riscv/crc64: add Zbc optimized CRC64 functions

Wire up crc64_be_arch() and crc64_nvme_arch() for 64-bit RISC-V using
crc-clmul-template.h.  This greatly improves the performance of these
CRCs on Zbc-capable CPUs in 64-bit kernels.

These optimized CRC64 functions are not yet supported in 32-bit kernels,
since crc-clmul-template.h assumes that the CRC fits in an unsigned
long.  That implementation limitation could be addressed, but it would
add a fair bit of complexity, so it has been omitted for now.

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/Kconfig

@@ -25,6 +25,7 @@ config RISCV
 	select ARCH_ENABLE_THP_MIGRATION if TRANSPARENT_HUGEPAGE
 	select ARCH_HAS_BINFMT_FLAT
 	select ARCH_HAS_CRC32 if RISCV_ISA_ZBC
+	select ARCH_HAS_CRC64 if 64BIT && RISCV_ISA_ZBC
 	select ARCH_HAS_CRC_T10DIF if RISCV_ISA_ZBC
 	select ARCH_HAS_CURRENT_STACK_POINTER
 	select ARCH_HAS_DEBUG_VIRTUAL if MMU

arch/riscv/lib/Makefile

@@ -17,6 +17,8 @@ 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

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

@@ -2,7 +2,7 @@
 /*
  * CRC constants generated by:
  *
- *	./scripts/gen-crc-consts.py riscv_clmul crc16_msb_0x8bb7,crc32_msb_0x04c11db7,crc32_lsb_0xedb88320,crc32_lsb_0x82f63b78
+ *	./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.
  */
@@ -88,3 +88,35 @@ static const struct crc_clmul_consts crc32_lsb_0x82f63b78_consts __maybe_unused
 	.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

arch/riscv/lib/crc-clmul.h

@@ -13,5 +13,11 @@ 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 */

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");

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);
+}

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);
+}