)) { + kfree(decomp_strm); + goto wait; + } + + stream->avail_decomp++; + WARN_ON(stream->avail_decomp > msblk->max_thread_num); + + mutex_unlock(&stream->mutex); + break; +wait: + /* + * If system memory is tough, let's for other's + * releasing instead of hurting VM because it could + * make page cache thrashing. + */ + mutex_unlock(&stream->mutex); + wait_event(stream->wait, + !list_empty(&stream->strm_list)); + } + + return decomp_strm; +} + + +static int squashfs_decompress(struct squashfs_sb_info *msblk, struct bio *bio, + int offset, int length, + struct squashfs_page_actor *output) +{ + int res; + struct squashfs_stream *stream = msblk->stream; + struct decomp_stream *decomp_stream = get_decomp_stream(msblk, stream); + res = msblk->decompressor->decompress(msblk, decomp_stream->stream, + bio, offset, length, output); + put_decomp_stream(decomp_stream, stream); + if (res < 0) + ERROR("%s decompression failed, data probably corrupt\n", + msblk->decompressor->name); + return res; +} + +const struct squashfs_decompressor_thread_ops squashfs_decompressor_multi = { + .create = squashfs_decompressor_create, + .destroy = squashfs_decompressor_destroy, + .decompress = squashfs_decompress, + .max_decompressors = squashfs_max_decompressors, +}; diff --git a/fs/squashfs/decompressor_multi_percpu.c b/fs/squashfs/decompressor_multi_percpu.c new file mode 100644 index 000000000..e4d7e507b --- /dev/null +++ b/fs/squashfs/decompressor_multi_percpu.c @@ -0,0 +1,110 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (c) 2013 + * Phillip Lougher <phillip@squashfs.org.uk> + */ + +#include <linux/types.h> +#include <linux/slab.h> +#include <linux/percpu.h> +#include <linux/local_lock.h> + +#include "squashfs_fs.h" +#include "squashfs_fs_sb.h" +#include "decompressor.h" +#include "squashfs.h" + +/* + * This file implements multi-threaded decompression using percpu + * variables, one thread per cpu core. + */ + +struct squashfs_stream { + void *stream; + local_lock_t lock; +}; + +static void *squashfs_decompressor_create(struct squashfs_sb_info *msblk, + void *comp_opts) +{ + struct squashfs_stream *stream; + struct squashfs_stream __percpu *percpu; + int err, cpu; + + percpu = alloc_percpu(struct squashfs_stream); + if (percpu == NULL) + return ERR_PTR(-ENOMEM); + + for_each_possible_cpu(cpu) { + stream = per_cpu_ptr(percpu, cpu); + stream->stream = msblk->decompressor->init(msblk, comp_opts); + if (IS_ERR(stream->stream)) { + err = PTR_ERR(stream->stream); + goto out; + } + local_lock_init(&stream->lock); + } + + kfree(comp_opts); + return (void *)(__force unsigned long) percpu; + +out: + for_each_possible_cpu(cpu) { + stream = per_cpu_ptr(percpu, cpu); + if (!IS_ERR_OR_NULL(stream->stream)) + msblk->decompressor->free(stream->stream); + } + free_percpu(percpu); + return ERR_PTR(err); +} + +static void squashfs_decompressor_destroy(struct squashfs_sb_info *msblk) +{ + struct squashfs_stream __percpu *percpu = + (void __percpu *)(unsigned long) msblk->stream; + struct squashfs_stream *stream; + int cpu; + + if (msblk->stream) { + for_each_possible_cpu(cpu) { + stream = per_cpu_ptr(percpu, cpu); + msblk->decompressor->free(stream->stream); + } + free_percpu(percpu); + } +} + +static int squashfs_decompress(struct squashfs_sb_info *msblk, struct bio *bio, + int offset, int length, struct squashfs_page_actor *output) +{ + struct squashfs_stream *stream; + struct squashfs_stream __percpu *percpu = + (void __percpu *)(unsigned long) msblk->stream; + int res; + + local_lock(&percpu->lock); + stream = this_cpu_ptr(percpu); + + res = msblk->decompressor->decompress(msblk, stream->stream, bio, + offset, length, output); + + local_unlock(&percpu->lock); + + if (res < 0) + ERROR("%s decompression failed, data probably corrupt\n", + msblk->decompressor->name); + + return res; +} + +static int squashfs_max_decompressors(void) +{ + return num_possible_cpus(); +} + +const struct squashfs_decompressor_thread_ops squashfs_decompressor_percpu = { + .create = squashfs_decompressor_create, + .destroy = squashfs_decompressor_destroy, + .decompress = squashfs_decompress, + .max_decompressors = squashfs_max_decompressors, +}; diff --git a/fs/squashfs/decompressor_single.c b/fs/squashfs/decompressor_single.c new file mode 100644 index 000000000..48501ba55 --- /dev/null +++ b/fs/squashfs/decompressor_single.c @@ -0,0 +1,91 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (c) 2013 + * Phillip Lougher <phillip@squashfs.org.uk> + */ + +#include <linux/types.h> +#include <linux/mutex.h> +#include <linux/slab.h> +#include <linux/bio.h> + +#include "squashfs_fs.h" +#include "squashfs_fs_sb.h" +#include "decompressor.h" +#include "squashfs.h" + +/* + * This file implements single-threaded decompression in the + * decompressor framework + */ + +struct squashfs_stream { + void *stream; + struct mutex mutex; +}; + +static void *squashfs_decompressor_create(struct squashfs_sb_info *msblk, + void *comp_opts) +{ + struct squashfs_stream *stream; + int err = -ENOMEM; + + stream = kmalloc_obj(*stream); + if (stream == NULL) + goto out; + + stream->stream = msblk->decompressor->init(msblk, comp_opts); + if (IS_ERR(stream->stream)) { + err = PTR_ERR(stream->stream); + goto out; + } + + kfree(comp_opts); + mutex_init(&stream->mutex); + return stream; + +out: + kfree(stream); + return ERR_PTR(err); +} + +static void squashfs_decompressor_destroy(struct squashfs_sb_info *msblk) +{ + struct squashfs_stream *stream = msblk->stream; + + if (stream) { + msblk->decompressor->free(stream->stream); + kfree(stream); + } +} + +static int squashfs_decompress(struct squashfs_sb_info *msblk, struct bio *bio, + int offset, int length, + struct squashfs_page_actor *output) +{ + int res; + struct squashfs_stream *stream = msblk->stream; + + mutex_lock(&stream->mutex); + res = msblk->decompressor->decompress(msblk, stream->stream, bio, + offset, length, output); + mutex_unlock(&stream->mutex); + + if (res < 0) + ERROR("%s decompression failed, data probably corrupt\n", + msblk->decompressor->name); + + return res; +} + +static int squashfs_max_decompressors(void) +{ + return 1; +} + +const struct squashfs_decompressor_thread_ops squashfs_decompressor_single = { + .create = squashfs_decompressor_create, + .destroy = squashfs_decompressor_destroy, + .decompress = squashfs_decompress, + .max_decompressors = squashfs_max_decompressors, +}; diff --git a/fs/squashfs/dir.c b/fs/squashfs/dir.c new file mode 100644 index 000000000..cd3598bd0 --- /dev/null +++ b/fs/squashfs/dir.c @@ -0,0 +1,225 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Squashfs - a compressed read only filesystem for Linux + * + * Copyright (c) 2002, 2003, 2004, 2005, 2006, 2007, 2008 + * Phillip Lougher <phillip@squashfs.org.uk> + * + * dir.c + */ + +/* + * This file implements code to read directories from disk. + * + * See namei.c for a description of directory organisation on disk. + */ + +#include <linux/fs.h> +#include <linux/filelock.h> +#include <linux/vfs.h> +#include <linux/slab.h> + +#include "squashfs_fs.h" +#include "squashfs_fs_sb.h" +#include "squashfs_fs_i.h" +#include "squashfs.h" + +static const unsigned char squashfs_filetype_table[] = { + DT_UNKNOWN, DT_DIR, DT_REG, DT_LNK, DT_BLK, DT_CHR, DT_FIFO, DT_SOCK +}; + +/* + * Lookup offset (f_pos) in the directory index, returning the + * metadata block containing it. + * + * If we get an error reading the index then return the part of the index + * (if any) we have managed to read - the index isn't essential, just + * quicker. + */ +static int get_dir_index_using_offset(struct super_block *sb, + u64 *next_block, int *next_offset, u64 index_start, int index_offset, + int i_count, u64 f_pos) +{ + struct squashfs_sb_info *msblk = sb->s_fs_info; + int err, i, index, length = 0; + unsigned int size; + struct squashfs_dir_index dir_index; + + TRACE("Entered get_dir_index_using_offset, i_count %d, f_pos %lld\n", + i_count, f_pos); + + /* + * Translate from external f_pos to the internal f_pos. This + * is offset by 3 because we invent "." and ".." entries which are + * not actually stored in the directory. + */ + if (f_pos <= 3) + return f_pos; + f_pos -= 3; + + for (i = 0; i < i_count; i++) { + err = squashfs_read_metadata(sb, &dir_index, &index_start, + &index_offset, sizeof(dir_index)); + if (err < 0) + break; + + index = le32_to_cpu(dir_index.index); + if (index > f_pos) + /* + * Found the index we're looking for. + */ + break; + + size = le32_to_cpu(dir_index.size) + 1; + + /* size should never be larger than SQUASHFS_NAME_LEN */ + if (size > SQUASHFS_NAME_LEN) + break; + + err = squashfs_read_metadata(sb, NULL, &index_start, + &index_offset, size); + if (err < 0) + break; + + length = index; + *next_block = le32_to_cpu(dir_index.start_block) + + msblk->directory_table; + } + + *next_offset = (length + *next_offset) % SQUASHFS_METADATA_SIZE; + + /* + * Translate back from internal f_pos to external f_pos. + */ + return length + 3; +} + + +static int squashfs_readdir(struct file *file, struct dir_context *ctx) +{ + struct inode *inode = file_inode(file); + struct squashfs_sb_info *msblk = inode->i_sb->s_fs_info; + u64 block = squashfs_i(inode)->start + msblk->directory_table; + int offset = squashfs_i(inode)->offset, length, err; + unsigned int inode_number, dir_count, size, type; + struct squashfs_dir_header dirh; + struct squashfs_dir_entry *dire; + + TRACE("Entered squashfs_readdir [%llx:%x]\n", block, offset); + + dire = kmalloc(sizeof(*dire) + SQUASHFS_NAME_LEN + 1, GFP_KERNEL); + if (dire == NULL) { + ERROR("Failed to allocate squashfs_dir_entry\n"); + goto finish; + } + + /* + * Return "." and ".." entries as the first two filenames in the + * directory. To maximise compression these two entries are not + * stored in the directory, and so we invent them here. + * + * It also means that the external f_pos is offset by 3 from the + * on-disk directory f_pos. + */ + while (ctx->pos < 3) { + char *name; + int i_ino; + + if (ctx->pos == 0) { + name = "."; + size = 1; + i_ino = inode->i_ino; + } else { + name = ".."; + size = 2; + i_ino = squashfs_i(inode)->parent; + } + + if (!dir_emit(ctx, name, size, i_ino, + squashfs_filetype_table[1])) + goto finish; + + ctx->pos += size; + } + + length = get_dir_index_using_offset(inode->i_sb, &block, &offset, + squashfs_i(inode)->dir_idx_start, + squashfs_i(inode)->dir_idx_offset, + squashfs_i(inode)->dir_idx_cnt, + ctx->pos); + + while (length < i_size_read(inode)) { + /* + * Read directory header + */ + err = squashfs_read_metadata(inode->i_sb, &dirh, &block, + &offset, sizeof(dirh)); + if (err < 0) + goto failed_read; + + length += sizeof(dirh); + + dir_count = le32_to_cpu(dirh.count) + 1; + + if (dir_count > SQUASHFS_DIR_COUNT) + goto failed_read; + + while (dir_count--) { + /* + * Read directory entry. + */ + err = squashfs_read_metadata(inode->i_sb, dire, &block, + &offset, sizeof(*dire)); + if (err < 0) + goto failed_read; + + size = le16_to_cpu(dire->size) + 1; + + /* size should never be larger than SQUASHFS_NAME_LEN */ + if (size > SQUASHFS_NAME_LEN) + goto failed_read; + + err = squashfs_read_metadata(inode->i_sb, dire->name, + &block, &offset, size); + if (err < 0) + goto failed_read; + + length += sizeof(*dire) + size; + + if (ctx->pos >= length) + continue; + + dire->name[size] = '\0'; + inode_number = le32_to_cpu(dirh.inode_number) + + ((short) le16_to_cpu(dire->inode_number)); + type = le16_to_cpu(dire->type); + + if (type > SQUASHFS_MAX_DIR_TYPE) + goto failed_read; + + if (!dir_emit(ctx, dire->name, size, + inode_number, + squashfs_filetype_table[type])) + goto finish; + + ctx->pos = length; + } + } + +finish: + kfree(dire); + return 0; + +failed_read: + ERROR("Unable to read directory block [%llx:%x]\n", block, offset); + kfree(dire); + return 0; +} + + +const struct file_operations squashfs_dir_ops = { + .read = generic_read_dir, + .iterate_shared = squashfs_readdir, + .llseek = generic_file_llseek, + .setlease = generic_setlease, +}; diff --git a/fs/squashfs/export.c b/fs/squashfs/export.c new file mode 100644 index 000000000..62972f0ff --- /dev/null +++ b/fs/squashfs/export.c @@ -0,0 +1,180 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Squashfs - a compressed read only filesystem for Linux + * + * Copyright (c) 2002, 2003, 2004, 2005, 2006, 2007, 2008 + * Phillip Lougher <phillip@squashfs.org.uk> + * + * export.c + */ + +/* + * This file implements code to make Squashfs filesystems exportable (NFS etc.) + * + * The export code uses an inode lookup table to map inode numbers passed in + * filehandles to an inode location on disk. This table is stored compressed + * into metadata blocks. A second index table is used to locate these. This + * second index table for speed of access (and because it is small) is read at + * mount time and cached in memory. + * + * The inode lookup table is used only by the export code, inode disk + * locations are directly encoded in directories, enabling direct access + * without an intermediate lookup for all operations except the export ops. + */ + +#include <linux/fs.h> +#include <linux/vfs.h> +#include <linux/dcache.h> +#include <linux/exportfs.h> +#include <linux/slab.h> + +#include "squashfs_fs.h" +#include "squashfs_fs_sb.h" +#include "squashfs_fs_i.h" +#include "squashfs.h" + +/* + * Look-up inode number (ino) in table, returning the inode location. + */ +static long long squashfs_inode_lookup(struct super_block *sb, int ino_num) +{ + struct squashfs_sb_info *msblk = sb->s_fs_info; + int blk = SQUASHFS_LOOKUP_BLOCK(ino_num - 1); + int offset = SQUASHFS_LOOKUP_BLOCK_OFFSET(ino_num - 1); + u64 start; + __le64 ino; + int err; + + TRACE("Entered squashfs_inode_lookup, inode_number = %d\n", ino_num); + + if (ino_num == 0 || (ino_num - 1) >= msblk->inodes) + return -EINVAL; + + start = le64_to_cpu(msblk->inode_lookup_table[blk]); + + err = squashfs_read_metadata(sb, &ino, &start, &offset, sizeof(ino)); + if (err < 0) + return err; + + TRACE("squashfs_inode_lookup, inode = 0x%llx\n", + (u64) le64_to_cpu(ino)); + + return le64_to_cpu(ino); +} + + +static struct dentry *squashfs_export_iget(struct super_block *sb, + unsigned int ino_num) +{ + long long ino; + struct dentry *dentry = ERR_PTR(-ENOENT); + + TRACE("Entered squashfs_export_iget\n"); + + ino = squashfs_inode_lookup(sb, ino_num); + if (ino >= 0) + dentry = d_obtain_alias(squashfs_iget(sb, ino, ino_num)); + + return dentry; +} + + +static struct dentry *squashfs_fh_to_dentry(struct super_block *sb, + struct fid *fid, int fh_len, int fh_type) +{ + if ((fh_type != FILEID_INO32_GEN && fh_type != FILEID_INO32_GEN_PARENT) + || fh_len < 2) + return NULL; + + return squashfs_export_iget(sb, fid->i32.ino); +} + + +static struct dentry *squashfs_fh_to_parent(struct super_block *sb, + struct fid *fid, int fh_len, int fh_type) +{ + if (fh_type != FILEID_INO32_GEN_PARENT || fh_len < 4) + return NULL; + + return squashfs_export_iget(sb, fid->i32.parent_ino); +} + + +static struct dentry *squashfs_get_parent(struct dentry *child) +{ + struct inode *inode = d_inode(child); + unsigned int parent_ino = squashfs_i(inode)->parent; + + return squashfs_export_iget(inode->i_sb, parent_ino); +} + + +/* + * Read uncompressed inode lookup table indexes off disk into memory + */ +__le64 *squashfs_read_inode_lookup_table(struct super_block *sb, + u64 lookup_table_start, u64 next_table, unsigned int inodes) +{ + unsigned int length = SQUASHFS_LOOKUP_BLOCK_BYTES(inodes); + unsigned int indexes = SQUASHFS_LOOKUP_BLOCKS(inodes); + int n; + __le64 *table; + u64 start, end; + + TRACE("In read_inode_lookup_table, length %d\n", length); + + /* Sanity check values */ + + /* there should always be at least one inode */ + if (inodes == 0) + return ERR_PTR(-EINVAL); + + /* + * The computed size of the lookup table (length bytes) should exactly + * match the table start and end points + */ + if (length != (next_table - lookup_table_start)) + return ERR_PTR(-EINVAL); + + table = squashfs_read_table(sb, lookup_table_start, length); + if (IS_ERR(table)) + return table; + + /* + * table0], table[1], ... table[indexes - 1] store the locations + * of the compressed inode lookup blocks. Each entry should be + * less than the next (i.e. table[0] < table[1]), and the difference + * between them should be SQUASHFS_METADATA_SIZE or less. + * table[indexes - 1] should be less than lookup_table_start, and + * again the difference should be SQUASHFS_METADATA_SIZE or less + */ + for (n = 0; n < (indexes - 1); n++) { + start = le64_to_cpu(table[n]); + end = le64_to_cpu(table[n + 1]); + + if (start >= end + || (end - start) > + (SQUASHFS_METADATA_SIZE + SQUASHFS_BLOCK_OFFSET)) { + kfree(table); + return ERR_PTR(-EINVAL); + } + } + + start = le64_to_cpu(table[indexes - 1]); + if (start >= lookup_table_start || + (lookup_table_start - start) > + (SQUASHFS_METADATA_SIZE + SQUASHFS_BLOCK_OFFSET)) { + kfree(table); + return ERR_PTR(-EINVAL); + } + + return table; +} + + +const struct export_operations squashfs_export_ops = { + .encode_fh = generic_encode_ino32_fh, + .fh_to_dentry = squashfs_fh_to_dentry, + .fh_to_parent = squashfs_fh_to_parent, + .get_parent = squashfs_get_parent +}; diff --git a/fs/squashfs/file.c b/fs/squashfs/file.c new file mode 100644 index 000000000..d83594ce9 --- /dev/null +++ b/fs/squashfs/file.c @@ -0,0 +1,781 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Squashfs - a compressed read only filesystem for Linux + * + * Copyright (c) 2002, 2003, 2004, 2005, 2006, 2007, 2008 + * Phillip Lougher <phillip@squashfs.org.uk> + * + * file.c + */ + +/* + * This file contains code for handling regular files. A regular file + * consists of a sequence of contiguous compressed blocks, and/or a + * compressed fragment block (tail-end packed block). The compressed size + * of each datablock is stored in a block list contained within the + * file inode (itself stored in one or more compressed metadata blocks). + * + * To speed up access to datablocks when reading 'large' files (256 Mbytes or + * larger), the code implements an index cache that caches the mapping from + * block index to datablock location on disk. + * + * The index cache allows Squashfs to handle large files (up to 1.75 TiB) while + * retaining a simple and space-efficient block list on disk. The cache + * is split into slots, caching up to eight 224 GiB files (128 KiB blocks). + * Larger files use multiple slots, with 1.75 TiB files using all 8 slots. + * The index cache is designed to be memory efficient, and by default uses + * 16 KiB. + */ + +#include <linux/fs.h> +#include <linux/filelock.h> +#include <linux/vfs.h> +#include <linux/kernel.h> +#include <linux/slab.h> +#include <linux/string.h> +#include <linux/pagemap.h> +#include <linux/mutex.h> + +#include "squashfs_fs.h" +#include "squashfs_fs_sb.h" +#include "squashfs_fs_i.h" +#include "squashfs.h" +#include "page_actor.h" + +/* + * Locate cache slot in range [offset, index] for specified inode. If + * there's more than one return the slot closest to index. + */ +static struct meta_index *locate_meta_index(struct inode *inode, int offset, + int index) +{ + struct meta_index *meta = NULL; + struct squashfs_sb_info *msblk = inode->i_sb->s_fs_info; + int i; + + mutex_lock(&msblk->meta_index_mutex); + + TRACE("locate_meta_index: index %d, offset %d\n", index, offset); + + if (msblk->meta_index == NULL) + goto not_allocated; + + for (i = 0; i < SQUASHFS_META_SLOTS; i++) { + if (msblk->meta_index[i].inode_number == inode->i_ino && + msblk->meta_index[i].offset >= offset && + msblk->meta_index[i].offset <= index && + msblk->meta_index[i].locked == 0) { + TRACE("locate_meta_index: entry %d, offset %d\n", i, + msblk->meta_index[i].offset); + meta = &msblk->meta_index[i]; + offset = meta->offset; + } + } + + if (meta) + meta->locked = 1; + +not_allocated: + mutex_unlock(&msblk->meta_index_mutex); + + return meta; +} + + +/* + * Find and initialise an empty cache slot for index offset. + */ +static struct meta_index *empty_meta_index(struct inode *inode, int offset, + int skip) +{ + struct squashfs_sb_info *msblk = inode->i_sb->s_fs_info; + struct meta_index *meta = NULL; + int i; + + mutex_lock(&msblk->meta_index_mutex); + + TRACE("empty_meta_index: offset %d, skip %d\n", offset, skip); + + if (msblk->meta_index == NULL) { + /* + * First time cache index has been used, allocate and + * initialise. The cache index could be allocated at + * mount time but doing it here means it is allocated only + * if a 'large' file is read. + */ + msblk->meta_index = kzalloc_objs(*(msblk->meta_index), + SQUASHFS_META_SLOTS); + if (msblk->meta_index == NULL) { + ERROR("Failed to allocate meta_index\n"); + goto failed; + } + for (i = 0; i < SQUASHFS_META_SLOTS; i++) { + msblk->meta_index[i].inode_number = 0; + msblk->meta_index[i].locked = 0; + } + msblk->next_meta_index = 0; + } + + for (i = SQUASHFS_META_SLOTS; i && + msblk->meta_index[msblk->next_meta_index].locked; i--) + msblk->next_meta_index = (msblk->next_meta_index + 1) % + SQUASHFS_META_SLOTS; + + if (i == 0) { + TRACE("empty_meta_index: failed!\n"); + goto failed; + } + + TRACE("empty_meta_index: returned meta entry %d, %p\n", + msblk->next_meta_index, + &msblk->meta_index[msblk->next_meta_index]); + + meta = &msblk->meta_index[msblk->next_meta_index]; + msblk->next_meta_index = (msblk->next_meta_index + 1) % + SQUASHFS_META_SLOTS; + + meta->inode_number = inode->i_ino; + meta->offset = offset; + meta->skip = skip; + meta->entries = 0; + meta->locked = 1; + +failed: + mutex_unlock(&msblk->meta_index_mutex); + return meta; +} + + +static void release_meta_index(struct inode *inode, struct meta_index *meta) +{ + struct squashfs_sb_info *msblk = inode->i_sb->s_fs_info; + mutex_lock(&msblk->meta_index_mutex); + meta->locked = 0; + mutex_unlock(&msblk->meta_index_mutex); +} + + +/* + * Read the next n blocks from the block list, starting from + * metadata block <start_block, offset>. + */ +static long long read_indexes(struct super_block *sb, int n, + u64 *start_block, int *offset) +{ + int err, i; + long long block = 0; + __le32 *blist = kmalloc(PAGE_SIZE, GFP_KERNEL); + + if (blist == NULL) { + ERROR("read_indexes: Failed to allocate block_list\n"); + return -ENOMEM; + } + + while (n) { + int blocks = min_t(int, n, PAGE_SIZE >> 2); + + err = squashfs_read_metadata(sb, blist, start_block, + offset, blocks << 2); + if (err < 0) { + ERROR("read_indexes: reading block [%llx:%x]\n", + *start_block, *offset); + goto failure; + } + + for (i = 0; i < blocks; i++) { + int size = squashfs_block_size(blist[i]); + if (size < 0) { + err = size; + goto failure; + } + block += SQUASHFS_COMPRESSED_SIZE_BLOCK(size); + } + n -= blocks; + } + + kfree(blist); + return block; + +failure: + kfree(blist); + return err; +} + + +/* + * Each cache index slot has SQUASHFS_META_ENTRIES, each of which + * can cache one index -> datablock/blocklist-block mapping. We wish + * to distribute these over the length of the file, entry[0] maps index x, + * entry[1] maps index x + skip, entry[2] maps index x + 2 * skip, and so on. + * The larger the file, the greater the skip factor. The skip factor is + * limited to the size of the metadata cache (SQUASHFS_CACHED_BLKS) to ensure + * the number of metadata blocks that need to be read fits into the cache. + * If the skip factor is limited in this way then the file will use multiple + * slots. + */ +static inline int calculate_skip(u64 blocks) +{ + u64 skip = blocks / ((SQUASHFS_META_ENTRIES + 1) + * SQUASHFS_META_INDEXES); + return min((u64) SQUASHFS_CACHED_BLKS - 1, skip + 1); +} + + +/* + * Search and grow the index cache for the specified inode, returning the + * on-disk locations of the datablock and block list metadata block + * <index_block, index_offset> for index (scaled to nearest cache index). + */ +static int fill_meta_index(struct inode *inode, int index, + u64 *index_block, int *index_offset, u64 *data_block) +{ + struct squashfs_sb_info *msblk = inode->i_sb->s_fs_info; + int skip = calculate_skip(i_size_read(inode) >> msblk->block_log); + int offset = 0; + struct meta_index *meta; + struct meta_entry *meta_entry; + u64 cur_index_block = squashfs_i(inode)->block_list_start; + int cur_offset = squashfs_i(inode)->offset; + u64 cur_data_block = squashfs_i(inode)->start; + int err, i; + + /* + * Scale index to cache index (cache slot entry) + */ + index /= SQUASHFS_META_INDEXES * skip; + + while (offset < index) { + meta = locate_meta_index(inode, offset + 1, index); + + if (meta == NULL) { + meta = empty_meta_index(inode, offset + 1, skip); + if (meta == NULL) + goto all_done; + } else { + offset = index < meta->offset + meta->entries ? index : + meta->offset + meta->entries - 1; + meta_entry = &meta->meta_entry[offset - meta->offset]; + cur_index_block = meta_entry->index_block + + msblk->inode_table; + cur_offset = meta_entry->offset; + cur_data_block = meta_entry->data_block; + TRACE("get_meta_index: offset %d, meta->offset %d, " + "meta->entries %d\n", offset, meta->offset, + meta->entries); + TRACE("get_meta_index: index_block 0x%llx, offset 0x%x" + " data_block 0x%llx\n", cur_index_block, + cur_offset, cur_data_block); + } + + /* + * If necessary grow cache slot by reading block list. Cache + * slot is extended up to index or to the end of the slot, in + * which case further slots will be used. + */ + for (i = meta->offset + meta->entries; i <= index && + i < meta->offset + SQUASHFS_META_ENTRIES; i++) { + int blocks = skip * SQUASHFS_META_INDEXES; + long long res = read_indexes(inode->i_sb, blocks, + &cur_index_block, &cur_offset); + + if (res < 0) { + if (meta->entries == 0) + /* + * Don't leave an empty slot on read + * error allocated to this inode... + */ + meta->inode_number = 0; + err = res; + goto failed; + } + + cur_data_block += res; + meta_entry = &meta->meta_entry[i - meta->offset]; + meta_entry->index_block = cur_index_block - + msblk->inode_table; + meta_entry->offset = cur_offset; + meta_entry->data_block = cur_data_block; + meta->entries++; + offset++; + } + + TRACE("get_meta_index: meta->offset %d, meta->entries %d\n", + meta->offset, meta->entries); + + release_meta_index(inode, meta); + } + +all_done: + *index_block = cur_index_block; + *index_offset = cur_offset; + if (data_block) + *data_block = cur_data_block; + + /* + * Scale cache index (cache slot entry) to index + */ + return offset * SQUASHFS_META_INDEXES * skip; + +failed: + release_meta_index(inode, meta); + return err; +} + + +/* + * Get the on-disk location and compressed size of the datablock + * specified by index. Fill_meta_index() does most of the work. + */ +static int read_blocklist_ptrs(struct inode *inode, int index, u64 *start, + int *offset, u64 *block) +{ + long long blks; + __le32 size; + int res = fill_meta_index(inode, index, start, offset, block); + + TRACE("read_blocklist: res %d, index %d, start 0x%llx, offset 0x%x, block 0x%llx\n", + res, index, *start, *offset, block ? *block : 0); + + if (res < 0) + return res; + + /* + * res contains the index of the mapping returned by fill_meta_index(), + * this will likely be less than the desired index (because the + * meta_index cache works at a higher granularity). Read any + * extra block indexes needed. + */ + if (res < index) { + blks = read_indexes(inode->i_sb, index - res, start, offset); + if (blks < 0) + return (int) blks; + if (block) + *block += blks; + } + + /* + * Read length of block specified by index. + */ + res = squashfs_read_metadata(inode->i_sb, &size, start, offset, + sizeof(size)); + if (res < 0) + return res; + return squashfs_block_size(size); +} + +static inline int read_blocklist(struct inode *inode, int index, u64 *block) +{ + u64 start; + int offset; + + return read_blocklist_ptrs(inode, index, &start, &offset, block); +} + +static bool squashfs_fill_page(struct folio *folio, + struct squashfs_cache_entry *buffer, size_t offset, + size_t avail) +{ + size_t copied; + void *pageaddr; + + pageaddr = kmap_local_folio(folio, 0); + copied = squashfs_copy_data(pageaddr, buffer, offset, avail); + memset(pageaddr + copied, 0, PAGE_SIZE - copied); + kunmap_local(pageaddr); + + flush_dcache_folio(folio); + + return copied == avail; +} + +/* Copy data into page cache */ +void squashfs_copy_cache(struct folio *folio, + struct squashfs_cache_entry *buffer, size_t bytes, + size_t offset) +{ + struct address_space *mapping = folio->mapping; + struct inode *inode = mapping->host; + struct squashfs_sb_info *msblk = inode->i_sb->s_fs_info; + int i, mask = (1 << (msblk->block_log - PAGE_SHIFT)) - 1; + int start_index = folio->index & ~mask, end_index = start_index | mask; + + /* + * Loop copying datablock into pages. As the datablock likely covers + * many PAGE_SIZE pages (default block size is 128 KiB) explicitly + * grab the pages from the page cache, except for the page that we've + * been called to fill. + */ + for (i = start_index; i <= end_index && bytes > 0; i++, + bytes -= PAGE_SIZE, offset += PAGE_SIZE) { + struct folio *push_folio; + size_t avail = buffer ? min(bytes, PAGE_SIZE) : 0; + bool updated = false; + + TRACE("bytes %zu, i %d, available_bytes %zu\n", bytes, i, avail); + + push_folio = (i == folio->index) ? folio : + __filemap_get_folio(mapping, i, + FGP_LOCK|FGP_CREAT|FGP_NOFS|FGP_NOWAIT, + mapping_gfp_mask(mapping)); + + if (IS_ERR(push_folio)) + continue; + + if (folio_test_uptodate(push_folio)) + goto skip_folio; + + updated = squashfs_fill_page(push_folio, buffer, offset, avail); +skip_folio: + folio_end_read(push_folio, updated); + if (i != folio->index) + folio_put(push_folio); + } +} + +/* Read datablock stored packed inside a fragment (tail-end packed block) */ +static int squashfs_readpage_fragment(struct folio *folio, int expected) +{ + struct inode *inode = folio->mapping->host; + struct squashfs_cache_entry *buffer = squashfs_get_fragment(inode->i_sb, + squashfs_i(inode)->fragment_block, + squashfs_i(inode)->fragment_size); + int res = buffer->error; + + if (res) + ERROR("Unable to read page, block %llx, size %x\n", + squashfs_i(inode)->fragment_block, + squashfs_i(inode)->fragment_size); + else + squashfs_copy_cache(folio, buffer, expected, + squashfs_i(inode)->fragment_offset); + + squashfs_cache_put(buffer); + return res; +} + +static int squashfs_readpage_sparse(struct folio *folio, int expected) +{ + squashfs_copy_cache(folio, NULL, expected, 0); + return 0; +} + +static int squashfs_read_folio(struct file *file, struct folio *folio) +{ + struct inode *inode = folio->mapping->host; + struct squashfs_sb_info *msblk = inode->i_sb->s_fs_info; + int index = folio->index >> (msblk->block_log - PAGE_SHIFT); + int file_end = i_size_read(inode) >> msblk->block_log; + int expected = index == file_end ? + (i_size_read(inode) & (msblk->block_size - 1)) : + msblk->block_size; + int res = 0; + + TRACE("Entered squashfs_readpage, page index %lx, start block %llx\n", + folio->index, squashfs_i(inode)->start); + + if (folio->index >= ((i_size_read(inode) + PAGE_SIZE - 1) >> + PAGE_SHIFT)) + goto out; + + if (index < file_end || squashfs_i(inode)->fragment_block == + SQUASHFS_INVALID_BLK) { + u64 block = 0; + + res = read_blocklist(inode, index, &block); + if (res < 0) + goto out; + + if (res == 0) + res = squashfs_readpage_sparse(folio, expected); + else + res = squashfs_readpage_block(folio, block, res, expected); + } else + res = squashfs_readpage_fragment(folio, expected); + + if (!res) + return 0; + +out: + folio_zero_segment(folio, 0, folio_size(folio)); + folio_end_read(folio, res == 0); + + return res; +} + +static int squashfs_readahead_fragment(struct inode *inode, struct page **page, + unsigned int pages, unsigned int expected, loff_t start) +{ + struct squashfs_cache_entry *buffer = squashfs_get_fragment(inode->i_sb, + squashfs_i(inode)->fragment_block, + squashfs_i(inode)->fragment_size); + struct squashfs_sb_info *msblk = inode->i_sb->s_fs_info; + int i, bytes, copied; + struct squashfs_page_actor *actor; + unsigned int offset; + void *addr; + struct page *last_page; + + if (buffer->error) + goto out; + + actor = squashfs_page_actor_init_special(msblk, page, pages, + expected, start); + if (!actor) + goto out; + + squashfs_actor_nobuff(actor); + addr = squashfs_first_page(actor); + + for (copied = offset = 0; offset < expected; offset += PAGE_SIZE) { + int avail = min_t(int, expected - offset, PAGE_SIZE); + + if (!IS_ERR(addr)) { + bytes = squashfs_copy_data(addr, buffer, offset + + squashfs_i(inode)->fragment_offset, avail); + + if (bytes != avail) + goto failed; + } + + copied += avail; + addr = squashfs_next_page(actor); + } + + last_page = squashfs_page_actor_free(actor); + + if (copied == expected && !IS_ERR(last_page)) { + /* Last page (if present) may have trailing bytes not filled */ + bytes = copied % PAGE_SIZE; + if (bytes && last_page) + memzero_page(last_page, bytes, PAGE_SIZE - bytes); + + for (i = 0; i < pages; i++) { + flush_dcache_page(page[i]); + SetPageUptodate(page[i]); + } + } + + for (i = 0; i < pages; i++) { + unlock_page(page[i]); + put_page(page[i]); + } + + squashfs_cache_put(buffer); + return 0; + +failed: + squashfs_page_actor_free(actor); + +out: + squashfs_cache_put(buffer); + return 1; +} + +static void squashfs_readahead(struct readahead_control *ractl) +{ + struct inode *inode = ractl->mapping->host; + struct squashfs_sb_info *msblk = inode->i_sb->s_fs_info; + size_t mask = (1UL << msblk->block_log) - 1; + unsigned short shift = msblk->block_log - PAGE_SHIFT; + loff_t start = readahead_pos(ractl) & ~mask; + size_t len = readahead_length(ractl) + readahead_pos(ractl) - start; + struct squashfs_page_actor *actor; + unsigned int nr_pages = 0; + struct page **pages; + int i; + loff_t file_end = i_size_read(inode) >> msblk->block_log; + unsigned int max_pages = 1UL << shift; + + readahead_expand(ractl, start, (len | mask) + 1); + + pages = kmalloc_array(max_pages, sizeof(void *), GFP_KERNEL); + if (!pages) + return; + + for (;;) { + int res, bsize; + u64 block = 0; + unsigned int expected; + struct page *last_page; + + expected = start >> msblk->block_log == file_end ? + (i_size_read(inode) & (msblk->block_size - 1)) : + msblk->block_size; + + max_pages = (expected + PAGE_SIZE - 1) >> PAGE_SHIFT; + + nr_pages = __readahead_batch(ractl, pages, max_pages); + if (!nr_pages) + break; + + if (readahead_pos(ractl) >= i_size_read(inode)) + goto skip_pages; + + if (start >> msblk->block_log == file_end && + squashfs_i(inode)->fragment_block != SQUASHFS_INVALID_BLK) { + res = squashfs_readahead_fragment(inode, pages, + nr_pages, expected, start); + if (res) + goto skip_pages; + continue; + } + + bsize = read_blocklist(inode, start >> msblk->block_log, &block); + if (bsize == 0) + goto skip_pages; + + actor = squashfs_page_actor_init_special(msblk, pages, nr_pages, + expected, start); + if (!actor) + goto skip_pages; + + res = squashfs_read_data(inode->i_sb, block, bsize, NULL, actor); + + last_page = squashfs_page_actor_free(actor); + + if (res == expected && !IS_ERR(last_page)) { + int bytes; + + /* Last page (if present) may have trailing bytes not filled */ + bytes = res % PAGE_SIZE; + if (start >> msblk->block_log == file_end && bytes && last_page) + memzero_page(last_page, bytes, + PAGE_SIZE - bytes); + + for (i = 0; i < nr_pages; i++) { + flush_dcache_page(pages[i]); + SetPageUptodate(pages[i]); + } + } + + for (i = 0; i < nr_pages; i++) { + unlock_page(pages[i]); + put_page(pages[i]); + } + + start += readahead_batch_length(ractl); + } + + kfree(pages); + return; + +skip_pages: + for (i = 0; i < nr_pages; i++) { + unlock_page(pages[i]); + put_page(pages[i]); + } + kfree(pages); +} + +static loff_t seek_hole_data(struct file *file, loff_t offset, int whence) +{ + struct inode *inode = file->f_mapping->host; + struct super_block *sb = inode->i_sb; + struct squashfs_sb_info *msblk = sb->s_fs_info; + u64 start, index = offset >> msblk->block_log; + u64 file_end = (i_size_read(inode) + msblk->block_size - 1) >> msblk->block_log; + int s_offset, length; + __le32 *blist = NULL; + + /* reject offset if negative or beyond file end */ + if ((unsigned long long)offset >= i_size_read(inode)) + return -ENXIO; + + /* is offset within tailend and is tailend packed into a fragment? */ + if (index + 1 == file_end && + squashfs_i(inode)->fragment_block != SQUASHFS_INVALID_BLK) { + if (whence == SEEK_DATA) + return offset; + + /* there is an implicit hole at the end of any file */ + return i_size_read(inode); + } + + length = read_blocklist_ptrs(inode, index, &start, &s_offset, NULL); + if (length < 0) + return length; + + /* nothing more to do if offset matches desired whence value */ + if ((length == 0 && whence == SEEK_HOLE) || + (length && whence == SEEK_DATA)) + return offset; + + /* skip scanning forwards if we're at file end */ + if (++ index == file_end) + goto not_found; + + blist = kmalloc(SQUASHFS_SCAN_INDEXES << 2, GFP_KERNEL); + if (blist == NULL) { + ERROR("%s: Failed to allocate block_list\n", __func__); + return -ENOMEM; + } + + while (index < file_end) { + int i, indexes = min(file_end - index, SQUASHFS_SCAN_INDEXES); + + offset = squashfs_read_metadata(sb, blist, &start, &s_offset, indexes << 2); + if (offset < 0) + goto finished; + + for (i = 0; i < indexes; i++) { + length = squashfs_block_size(blist[i]); + if (length < 0) { + offset = length; + goto finished; + } + + /* does this block match desired whence value? */ + if ((length == 0 && whence == SEEK_HOLE) || + (length && whence == SEEK_DATA)) { + offset = (index + i) << msblk->block_log; + goto finished; + } + } + + index += indexes; + } + +not_found: + /* whence value determines what happens */ + if (whence == SEEK_DATA) + offset = -ENXIO; + else + /* there is an implicit hole at the end of any file */ + offset = i_size_read(inode); + +finished: + kfree(blist); + return offset; +} + +static loff_t squashfs_llseek(struct file *file, loff_t offset, int whence) +{ + struct inode *inode = file->f_mapping->host; + + switch (whence) { + default: + return generic_file_llseek(file, offset, whence); + case SEEK_DATA: + case SEEK_HOLE: + offset = seek_hole_data(file, offset, whence); + break; + } + + if (offset < 0) + return offset; + + return vfs_setpos(file, offset, inode->i_sb->s_maxbytes); +} + +const struct address_space_operations squashfs_aops = { + .read_folio = squashfs_read_folio, + .readahead = squashfs_readahead +}; + +const struct file_operations squashfs_file_operations = { + .llseek = squashfs_llseek, + .read_iter = generic_file_read_iter, + .mmap_prepare = generic_file_readonly_mmap_prepare, + .splice_read = filemap_splice_read, + .setlease = generic_setlease, +}; diff --git a/fs/squashfs/file_cache.c b/fs/squashfs/file_cache.c new file mode 100644 index 000000000..40e59a43d --- /dev/null +++ b/fs/squashfs/file_cache.c @@ -0,0 +1,36 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (c) 2013 + * Phillip Lougher <phillip@squashfs.org.uk> + */ + +#include <linux/fs.h> +#include <linux/vfs.h> +#include <linux/kernel.h> +#include <linux/slab.h> +#include <linux/string.h> +#include <linux/pagemap.h> +#include <linux/mutex.h> + +#include "squashfs_fs.h" +#include "squashfs_fs_sb.h" +#include "squashfs_fs_i.h" +#include "squashfs.h" + +/* Read separately compressed datablock and memcopy into page cache */ +int squashfs_readpage_block(struct folio *folio, u64 block, int bsize, int expected) +{ + struct inode *i = folio->mapping->host; + struct squashfs_cache_entry *buffer = squashfs_get_datablock(i->i_sb, + block, bsize); + int res = buffer->error; + + if (res) + ERROR("Unable to read page, block %llx, size %x\n", block, + bsize); + else + squashfs_copy_cache(folio, buffer, expected, 0); + + squashfs_cache_put(buffer); + return res; +} diff --git a/fs/squashfs/file_direct.c b/fs/squashfs/file_direct.c new file mode 100644 index 000000000..2c3e809d6 --- /dev/null +++ b/fs/squashfs/file_direct.c @@ -0,0 +1,124 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (c) 2013 + * Phillip Lougher <phillip@squashfs.org.uk> + */ + +#include <linux/fs.h> +#include <linux/vfs.h> +#include <linux/kernel.h> +#include <linux/slab.h> +#include <linux/string.h> +#include <linux/pagemap.h> +#include <linux/mutex.h> + +#include "squashfs_fs.h" +#include "squashfs_fs_sb.h" +#include "squashfs_fs_i.h" +#include "squashfs.h" +#include "page_actor.h" + +/* Read separately compressed datablock directly into page cache */ +int squashfs_readpage_block(struct folio *folio, u64 block, int bsize, + int expected) +{ + struct page *target_page = &folio->page; + struct inode *inode = folio->mapping->host; + struct squashfs_sb_info *msblk = inode->i_sb->s_fs_info; + loff_t file_end = (i_size_read(inode) - 1) >> PAGE_SHIFT; + int mask = (1 << (msblk->block_log - PAGE_SHIFT)) - 1; + loff_t start_index = folio->index & ~mask; + loff_t end_index = start_index | mask; + loff_t index; + int i, pages, bytes, res = -ENOMEM; + struct page **page, *last_page; + struct squashfs_page_actor *actor; + void *pageaddr; + + if (end_index > file_end) + end_index = file_end; + + pages = end_index - start_index + 1; + + page = kmalloc_array(pages, sizeof(void *), GFP_KERNEL); + if (page == NULL) + return res; + + /* Try to grab all the pages covered by the Squashfs block */ + for (i = 0, index = start_index; index <= end_index; index++) { + page[i] = (index == folio->index) ? target_page : + grab_cache_page_nowait(folio->mapping, index); + + if (page[i] == NULL) + continue; + + if (PageUptodate(page[i])) { + unlock_page(page[i]); + put_page(page[i]); + continue; + } + + i++; + } + + pages = i; + + /* + * Create a "page actor" which will kmap and kunmap the + * page cache pages appropriately within the decompressor + */ + actor = squashfs_page_actor_init_special(msblk, page, pages, expected, + start_index << PAGE_SHIFT); + if (actor == NULL) + goto out; + + /* Decompress directly into the page cache buffers */ + res = squashfs_read_data(inode->i_sb, block, bsize, NULL, actor); + + last_page = squashfs_page_actor_free(actor); + + if (res < 0) + goto mark_errored; + + if (res != expected || IS_ERR(last_page)) { + res = -EIO; + goto mark_errored; + } + + /* Last page (if present) may have trailing bytes not filled */ + bytes = res % PAGE_SIZE; + if (end_index == file_end && last_page && bytes) { + pageaddr = kmap_local_page(last_page); + memset(pageaddr + bytes, 0, PAGE_SIZE - bytes); + kunmap_local(pageaddr); + } + + /* Mark pages as uptodate, unlock and release */ + for (i = 0; i < pages; i++) { + flush_dcache_page(page[i]); + SetPageUptodate(page[i]); + unlock_page(page[i]); + if (page[i] != target_page) + put_page(page[i]); + } + + kfree(page); + + return 0; + +mark_errored: + /* Decompression failed. Target_page is + * dealt with by the caller + */ + for (i = 0; i < pages; i++) { + if (page[i] == NULL || page[i] == target_page) + continue; + flush_dcache_page(page[i]); + unlock_page(page[i]); + put_page(page[i]); + } + +out: + kfree(page); + return res; +} diff --git a/fs/squashfs/fragment.c b/fs/squashfs/fragment.c new file mode 100644 index 000000000..49602b9a4 --- /dev/null +++ b/fs/squashfs/fragment.c @@ -0,0 +1,89 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Squashfs - a compressed read only filesystem for Linux + * + * Copyright (c) 2002, 2003, 2004, 2005, 2006, 2007, 2008 + * Phillip Lougher <phillip@squashfs.org.uk> + * + * fragment.c + */ + +/* + * This file implements code to handle compressed fragments (tail-end packed + * datablocks). + * + * Regular files contain a fragment index which is mapped to a fragment + * location on disk and compressed size using a fragment lookup table. + * Like everything in Squashfs this fragment lookup table is itself stored + * compressed into metadata blocks. A second index table is used to locate + * these. This second index table for speed of access (and because it + * is small) is read at mount time and cached in memory. + */ + +#include <linux/fs.h> +#include <linux/vfs.h> +#include <linux/slab.h> + +#include "squashfs_fs.h" +#include "squashfs_fs_sb.h" +#include "squashfs.h" + +/* + * Look-up fragment using the fragment index table. Return the on disk + * location of the fragment and its compressed size + */ +int squashfs_frag_lookup(struct super_block *sb, unsigned int fragment, + u64 *fragment_block) +{ + struct squashfs_sb_info *msblk = sb->s_fs_info; + int block, offset, size; + struct squashfs_fragment_entry fragment_entry; + u64 start_block; + + if (fragment >= msblk->fragments) + return -EIO; + block = SQUASHFS_FRAGMENT_INDEX(fragment); + offset = SQUASHFS_FRAGMENT_INDEX_OFFSET(fragment); + + start_block = le64_to_cpu(msblk->fragment_index[block]); + + size = squashfs_read_metadata(sb, &fragment_entry, &start_block, + &offset, sizeof(fragment_entry)); + if (size < 0) + return size; + + *fragment_block = le64_to_cpu(fragment_entry.start_block); + return squashfs_block_size(fragment_entry.size); +} + + +/* + * Read the uncompressed fragment lookup table indexes off disk into memory + */ +__le64 *squashfs_read_fragment_index_table(struct super_block *sb, + u64 fragment_table_start, u64 next_table, unsigned int fragments) +{ + unsigned int length = SQUASHFS_FRAGMENT_INDEX_BYTES(fragments); + __le64 *table; + + /* + * Sanity check, length bytes should not extend into the next table - + * this check also traps instances where fragment_table_start is + * incorrectly larger than the next table start + */ + if (fragment_table_start + length > next_table) + return ERR_PTR(-EINVAL); + + table = squashfs_read_table(sb, fragment_table_start, length); + + /* + * table[0] points to the first fragment table metadata block, this + * should be less than fragment_table_start + */ + if (!IS_ERR(table) && le64_to_cpu(table[0]) >= fragment_table_start) { + kfree(table); + return ERR_PTR(-EINVAL); + } + + return table; +} diff --git a/fs/squashfs/id.c b/fs/squashfs/id.c new file mode 100644 index 000000000..ea5387679 --- /dev/null +++ b/fs/squashfs/id.c @@ -0,0 +1,115 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Squashfs - a compressed read only filesystem for Linux + * + * Copyright (c) 2002, 2003, 2004, 2005, 2006, 2007, 2008 + * Phillip Lougher <phillip@squashfs.org.uk> + * + * id.c + */ + +/* + * This file implements code to handle uids and gids. + * + * For space efficiency regular files store uid and gid indexes, which are + * converted to 32-bit uids/gids using an id look up table. This table is + * stored compressed into metadata blocks. A second index table is used to + * locate these. This second index table for speed of access (and because it + * is small) is read at mount time and cached in memory. + */ + +#include <linux/fs.h> +#include <linux/vfs.h> +#include <linux/slab.h> + +#include "squashfs_fs.h" +#include "squashfs_fs_sb.h" +#include "squashfs.h" + +/* + * Map uid/gid index into real 32-bit uid/gid using the id look up table + */ +int squashfs_get_id(struct super_block *sb, unsigned int index, + unsigned int *id) +{ + struct squashfs_sb_info *msblk = sb->s_fs_info; + int block = SQUASHFS_ID_BLOCK(index); + int offset = SQUASHFS_ID_BLOCK_OFFSET(index); + u64 start_block; + __le32 disk_id; + int err; + + if (index >= msblk->ids) + return -EINVAL; + + start_block = le64_to_cpu(msblk->id_table[block]); + + err = squashfs_read_metadata(sb, &disk_id, &start_block, &offset, + sizeof(disk_id)); + if (err < 0) + return err; + + *id = le32_to_cpu(disk_id); + return 0; +} + + +/* + * Read uncompressed id lookup table indexes from disk into memory + */ +__le64 *squashfs_read_id_index_table(struct super_block *sb, + u64 id_table_start, u64 next_table, unsigned short no_ids) +{ + unsigned int length = SQUASHFS_ID_BLOCK_BYTES(no_ids); + unsigned int indexes = SQUASHFS_ID_BLOCKS(no_ids); + int n; + __le64 *table; + u64 start, end; + + TRACE("In read_id_index_table, length %d\n", length); + + /* Sanity check values */ + + /* there should always be at least one id */ + if (no_ids == 0) + return ERR_PTR(-EINVAL); + + /* + * The computed size of the index table (length bytes) should exactly + * match the table start and end points + */ + if (length != (next_table - id_table_start)) + return ERR_PTR(-EINVAL); + + table = squashfs_read_table(sb, id_table_start, length); + if (IS_ERR(table)) + return table; + + /* + * table[0], table[1], ... table[indexes - 1] store the locations + * of the compressed id blocks. Each entry should be less than + * the next (i.e. table[0] < table[1]), and the difference between them + * should be SQUASHFS_METADATA_SIZE or less. table[indexes - 1] + * should be less than id_table_start, and again the difference + * should be SQUASHFS_METADATA_SIZE or less + */ + for (n = 0; n < (indexes - 1); n++) { + start = le64_to_cpu(table[n]); + end = le64_to_cpu(table[n + 1]); + + if (start >= end || (end - start) > + (SQUASHFS_METADATA_SIZE + SQUASHFS_BLOCK_OFFSET)) { + kfree(table); + return ERR_PTR(-EINVAL); + } + } + + start = le64_to_cpu(table[indexes - 1]); + if (start >= id_table_start || (id_table_start - start) > + (SQUASHFS_METADATA_SIZE + SQUASHFS_BLOCK_OFFSET)) { + kfree(table); + return ERR_PTR(-EINVAL); + } + + return table; +} diff --git a/fs/squashfs/inode.c b/fs/squashfs/inode.c new file mode 100644 index 000000000..82b687414 --- /dev/null +++ b/fs/squashfs/inode.c @@ -0,0 +1,456 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Squashfs - a compressed read only filesystem for Linux + * + * Copyright (c) 2002, 2003, 2004, 2005, 2006, 2007, 2008 + * Phillip Lougher <phillip@squashfs.org.uk> + * + * inode.c + */ + +/* + * This file implements code to create and read inodes from disk. + * + * Inodes in Squashfs are identified by a 48-bit inode which encodes the + * location of the compressed metadata block containing the inode, and the byte + * offset into that block where the inode is placed (<block, offset>). + * + * To maximise compression there are different inodes for each file type + * (regular file, directory, device, etc.), the inode contents and length + * varying with the type. + * + * To further maximise compression, two types of regular file inode and + * directory inode are defined: inodes optimised for frequently occurring + * regular files and directories, and extended types where extra + * information has to be stored. + */ + +#include <linux/fs.h> +#include <linux/vfs.h> +#include <linux/xattr.h> +#include <linux/pagemap.h> + +#include "squashfs_fs.h" +#include "squashfs_fs_sb.h" +#include "squashfs_fs_i.h" +#include "squashfs.h" +#include "xattr.h" + +/* + * Initialise VFS inode with the base inode information common to all + * Squashfs inode types. Sqsh_ino contains the unswapped base inode + * off disk. + */ +static int squashfs_new_inode(struct super_block *sb, struct inode *inode, + struct squashfs_base_inode *sqsh_ino) +{ + uid_t i_uid; + gid_t i_gid; + int err; + + inode->i_ino = le32_to_cpu(sqsh_ino->inode_number); + if (inode->i_ino == 0) + return -EINVAL; + + err = squashfs_get_id(sb, le16_to_cpu(sqsh_ino->uid), &i_uid); + if (err) + return err; + + err = squashfs_get_id(sb, le16_to_cpu(sqsh_ino->guid), &i_gid); + if (err) + return err; + + i_uid_write(inode, i_uid); + i_gid_write(inode, i_gid); + inode_set_mtime(inode, le32_to_cpu(sqsh_ino->mtime), 0); + inode_set_atime(inode, inode_get_mtime_sec(inode), 0); + inode_set_ctime(inode, inode_get_mtime_sec(inode), 0); + inode->i_mode = le16_to_cpu(sqsh_ino->mode); + inode->i_size = 0; + + /* File type must not be set at this moment, for it will later be set by the caller. */ + if (inode->i_mode & S_IFMT) + err = -EIO; + + return err; +} + + +struct inode *squashfs_iget(struct super_block *sb, long long ino, + unsigned int ino_number) +{ + struct inode *inode = iget_locked(sb, ino_number); + int err; + + TRACE("Entered squashfs_iget\n"); + + if (!inode) + return ERR_PTR(-ENOMEM); + if (!(inode_state_read_once(inode) & I_NEW)) + return inode; + + err = squashfs_read_inode(inode, ino); + if (err) { + iget_failed(inode); + return ERR_PTR(err); + } + + unlock_new_inode(inode); + return inode; +} + + +/* + * Initialise VFS inode by reading inode from inode table (compressed + * metadata). The format and amount of data read depends on type. + */ +int squashfs_read_inode(struct inode *inode, long long ino) +{ + struct super_block *sb = inode->i_sb; + struct squashfs_sb_info *msblk = sb->s_fs_info; + u64 block = SQUASHFS_INODE_BLK(ino) + msblk->inode_table; + int err, type, offset = SQUASHFS_INODE_OFFSET(ino); + union squashfs_inode squashfs_ino; + struct squashfs_base_inode *sqshb_ino = &squashfs_ino.base; + int xattr_id = SQUASHFS_INVALID_XATTR; + + TRACE("Entered squashfs_read_inode\n"); + + /* + * Read inode base common to all inode types. + */ + err = squashfs_read_metadata(sb, sqshb_ino, &block, + &offset, sizeof(*sqshb_ino)); + if (err < 0) + goto failed_read; + + err = squashfs_new_inode(sb, inode, sqshb_ino); + if (err) + goto failed_read; + + block = SQUASHFS_INODE_BLK(ino) + msblk->inode_table; + offset = SQUASHFS_INODE_OFFSET(ino); + + type = le16_to_cpu(sqshb_ino->inode_type); + switch (type) { + case SQUASHFS_REG_TYPE: { + unsigned int frag_offset, frag; + int frag_size; + u64 frag_blk; + struct squashfs_reg_inode *sqsh_ino = &squashfs_ino.reg; + + err = squashfs_read_metadata(sb, sqsh_ino, &block, &offset, + sizeof(*sqsh_ino)); + if (err < 0) + goto failed_read; + + inode->i_size = le32_to_cpu(sqsh_ino->file_size); + frag = le32_to_cpu(sqsh_ino->fragment); + if (frag != SQUASHFS_INVALID_FRAG) { + /* + * the file cannot have a fragment (tailend) and have a + * file size a multiple of the block size + */ + if ((inode->i_size & (msblk->block_size - 1)) == 0) { + err = -EINVAL; + goto failed_read; + } + frag_offset = le32_to_cpu(sqsh_ino->offset); + frag_size = squashfs_frag_lookup(sb, frag, &frag_blk); + if (frag_size < 0) { + err = frag_size; + goto failed_read; + } + } else { + frag_blk = SQUASHFS_INVALID_BLK; + frag_size = 0; + frag_offset = 0; + } + + set_nlink(inode, 1); + inode->i_fop = &squashfs_file_operations; + inode->i_mode |= S_IFREG; + inode->i_blocks = ((inode->i_size - 1) >> 9) + 1; + squashfs_i(inode)->fragment_block = frag_blk; + squashfs_i(inode)->fragment_size = frag_size; + squashfs_i(inode)->fragment_offset = frag_offset; + squashfs_i(inode)->start = le32_to_cpu(sqsh_ino->start_block); + squashfs_i(inode)->block_list_start = block; + squashfs_i(inode)->offset = offset; + squashfs_i(inode)->parent = 0; + inode->i_data.a_ops = &squashfs_aops; + + TRACE("File inode %x:%x, start_block %llx, block_list_start " + "%llx, offset %x\n", SQUASHFS_INODE_BLK(ino), + offset, squashfs_i(inode)->start, block, offset); + break; + } + case SQUASHFS_LREG_TYPE: { + unsigned int frag_offset, frag; + int frag_size; + u64 frag_blk; + struct squashfs_lreg_inode *sqsh_ino = &squashfs_ino.lreg; + + err = squashfs_read_metadata(sb, sqsh_ino, &block, &offset, + sizeof(*sqsh_ino)); + if (err < 0) + goto failed_read; + + inode->i_size = le64_to_cpu(sqsh_ino->file_size); + if (inode->i_size < 0) { + err = -EINVAL; + goto failed_read; + } + frag = le32_to_cpu(sqsh_ino->fragment); + if (frag != SQUASHFS_INVALID_FRAG) { + /* + * the file cannot have a fragment (tailend) and have a + * file size a multiple of the block size + */ + if ((inode->i_size & (msblk->block_size - 1)) == 0) { + err = -EINVAL; + goto failed_read; + } + frag_offset = le32_to_cpu(sqsh_ino->offset); + frag_size = squashfs_frag_lookup(sb, frag, &frag_blk); + if (frag_size < 0) { + err = frag_size; + goto failed_read; + } + } else { + frag_blk = SQUASHFS_INVALID_BLK; + frag_size = 0; + frag_offset = 0; + } + + xattr_id = le32_to_cpu(sqsh_ino->xattr); + set_nlink(inode, le32_to_cpu(sqsh_ino->nlink)); + inode->i_op = &squashfs_inode_ops; + inode->i_fop = &squashfs_file_operations; + inode->i_mode |= S_IFREG; + inode->i_blocks = (inode->i_size - + le64_to_cpu(sqsh_ino->sparse) + 511) >> 9; + + squashfs_i(inode)->fragment_block = frag_blk; + squashfs_i(inode)->fragment_size = frag_size; + squashfs_i(inode)->fragment_offset = frag_offset; + squashfs_i(inode)->start = le64_to_cpu(sqsh_ino->start_block); + squashfs_i(inode)->block_list_start = block; + squashfs_i(inode)->offset = offset; + squashfs_i(inode)->parent = 0; + inode->i_data.a_ops = &squashfs_aops; + + TRACE("File inode %x:%x, start_block %llx, block_list_start " + "%llx, offset %x\n", SQUASHFS_INODE_BLK(ino), + offset, squashfs_i(inode)->start, block, offset); + break; + } + case SQUASHFS_DIR_TYPE: { + struct squashfs_dir_inode *sqsh_ino = &squashfs_ino.dir; + + err = squashfs_read_metadata(sb, sqsh_ino, &block, &offset, + sizeof(*sqsh_ino)); + if (err < 0) + goto failed_read; + + set_nlink(inode, le32_to_cpu(sqsh_ino->nlink)); + inode->i_size = le16_to_cpu(sqsh_ino->file_size); + inode->i_op = &squashfs_dir_inode_ops; + inode->i_fop = &squashfs_dir_ops; + inode->i_mode |= S_IFDIR; + squashfs_i(inode)->start = le32_to_cpu(sqsh_ino->start_block); + squashfs_i(inode)->offset = le16_to_cpu(sqsh_ino->offset); + squashfs_i(inode)->dir_idx_cnt = 0; + squashfs_i(inode)->parent = le32_to_cpu(sqsh_ino->parent_inode); + + TRACE("Directory inode %x:%x, start_block %llx, offset %x\n", + SQUASHFS_INODE_BLK(ino), offset, + squashfs_i(inode)->start, + le16_to_cpu(sqsh_ino->offset)); + break; + } + case SQUASHFS_LDIR_TYPE: { + struct squashfs_ldir_inode *sqsh_ino = &squashfs_ino.ldir; + + err = squashfs_read_metadata(sb, sqsh_ino, &block, &offset, + sizeof(*sqsh_ino)); + if (err < 0) + goto failed_read; + + xattr_id = le32_to_cpu(sqsh_ino->xattr); + set_nlink(inode, le32_to_cpu(sqsh_ino->nlink)); + inode->i_size = le32_to_cpu(sqsh_ino->file_size); + inode->i_op = &squashfs_dir_inode_ops; + inode->i_fop = &squashfs_dir_ops; + inode->i_mode |= S_IFDIR; + squashfs_i(inode)->start = le32_to_cpu(sqsh_ino->start_block); + squashfs_i(inode)->offset = le16_to_cpu(sqsh_ino->offset); + squashfs_i(inode)->dir_idx_start = block; + squashfs_i(inode)->dir_idx_offset = offset; + squashfs_i(inode)->dir_idx_cnt = le16_to_cpu(sqsh_ino->i_count); + squashfs_i(inode)->parent = le32_to_cpu(sqsh_ino->parent_inode); + + TRACE("Long directory inode %x:%x, start_block %llx, offset " + "%x\n", SQUASHFS_INODE_BLK(ino), offset, + squashfs_i(inode)->start, + le16_to_cpu(sqsh_ino->offset)); + break; + } + case SQUASHFS_SYMLINK_TYPE: + case SQUASHFS_LSYMLINK_TYPE: { + struct squashfs_symlink_inode *sqsh_ino = &squashfs_ino.symlink; + + err = squashfs_read_metadata(sb, sqsh_ino, &block, &offset, + sizeof(*sqsh_ino)); + if (err < 0) + goto failed_read; + + inode->i_size = le32_to_cpu(sqsh_ino->symlink_size); + if (inode->i_size > PAGE_SIZE) { + ERROR("Corrupted symlink\n"); + return -EINVAL; + } + + set_nlink(inode, le32_to_cpu(sqsh_ino->nlink)); + inode->i_op = &squashfs_symlink_inode_ops; + inode_nohighmem(inode); + inode->i_data.a_ops = &squashfs_symlink_aops; + inode->i_mode |= S_IFLNK; + squashfs_i(inode)->start = block; + squashfs_i(inode)->offset = offset; + squashfs_i(inode)->parent = 0; + + if (type == SQUASHFS_LSYMLINK_TYPE) { + __le32 xattr; + + err = squashfs_read_metadata(sb, NULL, &block, + &offset, inode->i_size); + if (err < 0) + goto failed_read; + err = squashfs_read_metadata(sb, &xattr, &block, + &offset, sizeof(xattr)); + if (err < 0) + goto failed_read; + xattr_id = le32_to_cpu(xattr); + } + + TRACE("Symbolic link inode %x:%x, start_block %llx, offset " + "%x\n", SQUASHFS_INODE_BLK(ino), offset, + block, offset); + break; + } + case SQUASHFS_BLKDEV_TYPE: + case SQUASHFS_CHRDEV_TYPE: { + struct squashfs_dev_inode *sqsh_ino = &squashfs_ino.dev; + unsigned int rdev; + + err = squashfs_read_metadata(sb, sqsh_ino, &block, &offset, + sizeof(*sqsh_ino)); + if (err < 0) + goto failed_read; + + if (type == SQUASHFS_CHRDEV_TYPE) + inode->i_mode |= S_IFCHR; + else + inode->i_mode |= S_IFBLK; + set_nlink(inode, le32_to_cpu(sqsh_ino->nlink)); + rdev = le32_to_cpu(sqsh_ino->rdev); + init_special_inode(inode, inode->i_mode, new_decode_dev(rdev)); + squashfs_i(inode)->parent = 0; + + TRACE("Device inode %x:%x, rdev %x\n", + SQUASHFS_INODE_BLK(ino), offset, rdev); + break; + } + case SQUASHFS_LBLKDEV_TYPE: + case SQUASHFS_LCHRDEV_TYPE: { + struct squashfs_ldev_inode *sqsh_ino = &squashfs_ino.ldev; + unsigned int rdev; + + err = squashfs_read_metadata(sb, sqsh_ino, &block, &offset, + sizeof(*sqsh_ino)); + if (err < 0) + goto failed_read; + + if (type == SQUASHFS_LCHRDEV_TYPE) + inode->i_mode |= S_IFCHR; + else + inode->i_mode |= S_IFBLK; + xattr_id = le32_to_cpu(sqsh_ino->xattr); + inode->i_op = &squashfs_inode_ops; + set_nlink(inode, le32_to_cpu(sqsh_ino->nlink)); + rdev = le32_to_cpu(sqsh_ino->rdev); + init_special_inode(inode, inode->i_mode, new_decode_dev(rdev)); + squashfs_i(inode)->parent = 0; + + TRACE("Device inode %x:%x, rdev %x\n", + SQUASHFS_INODE_BLK(ino), offset, rdev); + break; + } + case SQUASHFS_FIFO_TYPE: + case SQUASHFS_SOCKET_TYPE: { + struct squashfs_ipc_inode *sqsh_ino = &squashfs_ino.ipc; + + err = squashfs_read_metadata(sb, sqsh_ino, &block, &offset, + sizeof(*sqsh_ino)); + if (err < 0) + goto failed_read; + + if (type == SQUASHFS_FIFO_TYPE) + inode->i_mode |= S_IFIFO; + else + inode->i_mode |= S_IFSOCK; + set_nlink(inode, le32_to_cpu(sqsh_ino->nlink)); + init_special_inode(inode, inode->i_mode, 0); + squashfs_i(inode)->parent = 0; + break; + } + case SQUASHFS_LFIFO_TYPE: + case SQUASHFS_LSOCKET_TYPE: { + struct squashfs_lipc_inode *sqsh_ino = &squashfs_ino.lipc; + + err = squashfs_read_metadata(sb, sqsh_ino, &block, &offset, + sizeof(*sqsh_ino)); + if (err < 0) + goto failed_read; + + if (type == SQUASHFS_LFIFO_TYPE) + inode->i_mode |= S_IFIFO; + else + inode->i_mode |= S_IFSOCK; + xattr_id = le32_to_cpu(sqsh_ino->xattr); + inode->i_op = &squashfs_inode_ops; + set_nlink(inode, le32_to_cpu(sqsh_ino->nlink)); + init_special_inode(inode, inode->i_mode, 0); + squashfs_i(inode)->parent = 0; + break; + } + default: + ERROR("Unknown inode type %d in squashfs_iget!\n", type); + return -EINVAL; + } + + if (xattr_id != SQUASHFS_INVALID_XATTR && msblk->xattr_id_table) { + err = squashfs_xattr_lookup(sb, xattr_id, + &squashfs_i(inode)->xattr_count, + &squashfs_i(inode)->xattr_size, + &squashfs_i(inode)->xattr); + if (err < 0) + goto failed_read; + inode->i_blocks += ((squashfs_i(inode)->xattr_size - 1) >> 9) + + 1; + } else + squashfs_i(inode)->xattr_count = 0; + + return 0; + +failed_read: + ERROR("Unable to read inode 0x%llx\n", ino); + return err; +} + + +const struct inode_operations squashfs_inode_ops = { + .listxattr = squashfs_listxattr +}; + diff --git a/fs/squashfs/lz4_wrapper.c b/fs/squashfs/lz4_wrapper.c new file mode 100644 index 000000000..1646bbee2 --- /dev/null +++ b/fs/squashfs/lz4_wrapper.c @@ -0,0 +1,146 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (c) 2013, 2014 + * Phillip Lougher <phillip@squashfs.org.uk> + */ + +#include <linux/bio.h> +#include <linux/mutex.h> +#include <linux/slab.h> +#include <linux/vmalloc.h> +#include <linux/lz4.h> + +#include "squashfs_fs.h" +#include "squashfs_fs_sb.h" +#include "squashfs.h" +#include "decompressor.h" +#include "page_actor.h" + +#define LZ4_LEGACY 1 + +struct lz4_comp_opts { + __le32 version; + __le32 flags; +}; + +struct squashfs_lz4 { + void *input; + void *output; +}; + + +static void *lz4_comp_opts(struct squashfs_sb_info *msblk, + void *buff, int len) +{ + struct lz4_comp_opts *comp_opts = buff; + + /* LZ4 compressed filesystems always have compression options */ + if (comp_opts == NULL || len < sizeof(*comp_opts)) + return ERR_PTR(-EIO); + + if (le32_to_cpu(comp_opts->version) != LZ4_LEGACY) { + /* LZ4 format currently used by the kernel is the 'legacy' + * format */ + ERROR("Unknown LZ4 version\n"); + return ERR_PTR(-EINVAL); + } + + return NULL; +} + + +static void *lz4_init(struct squashfs_sb_info *msblk, void *buff) +{ + int block_size = max_t(int, msblk->block_size, SQUASHFS_METADATA_SIZE); + struct squashfs_lz4 *stream; + + stream = kzalloc_obj(*stream); + if (stream == NULL) + goto failed; + stream->input = vmalloc(block_size); + if (stream->input == NULL) + goto failed2; + stream->output = vmalloc(block_size); + if (stream->output == NULL) + goto failed3; + + return stream; + +failed3: + vfree(stream->input); +failed2: + kfree(stream); +failed: + ERROR("Failed to initialise LZ4 decompressor\n"); + return ERR_PTR(-ENOMEM); +} + + +static void lz4_free(void *strm) +{ + struct squashfs_lz4 *stream = strm; + + if (stream) { + vfree(stream->input); + vfree(stream->output); + } + kfree(stream); +} + + +static int lz4_uncompress(struct squashfs_sb_info *msblk, void *strm, + struct bio *bio, int offset, int length, + struct squashfs_page_actor *output) +{ + struct bvec_iter_all iter_all = {}; + struct bio_vec *bvec = bvec_init_iter_all(&iter_all); + struct squashfs_lz4 *stream = strm; + void *buff = stream->input, *data; + int bytes = length, res; + + while (bio_next_segment(bio, &iter_all)) { + int avail = min(bytes, ((int)bvec->bv_len) - offset); + + data = bvec_virt(bvec); + memcpy(buff, data + offset, avail); + buff += avail; + bytes -= avail; + offset = 0; + } + + res = LZ4_decompress_safe(stream->input, stream->output, + length, output->length); + + if (res < 0) + return -EIO; + + bytes = res; + data = squashfs_first_page(output); + buff = stream->output; + while (data) { + if (bytes <= PAGE_SIZE) { + if (!IS_ERR(data)) + memcpy(data, buff, bytes); + break; + } + if (!IS_ERR(data)) + memcpy(data, buff, PAGE_SIZE); + buff += PAGE_SIZE; + bytes -= PAGE_SIZE; + data = squashfs_next_page(output); + } + squashfs_finish_page(output); + + return res; +} + +const struct squashfs_decompressor squashfs_lz4_comp_ops = { + .init = lz4_init, + .comp_opts = lz4_comp_opts, + .free = lz4_free, + .decompress = lz4_uncompress, + .id = LZ4_COMPRESSION, + .name = "lz4", + .alloc_buffer = 0, + .supported = 1 +}; diff --git a/fs/squashfs/lzo_wrapper.c b/fs/squashfs/lzo_wrapper.c new file mode 100644 index 000000000..be1df7a25 --- /dev/null +++ b/fs/squashfs/lzo_wrapper.c @@ -0,0 +1,123 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Squashfs - a compressed read only filesystem for Linux + * + * Copyright (c) 2010 LG Electronics + * Chan Jeong <chan.jeong@lge.com> + * + * lzo_wrapper.c + */ + +#include <linux/mutex.h> +#include <linux/bio.h> +#include <linux/slab.h> +#include <linux/vmalloc.h> +#include <linux/lzo.h> + +#include "squashfs_fs.h" +#include "squashfs_fs_sb.h" +#include "squashfs.h" +#include "decompressor.h" +#include "page_actor.h" + +struct squashfs_lzo { + void *input; + void *output; +}; + +static void *lzo_init(struct squashfs_sb_info *msblk, void *buff) +{ + int block_size = max_t(int, msblk->block_size, SQUASHFS_METADATA_SIZE); + + struct squashfs_lzo *stream = kzalloc_obj(*stream); + if (stream == NULL) + goto failed; + stream->input = vmalloc(block_size); + if (stream->input == NULL) + goto failed; + stream->output = vmalloc(block_size); + if (stream->output == NULL) + goto failed2; + + return stream; + +failed2: + vfree(stream->input); +failed: + ERROR("Failed to allocate lzo workspace\n"); + kfree(stream); + return ERR_PTR(-ENOMEM); +} + + +static void lzo_free(void *strm) +{ + struct squashfs_lzo *stream = strm; + + if (stream) { + vfree(stream->input); + vfree(stream->output); + } + kfree(stream); +} + + +static int lzo_uncompress(struct squashfs_sb_info *msblk, void *strm, + struct bio *bio, int offset, int length, + struct squashfs_page_actor *output) +{ + struct bvec_iter_all iter_all = {}; + struct bio_vec *bvec = bvec_init_iter_all(&iter_all); + struct squashfs_lzo *stream = strm; + void *buff = stream->input, *data; + int bytes = length, res; + size_t out_len = output->length; + + while (bio_next_segment(bio, &iter_all)) { + int avail = min(bytes, ((int)bvec->bv_len) - offset); + + data = bvec_virt(bvec); + memcpy(buff, data + offset, avail); + buff += avail; + bytes -= avail; + offset = 0; + } + + res = lzo1x_decompress_safe(stream->input, (size_t)length, + stream->output, &out_len); + if (res != LZO_E_OK) + goto failed; + + res = bytes = (int)out_len; + data = squashfs_first_page(output); + buff = stream->output; + while (data) { + if (bytes <= PAGE_SIZE) { + if (!IS_ERR(data)) + memcpy(data, buff, bytes); + break; + } else { + if (!IS_ERR(data)) + memcpy(data, buff, PAGE_SIZE); + buff += PAGE_SIZE; + bytes -= PAGE_SIZE; + data = squashfs_next_page(output); + } + } + squashfs_finish_page(output); + + return res; + +failed: + return -EIO; +} + +const struct squashfs_decompressor squashfs_lzo_comp_ops = { + .init = lzo_init, + .free = lzo_free, + .decompress = lzo_uncompress, + .id = LZO_COMPRESSION, + .name = "lzo", + .alloc_buffer = 0, + .supported = 1 +}; diff --git a/fs/squashfs/namei.c b/fs/squashfs/namei.c new file mode 100644 index 000000000..65aae7e2a --- /dev/null +++ b/fs/squashfs/namei.c @@ -0,0 +1,232 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Squashfs - a compressed read only filesystem for Linux + * + * Copyright (c) 2002, 2003, 2004, 2005, 2006, 2007, 2008 + * Phillip Lougher <phillip@squashfs.org.uk> + * + * namei.c + */ + +/* + * This file implements code to do filename lookup in directories. + * + * Like inodes, directories are packed into compressed metadata blocks, stored + * in a directory table. Directories are accessed using the start address of + * the metablock containing the directory and the offset into the + * decompressed block (<block, offset>). + * + * Directories are organised in a slightly complex way, and are not simply + * a list of file names. The organisation takes advantage of the + * fact that (in most cases) the inodes of the files will be in the same + * compressed metadata block, and therefore, can share the start block. + * Directories are therefore organised in a two level list, a directory + * header containing the shared start block value, and a sequence of directory + * entries, each of which share the shared start block. A new directory header + * is written once/if the inode start block changes. The directory + * header/directory entry list is repeated as many times as necessary. + * + * Directories are sorted, and can contain a directory index to speed up + * file lookup. Directory indexes store one entry per metablock, each entry + * storing the index/filename mapping to the first directory header + * in each metadata block. Directories are sorted in alphabetical order, + * and at lookup the index is scanned linearly looking for the first filename + * alphabetically larger than the filename being looked up. At this point the + * location of the metadata block the filename is in has been found. + * The general idea of the index is ensure only one metadata block needs to be + * decompressed to do a lookup irrespective of the length of the directory. + * This scheme has the advantage that it doesn't require extra memory overhead + * and doesn't require much extra storage on disk. + */ + +#include <linux/fs.h> +#include <linux/vfs.h> +#include <linux/slab.h> +#include <linux/string.h> +#include <linux/dcache.h> +#include <linux/xattr.h> + +#include "squashfs_fs.h" +#include "squashfs_fs_sb.h" +#include "squashfs_fs_i.h" +#include "squashfs.h" +#include "xattr.h" + +/* + * Lookup name in the directory index, returning the location of the metadata + * block containing it, and the directory index this represents. + * + * If we get an error reading the index then return the part of the index + * (if any) we have managed to read - the index isn't essential, just + * quicker. + */ +static int get_dir_index_using_name(struct super_block *sb, + u64 *next_block, int *next_offset, u64 index_start, + int index_offset, int i_count, const char *name) +{ + struct squashfs_sb_info *msblk = sb->s_fs_info; + int i, length = 0, err; + unsigned int size; + struct squashfs_dir_index *index; + + TRACE("Entered get_dir_index_using_name, i_count %d\n", i_count); + + index = kmalloc(sizeof(*index) + SQUASHFS_NAME_LEN + 1, GFP_KERNEL); + if (index == NULL) { + ERROR("Failed to allocate squashfs_dir_index\n"); + goto out; + } + + for (i = 0; i < i_count; i++) { + err = squashfs_read_metadata(sb, index, &index_start, + &index_offset, sizeof(*index)); + if (err < 0) + break; + + + size = le32_to_cpu(index->size) + 1; + if (size > SQUASHFS_NAME_LEN) + break; + + err = squashfs_read_metadata(sb, index->name, &index_start, + &index_offset, size); + if (err < 0) + break; + + index->name[size] = '\0'; + + if (strcmp(index->name, name) > 0) + break; + + length = le32_to_cpu(index->index); + *next_block = le32_to_cpu(index->start_block) + + msblk->directory_table; + } + + *next_offset = (length + *next_offset) % SQUASHFS_METADATA_SIZE; + kfree(index); + +out: + /* + * Return index (f_pos) of the looked up metadata block. Translate + * from internal f_pos to external f_pos which is offset by 3 because + * we invent "." and ".." entries which are not actually stored in the + * directory. + */ + return length + 3; +} + + +static struct dentry *squashfs_lookup(struct inode *dir, struct dentry *dentry, + unsigned int flags) +{ + const unsigned char *name = dentry->d_name.name; + int len = dentry->d_name.len; + struct inode *inode = NULL; + struct squashfs_sb_info *msblk = dir->i_sb->s_fs_info; + struct squashfs_dir_header dirh; + struct squashfs_dir_entry *dire; + u64 block = squashfs_i(dir)->start + msblk->directory_table; + int offset = squashfs_i(dir)->offset; + int err, length; + unsigned int dir_count, size; + + TRACE("Entered squashfs_lookup [%llx:%x]\n", block, offset); + + dire = kmalloc(sizeof(*dire) + SQUASHFS_NAME_LEN + 1, GFP_KERNEL); + if (dire == NULL) { + ERROR("Failed to allocate squashfs_dir_entry\n"); + return ERR_PTR(-ENOMEM); + } + + if (len > SQUASHFS_NAME_LEN) { + err = -ENAMETOOLONG; + goto failed; + } + + length = get_dir_index_using_name(dir->i_sb, &block, &offset, + squashfs_i(dir)->dir_idx_start, + squashfs_i(dir)->dir_idx_offset, + squashfs_i(dir)->dir_idx_cnt, name); + + while (length < i_size_read(dir)) { + /* + * Read directory header. + */ + err = squashfs_read_metadata(dir->i_sb, &dirh, &block, + &offset, sizeof(dirh)); + if (err < 0) + goto read_failure; + + length += sizeof(dirh); + + dir_count = le32_to_cpu(dirh.count) + 1; + + if (dir_count > SQUASHFS_DIR_COUNT) + goto data_error; + + while (dir_count--) { + /* + * Read directory entry. + */ + err = squashfs_read_metadata(dir->i_sb, dire, &block, + &offset, sizeof(*dire)); + if (err < 0) + goto read_failure; + + size = le16_to_cpu(dire->size) + 1; + + /* size should never be larger than SQUASHFS_NAME_LEN */ + if (size > SQUASHFS_NAME_LEN) + goto data_error; + + err = squashfs_read_metadata(dir->i_sb, dire->name, + &block, &offset, size); + if (err < 0) + goto read_failure; + + length += sizeof(*dire) + size; + + if (name[0] < dire->name[0]) + goto exit_lookup; + + if (len == size && !strncmp(name, dire->name, len)) { + unsigned int blk, off, ino_num; + long long ino; + blk = le32_to_cpu(dirh.start_block); + off = le16_to_cpu(dire->offset); + ino_num = le32_to_cpu(dirh.inode_number) + + (short) le16_to_cpu(dire->inode_number); + ino = SQUASHFS_MKINODE(blk, off); + + TRACE("calling squashfs_iget for directory " + "entry %s, inode %x:%x, %d\n", name, + blk, off, ino_num); + + inode = squashfs_iget(dir->i_sb, ino, ino_num); + goto exit_lookup; + } + } + } + +exit_lookup: + kfree(dire); + return d_splice_alias(inode, dentry); + +data_error: + err = -EIO; + +read_failure: + ERROR("Unable to read directory block [%llx:%x]\n", + squashfs_i(dir)->start + msblk->directory_table, + squashfs_i(dir)->offset); +failed: + kfree(dire); + return ERR_PTR(err); +} + + +const struct inode_operations squashfs_dir_inode_ops = { + .lookup = squashfs_lookup, + .listxattr = squashfs_listxattr +}; diff --git a/fs/squashfs/page_actor.c b/fs/squashfs/page_actor.c new file mode 100644 index 000000000..79b73e98a --- /dev/null +++ b/fs/squashfs/page_actor.c @@ -0,0 +1,141 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (c) 2013 + * Phillip Lougher <phillip@squashfs.org.uk> + */ + +#include <linux/kernel.h> +#include <linux/slab.h> +#include <linux/pagemap.h> +#include "squashfs_fs_sb.h" +#include "decompressor.h" +#include "page_actor.h" + +/* + * This file contains implementations of page_actor for decompressing into + * an intermediate buffer, and for decompressing directly into the + * page cache. + * + * Calling code should avoid sleeping between calls to squashfs_first_page() + * and squashfs_finish_page(). + */ + +/* Implementation of page_actor for decompressing into intermediate buffer */ +static void *cache_first_page(struct squashfs_page_actor *actor) +{ + actor->next_page = 1; + return actor->buffer[0]; +} + +static void *cache_next_page(struct squashfs_page_actor *actor) +{ + if (actor->next_page == actor->pages) + return NULL; + + return actor->buffer[actor->next_page++]; +} + +static void cache_finish_page(struct squashfs_page_actor *actor) +{ + /* empty */ +} + +struct squashfs_page_actor *squashfs_page_actor_init(void **buffer, + int pages, int length) +{ + struct squashfs_page_actor *actor = kmalloc_obj(*actor); + + if (actor == NULL) + return NULL; + + actor->length = length ? : pages * PAGE_SIZE; + actor->buffer = buffer; + actor->pages = pages; + actor->next_page = 0; + actor->tmp_buffer = NULL; + actor->squashfs_first_page = cache_first_page; + actor->squashfs_next_page = cache_next_page; + actor->squashfs_finish_page = cache_finish_page; + return actor; +} + +/* Implementation of page_actor for decompressing directly into page cache. */ +static loff_t page_next_index(struct squashfs_page_actor *actor) +{ + return page_folio(actor->page[actor->next_page])->index; +} + +static void *handle_next_page(struct squashfs_page_actor *actor) +{ + int max_pages = (actor->length + PAGE_SIZE - 1) >> PAGE_SHIFT; + + if (actor->returned_pages == max_pages) + return NULL; + + if ((actor->next_page == actor->pages) || + (actor->next_index != page_next_index(actor))) { + actor->next_index++; + actor->returned_pages++; + actor->last_page = NULL; + return actor->alloc_buffer ? actor->tmp_buffer : ERR_PTR(-ENOMEM); + } + + actor->next_index++; + actor->returned_pages++; + actor->last_page = actor->page[actor->next_page]; + return actor->pageaddr = kmap_local_page(actor->page[actor->next_page++]); +} + +static void *direct_first_page(struct squashfs_page_actor *actor) +{ + return handle_next_page(actor); +} + +static void *direct_next_page(struct squashfs_page_actor *actor) +{ + if (actor->pageaddr) { + kunmap_local(actor->pageaddr); + actor->pageaddr = NULL; + } + + return handle_next_page(actor); +} + +static void direct_finish_page(struct squashfs_page_actor *actor) +{ + if (actor->pageaddr) + kunmap_local(actor->pageaddr); +} + +struct squashfs_page_actor *squashfs_page_actor_init_special(struct squashfs_sb_info *msblk, + struct page **page, int pages, int length, loff_t start_index) +{ + struct squashfs_page_actor *actor = kmalloc_obj(*actor); + + if (actor == NULL) + return NULL; + + if (msblk->decompressor->alloc_buffer) { + actor->tmp_buffer = kmalloc(PAGE_SIZE, GFP_KERNEL); + + if (actor->tmp_buffer == NULL) { + kfree(actor); + return NULL; + } + } else + actor->tmp_buffer = NULL; + + actor->length = length ? : pages * PAGE_SIZE; + actor->page = page; + actor->pages = pages; + actor->next_page = 0; + actor->returned_pages = 0; + actor->next_index = start_index >> PAGE_SHIFT; + actor->pageaddr = NULL; + actor->last_page = NULL; + actor->alloc_buffer = msblk->decompressor->alloc_buffer; + actor->squashfs_first_page = direct_first_page; + actor->squashfs_next_page = direct_next_page; + actor->squashfs_finish_page = direct_finish_page; + return actor; +} diff --git a/fs/squashfs/page_actor.h b/fs/squashfs/page_actor.h new file mode 100644 index 000000000..ffe25eb77 --- /dev/null +++ b/fs/squashfs/page_actor.h @@ -0,0 +1,59 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +#ifndef PAGE_ACTOR_H +#define PAGE_ACTOR_H +/* + * Copyright (c) 2013 + * Phillip Lougher <phillip@squashfs.org.uk> + */ + +struct squashfs_page_actor { + union { + void **buffer; + struct page **page; + }; + void *pageaddr; + void *tmp_buffer; + void *(*squashfs_first_page)(struct squashfs_page_actor *); + void *(*squashfs_next_page)(struct squashfs_page_actor *); + void (*squashfs_finish_page)(struct squashfs_page_actor *); + struct page *last_page; + int pages; + int length; + int next_page; + int alloc_buffer; + int returned_pages; + pgoff_t next_index; +}; + +extern struct squashfs_page_actor *squashfs_page_actor_init(void **buffer, + int pages, int length); +extern struct squashfs_page_actor *squashfs_page_actor_init_special( + struct squashfs_sb_info *msblk, + struct page **page, int pages, int length, + loff_t start_index); +static inline struct page *squashfs_page_actor_free(struct squashfs_page_actor *actor) +{ + struct page *last_page = actor->next_page == actor->pages ? actor->last_page : ERR_PTR(-EIO); + + kfree(actor->tmp_buffer); + kfree(actor); + + return last_page; +} +static inline void *squashfs_first_page(struct squashfs_page_actor *actor) +{ + return actor->squashfs_first_page(actor); +} +static inline void *squashfs_next_page(struct squashfs_page_actor *actor) +{ + return actor->squashfs_next_page(actor); +} +static inline void squashfs_finish_page(struct squashfs_page_actor *actor) +{ + actor->squashfs_finish_page(actor); +} +static inline void squashfs_actor_nobuff(struct squashfs_page_actor *actor) +{ + actor->alloc_buffer = 0; +} +#endif diff --git a/fs/squashfs/squashfs.h b/fs/squashfs/squashfs.h new file mode 100644 index 000000000..4851bd964 --- /dev/null +++ b/fs/squashfs/squashfs.h @@ -0,0 +1,120 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Squashfs - a compressed read only filesystem for Linux + * + * Copyright (c) 2002, 2003, 2004, 2005, 2006, 2007, 2008 + * Phillip Lougher <phillip@squashfs.org.uk> + * + * squashfs.h + */ + +#define TRACE(s, args...) pr_debug("SQUASHFS: "s, ## args) + +#define ERROR(s, args...) pr_err("SQUASHFS error: "s, ## args) + +#define WARNING(s, args...) pr_warn("SQUASHFS: "s, ## args) + +#ifdef CONFIG_SQUASHFS_FILE_CACHE +#define SQUASHFS_READ_PAGES msblk->max_thread_num +#else +#define SQUASHFS_READ_PAGES 0 +#endif + +/* block.c */ +extern int squashfs_read_data(struct super_block *, u64, int, u64 *, + struct squashfs_page_actor *); + +/* cache.c */ +extern struct squashfs_cache *squashfs_cache_init(char *, int, int); +extern void squashfs_cache_delete(struct squashfs_cache *); +extern struct squashfs_cache_entry *squashfs_cache_get(struct super_block *, + struct squashfs_cache *, u64, int); +extern void squashfs_cache_put(struct squashfs_cache_entry *); +extern int squashfs_copy_data(void *, struct squashfs_cache_entry *, int, int); +extern int squashfs_read_metadata(struct super_block *, void *, u64 *, + int *, int); +extern struct squashfs_cache_entry *squashfs_get_fragment(struct super_block *, + u64, int); +extern struct squashfs_cache_entry *squashfs_get_datablock(struct super_block *, + u64, int); +extern void *squashfs_read_table(struct super_block *, u64, int); + +/* decompressor.c */ +extern const struct squashfs_decompressor *squashfs_lookup_decompressor(int); +extern void *squashfs_decompressor_setup(struct super_block *, unsigned short); + +/* decompressor_xxx.c */ + +struct squashfs_decompressor_thread_ops { + void * (*create)(struct squashfs_sb_info *msblk, void *comp_opts); + void (*destroy)(struct squashfs_sb_info *msblk); + int (*decompress)(struct squashfs_sb_info *msblk, struct bio *bio, + int offset, int length, struct squashfs_page_actor *output); + int (*max_decompressors)(void); +}; + +#ifdef CONFIG_SQUASHFS_DECOMP_SINGLE +extern const struct squashfs_decompressor_thread_ops squashfs_decompressor_single; +#endif +#ifdef CONFIG_SQUASHFS_DECOMP_MULTI +extern const struct squashfs_decompressor_thread_ops squashfs_decompressor_multi; +#endif +#ifdef CONFIG_SQUASHFS_DECOMP_MULTI_PERCPU +extern const struct squashfs_decompressor_thread_ops squashfs_decompressor_percpu; +#endif + +/* export.c */ +extern __le64 *squashfs_read_inode_lookup_table(struct super_block *, u64, u64, + unsigned int); + +/* fragment.c */ +extern int squashfs_frag_lookup(struct super_block *, unsigned int, u64 *); +extern __le64 *squashfs_read_fragment_index_table(struct super_block *, + u64, u64, unsigned int); + +/* file.c */ +void squashfs_copy_cache(struct folio *, struct squashfs_cache_entry *, + size_t bytes, size_t offset); + +/* file_xxx.c */ +int squashfs_readpage_block(struct folio *, u64 block, int bsize, int expected); + +/* id.c */ +extern int squashfs_get_id(struct super_block *, unsigned int, unsigned int *); +extern __le64 *squashfs_read_id_index_table(struct super_block *, u64, u64, + unsigned short); + +/* inode.c */ +extern struct inode *squashfs_iget(struct super_block *, long long, + unsigned int); +extern int squashfs_read_inode(struct inode *, long long); + +/* xattr.c */ +extern ssize_t squashfs_listxattr(struct dentry *, char *, size_t); + +/* + * Inodes, files, decompressor and xattr operations + */ + +/* dir.c */ +extern const struct file_operations squashfs_dir_ops; + +/* export.c */ +extern const struct export_operations squashfs_export_ops; + +/* file.c */ +extern const struct address_space_operations squashfs_aops; + +/* inode.c */ +extern const struct inode_operations squashfs_inode_ops; +extern const struct file_operations squashfs_file_operations; + +/* namei.c */ +extern const struct inode_operations squashfs_dir_inode_ops; + +/* symlink.c */ +extern const struct address_space_operations squashfs_symlink_aops; +extern const struct inode_operations squashfs_symlink_inode_ops; + +/* xattr.c */ +extern const struct xattr_handler * const squashfs_xattr_handlers[]; diff --git a/fs/squashfs/squashfs_fs.h b/fs/squashfs/squashfs_fs.h new file mode 100644 index 000000000..a955d9369 --- /dev/null +++ b/fs/squashfs/squashfs_fs.h @@ -0,0 +1,453 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +#ifndef SQUASHFS_FS +#define SQUASHFS_FS +/* + * Squashfs + * + * Copyright (c) 2002, 2003, 2004, 2005, 2006, 2007, 2008 + * Phillip Lougher <phillip@squashfs.org.uk> + * + * squashfs_fs.h + */ + +#define SQUASHFS_CACHED_FRAGMENTS CONFIG_SQUASHFS_FRAGMENT_CACHE_SIZE +#define SQUASHFS_MAJOR 4 +#define SQUASHFS_MINOR 0 +#define SQUASHFS_START 0 + +/* size of metadata (inode and directory) blocks */ +#define SQUASHFS_METADATA_SIZE 8192 +#define SQUASHFS_BLOCK_OFFSET 2 + +/* default size of block device I/O */ +#ifdef CONFIG_SQUASHFS_4K_DEVBLK_SIZE +#define SQUASHFS_DEVBLK_SIZE 4096 +#else +#define SQUASHFS_DEVBLK_SIZE 1024 +#endif + +#define SQUASHFS_FILE_MAX_SIZE 1048576 +#define SQUASHFS_FILE_MAX_LOG 20 + +/* Max length of filename (not 255) */ +#define SQUASHFS_NAME_LEN 256 + +/* Max value for directory header count*/ +#define SQUASHFS_DIR_COUNT 256 + +#define SQUASHFS_INVALID_FRAG (0xffffffffU) +#define SQUASHFS_INVALID_XATTR (0xffffffffU) +#define SQUASHFS_INVALID_BLK (-1LL) + +/* Filesystem flags */ +#define SQUASHFS_NOI 0 +#define SQUASHFS_NOD 1 +#define SQUASHFS_NOF 3 +#define SQUASHFS_NO_FRAG 4 +#define SQUASHFS_ALWAYS_FRAG 5 +#define SQUASHFS_DUPLICATE 6 +#define SQUASHFS_EXPORT 7 +#define SQUASHFS_COMP_OPT 10 + +#define SQUASHFS_BIT(flag, bit) ((flag >> bit) & 1) + +#define SQUASHFS_UNCOMPRESSED_INODES(flags) SQUASHFS_BIT(flags, \ + SQUASHFS_NOI) + +#define SQUASHFS_UNCOMPRESSED_DATA(flags) SQUASHFS_BIT(flags, \ + SQUASHFS_NOD) + +#define SQUASHFS_UNCOMPRESSED_FRAGMENTS(flags) SQUASHFS_BIT(flags, \ + SQUASHFS_NOF) + +#define SQUASHFS_NO_FRAGMENTS(flags) SQUASHFS_BIT(flags, \ + SQUASHFS_NO_FRAG) + +#define SQUASHFS_ALWAYS_FRAGMENTS(flags) SQUASHFS_BIT(flags, \ + SQUASHFS_ALWAYS_FRAG) + +#define SQUASHFS_DUPLICATES(flags) SQUASHFS_BIT(flags, \ + SQUASHFS_DUPLICATE) + +#define SQUASHFS_EXPORTABLE(flags) SQUASHFS_BIT(flags, \ + SQUASHFS_EXPORT) + +#define SQUASHFS_COMP_OPTS(flags) SQUASHFS_BIT(flags, \ + SQUASHFS_COMP_OPT) + +/* Inode types including extended types */ +#define SQUASHFS_DIR_TYPE 1 +#define SQUASHFS_REG_TYPE 2 +#define SQUASHFS_SYMLINK_TYPE 3 +#define SQUASHFS_BLKDEV_TYPE 4 +#define SQUASHFS_CHRDEV_TYPE 5 +#define SQUASHFS_FIFO_TYPE 6 +#define SQUASHFS_SOCKET_TYPE 7 +#define SQUASHFS_LDIR_TYPE 8 +#define SQUASHFS_LREG_TYPE 9 +#define SQUASHFS_LSYMLINK_TYPE 10 +#define SQUASHFS_LBLKDEV_TYPE 11 +#define SQUASHFS_LCHRDEV_TYPE 12 +#define SQUASHFS_LFIFO_TYPE 13 +#define SQUASHFS_LSOCKET_TYPE 14 + +/* Max type value stored in directory entry */ +#define SQUASHFS_MAX_DIR_TYPE 7 + +/* Xattr types */ +#define SQUASHFS_XATTR_USER 0 +#define SQUASHFS_XATTR_TRUSTED 1 +#define SQUASHFS_XATTR_SECURITY 2 +#define SQUASHFS_XATTR_VALUE_OOL 256 +#define SQUASHFS_XATTR_PREFIX_MASK 0xff + +/* Flag whether block is compressed or uncompressed, bit is set if block is + * uncompressed */ +#define SQUASHFS_COMPRESSED_BIT (1 << 15) + +#define SQUASHFS_COMPRESSED_SIZE(B) (((B) & ~SQUASHFS_COMPRESSED_BIT) ? \ + (B) & ~SQUASHFS_COMPRESSED_BIT : SQUASHFS_COMPRESSED_BIT) + +#define SQUASHFS_COMPRESSED(B) (!((B) & SQUASHFS_COMPRESSED_BIT)) + +#define SQUASHFS_COMPRESSED_BIT_BLOCK (1 << 24) + +#define SQUASHFS_COMPRESSED_SIZE_BLOCK(B) ((B) & \ + ~SQUASHFS_COMPRESSED_BIT_BLOCK) + +#define SQUASHFS_COMPRESSED_BLOCK(B) (!((B) & SQUASHFS_COMPRESSED_BIT_BLOCK)) + +static inline int squashfs_block_size(__le32 raw) +{ + u32 size = le32_to_cpu(raw); + return (size >> 25) ? -EIO : size; +} + +/* + * Inode number ops. Inodes consist of a compressed block number, and an + * uncompressed offset within that block + */ +#define SQUASHFS_INODE_BLK(A) ((unsigned int) ((A) >> 16)) + +#define SQUASHFS_INODE_OFFSET(A) ((unsigned int) ((A) & 0xffff)) + +#define SQUASHFS_MKINODE(A, B) ((long long)(((long long) (A)\ + << 16) + (B))) + +/* fragment and fragment table defines */ +#define SQUASHFS_FRAGMENT_BYTES(A) \ + ((A) * sizeof(struct squashfs_fragment_entry)) + +#define SQUASHFS_FRAGMENT_INDEX(A) (SQUASHFS_FRAGMENT_BYTES(A) / \ + SQUASHFS_METADATA_SIZE) + +#define SQUASHFS_FRAGMENT_INDEX_OFFSET(A) (SQUASHFS_FRAGMENT_BYTES(A) % \ + SQUASHFS_METADATA_SIZE) + +#define SQUASHFS_FRAGMENT_INDEXES(A) ((SQUASHFS_FRAGMENT_BYTES(A) + \ + SQUASHFS_METADATA_SIZE - 1) / \ + SQUASHFS_METADATA_SIZE) + +#define SQUASHFS_FRAGMENT_INDEX_BYTES(A) (SQUASHFS_FRAGMENT_INDEXES(A) *\ + sizeof(u64)) + +/* inode lookup table defines */ +#define SQUASHFS_LOOKUP_BYTES(A) ((A) * sizeof(u64)) + +#define SQUASHFS_LOOKUP_BLOCK(A) (SQUASHFS_LOOKUP_BYTES(A) / \ + SQUASHFS_METADATA_SIZE) + +#define SQUASHFS_LOOKUP_BLOCK_OFFSET(A) (SQUASHFS_LOOKUP_BYTES(A) % \ + SQUASHFS_METADATA_SIZE) + +#define SQUASHFS_LOOKUP_BLOCKS(A) ((SQUASHFS_LOOKUP_BYTES(A) + \ + SQUASHFS_METADATA_SIZE - 1) / \ + SQUASHFS_METADATA_SIZE) + +#define SQUASHFS_LOOKUP_BLOCK_BYTES(A) (SQUASHFS_LOOKUP_BLOCKS(A) *\ + sizeof(u64)) + +/* uid/gid lookup table defines */ +#define SQUASHFS_ID_BYTES(A) ((A) * sizeof(unsigned int)) + +#define SQUASHFS_ID_BLOCK(A) (SQUASHFS_ID_BYTES(A) / \ + SQUASHFS_METADATA_SIZE) + +#define SQUASHFS_ID_BLOCK_OFFSET(A) (SQUASHFS_ID_BYTES(A) % \ + SQUASHFS_METADATA_SIZE) + +#define SQUASHFS_ID_BLOCKS(A) ((SQUASHFS_ID_BYTES(A) + \ + SQUASHFS_METADATA_SIZE - 1) / \ + SQUASHFS_METADATA_SIZE) + +#define SQUASHFS_ID_BLOCK_BYTES(A) (SQUASHFS_ID_BLOCKS(A) *\ + sizeof(u64)) +/* xattr id lookup table defines */ +#define SQUASHFS_XATTR_BYTES(A) (((u64) (A)) * sizeof(struct squashfs_xattr_id)) + +#define SQUASHFS_XATTR_BLOCK(A) (SQUASHFS_XATTR_BYTES(A) / \ + SQUASHFS_METADATA_SIZE) + +#define SQUASHFS_XATTR_BLOCK_OFFSET(A) (SQUASHFS_XATTR_BYTES(A) % \ + SQUASHFS_METADATA_SIZE) + +#define SQUASHFS_XATTR_BLOCKS(A) ((SQUASHFS_XATTR_BYTES(A) + \ + SQUASHFS_METADATA_SIZE - 1) / \ + SQUASHFS_METADATA_SIZE) + +#define SQUASHFS_XATTR_BLOCK_BYTES(A) (SQUASHFS_XATTR_BLOCKS(A) *\ + sizeof(u64)) +#define SQUASHFS_XATTR_BLK(A) ((unsigned int) ((A) >> 16)) + +#define SQUASHFS_XATTR_OFFSET(A) ((unsigned int) ((A) & 0xffff)) + +/* cached data constants for filesystem */ +#define SQUASHFS_CACHED_BLKS 8 + +/* meta index cache */ +#define SQUASHFS_META_INDEXES (SQUASHFS_METADATA_SIZE / sizeof(unsigned int)) +#define SQUASHFS_META_ENTRIES 127 +#define SQUASHFS_META_SLOTS 8 +#define SQUASHFS_SCAN_INDEXES 1024 + +struct meta_entry { + u64 data_block; + unsigned int index_block; + unsigned short offset; + unsigned short pad; +}; + +struct meta_index { + unsigned int inode_number; + unsigned int offset; + unsigned short entries; + unsigned short skip; + unsigned short locked; + unsigned short pad; + struct meta_entry meta_entry[SQUASHFS_META_ENTRIES]; +}; + + +/* + * definitions for structures on disk + */ +#define ZLIB_COMPRESSION 1 +#define LZMA_COMPRESSION 2 +#define LZO_COMPRESSION 3 +#define XZ_COMPRESSION 4 +#define LZ4_COMPRESSION 5 +#define ZSTD_COMPRESSION 6 + +struct squashfs_super_block { + __le32 s_magic; + __le32 inodes; + __le32 mkfs_time; + __le32 block_size; + __le32 fragments; + __le16 compression; + __le16 block_log; + __le16 flags; + __le16 no_ids; + __le16 s_major; + __le16 s_minor; + __le64 root_inode; + __le64 bytes_used; + __le64 id_table_start; + __le64 xattr_id_table_start; + __le64 inode_table_start; + __le64 directory_table_start; + __le64 fragment_table_start; + __le64 lookup_table_start; +}; + +struct squashfs_dir_index { + __le32 index; + __le32 start_block; + __le32 size; + unsigned char name[]; +}; + +struct squashfs_base_inode { + __le16 inode_type; + __le16 mode; + __le16 uid; + __le16 guid; + __le32 mtime; + __le32 inode_number; +}; + +struct squashfs_ipc_inode { + __le16 inode_type; + __le16 mode; + __le16 uid; + __le16 guid; + __le32 mtime; + __le32 inode_number; + __le32 nlink; +}; + +struct squashfs_lipc_inode { + __le16 inode_type; + __le16 mode; + __le16 uid; + __le16 guid; + __le32 mtime; + __le32 inode_number; + __le32 nlink; + __le32 xattr; +}; + +struct squashfs_dev_inode { + __le16 inode_type; + __le16 mode; + __le16 uid; + __le16 guid; + __le32 mtime; + __le32 inode_number; + __le32 nlink; + __le32 rdev; +}; + +struct squashfs_ldev_inode { + __le16 inode_type; + __le16 mode; + __le16 uid; + __le16 guid; + __le32 mtime; + __le32 inode_number; + __le32 nlink; + __le32 rdev; + __le32 xattr; +}; + +struct squashfs_symlink_inode { + __le16 inode_type; + __le16 mode; + __le16 uid; + __le16 guid; + __le32 mtime; + __le32 inode_number; + __le32 nlink; + __le32 symlink_size; + char symlink[]; +}; + +struct squashfs_reg_inode { + __le16 inode_type; + __le16 mode; + __le16 uid; + __le16 guid; + __le32 mtime; + __le32 inode_number; + __le32 start_block; + __le32 fragment; + __le32 offset; + __le32 file_size; + __le16 block_list[]; +}; + +struct squashfs_lreg_inode { + __le16 inode_type; + __le16 mode; + __le16 uid; + __le16 guid; + __le32 mtime; + __le32 inode_number; + __le64 start_block; + __le64 file_size; + __le64 sparse; + __le32 nlink; + __le32 fragment; + __le32 offset; + __le32 xattr; + __le16 block_list[]; +}; + +struct squashfs_dir_inode { + __le16 inode_type; + __le16 mode; + __le16 uid; + __le16 guid; + __le32 mtime; + __le32 inode_number; + __le32 start_block; + __le32 nlink; + __le16 file_size; + __le16 offset; + __le32 parent_inode; +}; + +struct squashfs_ldir_inode { + __le16 inode_type; + __le16 mode; + __le16 uid; + __le16 guid; + __le32 mtime; + __le32 inode_number; + __le32 nlink; + __le32 file_size; + __le32 start_block; + __le32 parent_inode; + __le16 i_count; + __le16 offset; + __le32 xattr; + struct squashfs_dir_index index[]; +}; + +union squashfs_inode { + struct squashfs_base_inode base; + struct squashfs_dev_inode dev; + struct squashfs_ldev_inode ldev; + struct squashfs_symlink_inode symlink; + struct squashfs_reg_inode reg; + struct squashfs_lreg_inode lreg; + struct squashfs_dir_inode dir; + struct squashfs_ldir_inode ldir; + struct squashfs_ipc_inode ipc; + struct squashfs_lipc_inode lipc; +}; + +struct squashfs_dir_entry { + __le16 offset; + __le16 inode_number; + __le16 type; + __le16 size; + char name[]; +}; + +struct squashfs_dir_header { + __le32 count; + __le32 start_block; + __le32 inode_number; +}; + +struct squashfs_fragment_entry { + __le64 start_block; + __le32 size; + unsigned int unused; +}; + +struct squashfs_xattr_entry { + __le16 type; + __le16 size; + char data[]; +}; + +struct squashfs_xattr_val { + __le32 vsize; + char value[]; +}; + +struct squashfs_xattr_id { + __le64 xattr; + __le32 count; + __le32 size; +}; + +struct squashfs_xattr_id_table { + __le64 xattr_table_start; + __le32 xattr_ids; + __le32 unused; +}; + +#endif diff --git a/fs/squashfs/squashfs_fs_i.h b/fs/squashfs/squashfs_fs_i.h new file mode 100644 index 000000000..8e497ac07 --- /dev/null +++ b/fs/squashfs/squashfs_fs_i.h @@ -0,0 +1,41 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +#ifndef SQUASHFS_FS_I +#define SQUASHFS_FS_I +/* + * Squashfs + * + * Copyright (c) 2002, 2003, 2004, 2005, 2006, 2007, 2008 + * Phillip Lougher <phillip@squashfs.org.uk> + * + * squashfs_fs_i.h + */ + +struct squashfs_inode_info { + u64 start; + int offset; + u64 xattr; + unsigned int xattr_size; + int xattr_count; + int parent; + union { + struct { + u64 fragment_block; + int fragment_size; + int fragment_offset; + u64 block_list_start; + }; + struct { + u64 dir_idx_start; + int dir_idx_offset; + int dir_idx_cnt; + }; + }; + struct inode vfs_inode; +}; + + +static inline struct squashfs_inode_info *squashfs_i(struct inode *inode) +{ + return container_of(inode, struct squashfs_inode_info, vfs_inode); +} +#endif diff --git a/fs/squashfs/squashfs_fs_sb.h b/fs/squashfs/squashfs_fs_sb.h new file mode 100644 index 000000000..b87221ea9 --- /dev/null +++ b/fs/squashfs/squashfs_fs_sb.h @@ -0,0 +1,82 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +#ifndef SQUASHFS_FS_SB +#define SQUASHFS_FS_SB +/* + * Squashfs + * + * Copyright (c) 2002, 2003, 2004, 2005, 2006, 2007, 2008 + * Phillip Lougher <phillip@squashfs.org.uk> + * + * squashfs_fs_sb.h + */ + +#include "squashfs_fs.h" + +/* + * Waiters for a cache entry sleep on wait_queue as exclusive waiters, so + * freeing one entry wakes one task. See squashfs_cache_get(). + * + * num_waiters is only a hint used to skip pointless wakeups: it is + * incremented before a task queues itself and decremented after it is woken, + * so it can transiently exceed the number of queued tasks. It never + * undercounts them, which is what the wakeup paths rely on. + */ +struct squashfs_cache { + char *name; + int entries; + int curr_blk; + int next_blk; + int num_waiters; + int unused; + int block_size; + int pages; + spinlock_t lock; + wait_queue_head_t wait_queue; + struct squashfs_cache_entry *entry; +}; + +struct squashfs_cache_entry { + u64 block; + int length; + int refcount; + u64 next_index; + int pending; + int error; + int num_waiters; + wait_queue_head_t wait_queue; + struct squashfs_cache *cache; + void **data; + struct squashfs_page_actor *actor; +}; + +struct squashfs_sb_info { + const struct squashfs_decompressor *decompressor; + int devblksize; + int devblksize_log2; + struct squashfs_cache *block_cache; + struct squashfs_cache *fragment_cache; + struct squashfs_cache *read_page; + struct address_space *cache_mapping; + int next_meta_index; + __le64 *id_table; + __le64 *fragment_index; + __le64 *xattr_id_table; + struct mutex meta_index_mutex; + struct meta_index *meta_index; + void *stream; + __le64 *inode_lookup_table; + u64 inode_table; + u64 directory_table; + u64 xattr_table; + unsigned int block_size; + unsigned short block_log; + long long bytes_used; + unsigned int inodes; + unsigned int fragments; + unsigned int xattr_ids; + unsigned int ids; + bool panic_on_errors; + const struct squashfs_decompressor_thread_ops *thread_ops; + int max_thread_num; +}; +#endif diff --git a/fs/squashfs/super.c b/fs/squashfs/super.c new file mode 100644 index 000000000..5dabc5770 --- /dev/null +++ b/fs/squashfs/super.c @@ -0,0 +1,706 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Squashfs - a compressed read only filesystem for Linux + * + * Copyright (c) 2002, 2003, 2004, 2005, 2006, 2007, 2008 + * Phillip Lougher <phillip@squashfs.org.uk> + * + * super.c + */ + +/* + * This file implements code to read the superblock, read and initialise + * in-memory structures at mount time, and all the VFS glue code to register + * the filesystem. + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include <linux/blkdev.h> +#include <linux/fs.h> +#include <linux/fs_context.h> +#include <linux/fs_parser.h> +#include <linux/vfs.h> +#include <linux/slab.h> +#include <linux/mutex.h> +#include <linux/seq_file.h> +#include <linux/pagemap.h> +#include <linux/init.h> +#include <linux/module.h> +#include <linux/magic.h> +#include <linux/xattr.h> + +#include "squashfs_fs.h" +#include "squashfs_fs_sb.h" +#include "squashfs_fs_i.h" +#include "squashfs.h" +#include "decompressor.h" +#include "xattr.h" + +static struct file_system_type squashfs_fs_type; +static const struct super_operations squashfs_super_ops; + +enum Opt_errors { + Opt_errors_continue, + Opt_errors_panic, +}; + +enum squashfs_param { + Opt_errors, + Opt_threads, +}; + +struct squashfs_mount_opts { + enum Opt_errors errors; + const struct squashfs_decompressor_thread_ops *thread_ops; + int thread_num; +}; + +static const struct constant_table squashfs_param_errors[] = { + {"continue", Opt_errors_continue }, + {"panic", Opt_errors_panic }, + {} +}; + +static const struct fs_parameter_spec squashfs_fs_parameters[] = { + fsparam_enum("errors", Opt_errors, squashfs_param_errors), + fsparam_string("threads", Opt_threads), + {} +}; + + +static int squashfs_parse_param_threads_str(const char *str, struct squashfs_mount_opts *opts) +{ +#ifdef CONFIG_SQUASHFS_CHOICE_DECOMP_BY_MOUNT + if (strcmp(str, "single") == 0) { + opts->thread_ops = &squashfs_decompressor_single; + return 0; + } + if (strcmp(str, "multi") == 0) { + opts->thread_ops = &squashfs_decompressor_multi; + return 0; + } + if (strcmp(str, "percpu") == 0) { + opts->thread_ops = &squashfs_decompressor_percpu; + return 0; + } +#endif + return -EINVAL; +} + +static int squashfs_parse_param_threads_num(const char *str, struct squashfs_mount_opts *opts) +{ +#ifdef CONFIG_SQUASHFS_MOUNT_DECOMP_THREADS + int ret; + unsigned long num; + + ret = kstrtoul(str, 0, &num); + if (ret != 0) + return -EINVAL; + if (num > 1) { + opts->thread_ops = &squashfs_decompressor_multi; + if (num > opts->thread_ops->max_decompressors()) + return -EINVAL; + opts->thread_num = (int)num; + return 0; + } +#ifdef CONFIG_SQUASHFS_DECOMP_SINGLE + if (num == 1) { + opts->thread_ops = &squashfs_decompressor_single; + opts->thread_num = 1; + return 0; + } +#endif +#endif /* !CONFIG_SQUASHFS_MOUNT_DECOMP_THREADS */ + return -EINVAL; +} + +static int squashfs_parse_param_threads(const char *str, struct squashfs_mount_opts *opts) +{ + int ret = squashfs_parse_param_threads_str(str, opts); + + if (ret == 0) + return ret; + return squashfs_parse_param_threads_num(str, opts); +} + +static int squashfs_parse_param(struct fs_context *fc, struct fs_parameter *param) +{ + struct squashfs_mount_opts *opts = fc->fs_private; + struct fs_parse_result result; + int opt; + + opt = fs_parse(fc, squashfs_fs_parameters, param, &result); + if (opt < 0) + return opt; + + switch (opt) { + case Opt_errors: + opts->errors = result.uint_32; + break; + case Opt_threads: + if (squashfs_parse_param_threads(param->string, opts) != 0) + return -EINVAL; + break; + default: + return -EINVAL; + } + + return 0; +} + +static const struct squashfs_decompressor *supported_squashfs_filesystem( + struct fs_context *fc, + short major, short minor, short id) +{ + const struct squashfs_decompressor *decompressor; + + if (major < SQUASHFS_MAJOR) { + errorf(fc, "Major/Minor mismatch, older Squashfs %d.%d " + "filesystems are unsupported", major, minor); + return NULL; + } else if (major > SQUASHFS_MAJOR || minor > SQUASHFS_MINOR) { + errorf(fc, "Major/Minor mismatch, trying to mount newer " + "%d.%d filesystem", major, minor); + errorf(fc, "Please update your kernel"); + return NULL; + } + + decompressor = squashfs_lookup_decompressor(id); + if (!decompressor->supported) { + errorf(fc, "Filesystem uses \"%s\" compression. This is not supported", + decompressor->name); + return NULL; + } + + return decompressor; +} + + +static int squashfs_fill_super(struct super_block *sb, struct fs_context *fc) +{ + struct squashfs_mount_opts *opts = fc->fs_private; + struct squashfs_sb_info *msblk; + struct squashfs_super_block *sblk = NULL; + struct inode *root; + long long root_inode; + unsigned short flags; + unsigned int fragments; + u64 lookup_table_start, xattr_id_table_start, next_table; + int err, devblksize = sb_min_blocksize(sb, SQUASHFS_DEVBLK_SIZE); + + TRACE("Entered squashfs_fill_superblock\n"); + + if (!devblksize) { + errorf(fc, "squashfs: unable to set blocksize\n"); + return -EINVAL; + } + + sb->s_fs_info = kzalloc_obj(*msblk); + if (sb->s_fs_info == NULL) { + ERROR("Failed to allocate squashfs_sb_info\n"); + return -ENOMEM; + } + msblk = sb->s_fs_info; + msblk->thread_ops = opts->thread_ops; + + msblk->panic_on_errors = (opts->errors == Opt_errors_panic); + + msblk->devblksize = devblksize; + msblk->devblksize_log2 = ffz(~msblk->devblksize); + + mutex_init(&msblk->meta_index_mutex); + + /* + * msblk->bytes_used is checked in squashfs_read_table to ensure reads + * are not beyond filesystem end. But as we're using + * squashfs_read_table here to read the superblock (including the value + * of bytes_used) we need to set it to an initial sensible dummy value + */ + msblk->bytes_used = sizeof(*sblk); + sblk = squashfs_read_table(sb, SQUASHFS_START, sizeof(*sblk)); + + if (IS_ERR(sblk)) { + errorf(fc, "unable to read squashfs_super_block"); + err = PTR_ERR(sblk); + sblk = NULL; + goto failed_mount; + } + + err = -EINVAL; + + /* Check it is a SQUASHFS superblock */ + sb->s_magic = le32_to_cpu(sblk->s_magic); + if (sb->s_magic != SQUASHFS_MAGIC) { + if (!(fc->sb_flags & SB_SILENT)) + errorf(fc, "Can't find a SQUASHFS superblock on %pg", + sb->s_bdev); + goto failed_mount; + } + + if (opts->thread_num == 0) { + msblk->max_thread_num = msblk->thread_ops->max_decompressors(); + } else { + msblk->max_thread_num = opts->thread_num; + } + + /* Check the MAJOR & MINOR versions and lookup compression type */ + msblk->decompressor = supported_squashfs_filesystem( + fc, + le16_to_cpu(sblk->s_major), + le16_to_cpu(sblk->s_minor), + le16_to_cpu(sblk->compression)); + if (msblk->decompressor == NULL) + goto failed_mount; + + /* Check the filesystem does not extend beyond the end of the + block device */ + msblk->bytes_used = le64_to_cpu(sblk->bytes_used); + if (msblk->bytes_used < 0 || + msblk->bytes_used > bdev_nr_bytes(sb->s_bdev)) + goto failed_mount; + + /* Check block size for sanity */ + msblk->block_size = le32_to_cpu(sblk->block_size); + if (msblk->block_size > SQUASHFS_FILE_MAX_SIZE) + goto insanity; + + /* + * Check the system page size is not larger than the filesystem + * block size (by default 128K). This is currently not supported. + */ + if (PAGE_SIZE > msblk->block_size) { + errorf(fc, "Page size > filesystem block size (%d). This is " + "currently not supported!", msblk->block_size); + goto failed_mount; + } + + /* Check block log for sanity */ + msblk->block_log = le16_to_cpu(sblk->block_log); + if (msblk->block_log > SQUASHFS_FILE_MAX_LOG) + goto failed_mount; + + /* Check that block_size and block_log match */ + if (msblk->block_size != (1 << msblk->block_log)) + goto insanity; + + /* Check the root inode for sanity */ + root_inode = le64_to_cpu(sblk->root_inode); + if (SQUASHFS_INODE_OFFSET(root_inode) > SQUASHFS_METADATA_SIZE) + goto insanity; + + msblk->inode_table = le64_to_cpu(sblk->inode_table_start); + msblk->directory_table = le64_to_cpu(sblk->directory_table_start); + msblk->inodes = le32_to_cpu(sblk->inodes); + msblk->fragments = le32_to_cpu(sblk->fragments); + msblk->ids = le16_to_cpu(sblk->no_ids); + flags = le16_to_cpu(sblk->flags); + + TRACE("Found valid superblock on %pg\n", sb->s_bdev); + TRACE("Inodes are %scompressed\n", SQUASHFS_UNCOMPRESSED_INODES(flags) + ? "un" : ""); + TRACE("Data is %scompressed\n", SQUASHFS_UNCOMPRESSED_DATA(flags) + ? "un" : ""); + TRACE("Filesystem size %lld bytes\n", msblk->bytes_used); + TRACE("Block size %d\n", msblk->block_size); + TRACE("Number of inodes %d\n", msblk->inodes); + TRACE("Number of fragments %d\n", msblk->fragments); + TRACE("Number of ids %d\n", msblk->ids); + TRACE("sblk->inode_table_start %llx\n", msblk->inode_table); + TRACE("sblk->directory_table_start %llx\n", msblk->directory_table); + TRACE("sblk->fragment_table_start %llx\n", + (u64) le64_to_cpu(sblk->fragment_table_start)); + TRACE("sblk->id_table_start %llx\n", + (u64) le64_to_cpu(sblk->id_table_start)); + + sb->s_maxbytes = MAX_LFS_FILESIZE; + sb->s_time_min = 0; + sb->s_time_max = U32_MAX; + sb->s_flags |= SB_RDONLY; + sb->s_op = &squashfs_super_ops; + + msblk->block_cache = squashfs_cache_init("metadata", + SQUASHFS_CACHED_BLKS, SQUASHFS_METADATA_SIZE); + if (IS_ERR(msblk->block_cache)) { + err = PTR_ERR(msblk->block_cache); + goto failed_mount; + } + + /* Allocate read_page block */ + msblk->read_page = squashfs_cache_init("data", + SQUASHFS_READ_PAGES, msblk->block_size); + if (IS_ERR(msblk->read_page)) { + errorf(fc, "Failed to allocate read_page block"); + err = PTR_ERR(msblk->read_page); + goto failed_mount; + } + + if (msblk->devblksize == PAGE_SIZE) { + struct inode *cache = new_inode(sb); + + if (cache == NULL) { + err = -ENOMEM; + goto failed_mount; + } + + set_nlink(cache, 1); + cache->i_size = OFFSET_MAX; + mapping_set_gfp_mask(cache->i_mapping, GFP_NOFS); + + msblk->cache_mapping = cache->i_mapping; + } + + msblk->stream = squashfs_decompressor_setup(sb, flags); + if (IS_ERR(msblk->stream)) { + err = PTR_ERR(msblk->stream); + msblk->stream = NULL; + goto insanity; + } + + /* Handle xattrs */ + sb->s_xattr = squashfs_xattr_handlers; + xattr_id_table_start = le64_to_cpu(sblk->xattr_id_table_start); + if (xattr_id_table_start == SQUASHFS_INVALID_BLK) { + next_table = msblk->bytes_used; + goto allocate_id_index_table; + } + + /* Allocate and read xattr id lookup table */ + msblk->xattr_id_table = squashfs_read_xattr_id_table(sb, + xattr_id_table_start, &msblk->xattr_table, &msblk->xattr_ids); + if (IS_ERR(msblk->xattr_id_table)) { + errorf(fc, "unable to read xattr id index table"); + err = PTR_ERR(msblk->xattr_id_table); + msblk->xattr_id_table = NULL; + if (err != -ENOTSUPP) + goto failed_mount; + } + next_table = msblk->xattr_table; + +allocate_id_index_table: + /* Allocate and read id index table */ + msblk->id_table = squashfs_read_id_index_table(sb, + le64_to_cpu(sblk->id_table_start), next_table, msblk->ids); + if (IS_ERR(msblk->id_table)) { + errorf(fc, "unable to read id index table"); + err = PTR_ERR(msblk->id_table); + msblk->id_table = NULL; + goto failed_mount; + } + next_table = le64_to_cpu(msblk->id_table[0]); + + /* Handle inode lookup table */ + lookup_table_start = le64_to_cpu(sblk->lookup_table_start); + if (lookup_table_start == SQUASHFS_INVALID_BLK) + goto handle_fragments; + + /* Allocate and read inode lookup table */ + msblk->inode_lookup_table = squashfs_read_inode_lookup_table(sb, + lookup_table_start, next_table, msblk->inodes); + if (IS_ERR(msblk->inode_lookup_table)) { + errorf(fc, "unable to read inode lookup table"); + err = PTR_ERR(msblk->inode_lookup_table); + msblk->inode_lookup_table = NULL; + goto failed_mount; + } + next_table = le64_to_cpu(msblk->inode_lookup_table[0]); + + sb->s_export_op = &squashfs_export_ops; + +handle_fragments: + fragments = msblk->fragments; + if (fragments == 0) + goto check_directory_table; + + msblk->fragment_cache = squashfs_cache_init("fragment", + min(SQUASHFS_CACHED_FRAGMENTS, fragments), msblk->block_size); + if (IS_ERR(msblk->fragment_cache)) { + err = PTR_ERR(msblk->fragment_cache); + goto failed_mount; + } + + /* Allocate and read fragment index table */ + msblk->fragment_index = squashfs_read_fragment_index_table(sb, + le64_to_cpu(sblk->fragment_table_start), next_table, fragments); + if (IS_ERR(msblk->fragment_index)) { + errorf(fc, "unable to read fragment index table"); + err = PTR_ERR(msblk->fragment_index); + msblk->fragment_index = NULL; + goto failed_mount; + } + next_table = le64_to_cpu(msblk->fragment_index[0]); + +check_directory_table: + /* Sanity check directory_table */ + if (msblk->directory_table > next_table) { + err = -EINVAL; + goto insanity; + } + + /* Sanity check inode_table */ + if (msblk->inode_table >= msblk->directory_table) { + err = -EINVAL; + goto insanity; + } + + /* allocate root */ + root = new_inode(sb); + if (!root) { + err = -ENOMEM; + goto failed_mount; + } + + err = squashfs_read_inode(root, root_inode); + if (err) { + make_bad_inode(root); + iput(root); + goto failed_mount; + } + insert_inode_hash(root); + + sb->s_root = d_make_root(root); + if (sb->s_root == NULL) { + ERROR("Root inode create failed\n"); + err = -ENOMEM; + goto failed_mount; + } + + TRACE("Leaving squashfs_fill_super\n"); + kfree(sblk); + return 0; + +insanity: + errorf(fc, "squashfs image failed sanity check"); +failed_mount: + squashfs_cache_delete(msblk->block_cache); + squashfs_cache_delete(msblk->fragment_cache); + squashfs_cache_delete(msblk->read_page); + if (msblk->cache_mapping) + iput(msblk->cache_mapping->host); + msblk->thread_ops->destroy(msblk); + kfree(msblk->inode_lookup_table); + kfree(msblk->fragment_index); + kfree(msblk->id_table); + kfree(msblk->xattr_id_table); + kfree(sb->s_fs_info); + sb->s_fs_info = NULL; + kfree(sblk); + return err; +} + +static int squashfs_get_tree(struct fs_context *fc) +{ + return get_tree_bdev(fc, squashfs_fill_super); +} + +static int squashfs_reconfigure(struct fs_context *fc) +{ + struct super_block *sb = fc->root->d_sb; + struct squashfs_sb_info *msblk = sb->s_fs_info; + struct squashfs_mount_opts *opts = fc->fs_private; + + sync_filesystem(fc->root->d_sb); + fc->sb_flags |= SB_RDONLY; + + msblk->panic_on_errors = (opts->errors == Opt_errors_panic); + + return 0; +} + +static void squashfs_free_fs_context(struct fs_context *fc) +{ + kfree(fc->fs_private); +} + +static const struct fs_context_operations squashfs_context_ops = { + .get_tree = squashfs_get_tree, + .free = squashfs_free_fs_context, + .parse_param = squashfs_parse_param, + .reconfigure = squashfs_reconfigure, +}; + +static int squashfs_show_options(struct seq_file *s, struct dentry *root) +{ + struct super_block *sb = root->d_sb; + struct squashfs_sb_info *msblk = sb->s_fs_info; + + if (msblk->panic_on_errors) + seq_puts(s, ",errors=panic"); + else + seq_puts(s, ",errors=continue"); + +#ifdef CONFIG_SQUASHFS_CHOICE_DECOMP_BY_MOUNT + if (msblk->thread_ops == &squashfs_decompressor_single) { + seq_puts(s, ",threads=single"); + return 0; + } + if (msblk->thread_ops == &squashfs_decompressor_percpu) { + seq_puts(s, ",threads=percpu"); + return 0; + } +#endif +#ifdef CONFIG_SQUASHFS_MOUNT_DECOMP_THREADS + seq_printf(s, ",threads=%d", msblk->max_thread_num); +#endif + return 0; +} + +static int squashfs_init_fs_context(struct fs_context *fc) +{ + struct squashfs_mount_opts *opts; + + opts = kzalloc_obj(*opts); + if (!opts) + return -ENOMEM; + +#ifdef CONFIG_SQUASHFS_DECOMP_SINGLE + opts->thread_ops = &squashfs_decompressor_single; +#elif defined(CONFIG_SQUASHFS_DECOMP_MULTI) + opts->thread_ops = &squashfs_decompressor_multi; +#elif defined(CONFIG_SQUASHFS_DECOMP_MULTI_PERCPU) + opts->thread_ops = &squashfs_decompressor_percpu; +#else +#error "fail: unknown squashfs decompression thread mode?" +#endif + opts->thread_num = 0; + fc->fs_private = opts; + fc->ops = &squashfs_context_ops; + return 0; +} + +static int squashfs_statfs(struct dentry *dentry, struct kstatfs *buf) +{ + struct squashfs_sb_info *msblk = dentry->d_sb->s_fs_info; + u64 id = huge_encode_dev(dentry->d_sb->s_bdev->bd_dev); + + TRACE("Entered squashfs_statfs\n"); + + buf->f_type = SQUASHFS_MAGIC; + buf->f_bsize = msblk->block_size; + buf->f_blocks = ((msblk->bytes_used - 1) >> msblk->block_log) + 1; + buf->f_bfree = buf->f_bavail = 0; + buf->f_files = msblk->inodes; + buf->f_ffree = 0; + buf->f_namelen = SQUASHFS_NAME_LEN; + buf->f_fsid = u64_to_fsid(id); + + return 0; +} + + +static void squashfs_put_super(struct super_block *sb) +{ + if (sb->s_fs_info) { + struct squashfs_sb_info *sbi = sb->s_fs_info; + squashfs_cache_delete(sbi->block_cache); + squashfs_cache_delete(sbi->fragment_cache); + squashfs_cache_delete(sbi->read_page); + if (sbi->cache_mapping) + iput(sbi->cache_mapping->host); + sbi->thread_ops->destroy(sbi); + kfree(sbi->id_table); + kfree(sbi->fragment_index); + kfree(sbi->meta_index); + kfree(sbi->inode_lookup_table); + kfree(sbi->xattr_id_table); + kfree(sb->s_fs_info); + sb->s_fs_info = NULL; + } +} + +static struct kmem_cache *squashfs_inode_cachep; + + +static void init_once(void *foo) +{ + struct squashfs_inode_info *ei = foo; + + inode_init_once(&ei->vfs_inode); +} + + +static int __init init_inodecache(void) +{ + squashfs_inode_cachep = kmem_cache_create("squashfs_inode_cache", + sizeof(struct squashfs_inode_info), 0, + SLAB_HWCACHE_ALIGN|SLAB_RECLAIM_ACCOUNT|SLAB_ACCOUNT, + init_once); + + return squashfs_inode_cachep ? 0 : -ENOMEM; +} + + +static void destroy_inodecache(void) +{ + /* + * Make sure all delayed rcu free inodes are flushed before we + * destroy cache. + */ + rcu_barrier(); + kmem_cache_destroy(squashfs_inode_cachep); +} + + +static int __init init_squashfs_fs(void) +{ + int err = init_inodecache(); + + if (err) + return err; + + err = register_filesystem(&squashfs_fs_type); + if (err) { + destroy_inodecache(); + return err; + } + + pr_info("version 4.0 (2009/01/31) Phillip Lougher\n"); + + return 0; +} + + +static void __exit exit_squashfs_fs(void) +{ + unregister_filesystem(&squashfs_fs_type); + destroy_inodecache(); +} + + +static struct inode *squashfs_alloc_inode(struct super_block *sb) +{ + struct squashfs_inode_info *ei = + alloc_inode_sb(sb, squashfs_inode_cachep, GFP_KERNEL); + + return ei ? &ei->vfs_inode : NULL; +} + + +static void squashfs_free_inode(struct inode *inode) +{ + kmem_cache_free(squashfs_inode_cachep, squashfs_i(inode)); +} + +static struct file_system_type squashfs_fs_type = { + .owner = THIS_MODULE, + .name = "squashfs", + .init_fs_context = squashfs_init_fs_context, + .parameters = squashfs_fs_parameters, + .kill_sb = kill_block_super, + .fs_flags = FS_REQUIRES_DEV | FS_ALLOW_IDMAP, +}; +MODULE_ALIAS_FS("squashfs"); + +static const struct super_operations squashfs_super_ops = { + .alloc_inode = squashfs_alloc_inode, + .free_inode = squashfs_free_inode, + .statfs = squashfs_statfs, + .put_super = squashfs_put_super, + .show_options = squashfs_show_options, +}; + +module_init(init_squashfs_fs); +module_exit(exit_squashfs_fs); +MODULE_DESCRIPTION("squashfs 4.0, a compressed read-only filesystem"); +MODULE_AUTHOR("Phillip Lougher <phillip@squashfs.org.uk>"); +MODULE_LICENSE("GPL"); diff --git a/fs/squashfs/symlink.c b/fs/squashfs/symlink.c new file mode 100644 index 000000000..6ef735bd8 --- /dev/null +++ b/fs/squashfs/symlink.c @@ -0,0 +1,109 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Squashfs - a compressed read only filesystem for Linux + * + * Copyright (c) 2002, 2003, 2004, 2005, 2006, 2007, 2008 + * Phillip Lougher <phillip@squashfs.org.uk> + * + * symlink.c + */ + +/* + * This file implements code to handle symbolic links. + * + * The data contents of symbolic links are stored inside the symbolic + * link inode within the inode table. This allows the normally small symbolic + * link to be compressed as part of the inode table, achieving much greater + * compression than if the symbolic link was compressed individually. + */ + +#include <linux/fs.h> +#include <linux/vfs.h> +#include <linux/kernel.h> +#include <linux/string.h> +#include <linux/pagemap.h> +#include <linux/xattr.h> + +#include "squashfs_fs.h" +#include "squashfs_fs_sb.h" +#include "squashfs_fs_i.h" +#include "squashfs.h" +#include "xattr.h" + +static int squashfs_symlink_read_folio(struct file *file, struct folio *folio) +{ + struct inode *inode = folio->mapping->host; + struct super_block *sb = inode->i_sb; + struct squashfs_sb_info *msblk = sb->s_fs_info; + int index = folio_pos(folio); + u64 block = squashfs_i(inode)->start; + int offset = squashfs_i(inode)->offset; + int length = min_t(int, i_size_read(inode) - index, PAGE_SIZE); + int bytes, copied, error; + void *pageaddr; + struct squashfs_cache_entry *entry; + + TRACE("Entered squashfs_symlink_readpage, page index %ld, start block " + "%llx, offset %x\n", folio->index, block, offset); + + /* + * Skip index bytes into symlink metadata. + */ + if (index) { + bytes = squashfs_read_metadata(sb, NULL, &block, &offset, + index); + if (bytes < 0) { + ERROR("Unable to read symlink [%llx:%x]\n", + squashfs_i(inode)->start, + squashfs_i(inode)->offset); + error = bytes; + goto out; + } + } + + /* + * Read length bytes from symlink metadata. Squashfs_read_metadata + * is not used here because it can sleep and we want to use + * kmap_local to map the folio. Instead call the underlying + * squashfs_cache_get routine. As length bytes may overlap metadata + * blocks, we may need to call squashfs_cache_get multiple times. + */ + for (bytes = 0; bytes < length; offset = 0, bytes += copied) { + entry = squashfs_cache_get(sb, msblk->block_cache, block, 0); + if (entry->error) { + ERROR("Unable to read symlink [%llx:%x]\n", + squashfs_i(inode)->start, + squashfs_i(inode)->offset); + squashfs_cache_put(entry); + error = entry->error; + goto out; + } + + pageaddr = kmap_local_folio(folio, 0); + copied = squashfs_copy_data(pageaddr + bytes, entry, offset, + length - bytes); + if (copied == length - bytes) + memset(pageaddr + length, 0, PAGE_SIZE - length); + else + block = entry->next_index; + kunmap_local(pageaddr); + squashfs_cache_put(entry); + } + + flush_dcache_folio(folio); + error = 0; +out: + folio_end_read(folio, error == 0); + return error; +} + + +const struct address_space_operations squashfs_symlink_aops = { + .read_folio = squashfs_symlink_read_folio +}; + +const struct inode_operations squashfs_symlink_inode_ops = { + .get_link = page_get_link, + .listxattr = squashfs_listxattr +}; + diff --git a/fs/squashfs/xattr.c b/fs/squashfs/xattr.c new file mode 100644 index 000000000..ce6608cab --- /dev/null +++ b/fs/squashfs/xattr.c @@ -0,0 +1,271 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Squashfs - a compressed read only filesystem for Linux + * + * Copyright (c) 2010 + * Phillip Lougher <phillip@squashfs.org.uk> + * + * xattr.c + */ + +#include <linux/init.h> +#include <linux/module.h> +#include <linux/string.h> +#include <linux/fs.h> +#include <linux/vfs.h> +#include <linux/xattr.h> +#include <linux/slab.h> + +#include "squashfs_fs.h" +#include "squashfs_fs_sb.h" +#include "squashfs_fs_i.h" +#include "squashfs.h" + +static const struct xattr_handler *squashfs_xattr_handler(int); + +ssize_t squashfs_listxattr(struct dentry *d, char *buffer, + size_t buffer_size) +{ + struct inode *inode = d_inode(d); + struct super_block *sb = inode->i_sb; + struct squashfs_sb_info *msblk = sb->s_fs_info; + u64 start = SQUASHFS_XATTR_BLK(squashfs_i(inode)->xattr) + + msblk->xattr_table; + int offset = SQUASHFS_XATTR_OFFSET(squashfs_i(inode)->xattr); + int count = squashfs_i(inode)->xattr_count; + size_t rest = buffer_size; + int err; + + /* check that the file system has xattrs */ + if (msblk->xattr_id_table == NULL) + return -EOPNOTSUPP; + + /* loop reading each xattr name */ + while (count--) { + struct squashfs_xattr_entry entry; + struct squashfs_xattr_val val; + const struct xattr_handler *handler; + int name_size; + + err = squashfs_read_metadata(sb, &entry, &start, &offset, + sizeof(entry)); + if (err < 0) + goto failed; + + name_size = le16_to_cpu(entry.size); + handler = squashfs_xattr_handler(le16_to_cpu(entry.type)); + if (handler && (!handler->list || handler->list(d))) { + const char *prefix = handler->prefix ?: handler->name; + size_t prefix_size = strlen(prefix); + + if (buffer) { + if (prefix_size + name_size + 1 > rest) { + err = -ERANGE; + goto failed; + } + memcpy(buffer, prefix, prefix_size); + buffer += prefix_size; + } + err = squashfs_read_metadata(sb, buffer, &start, + &offset, name_size); + if (err < 0) + goto failed; + if (buffer) { + buffer[name_size] = '\0'; + buffer += name_size + 1; + } + rest -= prefix_size + name_size + 1; + } else { + /* no handler or insuffficient privileges, so skip */ + err = squashfs_read_metadata(sb, NULL, &start, + &offset, name_size); + if (err < 0) + goto failed; + } + + + /* skip remaining xattr entry */ + err = squashfs_read_metadata(sb, &val, &start, &offset, + sizeof(val)); + if (err < 0) + goto failed; + + err = squashfs_read_metadata(sb, NULL, &start, &offset, + le32_to_cpu(val.vsize)); + if (err < 0) + goto failed; + } + err = buffer_size - rest; + +failed: + return err; +} + + +static int squashfs_xattr_get(struct inode *inode, int name_index, + const char *name, void *buffer, size_t buffer_size) +{ + struct super_block *sb = inode->i_sb; + struct squashfs_sb_info *msblk = sb->s_fs_info; + u64 start = SQUASHFS_XATTR_BLK(squashfs_i(inode)->xattr) + + msblk->xattr_table; + int offset = SQUASHFS_XATTR_OFFSET(squashfs_i(inode)->xattr); + int count = squashfs_i(inode)->xattr_count; + int name_len = strlen(name); + int err, vsize; + char *target = kmalloc(name_len, GFP_KERNEL); + + if (target == NULL) + return -ENOMEM; + + /* loop reading each xattr name */ + for (; count; count--) { + struct squashfs_xattr_entry entry; + struct squashfs_xattr_val val; + int type, prefix, name_size; + + err = squashfs_read_metadata(sb, &entry, &start, &offset, + sizeof(entry)); + if (err < 0) + goto failed; + + name_size = le16_to_cpu(entry.size); + type = le16_to_cpu(entry.type); + prefix = type & SQUASHFS_XATTR_PREFIX_MASK; + + if (prefix == name_index && name_size == name_len) + err = squashfs_read_metadata(sb, target, &start, + &offset, name_size); + else + err = squashfs_read_metadata(sb, NULL, &start, + &offset, name_size); + if (err < 0) + goto failed; + + if (prefix == name_index && name_size == name_len && + strncmp(target, name, name_size) == 0) { + /* found xattr */ + if (type & SQUASHFS_XATTR_VALUE_OOL) { + __le64 xattr_val; + u64 xattr; + /* val is a reference to the real location */ + err = squashfs_read_metadata(sb, &val, &start, + &offset, sizeof(val)); + if (err < 0) + goto failed; + err = squashfs_read_metadata(sb, &xattr_val, + &start, &offset, sizeof(xattr_val)); + if (err < 0) + goto failed; + xattr = le64_to_cpu(xattr_val); + start = SQUASHFS_XATTR_BLK(xattr) + + msblk->xattr_table; + offset = SQUASHFS_XATTR_OFFSET(xattr); + } + /* read xattr value */ + err = squashfs_read_metadata(sb, &val, &start, &offset, + sizeof(val)); + if (err < 0) + goto failed; + + vsize = le32_to_cpu(val.vsize); + if (buffer) { + if (vsize > buffer_size) { + err = -ERANGE; + goto failed; + } + err = squashfs_read_metadata(sb, buffer, &start, + &offset, vsize); + if (err < 0) + goto failed; + } + break; + } + + /* no match, skip remaining xattr entry */ + err = squashfs_read_metadata(sb, &val, &start, &offset, + sizeof(val)); + if (err < 0) + goto failed; + err = squashfs_read_metadata(sb, NULL, &start, &offset, + le32_to_cpu(val.vsize)); + if (err < 0) + goto failed; + } + err = count ? vsize : -ENODATA; + +failed: + kfree(target); + return err; +} + + +static int squashfs_xattr_handler_get(const struct xattr_handler *handler, + struct dentry *unused, + struct inode *inode, + const char *name, + void *buffer, size_t size) +{ + return squashfs_xattr_get(inode, handler->flags, name, + buffer, size); +} + +/* + * User namespace support + */ +static const struct xattr_handler squashfs_xattr_user_handler = { + .prefix = XATTR_USER_PREFIX, + .flags = SQUASHFS_XATTR_USER, + .get = squashfs_xattr_handler_get +}; + +/* + * Trusted namespace support + */ +static bool squashfs_trusted_xattr_handler_list(struct dentry *d) +{ + return capable(CAP_SYS_ADMIN); +} + +static const struct xattr_handler squashfs_xattr_trusted_handler = { + .prefix = XATTR_TRUSTED_PREFIX, + .flags = SQUASHFS_XATTR_TRUSTED, + .list = squashfs_trusted_xattr_handler_list, + .get = squashfs_xattr_handler_get +}; + +/* + * Security namespace support + */ +static const struct xattr_handler squashfs_xattr_security_handler = { + .prefix = XATTR_SECURITY_PREFIX, + .flags = SQUASHFS_XATTR_SECURITY, + .get = squashfs_xattr_handler_get +}; + +static const struct xattr_handler *squashfs_xattr_handler(int type) +{ + if (type & ~(SQUASHFS_XATTR_PREFIX_MASK | SQUASHFS_XATTR_VALUE_OOL)) + /* ignore unrecognised type */ + return NULL; + + switch (type & SQUASHFS_XATTR_PREFIX_MASK) { + case SQUASHFS_XATTR_USER: + return &squashfs_xattr_user_handler; + case SQUASHFS_XATTR_TRUSTED: + return &squashfs_xattr_trusted_handler; + case SQUASHFS_XATTR_SECURITY: + return &squashfs_xattr_security_handler; + default: + /* ignore unrecognised type */ + return NULL; + } +} + +const struct xattr_handler * const squashfs_xattr_handlers[] = { + &squashfs_xattr_user_handler, + &squashfs_xattr_trusted_handler, + &squashfs_xattr_security_handler, + NULL +}; + diff --git a/fs/squashfs/xattr.h b/fs/squashfs/xattr.h new file mode 100644 index 000000000..f1a463d8b --- /dev/null +++ b/fs/squashfs/xattr.h @@ -0,0 +1,41 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Squashfs - a compressed read only filesystem for Linux + * + * Copyright (c) 2010 + * Phillip Lougher <phillip@squashfs.org.uk> + * + * xattr.h + */ + +#ifdef CONFIG_SQUASHFS_XATTR +extern __le64 *squashfs_read_xattr_id_table(struct super_block *, u64, + u64 *, unsigned int *); +extern int squashfs_xattr_lookup(struct super_block *, unsigned int, int *, + unsigned int *, unsigned long long *); +#else +static inline __le64 *squashfs_read_xattr_id_table(struct super_block *sb, + u64 start, u64 *xattr_table_start, unsigned int *xattr_ids) +{ + struct squashfs_xattr_id_table *id_table; + + id_table = squashfs_read_table(sb, start, sizeof(*id_table)); + if (IS_ERR(id_table)) + return (__le64 *) id_table; + + *xattr_table_start = le64_to_cpu(id_table->xattr_table_start); + kfree(id_table); + + ERROR("Xattrs in filesystem, these will be ignored\n"); + return ERR_PTR(-ENOTSUPP); +} + +static inline int squashfs_xattr_lookup(struct super_block *sb, + unsigned int index, int *count, unsigned int *size, + unsigned long long *xattr) +{ + return 0; +} +#define squashfs_listxattr NULL +#define squashfs_xattr_handlers NULL +#endif diff --git a/fs/squashfs/xattr_id.c b/fs/squashfs/xattr_id.c new file mode 100644 index 000000000..c8469c656 --- /dev/null +++ b/fs/squashfs/xattr_id.c @@ -0,0 +1,132 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Squashfs - a compressed read only filesystem for Linux + * + * Copyright (c) 2010 + * Phillip Lougher <phillip@squashfs.org.uk> + * + * xattr_id.c + */ + +/* + * This file implements code to map the 32-bit xattr id stored in the inode + * into the on disk location of the xattr data. + */ + +#include <linux/fs.h> +#include <linux/vfs.h> +#include <linux/slab.h> + +#include "squashfs_fs.h" +#include "squashfs_fs_sb.h" +#include "squashfs.h" +#include "xattr.h" + +/* + * Map xattr id using the xattr id look up table + */ +int squashfs_xattr_lookup(struct super_block *sb, unsigned int index, + int *count, unsigned int *size, unsigned long long *xattr) +{ + struct squashfs_sb_info *msblk = sb->s_fs_info; + int block = SQUASHFS_XATTR_BLOCK(index); + int offset = SQUASHFS_XATTR_BLOCK_OFFSET(index); + u64 start_block; + struct squashfs_xattr_id id; + int err; + + if (index >= msblk->xattr_ids) + return -EINVAL; + + start_block = le64_to_cpu(msblk->xattr_id_table[block]); + + err = squashfs_read_metadata(sb, &id, &start_block, &offset, + sizeof(id)); + if (err < 0) + return err; + + *xattr = le64_to_cpu(id.xattr); + *size = le32_to_cpu(id.size); + *count = le32_to_cpu(id.count); + return 0; +} + + +/* + * Read uncompressed xattr id lookup table indexes from disk into memory + */ +__le64 *squashfs_read_xattr_id_table(struct super_block *sb, u64 table_start, + u64 *xattr_table_start, unsigned int *xattr_ids) +{ + struct squashfs_sb_info *msblk = sb->s_fs_info; + unsigned int len, indexes; + struct squashfs_xattr_id_table *id_table; + __le64 *table; + u64 start, end; + int n; + + id_table = squashfs_read_table(sb, table_start, sizeof(*id_table)); + if (IS_ERR(id_table)) + return (__le64 *) id_table; + + *xattr_table_start = le64_to_cpu(id_table->xattr_table_start); + *xattr_ids = le32_to_cpu(id_table->xattr_ids); + kfree(id_table); + + /* Sanity check values */ + + /* there is always at least one xattr id */ + if (*xattr_ids == 0) + return ERR_PTR(-EINVAL); + + len = SQUASHFS_XATTR_BLOCK_BYTES(*xattr_ids); + indexes = SQUASHFS_XATTR_BLOCKS(*xattr_ids); + + /* + * The computed size of the index table (len bytes) should exactly + * match the table start and end points + */ + start = table_start + sizeof(*id_table); + end = msblk->bytes_used; + + if (len != (end - start)) + return ERR_PTR(-EINVAL); + + table = squashfs_read_table(sb, start, len); + if (IS_ERR(table)) + return table; + + /* table[0], table[1], ... table[indexes - 1] store the locations + * of the compressed xattr id blocks. Each entry should be less than + * the next (i.e. table[0] < table[1]), and the difference between them + * should be SQUASHFS_METADATA_SIZE or less. table[indexes - 1] + * should be less than table_start, and again the difference + * shouls be SQUASHFS_METADATA_SIZE or less. + * + * Finally xattr_table_start should be less than table[0]. + */ + for (n = 0; n < (indexes - 1); n++) { + start = le64_to_cpu(table[n]); + end = le64_to_cpu(table[n + 1]); + + if (start >= end || (end - start) > + (SQUASHFS_METADATA_SIZE + SQUASHFS_BLOCK_OFFSET)) { + kfree(table); + return ERR_PTR(-EINVAL); + } + } + + start = le64_to_cpu(table[indexes - 1]); + if (start >= table_start || (table_start - start) > + (SQUASHFS_METADATA_SIZE + SQUASHFS_BLOCK_OFFSET)) { + kfree(table); + return ERR_PTR(-EINVAL); + } + + if (*xattr_table_start >= le64_to_cpu(table[0])) { + kfree(table); + return ERR_PTR(-EINVAL); + } + + return table; +} diff --git a/fs/squashfs/xz_wrapper.c b/fs/squashfs/xz_wrapper.c new file mode 100644 index 000000000..0a4ff3ec9 --- /dev/null +++ b/fs/squashfs/xz_wrapper.c @@ -0,0 +1,196 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Squashfs - a compressed read only filesystem for Linux + * + * Copyright (c) 2002, 2003, 2004, 2005, 2006, 2007, 2008, 2009, 2010 + * Phillip Lougher <phillip@squashfs.org.uk> + * + * xz_wrapper.c + */ + + +#include <linux/mutex.h> +#include <linux/bio.h> +#include <linux/slab.h> +#include <linux/xz.h> +#include <linux/bitops.h> + +#include "squashfs_fs.h" +#include "squashfs_fs_sb.h" +#include "squashfs.h" +#include "decompressor.h" +#include "page_actor.h" + +struct squashfs_xz { + struct xz_dec *state; + struct xz_buf buf; +}; + +struct disk_comp_opts { + __le32 dictionary_size; + __le32 flags; +}; + +struct comp_opts { + int dict_size; +}; + +static void *squashfs_xz_comp_opts(struct squashfs_sb_info *msblk, + void *buff, int len) +{ + struct disk_comp_opts *comp_opts = buff; + struct comp_opts *opts; + int err = 0, n; + + opts = kmalloc_obj(*opts); + if (opts == NULL) { + err = -ENOMEM; + goto out2; + } + + if (comp_opts) { + /* check compressor options are the expected length */ + if (len < sizeof(*comp_opts)) { + err = -EIO; + goto out; + } + + opts->dict_size = le32_to_cpu(comp_opts->dictionary_size); + + /* the dictionary size should be 2^n or 2^n+2^(n+1) */ + n = ffs(opts->dict_size) - 1; + if (opts->dict_size != (1 << n) && opts->dict_size != (1 << n) + + (1 << (n + 1))) { + err = -EIO; + goto out; + } + } else + /* use defaults */ + opts->dict_size = max_t(int, msblk->block_size, + SQUASHFS_METADATA_SIZE); + + return opts; + +out: + kfree(opts); +out2: + return ERR_PTR(err); +} + + +static void *squashfs_xz_init(struct squashfs_sb_info *msblk, void *buff) +{ + struct comp_opts *comp_opts = buff; + struct squashfs_xz *stream; + int err; + + stream = kmalloc_obj(*stream); + if (stream == NULL) { + err = -ENOMEM; + goto failed; + } + + stream->state = xz_dec_init(XZ_PREALLOC, comp_opts->dict_size); + if (stream->state == NULL) { + kfree(stream); + err = -ENOMEM; + goto failed; + } + + return stream; + +failed: + ERROR("Failed to initialise xz decompressor\n"); + return ERR_PTR(err); +} + + +static void squashfs_xz_free(void *strm) +{ + struct squashfs_xz *stream = strm; + + if (stream) { + xz_dec_end(stream->state); + kfree(stream); + } +} + + +static int squashfs_xz_uncompress(struct squashfs_sb_info *msblk, void *strm, + struct bio *bio, int offset, int length, + struct squashfs_page_actor *output) +{ + struct bvec_iter_all iter_all = {}; + struct bio_vec *bvec = bvec_init_iter_all(&iter_all); + int total = 0, error = 0; + struct squashfs_xz *stream = strm; + + xz_dec_reset(stream->state); + stream->buf.in_pos = 0; + stream->buf.in_size = 0; + stream->buf.out_pos = 0; + stream->buf.out_size = PAGE_SIZE; + stream->buf.out = squashfs_first_page(output); + if (IS_ERR(stream->buf.out)) { + error = PTR_ERR(stream->buf.out); + goto finish; + } + + for (;;) { + enum xz_ret xz_err; + + if (stream->buf.in_pos == stream->buf.in_size) { + const void *data; + int avail; + + if (!bio_next_segment(bio, &iter_all)) { + /* XZ_STREAM_END must be reached. */ + error = -EIO; + break; + } + + avail = min(length, ((int)bvec->bv_len) - offset); + data = bvec_virt(bvec); + length -= avail; + stream->buf.in = data + offset; + stream->buf.in_size = avail; + stream->buf.in_pos = 0; + offset = 0; + } + + if (stream->buf.out_pos == stream->buf.out_size) { + stream->buf.out = squashfs_next_page(output); + if (IS_ERR(stream->buf.out)) { + error = PTR_ERR(stream->buf.out); + break; + } else if (stream->buf.out != NULL) { + stream->buf.out_pos = 0; + total += PAGE_SIZE; + } + } + + xz_err = xz_dec_run(stream->state, &stream->buf); + if (xz_err == XZ_STREAM_END) + break; + if (xz_err != XZ_OK) { + error = -EIO; + break; + } + } + +finish: + squashfs_finish_page(output); + + return error ? error : total + stream->buf.out_pos; +} + +const struct squashfs_decompressor squashfs_xz_comp_ops = { + .init = squashfs_xz_init, + .comp_opts = squashfs_xz_comp_opts, + .free = squashfs_xz_free, + .decompress = squashfs_xz_uncompress, + .id = XZ_COMPRESSION, + .name = "xz", + .alloc_buffer = 1, + .supported = 1 +}; diff --git a/fs/squashfs/zlib_wrapper.c b/fs/squashfs/zlib_wrapper.c new file mode 100644 index 000000000..a29001311 --- /dev/null +++ b/fs/squashfs/zlib_wrapper.c @@ -0,0 +1,137 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Squashfs - a compressed read only filesystem for Linux + * + * Copyright (c) 2002, 2003, 2004, 2005, 2006, 2007, 2008, 2009 + * Phillip Lougher <phillip@squashfs.org.uk> + * + * zlib_wrapper.c + */ + + +#include <linux/mutex.h> +#include <linux/bio.h> +#include <linux/slab.h> +#include <linux/zlib.h> +#include <linux/vmalloc.h> + +#include "squashfs_fs.h" +#include "squashfs_fs_sb.h" +#include "squashfs.h" +#include "decompressor.h" +#include "page_actor.h" + +static void *zlib_init(struct squashfs_sb_info *dummy, void *buff) +{ + z_stream *stream = kmalloc_obj(z_stream); + if (stream == NULL) + goto failed; + stream->workspace = vmalloc(zlib_inflate_workspacesize()); + if (stream->workspace == NULL) + goto failed; + + return stream; + +failed: + ERROR("Failed to allocate zlib workspace\n"); + kfree(stream); + return ERR_PTR(-ENOMEM); +} + + +static void zlib_free(void *strm) +{ + z_stream *stream = strm; + + if (stream) + vfree(stream->workspace); + kfree(stream); +} + + +static int zlib_uncompress(struct squashfs_sb_info *msblk, void *strm, + struct bio *bio, int offset, int length, + struct squashfs_page_actor *output) +{ + struct bvec_iter_all iter_all = {}; + struct bio_vec *bvec = bvec_init_iter_all(&iter_all); + int zlib_init = 0, error = 0; + z_stream *stream = strm; + + stream->avail_out = PAGE_SIZE; + stream->next_out = squashfs_first_page(output); + stream->avail_in = 0; + + if (IS_ERR(stream->next_out)) { + error = PTR_ERR(stream->next_out); + goto finish; + } + + for (;;) { + int zlib_err; + + if (stream->avail_in == 0) { + const void *data; + int avail; + + if (!bio_next_segment(bio, &iter_all)) { + /* Z_STREAM_END must be reached. */ + error = -EIO; + break; + } + + avail = min(length, ((int)bvec->bv_len) - offset); + data = bvec_virt(bvec); + length -= avail; + stream->next_in = data + offset; + stream->avail_in = avail; + offset = 0; + } + + if (stream->avail_out == 0) { + stream->next_out = squashfs_next_page(output); + if (IS_ERR(stream->next_out)) { + error = PTR_ERR(stream->next_out); + break; + } else if (stream->next_out != NULL) + stream->avail_out = PAGE_SIZE; + } + + if (!zlib_init) { + zlib_err = zlib_inflateInit(stream); + if (zlib_err != Z_OK) { + error = -EIO; + break; + } + zlib_init = 1; + } + + zlib_err = zlib_inflate(stream, Z_SYNC_FLUSH); + if (zlib_err == Z_STREAM_END) + break; + if (zlib_err != Z_OK) { + error = -EIO; + break; + } + } + +finish: + squashfs_finish_page(output); + + if (!error) + if (zlib_inflateEnd(stream) != Z_OK) + error = -EIO; + + return error ? error : stream->total_out; +} + +const struct squashfs_decompressor squashfs_zlib_comp_ops = { + .init = zlib_init, + .free = zlib_free, + .decompress = zlib_uncompress, + .id = ZLIB_COMPRESSION, + .name = "zlib", + .alloc_buffer = 1, + .supported = 1 +}; + diff --git a/fs/squashfs/zstd_wrapper.c b/fs/squashfs/zstd_wrapper.c new file mode 100644 index 000000000..487fbc51d --- /dev/null +++ b/fs/squashfs/zstd_wrapper.c @@ -0,0 +1,154 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Squashfs - a compressed read only filesystem for Linux + * + * Copyright (c) 2016-present, Facebook, Inc. + * All rights reserved. + * + * zstd_wrapper.c + */ + +#include <linux/mutex.h> +#include <linux/bio.h> +#include <linux/slab.h> +#include <linux/zstd.h> +#include <linux/vmalloc.h> + +#include "squashfs_fs.h" +#include "squashfs_fs_sb.h" +#include "squashfs.h" +#include "decompressor.h" +#include "page_actor.h" + +struct workspace { + void *mem; + size_t mem_size; + size_t window_size; +}; + +static void *zstd_init(struct squashfs_sb_info *msblk, void *buff) +{ + struct workspace *wksp = kmalloc_obj(*wksp); + + if (wksp == NULL) + goto failed; + wksp->window_size = max_t(size_t, + msblk->block_size, SQUASHFS_METADATA_SIZE); + wksp->mem_size = zstd_dstream_workspace_bound(wksp->window_size); + wksp->mem = vmalloc(wksp->mem_size); + if (wksp->mem == NULL) + goto failed; + + return wksp; + +failed: + ERROR("Failed to allocate zstd workspace\n"); + kfree(wksp); + return ERR_PTR(-ENOMEM); +} + + +static void zstd_free(void *strm) +{ + struct workspace *wksp = strm; + + if (wksp) + vfree(wksp->mem); + kfree(wksp); +} + + +static int zstd_uncompress(struct squashfs_sb_info *msblk, void *strm, + struct bio *bio, int offset, int length, + struct squashfs_page_actor *output) +{ + struct workspace *wksp = strm; + zstd_dstream *stream; + size_t total_out = 0; + int error = 0; + zstd_in_buffer in_buf = { NULL, 0, 0 }; + zstd_out_buffer out_buf = { NULL, 0, 0 }; + struct bvec_iter_all iter_all = {}; + struct bio_vec *bvec = bvec_init_iter_all(&iter_all); + + stream = zstd_init_dstream(wksp->window_size, wksp->mem, wksp->mem_size); + + if (!stream) { + ERROR("Failed to initialize zstd decompressor\n"); + return -EIO; + } + + out_buf.size = PAGE_SIZE; + out_buf.dst = squashfs_first_page(output); + if (IS_ERR(out_buf.dst)) { + error = PTR_ERR(out_buf.dst); + goto finish; + } + + for (;;) { + size_t zstd_err; + + if (in_buf.pos == in_buf.size) { + const void *data; + int avail; + + if (!bio_next_segment(bio, &iter_all)) { + error = -EIO; + break; + } + + avail = min(length, ((int)bvec->bv_len) - offset); + data = bvec_virt(bvec); + length -= avail; + in_buf.src = data + offset; + in_buf.size = avail; + in_buf.pos = 0; + offset = 0; + } + + if (out_buf.pos == out_buf.size) { + out_buf.dst = squashfs_next_page(output); + if (IS_ERR(out_buf.dst)) { + error = PTR_ERR(out_buf.dst); + break; + } else if (out_buf.dst == NULL) { + /* Shouldn't run out of pages + * before stream is done. + */ + error = -EIO; + break; + } + out_buf.pos = 0; + out_buf.size = PAGE_SIZE; + } + + total_out -= out_buf.pos; + zstd_err = zstd_decompress_stream(stream, &out_buf, &in_buf); + total_out += out_buf.pos; /* add the additional data produced */ + if (zstd_err == 0) + break; + + if (zstd_is_error(zstd_err)) { + ERROR("zstd decompression error: %d\n", + (int)zstd_get_error_code(zstd_err)); + error = -EIO; + break; + } + } + +finish: + + squashfs_finish_page(output); + + return error ? error : total_out; +} + +const struct squashfs_decompressor squashfs_zstd_comp_ops = { + .init = zstd_init, + .free = zstd_free, + .decompress = zstd_uncompress, + .id = ZSTD_COMPRESSION, + .name = "zstd", + .alloc_buffer = 1, + .supported = 1 +}; |
