decompress_unzstd.c | Explore in Territory

// SPDX-License-Identifier: GPL-2.0

/*
 * Important notes about in-place decompression
 *
 * At least on x86, the kernel is decompressed in place: the compressed data
 * is placed to the end of the output buffer, and the decompressor overwrites
 * most of the compressed data. There must be enough safety margin to
 * guarantee that the write position is always behind the read position.
 *
 * The safety margin for ZSTD with a 128 KB block size is calculated below.
 * Note that the margin with ZSTD is bigger than with GZIP or XZ!
 *
 * The worst case for in-place decompression is that the beginning of
 * the file is compressed extremely well, and the rest of the file is
 * uncompressible. Thus, we must look for worst-case expansion when the
 * compressor is encoding uncompressible data.
 *
 * The structure of the .zst file in case of a compressed kernel is as follows.
 * Maximum sizes (as bytes) of the fields are in parenthesis.
 *
 *    Frame Header: (18)
 *    Blocks: (N)
 *    Checksum: (4)
 *
 * The frame header and checksum overhead is at most 22 bytes.
 *
 * ZSTD stores the data in blocks. Each block has a header whose size is
 * a 3 bytes. After the block header, there is up to 128 KB of payload.
 * The maximum uncompressed size of the payload is 128 KB. The minimum
 * uncompressed size of the payload is never less than the payload size
 * (excluding the block header).
 *
 * The assumption, that the uncompressed size of the payload is never
 * smaller than the payload itself, is valid only when talking about
 * the payload as a whole. It is possible that the payload has parts where
 * the decompressor consumes more input than it produces output. Calculating
 * the worst case for this would be tricky. Instead of trying to do that,
 * let's simply make sure that the decompressor never overwrites any bytes
 * of the payload which it is currently reading.
 *
 * Now we have enough information to calculate the safety margin. We need
 *   - 22 bytes for the .zst file format headers;
 *   - 3 bytes per every 128 KiB of uncompressed size (one block header per
 *     block); and
 *   - 128 KiB (biggest possible zstd block size) to make sure that the
 *     decompressor never overwrites anything from the block it is currently
 *     reading.
 *
 * We get the following formula:
 *
 *    safety_margin = 22 + uncompressed_size * 3 / 131072 + 131072
 *                 <= 22 + (uncompressed_size >> 15) + 131072
 */

/*
 * Preboot environments #include "path/to/decompress_unzstd.c".
 * All of the source files we depend on must be #included.
 * zstd's only source dependency is xxhash, which has no source
 * dependencies.
 *
 * When UNZSTD_PREBOOT is defined we declare __decompress(), which is
 * used for kernel decompression, instead of unzstd().
 *
 * Define __DISABLE_EXPORTS in preboot environments to prevent symbols
 * from xxhash and zstd from being exported by the EXPORT_SYMBOL macro.
 */
#ifdef STATIC
#define UNZSTD_PREBOOT
# include "xxhash.c"
# include "zstd/decompress_sources.h"
#else
#include <linux/decompress/unzstd.h>
#endif

#include <linux/decompress/mm.h>
#include <linux/kernel.h>
#include <linux/zstd.h>

/* 128MB is the maximum window size supported by zstd. */
#define ZSTD_WINDOWSIZE_MAX …
/*
 * Size of the input and output buffers in multi-call mode.
 * Pick a larger size because it isn't used during kernel decompression,
 * since that is single pass, and we have to allocate a large buffer for
 * zstd's window anyway. The larger size speeds up initramfs decompression.
 */
#define ZSTD_IOBUF_SIZE …

static int INIT handle_zstd_error(size_t ret, void (*error)(char *x))
{ … }

/*
 * Handle the case where we have the entire input and output in one segment.
 * We can allocate less memory (no circular buffer for the sliding window),
 * and avoid some memcpy() calls.
 */
static int INIT decompress_single(const u8 *in_buf, long in_len, u8 *out_buf,
				  long out_len, long *in_pos,
				  void (*error)(char *x))
{ … }

static int INIT __unzstd(unsigned char *in_buf, long in_len,
			 long (*fill)(void*, unsigned long),
			 long (*flush)(void*, unsigned long),
			 unsigned char *out_buf, long out_len,
			 long *in_pos,
			 void (*error)(char *x))
{ … }

#ifndef UNZSTD_PREBOOT
STATIC int INIT unzstd(unsigned char *buf, long len,
		       long (*fill)(void*, unsigned long),
		       long (*flush)(void*, unsigned long),
		       unsigned char *out_buf,
		       long *pos,
		       void (*error)(char *x))
{ … }
#else
STATIC int INIT __decompress(unsigned char *buf, long len,
			     long (*fill)(void*, unsigned long),
			     long (*flush)(void*, unsigned long),
			     unsigned char *out_buf, long out_len,
			     long *pos,
			     void (*error)(char *x))
{
	return __unzstd(buf, len, fill, flush, out_buf, out_len, pos, error);
}
#endif
linux/lib/decompress_unzstd.c
