diff options
Diffstat (limited to 'fs/cramfs')
| -rw-r--r-- | fs/cramfs/Kconfig | 54 | ||||
| -rw-r--r-- | fs/cramfs/Makefile | 8 | ||||
| -rw-r--r-- | fs/cramfs/README | 197 | ||||
| -rw-r--r-- | fs/cramfs/inode.c | 1012 | ||||
| -rw-r--r-- | fs/cramfs/internal.h | 4 | ||||
| -rw-r--r-- | fs/cramfs/uncompress.c | 80 |
6 files changed, 1355 insertions, 0 deletions
diff --git a/fs/cramfs/Kconfig b/fs/cramfs/Kconfig new file mode 100644 index 000000000..d98cef0db --- /dev/null +++ b/fs/cramfs/Kconfig @@ -0,0 +1,54 @@ +# SPDX-License-Identifier: GPL-2.0-only +config CRAMFS + tristate "Compressed ROM file system support (cramfs)" + select ZLIB_INFLATE + help + Saying Y here includes support for CramFs (Compressed ROM File + System). CramFs is designed to be a simple, small, and compressed + file system for ROM based embedded systems. CramFs is read-only, + limited to 256MB file systems (with 16MB files), and doesn't support + 16/32 bits uid/gid, hard links and timestamps. + + See <file:Documentation/filesystems/cramfs.rst> and + <file:fs/cramfs/README> for further information. + + To compile this as a module, choose M here: the module will be called + cramfs. Note that the root file system (the one containing the + directory /) cannot be compiled as a module. + + This filesystem is limited in capabilities and performance on + purpose to remain small and low on RAM usage. It is most suitable + for small embedded systems. If you have ample RAM to spare, you may + consider a more capable compressed filesystem such as SquashFS + which is much better in terms of performance and features. + + If unsure, say N. + +config CRAMFS_BLOCKDEV + bool "Support CramFs image over a regular block device" if EXPERT + depends on CRAMFS && BLOCK + default y + help + This option allows the CramFs driver to load data from a regular + block device such a disk partition or a ramdisk. + +config CRAMFS_MTD + bool "Support CramFs image directly mapped in physical memory" + depends on CRAMFS && CRAMFS <= MTD + default y if !CRAMFS_BLOCKDEV + help + This option allows the CramFs driver to load data directly from + a linear adressed memory range (usually non volatile memory + like flash) instead of going through the block device layer. + This saves some memory since no intermediate buffering is + necessary. + + The location of the CramFs image is determined by a + MTD device capable of direct memory mapping e.g. from + the 'physmap' map driver or a resulting MTD partition. + For example, this would mount the cramfs image stored in + the MTD partition named "xip_fs" on the /mnt mountpoint: + + mount -t cramfs mtd:xip_fs /mnt + + If unsure, say N. diff --git a/fs/cramfs/Makefile b/fs/cramfs/Makefile new file mode 100644 index 000000000..8c3ed2982 --- /dev/null +++ b/fs/cramfs/Makefile @@ -0,0 +1,8 @@ +# SPDX-License-Identifier: GPL-2.0-only +# +# Makefile for the linux cramfs routines. +# + +obj-$(CONFIG_CRAMFS) += cramfs.o + +cramfs-objs := inode.o uncompress.o diff --git a/fs/cramfs/README b/fs/cramfs/README new file mode 100644 index 000000000..d71b27e0f --- /dev/null +++ b/fs/cramfs/README @@ -0,0 +1,197 @@ +Notes on Filesystem Layout +-------------------------- + +These notes describe what mkcramfs generates. Kernel requirements are +a bit looser, e.g. it doesn't care if the <file_data> items are +swapped around (though it does care that directory entries (inodes) in +a given directory are contiguous, as this is used by readdir). + +All data is currently in host-endian format; neither mkcramfs nor the +kernel ever do swabbing. (See section `Block Size' below.) + +<filesystem>: + <superblock> + <directory_structure> + <data> + +<superblock>: struct cramfs_super (see cramfs_fs.h). + +<directory_structure>: + For each file: + struct cramfs_inode (see cramfs_fs.h). + Filename. Not generally null-terminated, but it is + null-padded to a multiple of 4 bytes. + +The order of inode traversal is described as "width-first" (not to be +confused with breadth-first); i.e. like depth-first but listing all of +a directory's entries before recursing down its subdirectories: the +same order as `ls -AUR' (but without the /^\..*:$/ directory header +lines); put another way, the same order as `find -type d -exec +ls -AU1 {} \;'. + +Beginning in 2.4.7, directory entries are sorted. This optimization +allows cramfs_lookup to return more quickly when a filename does not +exist, speeds up user-space directory sorts, etc. + +<data>: + One <file_data> for each file that's either a symlink or a + regular file of non-zero st_size. + +<file_data>: + nblocks * <block_pointer> + (where nblocks = (st_size - 1) / blksize + 1) + nblocks * <block> + padding to multiple of 4 bytes + +The i'th <block_pointer> for a file stores the byte offset of the +*end* of the i'th <block> (i.e. one past the last byte, which is the +same as the start of the (i+1)'th <block> if there is one). The first +<block> immediately follows the last <block_pointer> for the file. +<block_pointer>s are each 32 bits long. + +When the CRAMFS_FLAG_EXT_BLOCK_POINTERS capability bit is set, each +<block_pointer>'s top bits may contain special flags as follows: + +CRAMFS_BLK_FLAG_UNCOMPRESSED (bit 31): + The block data is not compressed and should be copied verbatim. + +CRAMFS_BLK_FLAG_DIRECT_PTR (bit 30): + The <block_pointer> stores the actual block start offset and not + its end, shifted right by 2 bits. The block must therefore be + aligned to a 4-byte boundary. The block size is either blksize + if CRAMFS_BLK_FLAG_UNCOMPRESSED is also specified, otherwise + the compressed data length is included in the first 2 bytes of + the block data. This is used to allow discontiguous data layout + and specific data block alignments e.g. for XIP applications. + + +The order of <file_data>'s is a depth-first descent of the directory +tree, i.e. the same order as `find -size +0 \( -type f -o -type l \) +-print'. + + +<block>: The i'th <block> is the output of zlib's compress function +applied to the i'th blksize-sized chunk of the input data if the +corresponding CRAMFS_BLK_FLAG_UNCOMPRESSED <block_ptr> bit is not set, +otherwise it is the input data directly. +(For the last <block> of the file, the input may of course be smaller.) +Each <block> may be a different size. (See <block_pointer> above.) + +<block>s are merely byte-aligned, not generally u32-aligned. + +When CRAMFS_BLK_FLAG_DIRECT_PTR is specified then the corresponding +<block> may be located anywhere and not necessarily contiguous with +the previous/next blocks. In that case it is minimally u32-aligned. +If CRAMFS_BLK_FLAG_UNCOMPRESSED is also specified then the size is always +blksize except for the last block which is limited by the file length. +If CRAMFS_BLK_FLAG_DIRECT_PTR is set and CRAMFS_BLK_FLAG_UNCOMPRESSED +is not set then the first 2 bytes of the block contains the size of the +remaining block data as this cannot be determined from the placement of +logically adjacent blocks. + + +Holes +----- + +This kernel supports cramfs holes (i.e. [efficient representation of] +blocks in uncompressed data consisting entirely of NUL bytes), but by +default mkcramfs doesn't test for & create holes, since cramfs in +kernels up to at least 2.3.39 didn't support holes. Run mkcramfs +with -z if you want it to create files that can have holes in them. + + +Tools +----- + +The cramfs user-space tools, including mkcramfs and cramfsck, are +located at <http://sourceforge.net/projects/cramfs/>. + + +Future Development +================== + +Block Size +---------- + +(Block size in cramfs refers to the size of input data that is +compressed at a time. It's intended to be somewhere around +PAGE_SIZE for cramfs_readpage's convenience.) + +The superblock ought to indicate the block size that the fs was +written for, since comments in <linux/pagemap.h> indicate that +PAGE_SIZE may grow in future (if I interpret the comment +correctly). + +Currently, mkcramfs #define's PAGE_SIZE as 4096 and uses that +for blksize, whereas Linux-2.3.39 uses its PAGE_SIZE, which in +turn is defined as PAGE_SIZE (which can be as large as 32KB on arm). +This discrepancy is a bug, though it's not clear which should be +changed. + +One option is to change mkcramfs to take its PAGE_SIZE from +<asm/page.h>. Personally I don't like this option, but it does +require the least amount of change: just change `#define +PAGE_SIZE (4096)' to `#include <asm/page.h>'. The disadvantage +is that the generated cramfs cannot always be shared between different +kernels, not even necessarily kernels of the same architecture if +PAGE_SIZE is subject to change between kernel versions +(currently possible with arm and ia64). + +The remaining options try to make cramfs more sharable. + +One part of that is addressing endianness. The two options here are +`always use little-endian' (like ext2fs) or `writer chooses +endianness; kernel adapts at runtime'. Little-endian wins because of +code simplicity and little CPU overhead even on big-endian machines. + +The cost of swabbing is changing the code to use the le32_to_cpu +etc. macros as used by ext2fs. We don't need to swab the compressed +data, only the superblock, inodes and block pointers. + + +The other part of making cramfs more sharable is choosing a block +size. The options are: + + 1. Always 4096 bytes. + + 2. Writer chooses blocksize; kernel adapts but rejects blocksize > + PAGE_SIZE. + + 3. Writer chooses blocksize; kernel adapts even to blocksize > + PAGE_SIZE. + +It's easy enough to change the kernel to use a smaller value than +PAGE_SIZE: just make cramfs_readpage read multiple blocks. + +The cost of option 1 is that kernels with a larger PAGE_SIZE +value don't get as good compression as they can. + +The cost of option 2 relative to option 1 is that the code uses +variables instead of #define'd constants. The gain is that people +with kernels having larger PAGE_SIZE can make use of that if +they don't mind their cramfs being inaccessible to kernels with +smaller PAGE_SIZE values. + +Option 3 is easy to implement if we don't mind being CPU-inefficient: +e.g. get readpage to decompress to a buffer of size MAX_BLKSIZE (which +must be no larger than 32KB) and discard what it doesn't need. +Getting readpage to read into all the covered pages is harder. + +The main advantage of option 3 over 1, 2, is better compression. The +cost is greater complexity. Probably not worth it, but I hope someone +will disagree. (If it is implemented, then I'll re-use that code in +e2compr.) + + +Another cost of 2 and 3 over 1 is making mkcramfs use a different +block size, but that just means adding and parsing a -b option. + + +Inode Size +---------- + +Given that cramfs will probably be used for CDs etc. as well as just +silicon ROMs, it might make sense to expand the inode a little from +its current 12 bytes. Inodes other than the root inode are followed +by filename, so the expansion doesn't even have to be a multiple of 4 +bytes. diff --git a/fs/cramfs/inode.c b/fs/cramfs/inode.c new file mode 100644 index 000000000..4b90cfd1e --- /dev/null +++ b/fs/cramfs/inode.c @@ -0,0 +1,1012 @@ +/* + * Compressed rom filesystem for Linux. + * + * Copyright (C) 1999 Linus Torvalds. + * + * This file is released under the GPL. + */ + +/* + * These are the VFS interfaces to the compressed rom filesystem. + * The actual compression is based on zlib, see the other files. + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include <linux/module.h> +#include <linux/fs.h> +#include <linux/file.h> +#include <linux/pagemap.h> +#include <linux/pfn_t.h> +#include <linux/ramfs.h> +#include <linux/init.h> +#include <linux/string.h> +#include <linux/blkdev.h> +#include <linux/mtd/mtd.h> +#include <linux/mtd/super.h> +#include <linux/fs_context.h> +#include <linux/slab.h> +#include <linux/vfs.h> +#include <linux/mutex.h> +#include <uapi/linux/cramfs_fs.h> +#include <linux/uaccess.h> + +#include "internal.h" + +/* + * cramfs super-block data in memory + */ +struct cramfs_sb_info { + unsigned long magic; + unsigned long size; + unsigned long blocks; + unsigned long files; + unsigned long flags; + void *linear_virt_addr; + resource_size_t linear_phys_addr; + size_t mtd_point_size; +}; + +static inline struct cramfs_sb_info *CRAMFS_SB(struct super_block *sb) +{ + return sb->s_fs_info; +} + +static const struct super_operations cramfs_ops; +static const struct inode_operations cramfs_dir_inode_operations; +static const struct file_operations cramfs_directory_operations; +static const struct file_operations cramfs_physmem_fops; +static const struct address_space_operations cramfs_aops; + +static DEFINE_MUTEX(read_mutex); + + +/* These macros may change in future, to provide better st_ino semantics. */ +#define OFFSET(x) ((x)->i_ino) + +static unsigned long cramino(const struct cramfs_inode *cino, unsigned int offset) +{ + if (!cino->offset) + return offset + 1; + if (!cino->size) + return offset + 1; + + /* + * The file mode test fixes buggy mkcramfs implementations where + * cramfs_inode->offset is set to a non zero value for entries + * which did not contain data, like devices node and fifos. + */ + switch (cino->mode & S_IFMT) { + case S_IFREG: + case S_IFDIR: + case S_IFLNK: + return cino->offset << 2; + default: + break; + } + return offset + 1; +} + +static struct inode *get_cramfs_inode(struct super_block *sb, + const struct cramfs_inode *cramfs_inode, unsigned int offset) +{ + struct inode *inode; + static struct timespec64 zerotime; + + inode = iget_locked(sb, cramino(cramfs_inode, offset)); + if (!inode) + return ERR_PTR(-ENOMEM); + if (!(inode->i_state & I_NEW)) + return inode; + + switch (cramfs_inode->mode & S_IFMT) { + case S_IFREG: + inode->i_fop = &generic_ro_fops; + inode->i_data.a_ops = &cramfs_aops; + if (IS_ENABLED(CONFIG_CRAMFS_MTD) && + CRAMFS_SB(sb)->flags & CRAMFS_FLAG_EXT_BLOCK_POINTERS && + CRAMFS_SB(sb)->linear_phys_addr) + inode->i_fop = &cramfs_physmem_fops; + break; + case S_IFDIR: + inode->i_op = &cramfs_dir_inode_operations; + inode->i_fop = &cramfs_directory_operations; + break; + case S_IFLNK: + inode->i_op = &page_symlink_inode_operations; + inode_nohighmem(inode); + inode->i_data.a_ops = &cramfs_aops; + break; + default: + init_special_inode(inode, cramfs_inode->mode, + old_decode_dev(cramfs_inode->size)); + } + + inode->i_mode = cramfs_inode->mode; + i_uid_write(inode, cramfs_inode->uid); + i_gid_write(inode, cramfs_inode->gid); + + /* if the lower 2 bits are zero, the inode contains data */ + if (!(inode->i_ino & 3)) { + inode->i_size = cramfs_inode->size; + inode->i_blocks = (cramfs_inode->size - 1) / 512 + 1; + } + + /* Struct copy intentional */ + inode->i_mtime = inode->i_atime = inode->i_ctime = zerotime; + /* inode->i_nlink is left 1 - arguably wrong for directories, + but it's the best we can do without reading the directory + contents. 1 yields the right result in GNU find, even + without -noleaf option. */ + + unlock_new_inode(inode); + + return inode; +} + +/* + * We have our own block cache: don't fill up the buffer cache + * with the rom-image, because the way the filesystem is set + * up the accesses should be fairly regular and cached in the + * page cache and dentry tree anyway.. + * + * This also acts as a way to guarantee contiguous areas of up to + * BLKS_PER_BUF*PAGE_SIZE, so that the caller doesn't need to + * worry about end-of-buffer issues even when decompressing a full + * page cache. + * + * Note: This is all optimized away at compile time when + * CONFIG_CRAMFS_BLOCKDEV=n. + */ +#define READ_BUFFERS (2) +/* NEXT_BUFFER(): Loop over [0..(READ_BUFFERS-1)]. */ +#define NEXT_BUFFER(_ix) ((_ix) ^ 1) + +/* + * BLKS_PER_BUF_SHIFT should be at least 2 to allow for "compressed" + * data that takes up more space than the original and with unlucky + * alignment. + */ +#define BLKS_PER_BUF_SHIFT (2) +#define BLKS_PER_BUF (1 << BLKS_PER_BUF_SHIFT) +#define BUFFER_SIZE (BLKS_PER_BUF*PAGE_SIZE) + +static unsigned char read_buffers[READ_BUFFERS][BUFFER_SIZE]; +static unsigned buffer_blocknr[READ_BUFFERS]; +static struct super_block *buffer_dev[READ_BUFFERS]; +static int next_buffer; + +/* + * Populate our block cache and return a pointer to it. + */ +static void *cramfs_blkdev_read(struct super_block *sb, unsigned int offset, + unsigned int len) +{ + struct address_space *mapping = sb->s_bdev->bd_inode->i_mapping; + struct page *pages[BLKS_PER_BUF]; + unsigned i, blocknr, buffer; + unsigned long devsize; + char *data; + + if (!len) + return NULL; + blocknr = offset >> PAGE_SHIFT; + offset &= PAGE_SIZE - 1; + + /* Check if an existing buffer already has the data.. */ + for (i = 0; i < READ_BUFFERS; i++) { + unsigned int blk_offset; + + if (buffer_dev[i] != sb) + continue; + if (blocknr < buffer_blocknr[i]) + continue; + blk_offset = (blocknr - buffer_blocknr[i]) << PAGE_SHIFT; + blk_offset += offset; + if (blk_offset > BUFFER_SIZE || + blk_offset + len > BUFFER_SIZE) + continue; + return read_buffers[i] + blk_offset; + } + + devsize = mapping->host->i_size >> PAGE_SHIFT; + + /* Ok, read in BLKS_PER_BUF pages completely first. */ + for (i = 0; i < BLKS_PER_BUF; i++) { + struct page *page = NULL; + + if (blocknr + i < devsize) { + page = read_mapping_page(mapping, blocknr + i, NULL); + /* synchronous error? */ + if (IS_ERR(page)) + page = NULL; + } + pages[i] = page; + } + + for (i = 0; i < BLKS_PER_BUF; i++) { + struct page *page = pages[i]; + + if (page) { + wait_on_page_locked(page); + if (!PageUptodate(page)) { + /* asynchronous error */ + put_page(page); + pages[i] = NULL; + } + } + } + + buffer = next_buffer; + next_buffer = NEXT_BUFFER(buffer); + buffer_blocknr[buffer] = blocknr; + buffer_dev[buffer] = sb; + + data = read_buffers[buffer]; + for (i = 0; i < BLKS_PER_BUF; i++) { + struct page *page = pages[i]; + + if (page) { + memcpy(data, kmap(page), PAGE_SIZE); + kunmap(page); + put_page(page); + } else + memset(data, 0, PAGE_SIZE); + data += PAGE_SIZE; + } + return read_buffers[buffer] + offset; +} + +/* + * Return a pointer to the linearly addressed cramfs image in memory. + */ +static void *cramfs_direct_read(struct super_block *sb, unsigned int offset, + unsigned int len) +{ + struct cramfs_sb_info *sbi = CRAMFS_SB(sb); + + if (!len) + return NULL; + if (len > sbi->size || offset > sbi->size - len) + return page_address(ZERO_PAGE(0)); + return sbi->linear_virt_addr + offset; +} + +/* + * Returns a pointer to a buffer containing at least LEN bytes of + * filesystem starting at byte offset OFFSET into the filesystem. + */ +static void *cramfs_read(struct super_block *sb, unsigned int offset, + unsigned int len) +{ + struct cramfs_sb_info *sbi = CRAMFS_SB(sb); + + if (IS_ENABLED(CONFIG_CRAMFS_MTD) && sbi->linear_virt_addr) + return cramfs_direct_read(sb, offset, len); + else if (IS_ENABLED(CONFIG_CRAMFS_BLOCKDEV)) + return cramfs_blkdev_read(sb, offset, len); + else + return NULL; +} + +/* + * For a mapping to be possible, we need a range of uncompressed and + * contiguous blocks. Return the offset for the first block and number of + * valid blocks for which that is true, or zero otherwise. + */ +static u32 cramfs_get_block_range(struct inode *inode, u32 pgoff, u32 *pages) +{ + struct cramfs_sb_info *sbi = CRAMFS_SB(inode->i_sb); + int i; + u32 *blockptrs, first_block_addr; + + /* + * We can dereference memory directly here as this code may be + * reached only when there is a direct filesystem image mapping + * available in memory. + */ + blockptrs = (u32 *)(sbi->linear_virt_addr + OFFSET(inode) + pgoff * 4); + first_block_addr = blockptrs[0] & ~CRAMFS_BLK_FLAGS; + i = 0; + do { + u32 block_off = i * (PAGE_SIZE >> CRAMFS_BLK_DIRECT_PTR_SHIFT); + u32 expect = (first_block_addr + block_off) | + CRAMFS_BLK_FLAG_DIRECT_PTR | + CRAMFS_BLK_FLAG_UNCOMPRESSED; + if (blockptrs[i] != expect) { + pr_debug("range: block %d/%d got %#x expects %#x\n", + pgoff+i, pgoff + *pages - 1, + blockptrs[i], expect); + if (i == 0) + return 0; + break; + } + } while (++i < *pages); + + *pages = i; + return first_block_addr << CRAMFS_BLK_DIRECT_PTR_SHIFT; +} + +#ifdef CONFIG_MMU + +/* + * Return true if the last page of a file in the filesystem image contains + * some other data that doesn't belong to that file. It is assumed that the + * last block is CRAMFS_BLK_FLAG_DIRECT_PTR | CRAMFS_BLK_FLAG_UNCOMPRESSED + * (verified by cramfs_get_block_range() and directly accessible in memory. + */ +static bool cramfs_last_page_is_shared(struct inode *inode) +{ + struct cramfs_sb_info *sbi = CRAMFS_SB(inode->i_sb); + u32 partial, last_page, blockaddr, *blockptrs; + char *tail_data; + + partial = offset_in_page(inode->i_size); + if (!partial) + return false; + last_page = inode->i_size >> PAGE_SHIFT; + blockptrs = (u32 *)(sbi->linear_virt_addr + OFFSET(inode)); + blockaddr = blockptrs[last_page] & ~CRAMFS_BLK_FLAGS; + blockaddr <<= CRAMFS_BLK_DIRECT_PTR_SHIFT; + tail_data = sbi->linear_virt_addr + blockaddr + partial; + return memchr_inv(tail_data, 0, PAGE_SIZE - partial) ? true : false; +} + +static int cramfs_physmem_mmap(struct file *file, struct vm_area_struct *vma) +{ + struct inode *inode = file_inode(file); + struct cramfs_sb_info *sbi = CRAMFS_SB(inode->i_sb); + unsigned int pages, max_pages, offset; + unsigned long address, pgoff = vma->vm_pgoff; + char *bailout_reason; + int ret; + + ret = generic_file_readonly_mmap(file, vma); + if (ret) + return ret; + + /* + * Now try to pre-populate ptes for this vma with a direct + * mapping avoiding memory allocation when possible. + */ + + /* Could COW work here? */ + bailout_reason = "vma is writable"; + if (vma->vm_flags & VM_WRITE) + goto bailout; + + max_pages = (inode->i_size + PAGE_SIZE - 1) >> PAGE_SHIFT; + bailout_reason = "beyond file limit"; + if (pgoff >= max_pages) + goto bailout; + pages = min(vma_pages(vma), max_pages - pgoff); + + offset = cramfs_get_block_range(inode, pgoff, &pages); + bailout_reason = "unsuitable block layout"; + if (!offset) + goto bailout; + address = sbi->linear_phys_addr + offset; + bailout_reason = "data is not page aligned"; + if (!PAGE_ALIGNED(address)) + goto bailout; + + /* Don't map the last page if it contains some other data */ + if (pgoff + pages == max_pages && cramfs_last_page_is_shared(inode)) { + pr_debug("mmap: %s: last page is shared\n", + file_dentry(file)->d_name.name); + pages--; + } + + if (!pages) { + bailout_reason = "no suitable block remaining"; + goto bailout; + } + + if (pages == vma_pages(vma)) { + /* + * The entire vma is mappable. remap_pfn_range() will + * make it distinguishable from a non-direct mapping + * in /proc/<pid>/maps by substituting the file offset + * with the actual physical address. + */ + ret = remap_pfn_range(vma, vma->vm_start, address >> PAGE_SHIFT, + pages * PAGE_SIZE, vma->vm_page_prot); + } else { + /* + * Let's create a mixed map if we can't map it all. + * The normal paging machinery will take care of the + * unpopulated ptes via cramfs_readpage(). + */ + int i; + vma->vm_flags |= VM_MIXEDMAP; + for (i = 0; i < pages && !ret; i++) { + vm_fault_t vmf; + unsigned long off = i * PAGE_SIZE; + pfn_t pfn = phys_to_pfn_t(address + off, PFN_DEV); + vmf = vmf_insert_mixed(vma, vma->vm_start + off, pfn); + if (vmf & VM_FAULT_ERROR) + ret = vm_fault_to_errno(vmf, 0); + } + } + + if (!ret) + pr_debug("mapped %s[%lu] at 0x%08lx (%u/%lu pages) " + "to vma 0x%08lx, page_prot 0x%llx\n", + file_dentry(file)->d_name.name, pgoff, + address, pages, vma_pages(vma), vma->vm_start, + (unsigned long long)pgprot_val(vma->vm_page_prot)); + return ret; + +bailout: + pr_debug("%s[%lu]: direct mmap impossible: %s\n", + file_dentry(file)->d_name.name, pgoff, bailout_reason); + /* Didn't manage any direct map, but normal paging is still possible */ + return 0; +} + +#else /* CONFIG_MMU */ + +static int cramfs_physmem_mmap(struct file *file, struct vm_area_struct *vma) +{ + return vma->vm_flags & (VM_SHARED | VM_MAYSHARE) ? 0 : -ENOSYS; +} + +static unsigned long cramfs_physmem_get_unmapped_area(struct file *file, + unsigned long addr, unsigned long len, + unsigned long pgoff, unsigned long flags) +{ + struct inode *inode = file_inode(file); + struct super_block *sb = inode->i_sb; + struct cramfs_sb_info *sbi = CRAMFS_SB(sb); + unsigned int pages, block_pages, max_pages, offset; + + pages = (len + PAGE_SIZE - 1) >> PAGE_SHIFT; + max_pages = (inode->i_size + PAGE_SIZE - 1) >> PAGE_SHIFT; + if (pgoff >= max_pages || pages > max_pages - pgoff) + return -EINVAL; + block_pages = pages; + offset = cramfs_get_block_range(inode, pgoff, &block_pages); + if (!offset || block_pages != pages) + return -ENOSYS; + addr = sbi->linear_phys_addr + offset; + pr_debug("get_unmapped for %s ofs %#lx siz %lu at 0x%08lx\n", + file_dentry(file)->d_name.name, pgoff*PAGE_SIZE, len, addr); + return addr; +} + +static unsigned int cramfs_physmem_mmap_capabilities(struct file *file) +{ + return NOMMU_MAP_COPY | NOMMU_MAP_DIRECT | + NOMMU_MAP_READ | NOMMU_MAP_EXEC; +} + +#endif /* CONFIG_MMU */ + +static const struct file_operations cramfs_physmem_fops = { + .llseek = generic_file_llseek, + .read_iter = generic_file_read_iter, + .splice_read = generic_file_splice_read, + .mmap = cramfs_physmem_mmap, +#ifndef CONFIG_MMU + .get_unmapped_area = cramfs_physmem_get_unmapped_area, + .mmap_capabilities = cramfs_physmem_mmap_capabilities, +#endif +}; + +static void cramfs_kill_sb(struct super_block *sb) +{ + struct cramfs_sb_info *sbi = CRAMFS_SB(sb); + + if (IS_ENABLED(CONFIG_CRAMFS_MTD) && sb->s_mtd) { + if (sbi && sbi->mtd_point_size) + mtd_unpoint(sb->s_mtd, 0, sbi->mtd_point_size); + kill_mtd_super(sb); + } else if (IS_ENABLED(CONFIG_CRAMFS_BLOCKDEV) && sb->s_bdev) { + kill_block_super(sb); + } + kfree(sbi); +} + +static int cramfs_reconfigure(struct fs_context *fc) +{ + sync_filesystem(fc->root->d_sb); + fc->sb_flags |= SB_RDONLY; + return 0; +} + +static int cramfs_read_super(struct super_block *sb, struct fs_context *fc, + struct cramfs_super *super) +{ + struct cramfs_sb_info *sbi = CRAMFS_SB(sb); + unsigned long root_offset; + bool silent = fc->sb_flags & SB_SILENT; + + /* We don't know the real size yet */ + sbi->size = PAGE_SIZE; + + /* Read the first block and get the superblock from it */ + mutex_lock(&read_mutex); + memcpy(super, cramfs_read(sb, 0, sizeof(*super)), sizeof(*super)); + mutex_unlock(&read_mutex); + + /* Do sanity checks on the superblock */ + if (super->magic != CRAMFS_MAGIC) { + /* check for wrong endianness */ + if (super->magic == CRAMFS_MAGIC_WEND) { + if (!silent) + errorfc(fc, "wrong endianness"); + return -EINVAL; + } + + /* check at 512 byte offset */ + mutex_lock(&read_mutex); + memcpy(super, + cramfs_read(sb, 512, sizeof(*super)), + sizeof(*super)); + mutex_unlock(&read_mutex); + if (super->magic != CRAMFS_MAGIC) { + if (super->magic == CRAMFS_MAGIC_WEND && !silent) + errorfc(fc, "wrong endianness"); + else if (!silent) + errorfc(fc, "wrong magic"); + return -EINVAL; + } + } + + /* get feature flags first */ + if (super->flags & ~CRAMFS_SUPPORTED_FLAGS) { + errorfc(fc, "unsupported filesystem features"); + return -EINVAL; + } + + /* Check that the root inode is in a sane state */ + if (!S_ISDIR(super->root.mode)) { + errorfc(fc, "root is not a directory"); + return -EINVAL; + } + /* correct strange, hard-coded permissions of mkcramfs */ + super->root.mode |= 0555; + + root_offset = super->root.offset << 2; + if (super->flags & CRAMFS_FLAG_FSID_VERSION_2) { + sbi->size = super->size; + sbi->blocks = super->fsid.blocks; + sbi->files = super->fsid.files; + } else { + sbi->size = 1<<28; + sbi->blocks = 0; + sbi->files = 0; + } + sbi->magic = super->magic; + sbi->flags = super->flags; + if (root_offset == 0) + infofc(fc, "empty filesystem"); + else if (!(super->flags & CRAMFS_FLAG_SHIFTED_ROOT_OFFSET) && + ((root_offset != sizeof(struct cramfs_super)) && + (root_offset != 512 + sizeof(struct cramfs_super)))) + { + errorfc(fc, "bad root offset %lu", root_offset); + return -EINVAL; + } + + return 0; +} + +static int cramfs_finalize_super(struct super_block *sb, + struct cramfs_inode *cramfs_root) +{ + struct inode *root; + + /* Set it all up.. */ + sb->s_flags |= SB_RDONLY; + sb->s_time_min = 0; + sb->s_time_max = 0; + sb->s_op = &cramfs_ops; + root = get_cramfs_inode(sb, cramfs_root, 0); + if (IS_ERR(root)) + return PTR_ERR(root); + sb->s_root = d_make_root(root); + if (!sb->s_root) + return -ENOMEM; + return 0; +} + +static int cramfs_blkdev_fill_super(struct super_block *sb, struct fs_context *fc) +{ + struct cramfs_sb_info *sbi; + struct cramfs_super super; + int i, err; + + sbi = kzalloc(sizeof(struct cramfs_sb_info), GFP_KERNEL); + if (!sbi) + return -ENOMEM; + sb->s_fs_info = sbi; + + /* Invalidate the read buffers on mount: think disk change.. */ + for (i = 0; i < READ_BUFFERS; i++) + buffer_blocknr[i] = -1; + + err = cramfs_read_super(sb, fc, &super); + if (err) + return err; + return cramfs_finalize_super(sb, &super.root); +} + +static int cramfs_mtd_fill_super(struct super_block *sb, struct fs_context *fc) +{ + struct cramfs_sb_info *sbi; + struct cramfs_super super; + int err; + + sbi = kzalloc(sizeof(struct cramfs_sb_info), GFP_KERNEL); + if (!sbi) + return -ENOMEM; + sb->s_fs_info = sbi; + + /* Map only one page for now. Will remap it when fs size is known. */ + err = mtd_point(sb->s_mtd, 0, PAGE_SIZE, &sbi->mtd_point_size, + &sbi->linear_virt_addr, &sbi->linear_phys_addr); + if (err || sbi->mtd_point_size != PAGE_SIZE) { + pr_err("unable to get direct memory access to mtd:%s\n", + sb->s_mtd->name); + return err ? : -ENODATA; + } + + pr_info("checking physical address %pap for linear cramfs image\n", + &sbi->linear_phys_addr); + err = cramfs_read_super(sb, fc, &super); + if (err) + return err; + + /* Remap the whole filesystem now */ + pr_info("linear cramfs image on mtd:%s appears to be %lu KB in size\n", + sb->s_mtd->name, sbi->size/1024); + mtd_unpoint(sb->s_mtd, 0, PAGE_SIZE); + err = mtd_point(sb->s_mtd, 0, sbi->size, &sbi->mtd_point_size, + &sbi->linear_virt_addr, &sbi->linear_phys_addr); + if (err || sbi->mtd_point_size != sbi->size) { + pr_err("unable to get direct memory access to mtd:%s\n", + sb->s_mtd->name); + return err ? : -ENODATA; + } + + return cramfs_finalize_super(sb, &super.root); +} + +static int cramfs_statfs(struct dentry *dentry, struct kstatfs *buf) +{ + struct super_block *sb = dentry->d_sb; + u64 id = 0; + + if (sb->s_bdev) + id = huge_encode_dev(sb->s_bdev->bd_dev); + else if (sb->s_dev) + id = huge_encode_dev(sb->s_dev); + + buf->f_type = CRAMFS_MAGIC; + buf->f_bsize = PAGE_SIZE; + buf->f_blocks = CRAMFS_SB(sb)->blocks; + buf->f_bfree = 0; + buf->f_bavail = 0; + buf->f_files = CRAMFS_SB(sb)->files; + buf->f_ffree = 0; + buf->f_fsid = u64_to_fsid(id); + buf->f_namelen = CRAMFS_MAXPATHLEN; + return 0; +} + +/* + * Read a cramfs directory entry. + */ +static int cramfs_readdir(struct file *file, struct dir_context *ctx) +{ + struct inode *inode = file_inode(file); + struct super_block *sb = inode->i_sb; + char *buf; + unsigned int offset; + + /* Offset within the thing. */ + if (ctx->pos >= inode->i_size) + return 0; + offset = ctx->pos; + /* Directory entries are always 4-byte aligned */ + if (offset & 3) + return -EINVAL; + + buf = kmalloc(CRAMFS_MAXPATHLEN, GFP_KERNEL); + if (!buf) + return -ENOMEM; + + while (offset < inode->i_size) { + struct cramfs_inode *de; + unsigned long nextoffset; + char *name; + ino_t ino; + umode_t mode; + int namelen; + + mutex_lock(&read_mutex); + de = cramfs_read(sb, OFFSET(inode) + offset, sizeof(*de)+CRAMFS_MAXPATHLEN); + name = (char *)(de+1); + + /* + * Namelengths on disk are shifted by two + * and the name padded out to 4-byte boundaries + * with zeroes. + */ + namelen = de->namelen << 2; + memcpy(buf, name, namelen); + ino = cramino(de, OFFSET(inode) + offset); + mode = de->mode; + mutex_unlock(&read_mutex); + nextoffset = offset + sizeof(*de) + namelen; + for (;;) { + if (!namelen) { + kfree(buf); + return -EIO; + } + if (buf[namelen-1]) + break; + namelen--; + } + if (!dir_emit(ctx, buf, namelen, ino, mode >> 12)) + break; + + ctx->pos = offset = nextoffset; + } + kfree(buf); + return 0; +} + +/* + * Lookup and fill in the inode data.. + */ +static struct dentry *cramfs_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) +{ + unsigned int offset = 0; + struct inode *inode = NULL; + int sorted; + + mutex_lock(&read_mutex); + sorted = CRAMFS_SB(dir->i_sb)->flags & CRAMFS_FLAG_SORTED_DIRS; + while (offset < dir->i_size) { + struct cramfs_inode *de; + char *name; + int namelen, retval; + int dir_off = OFFSET(dir) + offset; + + de = cramfs_read(dir->i_sb, dir_off, sizeof(*de)+CRAMFS_MAXPATHLEN); + name = (char *)(de+1); + + /* Try to take advantage of sorted directories */ + if (sorted && (dentry->d_name.name[0] < name[0])) + break; + + namelen = de->namelen << 2; + offset += sizeof(*de) + namelen; + + /* Quick check that the name is roughly the right length */ + if (((dentry->d_name.len + 3) & ~3) != namelen) + continue; + + for (;;) { + if (!namelen) { + inode = ERR_PTR(-EIO); + goto out; + } + if (name[namelen-1]) + break; + namelen--; + } + if (namelen != dentry->d_name.len) + continue; + retval = memcmp(dentry->d_name.name, name, namelen); + if (retval > 0) + continue; + if (!retval) { + inode = get_cramfs_inode(dir->i_sb, de, dir_off); + break; + } + /* else (retval < 0) */ + if (sorted) + break; + } +out: + mutex_unlock(&read_mutex); + return d_splice_alias(inode, dentry); +} + +static int cramfs_readpage(struct file *file, struct page *page) +{ + struct inode *inode = page->mapping->host; + u32 maxblock; + int bytes_filled; + void *pgdata; + + maxblock = (inode->i_size + PAGE_SIZE - 1) >> PAGE_SHIFT; + bytes_filled = 0; + pgdata = kmap(page); + + if (page->index < maxblock) { + struct super_block *sb = inode->i_sb; + u32 blkptr_offset = OFFSET(inode) + page->index * 4; + u32 block_ptr, block_start, block_len; + bool uncompressed, direct; + + mutex_lock(&read_mutex); + block_ptr = *(u32 *) cramfs_read(sb, blkptr_offset, 4); + uncompressed = (block_ptr & CRAMFS_BLK_FLAG_UNCOMPRESSED); + direct = (block_ptr & CRAMFS_BLK_FLAG_DIRECT_PTR); + block_ptr &= ~CRAMFS_BLK_FLAGS; + + if (direct) { + /* + * The block pointer is an absolute start pointer, + * shifted by 2 bits. The size is included in the + * first 2 bytes of the data block when compressed, + * or PAGE_SIZE otherwise. + */ + block_start = block_ptr << CRAMFS_BLK_DIRECT_PTR_SHIFT; + if (uncompressed) { + block_len = PAGE_SIZE; + /* if last block: cap to file length */ + if (page->index == maxblock - 1) + block_len = + offset_in_page(inode->i_size); + } else { + block_len = *(u16 *) + cramfs_read(sb, block_start, 2); + block_start += 2; + } + } else { + /* + * The block pointer indicates one past the end of + * the current block (start of next block). If this + * is the first block then it starts where the block + * pointer table ends, otherwise its start comes + * from the previous block's pointer. + */ + block_start = OFFSET(inode) + maxblock * 4; + if (page->index) + block_start = *(u32 *) + cramfs_read(sb, blkptr_offset - 4, 4); + /* Beware... previous ptr might be a direct ptr */ + if (unlikely(block_start & CRAMFS_BLK_FLAG_DIRECT_PTR)) { + /* See comments on earlier code. */ + u32 prev_start = block_start; + block_start = prev_start & ~CRAMFS_BLK_FLAGS; + block_start <<= CRAMFS_BLK_DIRECT_PTR_SHIFT; + if (prev_start & CRAMFS_BLK_FLAG_UNCOMPRESSED) { + block_start += PAGE_SIZE; + } else { + block_len = *(u16 *) + cramfs_read(sb, block_start, 2); + block_start += 2 + block_len; + } + } + block_start &= ~CRAMFS_BLK_FLAGS; + block_len = block_ptr - block_start; + } + + if (block_len == 0) + ; /* hole */ + else if (unlikely(block_len > 2*PAGE_SIZE || + (uncompressed && block_len > PAGE_SIZE))) { + mutex_unlock(&read_mutex); + pr_err("bad data blocksize %u\n", block_len); + goto err; + } else if (uncompressed) { + memcpy(pgdata, + cramfs_read(sb, block_start, block_len), + block_len); + bytes_filled = block_len; + } else { + bytes_filled = cramfs_uncompress_block(pgdata, + PAGE_SIZE, + cramfs_read(sb, block_start, block_len), + block_len); + } + mutex_unlock(&read_mutex); + if (unlikely(bytes_filled < 0)) + goto err; + } + + memset(pgdata + bytes_filled, 0, PAGE_SIZE - bytes_filled); + flush_dcache_page(page); + kunmap(page); + SetPageUptodate(page); + unlock_page(page); + return 0; + +err: + kunmap(page); + ClearPageUptodate(page); + SetPageError(page); + unlock_page(page); + return 0; +} + +static const struct address_space_operations cramfs_aops = { + .readpage = cramfs_readpage +}; + +/* + * Our operations: + */ + +/* + * A directory can only readdir + */ +static const struct file_operations cramfs_directory_operations = { + .llseek = generic_file_llseek, + .read = generic_read_dir, + .iterate_shared = cramfs_readdir, +}; + +static const struct inode_operations cramfs_dir_inode_operations = { + .lookup = cramfs_lookup, +}; + +static const struct super_operations cramfs_ops = { + .statfs = cramfs_statfs, +}; + +static int cramfs_get_tree(struct fs_context *fc) +{ + int ret = -ENOPROTOOPT; + + if (IS_ENABLED(CONFIG_CRAMFS_MTD)) { + ret = get_tree_mtd(fc, cramfs_mtd_fill_super); + if (!ret) + return 0; + } + if (IS_ENABLED(CONFIG_CRAMFS_BLOCKDEV)) + ret = get_tree_bdev(fc, cramfs_blkdev_fill_super); + return ret; +} + +static const struct fs_context_operations cramfs_context_ops = { + .get_tree = cramfs_get_tree, + .reconfigure = cramfs_reconfigure, +}; + +/* + * Set up the filesystem mount context. + */ +static int cramfs_init_fs_context(struct fs_context *fc) +{ + fc->ops = &cramfs_context_ops; + return 0; +} + +static struct file_system_type cramfs_fs_type = { + .owner = THIS_MODULE, + .name = "cramfs", + .init_fs_context = cramfs_init_fs_context, + .kill_sb = cramfs_kill_sb, + .fs_flags = FS_REQUIRES_DEV, +}; +MODULE_ALIAS_FS("cramfs"); + +static int __init init_cramfs_fs(void) +{ + int rv; + + rv = cramfs_uncompress_init(); + if (rv < 0) + return rv; + rv = register_filesystem(&cramfs_fs_type); + if (rv < 0) + cramfs_uncompress_exit(); + return rv; +} + +static void __exit exit_cramfs_fs(void) +{ + cramfs_uncompress_exit(); + unregister_filesystem(&cramfs_fs_type); +} + +module_init(init_cramfs_fs) +module_exit(exit_cramfs_fs) +MODULE_LICENSE("GPL"); diff --git a/fs/cramfs/internal.h b/fs/cramfs/internal.h new file mode 100644 index 000000000..349d71272 --- /dev/null +++ b/fs/cramfs/internal.h @@ -0,0 +1,4 @@ +/* Uncompression interfaces to the underlying zlib */ +int cramfs_uncompress_block(void *dst, int dstlen, void *src, int srclen); +int cramfs_uncompress_init(void); +void cramfs_uncompress_exit(void); diff --git a/fs/cramfs/uncompress.c b/fs/cramfs/uncompress.c new file mode 100644 index 000000000..975d98fc2 --- /dev/null +++ b/fs/cramfs/uncompress.c @@ -0,0 +1,80 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * uncompress.c + * + * (C) Copyright 1999 Linus Torvalds + * + * cramfs interfaces to the uncompression library. There's really just + * three entrypoints: + * + * - cramfs_uncompress_init() - called to initialize the thing. + * - cramfs_uncompress_exit() - tell me when you're done + * - cramfs_uncompress_block() - uncompress a block. + * + * NOTE NOTE NOTE! The uncompression is entirely single-threaded. We + * only have one stream, and we'll initialize it only once even if it + * then is used by multiple filesystems. + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include <linux/kernel.h> +#include <linux/errno.h> +#include <linux/vmalloc.h> +#include <linux/zlib.h> +#include "internal.h" + +static z_stream stream; +static int initialized; + +/* Returns length of decompressed data. */ +int cramfs_uncompress_block(void *dst, int dstlen, void *src, int srclen) +{ + int err; + + stream.next_in = src; + stream.avail_in = srclen; + + stream.next_out = dst; + stream.avail_out = dstlen; + + err = zlib_inflateReset(&stream); + if (err != Z_OK) { + pr_err("zlib_inflateReset error %d\n", err); + zlib_inflateEnd(&stream); + zlib_inflateInit(&stream); + } + + err = zlib_inflate(&stream, Z_FINISH); + if (err != Z_STREAM_END) + goto err; + return stream.total_out; + +err: + pr_err("Error %d while decompressing!\n", err); + pr_err("%p(%d)->%p(%d)\n", src, srclen, dst, dstlen); + return -EIO; +} + +int cramfs_uncompress_init(void) +{ + if (!initialized++) { + stream.workspace = vmalloc(zlib_inflate_workspacesize()); + if (!stream.workspace) { + initialized = 0; + return -ENOMEM; + } + stream.next_in = NULL; + stream.avail_in = 0; + zlib_inflateInit(&stream); + } + return 0; +} + +void cramfs_uncompress_exit(void) +{ + if (!--initialized) { + zlib_inflateEnd(&stream); + vfree(stream.workspace); + } +} |