arm/crc-t10dif: expose CRC-T10DIF function through lib

Move the arm CRC-T10DIF assembly code into the lib directory and wire it
up to the library interface.  This allows it to be used without going
through the crypto API.  It remains usable via the crypto API too via
the shash algorithms that use the library interface.  Thus all the
arch-specific "shash" code becomes unnecessary and is removed.

Note: to see the diff from arch/arm/crypto/crct10dif-ce-glue.c to
arch/arm/lib/crc-t10dif-glue.c, view this commit with 'git show -M10'.

Reviewed-by: Ard Biesheuvel <ardb@kernel.org>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Link: https://lore.kernel.org/r/20241202012056.209768-6-ebiggers@kernel.org
Signed-off-by: Eric Biggers <ebiggers@google.com>

Author: ebiggers

arch/arm/Kconfig

@@ -8,6 +8,7 @@ config ARM
 	select ARCH_HAS_CPU_CACHE_ALIASING
 	select ARCH_HAS_CPU_FINALIZE_INIT if MMU
 	select ARCH_HAS_CRC32 if KERNEL_MODE_NEON
+	select ARCH_HAS_CRC_T10DIF if KERNEL_MODE_NEON
 	select ARCH_HAS_CURRENT_STACK_POINTER
 	select ARCH_HAS_DEBUG_VIRTUAL if MMU
 	select ARCH_HAS_DMA_ALLOC if MMU

arch/arm/crypto/Kconfig

@@ -222,16 +222,5 @@ config CRYPTO_CHACHA20_NEON
 	  Architecture: arm using:
 	  - NEON (Advanced SIMD) extensions
 
-config CRYPTO_CRCT10DIF_ARM_CE
-	tristate "CRCT10DIF"
-	depends on KERNEL_MODE_NEON
-	depends on CRC_T10DIF
-	select CRYPTO_HASH
-	help
-	  CRC16 CRC algorithm used for the T10 (SCSI) Data Integrity Field (DIF)
-
-	  Architecture: arm using:
-	  - PMULL (Polynomial Multiply Long) instructions
-
 endmenu
 

arch/arm/crypto/Makefile

@@ -20,7 +20,6 @@ obj-$(CONFIG_CRYPTO_AES_ARM_CE) += aes-arm-ce.o
 obj-$(CONFIG_CRYPTO_SHA1_ARM_CE) += sha1-arm-ce.o
 obj-$(CONFIG_CRYPTO_SHA2_ARM_CE) += sha2-arm-ce.o
 obj-$(CONFIG_CRYPTO_GHASH_ARM_CE) += ghash-arm-ce.o
-obj-$(CONFIG_CRYPTO_CRCT10DIF_ARM_CE) += crct10dif-arm-ce.o
 
 aes-arm-y	:= aes-cipher-core.o aes-cipher-glue.o
 aes-arm-bs-y	:= aes-neonbs-core.o aes-neonbs-glue.o
@@ -36,7 +35,6 @@ sha1-arm-ce-y	:= sha1-ce-core.o sha1-ce-glue.o
 sha2-arm-ce-y	:= sha2-ce-core.o sha2-ce-glue.o
 aes-arm-ce-y	:= aes-ce-core.o aes-ce-glue.o
 ghash-arm-ce-y	:= ghash-ce-core.o ghash-ce-glue.o
-crct10dif-arm-ce-y	:= crct10dif-ce-core.o crct10dif-ce-glue.o
 chacha-neon-y := chacha-scalar-core.o chacha-glue.o
 chacha-neon-$(CONFIG_KERNEL_MODE_NEON) += chacha-neon-core.o
 poly1305-arm-y := poly1305-core.o poly1305-glue.o

arch/arm/crypto/crct10dif-ce-glue.c

@@ -48,3 +48,6 @@ obj-$(CONFIG_FUNCTION_ERROR_INJECTION) += error-inject.o
 
 obj-$(CONFIG_CRC32_ARCH) += crc32-arm.o
 crc32-arm-y := crc32-glue.o crc32-core.o
+
+obj-$(CONFIG_CRC_T10DIF_ARCH) += crc-t10dif-arm.o
+crc-t10dif-arm-y := crc-t10dif-glue.o crc-t10dif-core.o

arch/arm/lib/Makefile

@@ -0,0 +1,80 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Accelerated CRC-T10DIF using ARM NEON and Crypto Extensions instructions
+ *
+ * Copyright (C) 2016 Linaro Ltd <ard.biesheuvel@linaro.org>
+ */
+
+#include <linux/crc-t10dif.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/string.h>
+
+#include <crypto/internal/simd.h>
+
+#include <asm/neon.h>
+#include <asm/simd.h>
+
+static DEFINE_STATIC_KEY_FALSE(have_neon);
+static DEFINE_STATIC_KEY_FALSE(have_pmull);
+
+#define CRC_T10DIF_PMULL_CHUNK_SIZE	16U
+
+asmlinkage u16 crc_t10dif_pmull64(u16 init_crc, const u8 *buf, size_t len);
+asmlinkage void crc_t10dif_pmull8(u16 init_crc, const u8 *buf, size_t len,
+				  u8 out[16]);
+
+u16 crc_t10dif_arch(u16 crc, const u8 *data, size_t length)
+{
+	if (length >= CRC_T10DIF_PMULL_CHUNK_SIZE) {
+		if (static_branch_likely(&have_pmull)) {
+			if (crypto_simd_usable()) {
+				kernel_neon_begin();
+				crc = crc_t10dif_pmull64(crc, data, length);
+				kernel_neon_end();
+				return crc;
+			}
+		} else if (length > CRC_T10DIF_PMULL_CHUNK_SIZE &&
+			   static_branch_likely(&have_neon) &&
+			   crypto_simd_usable()) {
+			u8 buf[16] __aligned(16);
+
+			kernel_neon_begin();
+			crc_t10dif_pmull8(crc, data, length, buf);
+			kernel_neon_end();
+
+			crc = 0;
+			data = buf;
+			length = sizeof(buf);
+		}
+	}
+	return crc_t10dif_generic(crc, data, length);
+}
+EXPORT_SYMBOL(crc_t10dif_arch);
+
+static int __init crc_t10dif_arm_init(void)
+{
+	if (elf_hwcap & HWCAP_NEON) {
+		static_branch_enable(&have_neon);
+		if (elf_hwcap2 & HWCAP2_PMULL)
+			static_branch_enable(&have_pmull);
+	}
+	return 0;
+}
+arch_initcall(crc_t10dif_arm_init);
+
+static void __exit crc_t10dif_arm_exit(void)
+{
+}
+module_exit(crc_t10dif_arm_exit);
+
+bool crc_t10dif_is_optimized(void)
+{
+	return static_key_enabled(&have_neon);
+}
+EXPORT_SYMBOL(crc_t10dif_is_optimized);
+
+MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>");
+MODULE_DESCRIPTION("Accelerated CRC-T10DIF using ARM NEON and Crypto Extensions");
+MODULE_LICENSE("GPL v2");