riscv/crc32: reimplement the CRC32 functions using new template

Delete the previous Zbc optimized CRC32 code, and re-implement it using
the new template.  The new implementation is more optimized and shares
more code among CRC variants.

Tested-by: Björn Töpel <[email protected]>
Acked-by: Alexandre Ghiti <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Eric Biggers <[email protected]>

Author: ebiggers

arch/riscv/lib/Makefile

@@ -16,6 +16,7 @@ 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-$(CONFIG_FUNCTION_ERROR_INJECTION) += error-inject.o
 lib-$(CONFIG_RISCV_ISA_V)	+= xor.o
 lib-$(CONFIG_RISCV_ISA_V)	+= riscv_v_helpers.o

arch/riscv/lib/crc-clmul-consts.h

@@ -0,0 +1,72 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * CRC constants generated by:
+ *
+ *	./scripts/gen-crc-consts.py riscv_clmul crc32_msb_0x04c11db7,crc32_lsb_0xedb88320,crc32_lsb_0x82f63b78
+ *
+ * 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-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
+};

arch/riscv/lib/crc-clmul.h

@@ -0,0 +1,15 @@
+/* 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"
+
+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);
+
+#endif /* _RISCV_CRC_CLMUL_H */