diff options
Diffstat (limited to 'arch/riscv/lib')
| -rw-r--r-- | arch/riscv/lib/Makefile | 5 | ||||
| -rw-r--r-- | arch/riscv/lib/crc-clmul-consts.h | 122 | ||||
| -rw-r--r-- | arch/riscv/lib/crc-clmul-template.h | 265 | ||||
| -rw-r--r-- | arch/riscv/lib/crc-clmul.h | 23 | ||||
| -rw-r--r-- | arch/riscv/lib/crc-t10dif.c | 24 | ||||
| -rw-r--r-- | arch/riscv/lib/crc16_msb.c | 18 | ||||
| -rw-r--r-- | arch/riscv/lib/crc32-riscv.c | 311 | ||||
| -rw-r--r-- | arch/riscv/lib/crc32.c | 53 | ||||
| -rw-r--r-- | arch/riscv/lib/crc32_lsb.c | 18 | ||||
| -rw-r--r-- | arch/riscv/lib/crc32_msb.c | 18 | ||||
| -rw-r--r-- | arch/riscv/lib/crc64.c | 34 | ||||
| -rw-r--r-- | arch/riscv/lib/crc64_lsb.c | 18 | ||||
| -rw-r--r-- | arch/riscv/lib/crc64_msb.c | 18 | ||||
| -rw-r--r-- | arch/riscv/lib/csum.c | 21 | ||||
| -rw-r--r-- | arch/riscv/lib/strcmp.S | 5 | ||||
| -rw-r--r-- | arch/riscv/lib/strlen.S | 5 | ||||
| -rw-r--r-- | arch/riscv/lib/strncmp.S | 5 |
17 files changed, 628 insertions, 335 deletions
diff --git a/arch/riscv/lib/Makefile b/arch/riscv/lib/Makefile index 79368a895fee..b1c46153606a 100644 --- a/arch/riscv/lib/Makefile +++ b/arch/riscv/lib/Makefile @@ -16,6 +16,11 @@ lib-$(CONFIG_MMU) += uaccess.o lib-$(CONFIG_64BIT) += tishift.o lib-$(CONFIG_RISCV_ISA_ZICBOZ) += clear_page.o obj-$(CONFIG_CRC32_ARCH) += crc32-riscv.o +crc32-riscv-y := crc32.o crc32_msb.o crc32_lsb.o +obj-$(CONFIG_CRC64_ARCH) += crc64-riscv.o +crc64-riscv-y := crc64.o crc64_msb.o crc64_lsb.o +obj-$(CONFIG_CRC_T10DIF_ARCH) += crc-t10dif-riscv.o +crc-t10dif-riscv-y := crc-t10dif.o crc16_msb.o obj-$(CONFIG_FUNCTION_ERROR_INJECTION) += error-inject.o lib-$(CONFIG_RISCV_ISA_V) += xor.o lib-$(CONFIG_RISCV_ISA_V) += riscv_v_helpers.o diff --git a/arch/riscv/lib/crc-clmul-consts.h b/arch/riscv/lib/crc-clmul-consts.h new file mode 100644 index 000000000000..8d73449235ef --- /dev/null +++ b/arch/riscv/lib/crc-clmul-consts.h @@ -0,0 +1,122 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * CRC constants generated by: + * + * ./scripts/gen-crc-consts.py riscv_clmul crc16_msb_0x8bb7,crc32_msb_0x04c11db7,crc32_lsb_0xedb88320,crc32_lsb_0x82f63b78,crc64_msb_0x42f0e1eba9ea3693,crc64_lsb_0x9a6c9329ac4bc9b5 + * + * Do not edit manually. + */ + +struct crc_clmul_consts { + unsigned long fold_across_2_longs_const_hi; + unsigned long fold_across_2_longs_const_lo; + unsigned long barrett_reduction_const_1; + unsigned long barrett_reduction_const_2; +}; + +/* + * Constants generated for most-significant-bit-first CRC-16 using + * G(x) = x^16 + x^15 + x^11 + x^9 + x^8 + x^7 + x^5 + x^4 + x^2 + x^1 + x^0 + */ +static const struct crc_clmul_consts crc16_msb_0x8bb7_consts __maybe_unused = { +#ifdef CONFIG_64BIT + .fold_across_2_longs_const_hi = 0x0000000000001faa, /* x^192 mod G */ + .fold_across_2_longs_const_lo = 0x000000000000a010, /* x^128 mod G */ + .barrett_reduction_const_1 = 0xfb2d2bfc0e99d245, /* floor(x^79 / G) */ + .barrett_reduction_const_2 = 0x0000000000008bb7, /* G - x^16 */ +#else + .fold_across_2_longs_const_hi = 0x00005890, /* x^96 mod G */ + .fold_across_2_longs_const_lo = 0x0000f249, /* x^64 mod G */ + .barrett_reduction_const_1 = 0xfb2d2bfc, /* floor(x^47 / G) */ + .barrett_reduction_const_2 = 0x00008bb7, /* G - x^16 */ +#endif +}; + +/* + * Constants generated for most-significant-bit-first CRC-32 using + * G(x) = 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 + x^0 + */ +static const struct crc_clmul_consts crc32_msb_0x04c11db7_consts __maybe_unused = { +#ifdef CONFIG_64BIT + .fold_across_2_longs_const_hi = 0x00000000c5b9cd4c, /* x^192 mod G */ + .fold_across_2_longs_const_lo = 0x00000000e8a45605, /* x^128 mod G */ + .barrett_reduction_const_1 = 0x826880efa40da72d, /* floor(x^95 / G) */ + .barrett_reduction_const_2 = 0x0000000004c11db7, /* G - x^32 */ +#else + .fold_across_2_longs_const_hi = 0xf200aa66, /* x^96 mod G */ + .fold_across_2_longs_const_lo = 0x490d678d, /* x^64 mod G */ + .barrett_reduction_const_1 = 0x826880ef, /* floor(x^63 / G) */ + .barrett_reduction_const_2 = 0x04c11db7, /* G - x^32 */ +#endif +}; + +/* + * Constants generated for least-significant-bit-first CRC-32 using + * G(x) = 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 + x^0 + */ +static const struct crc_clmul_consts crc32_lsb_0xedb88320_consts __maybe_unused = { +#ifdef CONFIG_64BIT + .fold_across_2_longs_const_hi = 0x65673b4600000000, /* x^191 mod G */ + .fold_across_2_longs_const_lo = 0x9ba54c6f00000000, /* x^127 mod G */ + .barrett_reduction_const_1 = 0xb4e5b025f7011641, /* floor(x^95 / G) */ + .barrett_reduction_const_2 = 0x00000000edb88320, /* (G - x^32) * x^32 */ +#else + .fold_across_2_longs_const_hi = 0xccaa009e, /* x^95 mod G */ + .fold_across_2_longs_const_lo = 0xb8bc6765, /* x^63 mod G */ + .barrett_reduction_const_1 = 0xf7011641, /* floor(x^63 / G) */ + .barrett_reduction_const_2 = 0xedb88320, /* (G - x^32) * x^0 */ +#endif +}; + +/* + * Constants generated for least-significant-bit-first CRC-32 using + * G(x) = x^32 + x^28 + x^27 + x^26 + x^25 + x^23 + x^22 + x^20 + x^19 + x^18 + + * x^14 + x^13 + x^11 + x^10 + x^9 + x^8 + x^6 + x^0 + */ +static const struct crc_clmul_consts crc32_lsb_0x82f63b78_consts __maybe_unused = { +#ifdef CONFIG_64BIT + .fold_across_2_longs_const_hi = 0x3743f7bd00000000, /* x^191 mod G */ + .fold_across_2_longs_const_lo = 0x3171d43000000000, /* x^127 mod G */ + .barrett_reduction_const_1 = 0x4869ec38dea713f1, /* floor(x^95 / G) */ + .barrett_reduction_const_2 = 0x0000000082f63b78, /* (G - x^32) * x^32 */ +#else + .fold_across_2_longs_const_hi = 0x493c7d27, /* x^95 mod G */ + .fold_across_2_longs_const_lo = 0xdd45aab8, /* x^63 mod G */ + .barrett_reduction_const_1 = 0xdea713f1, /* floor(x^63 / G) */ + .barrett_reduction_const_2 = 0x82f63b78, /* (G - x^32) * x^0 */ +#endif +}; + +/* + * Constants generated for most-significant-bit-first CRC-64 using + * G(x) = x^64 + x^62 + x^57 + x^55 + x^54 + x^53 + x^52 + x^47 + x^46 + x^45 + + * x^40 + x^39 + x^38 + x^37 + x^35 + x^33 + x^32 + x^31 + x^29 + x^27 + + * x^24 + x^23 + x^22 + x^21 + x^19 + x^17 + x^13 + x^12 + x^10 + x^9 + + * x^7 + x^4 + x^1 + x^0 + */ +#ifdef CONFIG_64BIT +static const struct crc_clmul_consts crc64_msb_0x42f0e1eba9ea3693_consts __maybe_unused = { + .fold_across_2_longs_const_hi = 0x4eb938a7d257740e, /* x^192 mod G */ + .fold_across_2_longs_const_lo = 0x05f5c3c7eb52fab6, /* x^128 mod G */ + .barrett_reduction_const_1 = 0xabc694e836627c39, /* floor(x^127 / G) */ + .barrett_reduction_const_2 = 0x42f0e1eba9ea3693, /* G - x^64 */ +}; +#endif + +/* + * Constants generated for least-significant-bit-first CRC-64 using + * G(x) = x^64 + x^63 + x^61 + x^59 + x^58 + x^56 + x^55 + x^52 + x^49 + x^48 + + * x^47 + x^46 + x^44 + x^41 + x^37 + x^36 + x^34 + x^32 + x^31 + x^28 + + * x^26 + x^23 + x^22 + x^19 + x^16 + x^13 + x^12 + x^10 + x^9 + x^6 + + * x^4 + x^3 + x^0 + */ +#ifdef CONFIG_64BIT +static const struct crc_clmul_consts crc64_lsb_0x9a6c9329ac4bc9b5_consts __maybe_unused = { + .fold_across_2_longs_const_hi = 0xeadc41fd2ba3d420, /* x^191 mod G */ + .fold_across_2_longs_const_lo = 0x21e9761e252621ac, /* x^127 mod G */ + .barrett_reduction_const_1 = 0x27ecfa329aef9f77, /* floor(x^127 / G) */ + .barrett_reduction_const_2 = 0x9a6c9329ac4bc9b5, /* (G - x^64) * x^0 */ +}; +#endif diff --git a/arch/riscv/lib/crc-clmul-template.h b/arch/riscv/lib/crc-clmul-template.h new file mode 100644 index 000000000000..77187e7f1762 --- /dev/null +++ b/arch/riscv/lib/crc-clmul-template.h @@ -0,0 +1,265 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* Copyright 2025 Google LLC */ + +/* + * This file is a "template" that generates a CRC function optimized using the + * RISC-V Zbc (scalar carryless multiplication) extension. The includer of this + * file must define the following parameters to specify the type of CRC: + * + * crc_t: the data type of the CRC, e.g. u32 for a 32-bit CRC + * LSB_CRC: 0 for a msb (most-significant-bit) first CRC, i.e. natural + * mapping between bits and polynomial coefficients + * 1 for a lsb (least-significant-bit) first CRC, i.e. reflected + * mapping between bits and polynomial coefficients + */ + +#include <asm/byteorder.h> +#include <linux/minmax.h> + +#define CRC_BITS (8 * sizeof(crc_t)) /* a.k.a. 'n' */ + +static inline unsigned long clmul(unsigned long a, unsigned long b) +{ + unsigned long res; + + asm(".option push\n" + ".option arch,+zbc\n" + "clmul %0, %1, %2\n" + ".option pop\n" + : "=r" (res) : "r" (a), "r" (b)); + return res; +} + +static inline unsigned long clmulh(unsigned long a, unsigned long b) +{ + unsigned long res; + + asm(".option push\n" + ".option arch,+zbc\n" + "clmulh %0, %1, %2\n" + ".option pop\n" + : "=r" (res) : "r" (a), "r" (b)); + return res; +} + +static inline unsigned long clmulr(unsigned long a, unsigned long b) +{ + unsigned long res; + + asm(".option push\n" + ".option arch,+zbc\n" + "clmulr %0, %1, %2\n" + ".option pop\n" + : "=r" (res) : "r" (a), "r" (b)); + return res; +} + +/* + * crc_load_long() loads one "unsigned long" of aligned data bytes, producing a + * polynomial whose bit order matches the CRC's bit order. + */ +#ifdef CONFIG_64BIT +# if LSB_CRC +# define crc_load_long(x) le64_to_cpup(x) +# else +# define crc_load_long(x) be64_to_cpup(x) +# endif +#else +# if LSB_CRC +# define crc_load_long(x) le32_to_cpup(x) +# else +# define crc_load_long(x) be32_to_cpup(x) +# endif +#endif + +/* XOR @crc into the end of @msgpoly that represents the high-order terms. */ +static inline unsigned long +crc_clmul_prep(crc_t crc, unsigned long msgpoly) +{ +#if LSB_CRC + return msgpoly ^ crc; +#else + return msgpoly ^ ((unsigned long)crc << (BITS_PER_LONG - CRC_BITS)); +#endif +} + +/* + * Multiply the long-sized @msgpoly by x^n (a.k.a. x^CRC_BITS) and reduce it + * modulo the generator polynomial G. This gives the CRC of @msgpoly. + */ +static inline crc_t +crc_clmul_long(unsigned long msgpoly, const struct crc_clmul_consts *consts) +{ + unsigned long tmp; + + /* + * First step of Barrett reduction with integrated multiplication by + * x^n: calculate floor((msgpoly * x^n) / G). This is the value by + * which G needs to be multiplied to cancel out the x^n and higher terms + * of msgpoly * x^n. Do it using the following formula: + * + * msb-first: + * floor((msgpoly * floor(x^(BITS_PER_LONG-1+n) / G)) / x^(BITS_PER_LONG-1)) + * lsb-first: + * floor((msgpoly * floor(x^(BITS_PER_LONG-1+n) / G) * x) / x^BITS_PER_LONG) + * + * barrett_reduction_const_1 contains floor(x^(BITS_PER_LONG-1+n) / G), + * which fits a long exactly. Using any lower power of x there would + * not carry enough precision through the calculation, while using any + * higher power of x would require extra instructions to handle a wider + * multiplication. In the msb-first case, using this power of x results + * in needing a floored division by x^(BITS_PER_LONG-1), which matches + * what clmulr produces. In the lsb-first case, a factor of x gets + * implicitly introduced by each carryless multiplication (shown as + * '* x' above), and the floored division instead needs to be by + * x^BITS_PER_LONG which matches what clmul produces. + */ +#if LSB_CRC + tmp = clmul(msgpoly, consts->barrett_reduction_const_1); +#else + tmp = clmulr(msgpoly, consts->barrett_reduction_const_1); +#endif + + /* + * Second step of Barrett reduction: + * + * crc := (msgpoly * x^n) + (G * floor((msgpoly * x^n) / G)) + * + * This reduces (msgpoly * x^n) modulo G by adding the appropriate + * multiple of G to it. The result uses only the x^0..x^(n-1) terms. + * HOWEVER, since the unreduced value (msgpoly * x^n) is zero in those + * terms in the first place, it is more efficient to do the equivalent: + * + * crc := ((G - x^n) * floor((msgpoly * x^n) / G)) mod x^n + * + * In the lsb-first case further modify it to the following which avoids + * a shift, as the crc ends up in the physically low n bits from clmulr: + * + * product := ((G - x^n) * x^(BITS_PER_LONG - n)) * floor((msgpoly * x^n) / G) * x + * crc := floor(product / x^(BITS_PER_LONG + 1 - n)) mod x^n + * + * barrett_reduction_const_2 contains the constant multiplier (G - x^n) + * or (G - x^n) * x^(BITS_PER_LONG - n) from the formulas above. The + * cast of the result to crc_t is essential, as it applies the mod x^n! + */ +#if LSB_CRC + return clmulr(tmp, consts->barrett_reduction_const_2); +#else + return clmul(tmp, consts->barrett_reduction_const_2); +#endif +} + +/* Update @crc with the data from @msgpoly. */ +static inline crc_t +crc_clmul_update_long(crc_t crc, unsigned long msgpoly, + const struct crc_clmul_consts *consts) +{ + return crc_clmul_long(crc_clmul_prep(crc, msgpoly), consts); +} + +/* Update @crc with 1 <= @len < sizeof(unsigned long) bytes of data. */ +static inline crc_t +crc_clmul_update_partial(crc_t crc, const u8 *p, size_t len, + const struct crc_clmul_consts *consts) +{ + unsigned long msgpoly; + size_t i; + +#if LSB_CRC + msgpoly = (unsigned long)p[0] << (BITS_PER_LONG - 8); + for (i = 1; i < len; i++) + msgpoly = (msgpoly >> 8) ^ ((unsigned long)p[i] << (BITS_PER_LONG - 8)); +#else + msgpoly = p[0]; + for (i = 1; i < len; i++) + msgpoly = (msgpoly << 8) ^ p[i]; +#endif + + if (len >= sizeof(crc_t)) { + #if LSB_CRC + msgpoly ^= (unsigned long)crc << (BITS_PER_LONG - 8*len); + #else + msgpoly ^= (unsigned long)crc << (8*len - CRC_BITS); + #endif + return crc_clmul_long(msgpoly, consts); + } +#if LSB_CRC + msgpoly ^= (unsigned long)crc << (BITS_PER_LONG - 8*len); + return crc_clmul_long(msgpoly, consts) ^ (crc >> (8*len)); +#else + msgpoly ^= crc >> (CRC_BITS - 8*len); + return crc_clmul_long(msgpoly, consts) ^ (crc << (8*len)); +#endif +} + +static inline crc_t +crc_clmul(crc_t crc, const void *p, size_t len, + const struct crc_clmul_consts *consts) +{ + size_t align; + + /* This implementation assumes that the CRC fits in an unsigned long. */ + BUILD_BUG_ON(sizeof(crc_t) > sizeof(unsigned long)); + + /* If the buffer is not long-aligned, align it. */ + align = (unsigned long)p % sizeof(unsigned long); + if (align && len) { + align = min(sizeof(unsigned long) - align, len); + crc = crc_clmul_update_partial(crc, p, align, consts); + p += align; + len -= align; + } + + if (len >= 4 * sizeof(unsigned long)) { + unsigned long m0, m1; + + m0 = crc_clmul_prep(crc, crc_load_long(p)); + m1 = crc_load_long(p + sizeof(unsigned long)); + p += 2 * sizeof(unsigned long); + len -= 2 * sizeof(unsigned long); + /* + * Main loop. Each iteration starts with a message polynomial + * (x^BITS_PER_LONG)*m0 + m1, then logically extends it by two + * more longs of data to form x^(3*BITS_PER_LONG)*m0 + + * x^(2*BITS_PER_LONG)*m1 + x^BITS_PER_LONG*m2 + m3, then + * "folds" that back into a congruent (modulo G) value that uses + * just m0 and m1 again. This is done by multiplying m0 by the + * precomputed constant (x^(3*BITS_PER_LONG) mod G) and m1 by + * the precomputed constant (x^(2*BITS_PER_LONG) mod G), then + * adding the results to m2 and m3 as appropriate. Each such + * multiplication produces a result twice the length of a long, + * which in RISC-V is two instructions clmul and clmulh. + * + * This could be changed to fold across more than 2 longs at a + * time if there is a CPU that can take advantage of it. + */ + do { + unsigned long p0, p1, p2, p3; + + p0 = clmulh(m0, consts->fold_across_2_longs_const_hi); + p1 = clmul(m0, consts->fold_across_2_longs_const_hi); + p2 = clmulh(m1, consts->fold_across_2_longs_const_lo); + p3 = clmul(m1, consts->fold_across_2_longs_const_lo); + m0 = (LSB_CRC ? p1 ^ p3 : p0 ^ p2) ^ crc_load_long(p); + m1 = (LSB_CRC ? p0 ^ p2 : p1 ^ p3) ^ + crc_load_long(p + sizeof(unsigned long)); + + p += 2 * sizeof(unsigned long); + len -= 2 * sizeof(unsigned long); + } while (len >= 2 * sizeof(unsigned long)); + + crc = crc_clmul_long(m0, consts); + crc = crc_clmul_update_long(crc, m1, consts); + } + + while (len >= sizeof(unsigned long)) { + crc = crc_clmul_update_long(crc, crc_load_long(p), consts); + p += sizeof(unsigned long); + len -= sizeof(unsigned long); + } + + if (len) + crc = crc_clmul_update_partial(crc, p, len, consts); + + return crc; +} diff --git a/arch/riscv/lib/crc-clmul.h b/arch/riscv/lib/crc-clmul.h new file mode 100644 index 000000000000..dd1736245815 --- /dev/null +++ b/arch/riscv/lib/crc-clmul.h @@ -0,0 +1,23 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* Copyright 2025 Google LLC */ + +#ifndef _RISCV_CRC_CLMUL_H +#define _RISCV_CRC_CLMUL_H + +#include <linux/types.h> +#include "crc-clmul-consts.h" + +u16 crc16_msb_clmul(u16 crc, const void *p, size_t len, + const struct crc_clmul_consts *consts); +u32 crc32_msb_clmul(u32 crc, const void *p, size_t len, + const struct crc_clmul_consts *consts); +u32 crc32_lsb_clmul(u32 crc, const void *p, size_t len, + const struct crc_clmul_consts *consts); +#ifdef CONFIG_64BIT +u64 crc64_msb_clmul(u64 crc, const void *p, size_t len, + const struct crc_clmul_consts *consts); +u64 crc64_lsb_clmul(u64 crc, const void *p, size_t len, + const struct crc_clmul_consts *consts); +#endif + +#endif /* _RISCV_CRC_CLMUL_H */ diff --git a/arch/riscv/lib/crc-t10dif.c b/arch/riscv/lib/crc-t10dif.c new file mode 100644 index 000000000000..e6b0051ccd86 --- /dev/null +++ b/arch/riscv/lib/crc-t10dif.c @@ -0,0 +1,24 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * RISC-V optimized CRC-T10DIF function + * + * Copyright 2025 Google LLC + */ + +#include <asm/hwcap.h> +#include <asm/alternative-macros.h> +#include <linux/crc-t10dif.h> +#include <linux/module.h> + +#include "crc-clmul.h" + +u16 crc_t10dif_arch(u16 crc, const u8 *p, size_t len) +{ + if (riscv_has_extension_likely(RISCV_ISA_EXT_ZBC)) + return crc16_msb_clmul(crc, p, len, &crc16_msb_0x8bb7_consts); + return crc_t10dif_generic(crc, p, len); +} +EXPORT_SYMBOL(crc_t10dif_arch); + +MODULE_DESCRIPTION("RISC-V optimized CRC-T10DIF function"); +MODULE_LICENSE("GPL"); diff --git a/arch/riscv/lib/crc16_msb.c b/arch/riscv/lib/crc16_msb.c new file mode 100644 index 000000000000..554d295e95f5 --- /dev/null +++ b/arch/riscv/lib/crc16_msb.c @@ -0,0 +1,18 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * RISC-V optimized most-significant-bit-first CRC16 + * + * Copyright 2025 Google LLC + */ + +#include "crc-clmul.h" + +typedef u16 crc_t; +#define LSB_CRC 0 +#include "crc-clmul-template.h" + +u16 crc16_msb_clmul(u16 crc, const void *p, size_t len, + const struct crc_clmul_consts *consts) +{ + return crc_clmul(crc, p, len, consts); +} diff --git a/arch/riscv/lib/crc32-riscv.c b/arch/riscv/lib/crc32-riscv.c deleted file mode 100644 index 53d56ab422c7..000000000000 --- a/arch/riscv/lib/crc32-riscv.c +++ /dev/null @@ -1,311 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * Accelerated CRC32 implementation with Zbc extension. - * - * Copyright (C) 2024 Intel Corporation - */ - -#include <asm/hwcap.h> -#include <asm/alternative-macros.h> -#include <asm/byteorder.h> - -#include <linux/types.h> -#include <linux/minmax.h> -#include <linux/crc32poly.h> -#include <linux/crc32.h> -#include <linux/byteorder/generic.h> -#include <linux/module.h> - -/* - * Refer to https://www.corsix.org/content/barrett-reduction-polynomials for - * better understanding of how this math works. - * - * let "+" denotes polynomial add (XOR) - * let "-" denotes polynomial sub (XOR) - * let "*" denotes polynomial multiplication - * let "/" denotes polynomial floor division - * let "S" denotes source data, XLEN bit wide - * let "P" denotes CRC32 polynomial - * let "T" denotes 2^(XLEN+32) - * let "QT" denotes quotient of T/P, with the bit for 2^XLEN being implicit - * - * crc32(S, P) - * => S * (2^32) - S * (2^32) / P * P - * => lowest 32 bits of: S * (2^32) / P * P - * => lowest 32 bits of: S * (2^32) * (T / P) / T * P - * => lowest 32 bits of: S * (2^32) * quotient / T * P - * => lowest 32 bits of: S * quotient / 2^XLEN * P - * => lowest 32 bits of: (clmul_high_part(S, QT) + S) * P - * => clmul_low_part(clmul_high_part(S, QT) + S, P) - * - * In terms of below implementations, the BE case is more intuitive, since the - * higher order bit sits at more significant position. - */ - -#if __riscv_xlen == 64 -/* Slide by XLEN bits per iteration */ -# define STEP_ORDER 3 - -/* Each below polynomial quotient has an implicit bit for 2^XLEN */ - -/* Polynomial quotient of (2^(XLEN+32))/CRC32_POLY, in LE format */ -# define CRC32_POLY_QT_LE 0x5a72d812fb808b20 - -/* Polynomial quotient of (2^(XLEN+32))/CRC32C_POLY, in LE format */ -# define CRC32C_POLY_QT_LE 0xa434f61c6f5389f8 - -/* Polynomial quotient of (2^(XLEN+32))/CRC32_POLY, in BE format, it should be - * the same as the bit-reversed version of CRC32_POLY_QT_LE - */ -# define CRC32_POLY_QT_BE 0x04d101df481b4e5a - -static inline u64 crc32_le_prep(u32 crc, unsigned long const *ptr) -{ - return (u64)crc ^ (__force u64)__cpu_to_le64(*ptr); -} - -static inline u32 crc32_le_zbc(unsigned long s, u32 poly, unsigned long poly_qt) -{ - u32 crc; - - /* We don't have a "clmulrh" insn, so use clmul + slli instead. */ - asm volatile (".option push\n" - ".option arch,+zbc\n" - "clmul %0, %1, %2\n" - "slli %0, %0, 1\n" - "xor %0, %0, %1\n" - "clmulr %0, %0, %3\n" - "srli %0, %0, 32\n" - ".option pop\n" - : "=&r" (crc) - : "r" (s), - "r" (poly_qt), - "r" ((u64)poly << 32) - :); - return crc; -} - -static inline u64 crc32_be_prep(u32 crc, unsigned long const *ptr) -{ - return ((u64)crc << 32) ^ (__force u64)__cpu_to_be64(*ptr); -} - -#elif __riscv_xlen == 32 -# define STEP_ORDER 2 -/* Each quotient should match the upper half of its analog in RV64 */ -# define CRC32_POLY_QT_LE 0xfb808b20 -# define CRC32C_POLY_QT_LE 0x6f5389f8 -# define CRC32_POLY_QT_BE 0x04d101df - -static inline u32 crc32_le_prep(u32 crc, unsigned long const *ptr) -{ - return crc ^ (__force u32)__cpu_to_le32(*ptr); -} - -static inline u32 crc32_le_zbc(unsigned long s, u32 poly, unsigned long poly_qt) -{ - u32 crc; - - /* We don't have a "clmulrh" insn, so use clmul + slli instead. */ - asm volatile (".option push\n" - ".option arch,+zbc\n" - "clmul %0, %1, %2\n" - "slli %0, %0, 1\n" - "xor %0, %0, %1\n" - "clmulr %0, %0, %3\n" - ".option pop\n" - : "=&r" (crc) - : "r" (s), - "r" (poly_qt), - "r" (poly) - :); - return crc; -} - -static inline u32 crc32_be_prep(u32 crc, unsigned long const *ptr) -{ - return crc ^ (__force u32)__cpu_to_be32(*ptr); -} - -#else -# error "Unexpected __riscv_xlen" -#endif - -static inline u32 crc32_be_zbc(unsigned long s) -{ - u32 crc; - - asm volatile (".option push\n" - ".option arch,+zbc\n" - "clmulh %0, %1, %2\n" - "xor %0, %0, %1\n" - "clmul %0, %0, %3\n" - ".option pop\n" - : "=&r" (crc) - : "r" (s), - "r" (CRC32_POLY_QT_BE), - "r" (CRC32_POLY_BE) - :); - return crc; -} - -#define STEP (1 << STEP_ORDER) -#define OFFSET_MASK (STEP - 1) - -typedef u32 (*fallback)(u32 crc, unsigned char const *p, size_t len); - -static inline u32 crc32_le_unaligned(u32 crc, unsigned char const *p, - size_t len, u32 poly, - unsigned long poly_qt) -{ - size_t bits = len * 8; - unsigned long s = 0; - u32 crc_low = 0; - - for (int i = 0; i < len; i++) - s = ((unsigned long)*p++ << (__riscv_xlen - 8)) | (s >> 8); - - s ^= (unsigned long)crc << (__riscv_xlen - bits); - if (__riscv_xlen == 32 || len < sizeof(u32)) - crc_low = crc >> bits; - - crc = crc32_le_zbc(s, poly, poly_qt); - crc ^= crc_low; - - return crc; -} - -static inline u32 __pure crc32_le_generic(u32 crc, unsigned char const *p, - size_t len, u32 poly, - unsigned long poly_qt, - fallback crc_fb) -{ - size_t offset, head_len, tail_len; - unsigned long const *p_ul; - unsigned long s; - - asm goto(ALTERNATIVE("j %l[legacy]", "nop", 0, - RISCV_ISA_EXT_ZBC, 1) - : : : : legacy); - - /* Handle the unaligned head. */ - offset = (unsigned long)p & OFFSET_MASK; - if (offset && len) { - head_len = min(STEP - offset, len); - crc = crc32_le_unaligned(crc, p, head_len, poly, poly_qt); - p += head_len; - len -= head_len; - } - - tail_len = len & OFFSET_MASK; - len = len >> STEP_ORDER; - p_ul = (unsigned long const *)p; - - for (int i = 0; i < len; i++) { - s = crc32_le_prep(crc, p_ul); - crc = crc32_le_zbc(s, poly, poly_qt); - p_ul++; - } - - /* Handle the tail bytes. */ - p = (unsigned char const *)p_ul; - if (tail_len) - crc = crc32_le_unaligned(crc, p, tail_len, poly, poly_qt); - - return crc; - -legacy: - return crc_fb(crc, p, len); -} - -u32 __pure crc32_le_arch(u32 crc, const u8 *p, size_t len) -{ - return crc32_le_generic(crc, p, len, CRC32_POLY_LE, CRC32_POLY_QT_LE, - crc32_le_base); -} -EXPORT_SYMBOL(crc32_le_arch); - -u32 __pure crc32c_le_arch(u32 crc, const u8 *p, size_t len) -{ - return crc32_le_generic(crc, p, len, CRC32C_POLY_LE, - CRC32C_POLY_QT_LE, crc32c_le_base); -} -EXPORT_SYMBOL(crc32c_le_arch); - -static inline u32 crc32_be_unaligned(u32 crc, unsigned char const *p, - size_t len) -{ - size_t bits = len * 8; - unsigned long s = 0; - u32 crc_low = 0; - - s = 0; - for (int i = 0; i < len; i++) - s = *p++ | (s << 8); - - if (__riscv_xlen == 32 || len < sizeof(u32)) { - s ^= crc >> (32 - bits); - crc_low = crc << bits; - } else { - s ^= (unsigned long)crc << (bits - 32); - } - - crc = crc32_be_zbc(s); - crc ^= crc_low; - - return crc; -} - -u32 __pure crc32_be_arch(u32 crc, const u8 *p, size_t len) -{ - size_t offset, head_len, tail_len; - unsigned long const *p_ul; - unsigned long s; - - asm goto(ALTERNATIVE("j %l[legacy]", "nop", 0, - RISCV_ISA_EXT_ZBC, 1) - : : : : legacy); - - /* Handle the unaligned head. */ - offset = (unsigned long)p & OFFSET_MASK; - if (offset && len) { - head_len = min(STEP - offset, len); - crc = crc32_be_unaligned(crc, p, head_len); - p += head_len; - len -= head_len; - } - - tail_len = len & OFFSET_MASK; - len = len >> STEP_ORDER; - p_ul = (unsigned long const *)p; - - for (int i = 0; i < len; i++) { - s = crc32_be_prep(crc, p_ul); - crc = crc32_be_zbc(s); - p_ul++; - } - - /* Handle the tail bytes. */ - p = (unsigned char const *)p_ul; - if (tail_len) - crc = crc32_be_unaligned(crc, p, tail_len); - - return crc; - -legacy: - return crc32_be_base(crc, p, len); -} -EXPORT_SYMBOL(crc32_be_arch); - -u32 crc32_optimizations(void) -{ - if (riscv_has_extension_likely(RISCV_ISA_EXT_ZBC)) - return CRC32_LE_OPTIMIZATION | - CRC32_BE_OPTIMIZATION | - CRC32C_OPTIMIZATION; - return 0; -} -EXPORT_SYMBOL(crc32_optimizations); - -MODULE_LICENSE("GPL"); -MODULE_DESCRIPTION("Accelerated CRC32 implementation with Zbc extension"); diff --git a/arch/riscv/lib/crc32.c b/arch/riscv/lib/crc32.c new file mode 100644 index 000000000000..a3188b7d9c40 --- /dev/null +++ b/arch/riscv/lib/crc32.c @@ -0,0 +1,53 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * RISC-V optimized CRC32 functions + * + * Copyright 2025 Google LLC + */ + +#include <asm/hwcap.h> +#include <asm/alternative-macros.h> +#include <linux/crc32.h> +#include <linux/module.h> + +#include "crc-clmul.h" + +u32 crc32_le_arch(u32 crc, const u8 *p, size_t len) +{ + if (riscv_has_extension_likely(RISCV_ISA_EXT_ZBC)) + return crc32_lsb_clmul(crc, p, len, + &crc32_lsb_0xedb88320_consts); + return crc32_le_base(crc, p, len); +} +EXPORT_SYMBOL(crc32_le_arch); + +u32 crc32_be_arch(u32 crc, const u8 *p, size_t len) +{ + if (riscv_has_extension_likely(RISCV_ISA_EXT_ZBC)) + return crc32_msb_clmul(crc, p, len, + &crc32_msb_0x04c11db7_consts); + return crc32_be_base(crc, p, len); +} +EXPORT_SYMBOL(crc32_be_arch); + +u32 crc32c_arch(u32 crc, const u8 *p, size_t len) +{ + if (riscv_has_extension_likely(RISCV_ISA_EXT_ZBC)) + return crc32_lsb_clmul(crc, p, len, + &crc32_lsb_0x82f63b78_consts); + return crc32c_base(crc, p, len); +} +EXPORT_SYMBOL(crc32c_arch); + +u32 crc32_optimizations(void) +{ + if (riscv_has_extension_likely(RISCV_ISA_EXT_ZBC)) + return CRC32_LE_OPTIMIZATION | + CRC32_BE_OPTIMIZATION | + CRC32C_OPTIMIZATION; + return 0; +} +EXPORT_SYMBOL(crc32_optimizations); + +MODULE_DESCRIPTION("RISC-V optimized CRC32 functions"); +MODULE_LICENSE("GPL"); diff --git a/arch/riscv/lib/crc32_lsb.c b/arch/riscv/lib/crc32_lsb.c new file mode 100644 index 000000000000..72fd67e7470c --- /dev/null +++ b/arch/riscv/lib/crc32_lsb.c @@ -0,0 +1,18 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * RISC-V optimized least-significant-bit-first CRC32 + * + * Copyright 2025 Google LLC + */ + +#include "crc-clmul.h" + +typedef u32 crc_t; +#define LSB_CRC 1 +#include "crc-clmul-template.h" + +u32 crc32_lsb_clmul(u32 crc, const void *p, size_t len, + const struct crc_clmul_consts *consts) +{ + return crc_clmul(crc, p, len, consts); +} diff --git a/arch/riscv/lib/crc32_msb.c b/arch/riscv/lib/crc32_msb.c new file mode 100644 index 000000000000..fdbeaccc369f --- /dev/null +++ b/arch/riscv/lib/crc32_msb.c @@ -0,0 +1,18 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * RISC-V optimized most-significant-bit-first CRC32 + * + * Copyright 2025 Google LLC + */ + +#include "crc-clmul.h" + +typedef u32 crc_t; +#define LSB_CRC 0 +#include "crc-clmul-template.h" + +u32 crc32_msb_clmul(u32 crc, const void *p, size_t len, + const struct crc_clmul_consts *consts) +{ + return crc_clmul(crc, p, len, consts); +} diff --git a/arch/riscv/lib/crc64.c b/arch/riscv/lib/crc64.c new file mode 100644 index 000000000000..f0015a27836a --- /dev/null +++ b/arch/riscv/lib/crc64.c @@ -0,0 +1,34 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * RISC-V optimized CRC64 functions + * + * Copyright 2025 Google LLC + */ + +#include <asm/hwcap.h> +#include <asm/alternative-macros.h> +#include <linux/crc64.h> +#include <linux/module.h> + +#include "crc-clmul.h" + +u64 crc64_be_arch(u64 crc, const u8 *p, size_t len) +{ + if (riscv_has_extension_likely(RISCV_ISA_EXT_ZBC)) + return crc64_msb_clmul(crc, p, len, + &crc64_msb_0x42f0e1eba9ea3693_consts); + return crc64_be_generic(crc, p, len); +} +EXPORT_SYMBOL(crc64_be_arch); + +u64 crc64_nvme_arch(u64 crc, const u8 *p, size_t len) +{ + if (riscv_has_extension_likely(RISCV_ISA_EXT_ZBC)) + return crc64_lsb_clmul(crc, p, len, + &crc64_lsb_0x9a6c9329ac4bc9b5_consts); + return crc64_nvme_generic(crc, p, len); +} +EXPORT_SYMBOL(crc64_nvme_arch); + +MODULE_DESCRIPTION("RISC-V optimized CRC64 functions"); +MODULE_LICENSE("GPL"); diff --git a/arch/riscv/lib/crc64_lsb.c b/arch/riscv/lib/crc64_lsb.c new file mode 100644 index 000000000000..c5371bb85d90 --- /dev/null +++ b/arch/riscv/lib/crc64_lsb.c @@ -0,0 +1,18 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * RISC-V optimized least-significant-bit-first CRC64 + * + * Copyright 2025 Google LLC + */ + +#include "crc-clmul.h" + +typedef u64 crc_t; +#define LSB_CRC 1 +#include "crc-clmul-template.h" + +u64 crc64_lsb_clmul(u64 crc, const void *p, size_t len, + const struct crc_clmul_consts *consts) +{ + return crc_clmul(crc, p, len, consts); +} diff --git a/arch/riscv/lib/crc64_msb.c b/arch/riscv/lib/crc64_msb.c new file mode 100644 index 000000000000..1925d1dbe225 --- /dev/null +++ b/arch/riscv/lib/crc64_msb.c @@ -0,0 +1,18 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * RISC-V optimized most-significant-bit-first CRC64 + * + * Copyright 2025 Google LLC + */ + +#include "crc-clmul.h" + +typedef u64 crc_t; +#define LSB_CRC 0 +#include "crc-clmul-template.h" + +u64 crc64_msb_clmul(u64 crc, const void *p, size_t len, + const struct crc_clmul_consts *consts) +{ + return crc_clmul(crc, p, len, consts); +} diff --git a/arch/riscv/lib/csum.c b/arch/riscv/lib/csum.c index 7fb12c59e571..9408f50ca59a 100644 --- a/arch/riscv/lib/csum.c +++ b/arch/riscv/lib/csum.c @@ -40,12 +40,7 @@ __sum16 csum_ipv6_magic(const struct in6_addr *saddr, uproto = (__force unsigned int)htonl(proto); sum += uproto; - /* - * Zbb support saves 4 instructions, so not worth checking without - * alternatives if supported - */ - if (IS_ENABLED(CONFIG_RISCV_ISA_ZBB) && - IS_ENABLED(CONFIG_RISCV_ALTERNATIVE)) { + if (IS_ENABLED(CONFIG_RISCV_ISA_ZBB) && IS_ENABLED(CONFIG_TOOLCHAIN_HAS_ZBB)) { unsigned long fold_temp; /* @@ -157,12 +152,7 @@ do_csum_with_alignment(const unsigned char *buff, int len) csum = do_csum_common(ptr, end, data); #ifdef CC_HAS_ASM_GOTO_TIED_OUTPUT - /* - * Zbb support saves 6 instructions, so not worth checking without - * alternatives if supported - */ - if (IS_ENABLED(CONFIG_RISCV_ISA_ZBB) && - IS_ENABLED(CONFIG_RISCV_ALTERNATIVE)) { + if (IS_ENABLED(CONFIG_RISCV_ISA_ZBB) && IS_ENABLED(CONFIG_TOOLCHAIN_HAS_ZBB)) { unsigned long fold_temp; /* @@ -244,12 +234,7 @@ do_csum_no_alignment(const unsigned char *buff, int len) end = (const unsigned long *)(buff + len); csum = do_csum_common(ptr, end, data); - /* - * Zbb support saves 6 instructions, so not worth checking without - * alternatives if supported - */ - if (IS_ENABLED(CONFIG_RISCV_ISA_ZBB) && - IS_ENABLED(CONFIG_RISCV_ALTERNATIVE)) { + if (IS_ENABLED(CONFIG_RISCV_ISA_ZBB) && IS_ENABLED(CONFIG_TOOLCHAIN_HAS_ZBB)) { unsigned long fold_temp; /* diff --git a/arch/riscv/lib/strcmp.S b/arch/riscv/lib/strcmp.S index 57a5c0066231..65027e742af1 100644 --- a/arch/riscv/lib/strcmp.S +++ b/arch/riscv/lib/strcmp.S @@ -8,7 +8,8 @@ /* int strcmp(const char *cs, const char *ct) */ SYM_FUNC_START(strcmp) - ALTERNATIVE("nop", "j strcmp_zbb", 0, RISCV_ISA_EXT_ZBB, CONFIG_RISCV_ISA_ZBB) + __ALTERNATIVE_CFG("nop", "j strcmp_zbb", 0, RISCV_ISA_EXT_ZBB, + IS_ENABLED(CONFIG_RISCV_ISA_ZBB) && IS_ENABLED(CONFIG_TOOLCHAIN_HAS_ZBB)) /* * Returns @@ -43,7 +44,7 @@ SYM_FUNC_START(strcmp) * The code was published as part of the bitmanip manual * in Appendix A. */ -#ifdef CONFIG_RISCV_ISA_ZBB +#if defined(CONFIG_RISCV_ISA_ZBB) && defined(CONFIG_TOOLCHAIN_HAS_ZBB) strcmp_zbb: .option push diff --git a/arch/riscv/lib/strlen.S b/arch/riscv/lib/strlen.S index 962983b73251..eb4d2b7ed22b 100644 --- a/arch/riscv/lib/strlen.S +++ b/arch/riscv/lib/strlen.S @@ -8,7 +8,8 @@ /* int strlen(const char *s) */ SYM_FUNC_START(strlen) - ALTERNATIVE("nop", "j strlen_zbb", 0, RISCV_ISA_EXT_ZBB, CONFIG_RISCV_ISA_ZBB) + __ALTERNATIVE_CFG("nop", "j strlen_zbb", 0, RISCV_ISA_EXT_ZBB, + IS_ENABLED(CONFIG_RISCV_ISA_ZBB) && IS_ENABLED(CONFIG_TOOLCHAIN_HAS_ZBB)) /* * Returns @@ -33,7 +34,7 @@ SYM_FUNC_START(strlen) /* * Variant of strlen using the ZBB extension if available */ -#ifdef CONFIG_RISCV_ISA_ZBB +#if defined(CONFIG_RISCV_ISA_ZBB) && defined(CONFIG_TOOLCHAIN_HAS_ZBB) strlen_zbb: #ifdef CONFIG_CPU_BIG_ENDIAN diff --git a/arch/riscv/lib/strncmp.S b/arch/riscv/lib/strncmp.S index 7b2d0ff9ed6c..062000c468c8 100644 --- a/arch/riscv/lib/strncmp.S +++ b/arch/riscv/lib/strncmp.S @@ -8,7 +8,8 @@ /* int strncmp(const char *cs, const char *ct, size_t count) */ SYM_FUNC_START(strncmp) - ALTERNATIVE("nop", "j strncmp_zbb", 0, RISCV_ISA_EXT_ZBB, CONFIG_RISCV_ISA_ZBB) + __ALTERNATIVE_CFG("nop", "j strncmp_zbb", 0, RISCV_ISA_EXT_ZBB, + IS_ENABLED(CONFIG_RISCV_ISA_ZBB) && IS_ENABLED(CONFIG_TOOLCHAIN_HAS_ZBB)) /* * Returns @@ -46,7 +47,7 @@ SYM_FUNC_START(strncmp) /* * Variant of strncmp using the ZBB extension if available */ -#ifdef CONFIG_RISCV_ISA_ZBB +#if defined(CONFIG_RISCV_ISA_ZBB) && defined(CONFIG_TOOLCHAIN_HAS_ZBB) strncmp_zbb: .option push |