linux/lib/xz/xz_dec_bcj.c

/*
 * Branch/Call/Jump (BCJ) filter decoders
 *
 * Authors: Lasse Collin <[email protected]>
 *          Igor Pavlov <https://7-zip.org/>
 *
 * This file has been put into the public domain.
 * You can do whatever you want with this file.
 */

#include "xz_private.h"

/*
 * The rest of the file is inside this ifdef. It makes things a little more
 * convenient when building without support for any BCJ filters.
 */
#ifdef XZ_DEC_BCJ

struct xz_dec_bcj { … };

#ifdef XZ_DEC_X86
/*
 * This is used to test the most significant byte of a memory address
 * in an x86 instruction.
 */
static inline int bcj_x86_test_msbyte(uint8_t b)
{ … }

static size_t bcj_x86(struct xz_dec_bcj *s, uint8_t *buf, size_t size)
{ … }
#endif

#ifdef XZ_DEC_POWERPC
static size_t bcj_powerpc(struct xz_dec_bcj *s, uint8_t *buf, size_t size)
{ … }
#endif

#ifdef XZ_DEC_IA64
static size_t bcj_ia64(struct xz_dec_bcj *s, uint8_t *buf, size_t size)
{
	static const uint8_t branch_table[32] = {
		0, 0, 0, 0, 0, 0, 0, 0,
		0, 0, 0, 0, 0, 0, 0, 0,
		4, 4, 6, 6, 0, 0, 7, 7,
		4, 4, 0, 0, 4, 4, 0, 0
	};

	/*
	 * The local variables take a little bit stack space, but it's less
	 * than what LZMA2 decoder takes, so it doesn't make sense to reduce
	 * stack usage here without doing that for the LZMA2 decoder too.
	 */

	/* Loop counters */
	size_t i;
	size_t j;

	/* Instruction slot (0, 1, or 2) in the 128-bit instruction word */
	uint32_t slot;

	/* Bitwise offset of the instruction indicated by slot */
	uint32_t bit_pos;

	/* bit_pos split into byte and bit parts */
	uint32_t byte_pos;
	uint32_t bit_res;

	/* Address part of an instruction */
	uint32_t addr;

	/* Mask used to detect which instructions to convert */
	uint32_t mask;

	/* 41-bit instruction stored somewhere in the lowest 48 bits */
	uint64_t instr;

	/* Instruction normalized with bit_res for easier manipulation */
	uint64_t norm;

	for (i = 0; i + 16 <= size; i += 16) {
		mask = branch_table[buf[i] & 0x1F];
		for (slot = 0, bit_pos = 5; slot < 3; ++slot, bit_pos += 41) {
			if (((mask >> slot) & 1) == 0)
				continue;

			byte_pos = bit_pos >> 3;
			bit_res = bit_pos & 7;
			instr = 0;
			for (j = 0; j < 6; ++j)
				instr |= (uint64_t)(buf[i + j + byte_pos])
						<< (8 * j);

			norm = instr >> bit_res;

			if (((norm >> 37) & 0x0F) == 0x05
					&& ((norm >> 9) & 0x07) == 0) {
				addr = (norm >> 13) & 0x0FFFFF;
				addr |= ((uint32_t)(norm >> 36) & 1) << 20;
				addr <<= 4;
				addr -= s->pos + (uint32_t)i;
				addr >>= 4;

				norm &= ~((uint64_t)0x8FFFFF << 13);
				norm |= (uint64_t)(addr & 0x0FFFFF) << 13;
				norm |= (uint64_t)(addr & 0x100000)
						<< (36 - 20);

				instr &= (1 << bit_res) - 1;
				instr |= norm << bit_res;

				for (j = 0; j < 6; j++)
					buf[i + j + byte_pos]
						= (uint8_t)(instr >> (8 * j));
			}
		}
	}

	return i;
}
#endif

#ifdef XZ_DEC_ARM
static size_t bcj_arm(struct xz_dec_bcj *s, uint8_t *buf, size_t size)
{ … }
#endif

#ifdef XZ_DEC_ARMTHUMB
static size_t bcj_armthumb(struct xz_dec_bcj *s, uint8_t *buf, size_t size)
{ … }
#endif

#ifdef XZ_DEC_SPARC
static size_t bcj_sparc(struct xz_dec_bcj *s, uint8_t *buf, size_t size)
{ … }
#endif

/*
 * Apply the selected BCJ filter. Update *pos and s->pos to match the amount
 * of data that got filtered.
 *
 * NOTE: This is implemented as a switch statement to avoid using function
 * pointers, which could be problematic in the kernel boot code, which must
 * avoid pointers to static data (at least on x86).
 */
static void bcj_apply(struct xz_dec_bcj *s,
		      uint8_t *buf, size_t *pos, size_t size)
{ … }

/*
 * Flush pending filtered data from temp to the output buffer.
 * Move the remaining mixture of possibly filtered and unfiltered
 * data to the beginning of temp.
 */
static void bcj_flush(struct xz_dec_bcj *s, struct xz_buf *b)
{ … }

/*
 * The BCJ filter functions are primitive in sense that they process the
 * data in chunks of 1-16 bytes. To hide this issue, this function does
 * some buffering.
 */
XZ_EXTERN enum xz_ret xz_dec_bcj_run(struct xz_dec_bcj *s,
				     struct xz_dec_lzma2 *lzma2,
				     struct xz_buf *b)
{ … }

XZ_EXTERN struct xz_dec_bcj *xz_dec_bcj_create(bool single_call)
{ … }

XZ_EXTERN enum xz_ret xz_dec_bcj_reset(struct xz_dec_bcj *s, uint8_t id)
{ … }

#endif