270f8710f9
ARMv8.0 has optional crc32 instruction for crc32 calculation. The instruction is mandatory since ARMv8.1. The crc32 calculation is faster using the dedicated instruction, e.g. 1.4 GHz iMX8MN gives: => time crc32 0x50000000 0x2000000 time: 0.126 seconds # crc32 instruction time: 0.213 seconds # software crc32 Add implementation using the compiler builtin wrapper for the crc32 instruction and enable it by default, since we don't support any platforms which do not implement this instruction. Signed-off-by: Marek Vasut <marex@denx.de> Cc: Simon Glass <sjg@chromium.org> [trini: Make crc32_table guarded by CONFIG_ARM64_CRC32] Signed-off-by: Tom Rini <trini@konsulko.com>
276 lines
11 KiB
C
276 lines
11 KiB
C
/*
|
|
* This file is derived from crc32.c from the zlib-1.1.3 distribution
|
|
* by Jean-loup Gailly and Mark Adler.
|
|
*/
|
|
|
|
/* crc32.c -- compute the CRC-32 of a data stream
|
|
* Copyright (C) 1995-1998 Mark Adler
|
|
* For conditions of distribution and use, see copyright notice in zlib.h
|
|
*/
|
|
|
|
#ifdef USE_HOSTCC
|
|
#include <arpa/inet.h>
|
|
#include <u-boot/crc.h>
|
|
#else
|
|
#include <common.h>
|
|
#include <efi_loader.h>
|
|
#endif
|
|
#include <compiler.h>
|
|
#include <u-boot/crc.h>
|
|
|
|
#if defined(CONFIG_HW_WATCHDOG) || defined(CONFIG_WATCHDOG)
|
|
#include <watchdog.h>
|
|
#endif
|
|
#include "u-boot/zlib.h"
|
|
|
|
#ifdef USE_HOSTCC
|
|
#define __efi_runtime
|
|
#define __efi_runtime_data
|
|
#define __efi_runtime_rodata
|
|
#endif
|
|
|
|
#define tole(x) cpu_to_le32(x)
|
|
|
|
#ifdef CONFIG_DYNAMIC_CRC_TABLE
|
|
|
|
static int __efi_runtime_data crc_table_empty = 1;
|
|
static uint32_t __efi_runtime_data crc_table[256];
|
|
static void __efi_runtime make_crc_table OF((void));
|
|
|
|
/*
|
|
Generate a table for a byte-wise 32-bit CRC calculation on the polynomial:
|
|
x^32+x^26+x^23+x^22+x^16+x^12+x^11+x^10+x^8+x^7+x^5+x^4+x^2+x+1.
|
|
|
|
Polynomials over GF(2) are represented in binary, one bit per coefficient,
|
|
with the lowest powers in the most significant bit. Then adding polynomials
|
|
is just exclusive-or, and multiplying a polynomial by x is a right shift by
|
|
one. If we call the above polynomial p, and represent a byte as the
|
|
polynomial q, also with the lowest power in the most significant bit (so the
|
|
byte 0xb1 is the polynomial x^7+x^3+x+1), then the CRC is (q*x^32) mod p,
|
|
where a mod b means the remainder after dividing a by b.
|
|
|
|
This calculation is done using the shift-register method of multiplying and
|
|
taking the remainder. The register is initialized to zero, and for each
|
|
incoming bit, x^32 is added mod p to the register if the bit is a one (where
|
|
x^32 mod p is p+x^32 = x^26+...+1), and the register is multiplied mod p by
|
|
x (which is shifting right by one and adding x^32 mod p if the bit shifted
|
|
out is a one). We start with the highest power (least significant bit) of
|
|
q and repeat for all eight bits of q.
|
|
|
|
The table is simply the CRC of all possible eight bit values. This is all
|
|
the information needed to generate CRC's on data a byte at a time for all
|
|
combinations of CRC register values and incoming bytes.
|
|
*/
|
|
static void __efi_runtime make_crc_table(void)
|
|
{
|
|
uint32_t c;
|
|
int n, k;
|
|
uLong poly; /* polynomial exclusive-or pattern */
|
|
/* terms of polynomial defining this crc (except x^32): */
|
|
static Byte __efi_runtime_data p[] = {
|
|
0, 1, 2, 4, 5, 7, 8, 10, 11, 12, 16, 22, 23, 26};
|
|
|
|
/* make exclusive-or pattern from polynomial (0xedb88320L) */
|
|
poly = 0L;
|
|
for (n = 0; n < sizeof(p)/sizeof(Byte); n++)
|
|
poly |= 1L << (31 - p[n]);
|
|
|
|
for (n = 0; n < 256; n++)
|
|
{
|
|
c = (uLong)n;
|
|
for (k = 0; k < 8; k++)
|
|
c = c & 1 ? poly ^ (c >> 1) : c >> 1;
|
|
crc_table[n] = tole(c);
|
|
}
|
|
crc_table_empty = 0;
|
|
}
|
|
#elif !defined(CONFIG_ARM64_CRC32)
|
|
/* ========================================================================
|
|
* Table of CRC-32's of all single-byte values (made by make_crc_table)
|
|
*/
|
|
|
|
static const uint32_t __efi_runtime_rodata crc_table[256] = {
|
|
tole(0x00000000L), tole(0x77073096L), tole(0xee0e612cL), tole(0x990951baL),
|
|
tole(0x076dc419L), tole(0x706af48fL), tole(0xe963a535L), tole(0x9e6495a3L),
|
|
tole(0x0edb8832L), tole(0x79dcb8a4L), tole(0xe0d5e91eL), tole(0x97d2d988L),
|
|
tole(0x09b64c2bL), tole(0x7eb17cbdL), tole(0xe7b82d07L), tole(0x90bf1d91L),
|
|
tole(0x1db71064L), tole(0x6ab020f2L), tole(0xf3b97148L), tole(0x84be41deL),
|
|
tole(0x1adad47dL), tole(0x6ddde4ebL), tole(0xf4d4b551L), tole(0x83d385c7L),
|
|
tole(0x136c9856L), tole(0x646ba8c0L), tole(0xfd62f97aL), tole(0x8a65c9ecL),
|
|
tole(0x14015c4fL), tole(0x63066cd9L), tole(0xfa0f3d63L), tole(0x8d080df5L),
|
|
tole(0x3b6e20c8L), tole(0x4c69105eL), tole(0xd56041e4L), tole(0xa2677172L),
|
|
tole(0x3c03e4d1L), tole(0x4b04d447L), tole(0xd20d85fdL), tole(0xa50ab56bL),
|
|
tole(0x35b5a8faL), tole(0x42b2986cL), tole(0xdbbbc9d6L), tole(0xacbcf940L),
|
|
tole(0x32d86ce3L), tole(0x45df5c75L), tole(0xdcd60dcfL), tole(0xabd13d59L),
|
|
tole(0x26d930acL), tole(0x51de003aL), tole(0xc8d75180L), tole(0xbfd06116L),
|
|
tole(0x21b4f4b5L), tole(0x56b3c423L), tole(0xcfba9599L), tole(0xb8bda50fL),
|
|
tole(0x2802b89eL), tole(0x5f058808L), tole(0xc60cd9b2L), tole(0xb10be924L),
|
|
tole(0x2f6f7c87L), tole(0x58684c11L), tole(0xc1611dabL), tole(0xb6662d3dL),
|
|
tole(0x76dc4190L), tole(0x01db7106L), tole(0x98d220bcL), tole(0xefd5102aL),
|
|
tole(0x71b18589L), tole(0x06b6b51fL), tole(0x9fbfe4a5L), tole(0xe8b8d433L),
|
|
tole(0x7807c9a2L), tole(0x0f00f934L), tole(0x9609a88eL), tole(0xe10e9818L),
|
|
tole(0x7f6a0dbbL), tole(0x086d3d2dL), tole(0x91646c97L), tole(0xe6635c01L),
|
|
tole(0x6b6b51f4L), tole(0x1c6c6162L), tole(0x856530d8L), tole(0xf262004eL),
|
|
tole(0x6c0695edL), tole(0x1b01a57bL), tole(0x8208f4c1L), tole(0xf50fc457L),
|
|
tole(0x65b0d9c6L), tole(0x12b7e950L), tole(0x8bbeb8eaL), tole(0xfcb9887cL),
|
|
tole(0x62dd1ddfL), tole(0x15da2d49L), tole(0x8cd37cf3L), tole(0xfbd44c65L),
|
|
tole(0x4db26158L), tole(0x3ab551ceL), tole(0xa3bc0074L), tole(0xd4bb30e2L),
|
|
tole(0x4adfa541L), tole(0x3dd895d7L), tole(0xa4d1c46dL), tole(0xd3d6f4fbL),
|
|
tole(0x4369e96aL), tole(0x346ed9fcL), tole(0xad678846L), tole(0xda60b8d0L),
|
|
tole(0x44042d73L), tole(0x33031de5L), tole(0xaa0a4c5fL), tole(0xdd0d7cc9L),
|
|
tole(0x5005713cL), tole(0x270241aaL), tole(0xbe0b1010L), tole(0xc90c2086L),
|
|
tole(0x5768b525L), tole(0x206f85b3L), tole(0xb966d409L), tole(0xce61e49fL),
|
|
tole(0x5edef90eL), tole(0x29d9c998L), tole(0xb0d09822L), tole(0xc7d7a8b4L),
|
|
tole(0x59b33d17L), tole(0x2eb40d81L), tole(0xb7bd5c3bL), tole(0xc0ba6cadL),
|
|
tole(0xedb88320L), tole(0x9abfb3b6L), tole(0x03b6e20cL), tole(0x74b1d29aL),
|
|
tole(0xead54739L), tole(0x9dd277afL), tole(0x04db2615L), tole(0x73dc1683L),
|
|
tole(0xe3630b12L), tole(0x94643b84L), tole(0x0d6d6a3eL), tole(0x7a6a5aa8L),
|
|
tole(0xe40ecf0bL), tole(0x9309ff9dL), tole(0x0a00ae27L), tole(0x7d079eb1L),
|
|
tole(0xf00f9344L), tole(0x8708a3d2L), tole(0x1e01f268L), tole(0x6906c2feL),
|
|
tole(0xf762575dL), tole(0x806567cbL), tole(0x196c3671L), tole(0x6e6b06e7L),
|
|
tole(0xfed41b76L), tole(0x89d32be0L), tole(0x10da7a5aL), tole(0x67dd4accL),
|
|
tole(0xf9b9df6fL), tole(0x8ebeeff9L), tole(0x17b7be43L), tole(0x60b08ed5L),
|
|
tole(0xd6d6a3e8L), tole(0xa1d1937eL), tole(0x38d8c2c4L), tole(0x4fdff252L),
|
|
tole(0xd1bb67f1L), tole(0xa6bc5767L), tole(0x3fb506ddL), tole(0x48b2364bL),
|
|
tole(0xd80d2bdaL), tole(0xaf0a1b4cL), tole(0x36034af6L), tole(0x41047a60L),
|
|
tole(0xdf60efc3L), tole(0xa867df55L), tole(0x316e8eefL), tole(0x4669be79L),
|
|
tole(0xcb61b38cL), tole(0xbc66831aL), tole(0x256fd2a0L), tole(0x5268e236L),
|
|
tole(0xcc0c7795L), tole(0xbb0b4703L), tole(0x220216b9L), tole(0x5505262fL),
|
|
tole(0xc5ba3bbeL), tole(0xb2bd0b28L), tole(0x2bb45a92L), tole(0x5cb36a04L),
|
|
tole(0xc2d7ffa7L), tole(0xb5d0cf31L), tole(0x2cd99e8bL), tole(0x5bdeae1dL),
|
|
tole(0x9b64c2b0L), tole(0xec63f226L), tole(0x756aa39cL), tole(0x026d930aL),
|
|
tole(0x9c0906a9L), tole(0xeb0e363fL), tole(0x72076785L), tole(0x05005713L),
|
|
tole(0x95bf4a82L), tole(0xe2b87a14L), tole(0x7bb12baeL), tole(0x0cb61b38L),
|
|
tole(0x92d28e9bL), tole(0xe5d5be0dL), tole(0x7cdcefb7L), tole(0x0bdbdf21L),
|
|
tole(0x86d3d2d4L), tole(0xf1d4e242L), tole(0x68ddb3f8L), tole(0x1fda836eL),
|
|
tole(0x81be16cdL), tole(0xf6b9265bL), tole(0x6fb077e1L), tole(0x18b74777L),
|
|
tole(0x88085ae6L), tole(0xff0f6a70L), tole(0x66063bcaL), tole(0x11010b5cL),
|
|
tole(0x8f659effL), tole(0xf862ae69L), tole(0x616bffd3L), tole(0x166ccf45L),
|
|
tole(0xa00ae278L), tole(0xd70dd2eeL), tole(0x4e048354L), tole(0x3903b3c2L),
|
|
tole(0xa7672661L), tole(0xd06016f7L), tole(0x4969474dL), tole(0x3e6e77dbL),
|
|
tole(0xaed16a4aL), tole(0xd9d65adcL), tole(0x40df0b66L), tole(0x37d83bf0L),
|
|
tole(0xa9bcae53L), tole(0xdebb9ec5L), tole(0x47b2cf7fL), tole(0x30b5ffe9L),
|
|
tole(0xbdbdf21cL), tole(0xcabac28aL), tole(0x53b39330L), tole(0x24b4a3a6L),
|
|
tole(0xbad03605L), tole(0xcdd70693L), tole(0x54de5729L), tole(0x23d967bfL),
|
|
tole(0xb3667a2eL), tole(0xc4614ab8L), tole(0x5d681b02L), tole(0x2a6f2b94L),
|
|
tole(0xb40bbe37L), tole(0xc30c8ea1L), tole(0x5a05df1bL), tole(0x2d02ef8dL)
|
|
};
|
|
#endif
|
|
|
|
#if 0
|
|
/* =========================================================================
|
|
* This function can be used by asm versions of crc32()
|
|
*/
|
|
const uint32_t * ZEXPORT get_crc_table()
|
|
{
|
|
#ifdef CONFIG_DYNAMIC_CRC_TABLE
|
|
if (crc_table_empty) make_crc_table();
|
|
#endif
|
|
return (const uint32_t *)crc_table;
|
|
}
|
|
#endif
|
|
|
|
/* ========================================================================= */
|
|
# if __BYTE_ORDER == __LITTLE_ENDIAN
|
|
# define DO_CRC(x) crc = tab[(crc ^ (x)) & 255] ^ (crc >> 8)
|
|
# else
|
|
# define DO_CRC(x) crc = tab[((crc >> 24) ^ (x)) & 255] ^ (crc << 8)
|
|
# endif
|
|
|
|
/* ========================================================================= */
|
|
|
|
/* No ones complement version. JFFS2 (and other things ?)
|
|
* don't use ones compliment in their CRC calculations.
|
|
*/
|
|
uint32_t __efi_runtime crc32_no_comp(uint32_t crc, const Bytef *buf, uInt len)
|
|
{
|
|
#ifdef CONFIG_ARM64_CRC32
|
|
crc = cpu_to_le32(crc);
|
|
while (len--)
|
|
crc = __builtin_aarch64_crc32b(crc, *buf++);
|
|
return le32_to_cpu(crc);
|
|
#else
|
|
const uint32_t *tab = crc_table;
|
|
const uint32_t *b =(const uint32_t *)buf;
|
|
size_t rem_len;
|
|
#ifdef CONFIG_DYNAMIC_CRC_TABLE
|
|
if (crc_table_empty)
|
|
make_crc_table();
|
|
#endif
|
|
crc = cpu_to_le32(crc);
|
|
/* Align it */
|
|
if (((long)b) & 3 && len) {
|
|
uint8_t *p = (uint8_t *)b;
|
|
do {
|
|
DO_CRC(*p++);
|
|
} while ((--len) && ((long)p)&3);
|
|
b = (uint32_t *)p;
|
|
}
|
|
|
|
rem_len = len & 3;
|
|
len = len >> 2;
|
|
for (--b; len; --len) {
|
|
/* load data 32 bits wide, xor data 32 bits wide. */
|
|
crc ^= *++b; /* use pre increment for speed */
|
|
DO_CRC(0);
|
|
DO_CRC(0);
|
|
DO_CRC(0);
|
|
DO_CRC(0);
|
|
}
|
|
len = rem_len;
|
|
/* And the last few bytes */
|
|
if (len) {
|
|
uint8_t *p = (uint8_t *)(b + 1) - 1;
|
|
do {
|
|
DO_CRC(*++p); /* use pre increment for speed */
|
|
} while (--len);
|
|
}
|
|
|
|
return le32_to_cpu(crc);
|
|
#endif
|
|
}
|
|
#undef DO_CRC
|
|
|
|
uint32_t __efi_runtime crc32(uint32_t crc, const Bytef *p, uInt len)
|
|
{
|
|
return crc32_no_comp(crc ^ 0xffffffffL, p, len) ^ 0xffffffffL;
|
|
}
|
|
|
|
/*
|
|
* Calculate the crc32 checksum triggering the watchdog every 'chunk_sz' bytes
|
|
* of input.
|
|
*/
|
|
uint32_t crc32_wd(uint32_t crc, const unsigned char *buf, uInt len,
|
|
uInt chunk_sz)
|
|
{
|
|
#if defined(CONFIG_HW_WATCHDOG) || defined(CONFIG_WATCHDOG)
|
|
const unsigned char *end, *curr;
|
|
int chunk;
|
|
|
|
curr = buf;
|
|
end = buf + len;
|
|
while (curr < end) {
|
|
chunk = end - curr;
|
|
if (chunk > chunk_sz)
|
|
chunk = chunk_sz;
|
|
crc = crc32(crc, curr, chunk);
|
|
curr += chunk;
|
|
WATCHDOG_RESET ();
|
|
}
|
|
#else
|
|
crc = crc32(crc, buf, len);
|
|
#endif
|
|
|
|
return crc;
|
|
}
|
|
|
|
void crc32_wd_buf(const unsigned char *input, unsigned int ilen,
|
|
unsigned char *output, unsigned int chunk_sz)
|
|
{
|
|
uint32_t crc;
|
|
|
|
crc = crc32_wd(0, input, ilen, chunk_sz);
|
|
crc = htonl(crc);
|
|
memcpy(output, &crc, sizeof(crc));
|
|
}
|