lib/crypto: arm/sha512: Migrate optimized SHA-512 code to library

Instead of exposing the arm-optimized SHA-512 code via arm-specific
crypto_shash algorithms, instead just implement the sha512_blocks()
library function.  This is much simpler, it makes the SHA-512 (and
SHA-384) library functions be arm-optimized, and it fixes the
longstanding issue where the arm-optimized SHA-512 code was disabled by
default.  SHA-512 still remains available through crypto_shash, but
individual architectures no longer need to handle it.

To match sha512_blocks(), change the type of the nblocks parameter of
the assembly functions from int to size_t.  The assembly functions
actually already treated it as size_t.

Acked-by: Ard Biesheuvel <ardb@kernel.org>
Link: https://lore.kernel.org/r/20250630160320.2888-8-ebiggers@kernel.org
Signed-off-by: Eric Biggers <ebiggers@kernel.org>

15 files changed, 55 insertions, 218 deletions

diff --git a/arch/arm/configs/exynos_defconfig b/arch/arm/configs/exynos_defconfig
index f71af368674c..d58e30069304 100644
--- a/arch/arm/configs/exynos_defconfig
+++ b/arch/arm/configs/exynos_defconfig
@@ -364,7 +364,6 @@ CONFIG_CRYPTO_USER_API_SKCIPHER=m
 CONFIG_CRYPTO_USER_API_RNG=m
 CONFIG_CRYPTO_USER_API_AEAD=m
 CONFIG_CRYPTO_SHA1_ARM_NEON=m
-CONFIG_CRYPTO_SHA512_ARM=m
 CONFIG_CRYPTO_AES_ARM_BS=m
 CONFIG_CRYPTO_CHACHA20_NEON=m
 CONFIG_CRYPTO_DEV_EXYNOS_RNG=y
diff --git a/arch/arm/configs/milbeaut_m10v_defconfig b/arch/arm/configs/milbeaut_m10v_defconfig
index 242e7d5a3f68..8ebf8bd872fe 100644
--- a/arch/arm/configs/milbeaut_m10v_defconfig
+++ b/arch/arm/configs/milbeaut_m10v_defconfig
@@ -100,7 +100,6 @@ CONFIG_CRYPTO_SEQIV=m
 CONFIG_CRYPTO_GHASH_ARM_CE=m
 CONFIG_CRYPTO_SHA1_ARM_NEON=m
 CONFIG_CRYPTO_SHA1_ARM_CE=m
-CONFIG_CRYPTO_SHA512_ARM=m
 CONFIG_CRYPTO_AES_ARM=m
 CONFIG_CRYPTO_AES_ARM_BS=m
 CONFIG_CRYPTO_AES_ARM_CE=m
diff --git a/arch/arm/configs/multi_v7_defconfig b/arch/arm/configs/multi_v7_defconfig
index 50c170b4619f..3fd07e864ca8 100644
--- a/arch/arm/configs/multi_v7_defconfig
+++ b/arch/arm/configs/multi_v7_defconfig
@@ -1282,7 +1282,6 @@ CONFIG_CRYPTO_USER_API_AEAD=m
 CONFIG_CRYPTO_GHASH_ARM_CE=m
 CONFIG_CRYPTO_SHA1_ARM_NEON=m
 CONFIG_CRYPTO_SHA1_ARM_CE=m
-CONFIG_CRYPTO_SHA512_ARM=m
 CONFIG_CRYPTO_AES_ARM=m
 CONFIG_CRYPTO_AES_ARM_BS=m
 CONFIG_CRYPTO_AES_ARM_CE=m
diff --git a/arch/arm/configs/omap2plus_defconfig b/arch/arm/configs/omap2plus_defconfig
index 9f9780c8e62a..530dfb8338c9 100644
--- a/arch/arm/configs/omap2plus_defconfig
+++ b/arch/arm/configs/omap2plus_defconfig
@@ -705,7 +705,6 @@ CONFIG_SECURITY=y
 CONFIG_CRYPTO_MICHAEL_MIC=y
 CONFIG_CRYPTO_GHASH_ARM_CE=m
 CONFIG_CRYPTO_SHA1_ARM_NEON=m
-CONFIG_CRYPTO_SHA512_ARM=m
 CONFIG_CRYPTO_AES_ARM=m
 CONFIG_CRYPTO_AES_ARM_BS=m
 CONFIG_CRYPTO_CHACHA20_NEON=m
diff --git a/arch/arm/configs/pxa_defconfig b/arch/arm/configs/pxa_defconfig
index ff29c5b0e9c9..eaa44574d4a6 100644
--- a/arch/arm/configs/pxa_defconfig
+++ b/arch/arm/configs/pxa_defconfig
@@ -659,7 +659,6 @@ CONFIG_CRYPTO_XCBC=m
 CONFIG_CRYPTO_DEFLATE=y
 CONFIG_CRYPTO_LZO=y
 CONFIG_CRYPTO_SHA1_ARM=m
-CONFIG_CRYPTO_SHA512_ARM=m
 CONFIG_CRYPTO_AES_ARM=m
 CONFIG_FONTS=y
 CONFIG_FONT_8x8=y
diff --git a/arch/arm/crypto/Kconfig b/arch/arm/crypto/Kconfig
index 7efb9a8596e4..a18f97f1597c 100644
--- a/arch/arm/crypto/Kconfig
+++ b/arch/arm/crypto/Kconfig
@@ -93,16 +93,6 @@ config CRYPTO_SHA1_ARM_CE
 
 	  Architecture: arm using ARMv8 Crypto Extensions
 
-config CRYPTO_SHA512_ARM
-	tristate "Hash functions: SHA-384 and SHA-512 (NEON)"
-	select CRYPTO_HASH
-	depends on !CPU_V7M
-	help
-	  SHA-384 and SHA-512 secure hash algorithms (FIPS 180)
-
-	  Architecture: arm using
-	  - NEON (Advanced SIMD) extensions
-
 config CRYPTO_AES_ARM
 	tristate "Ciphers: AES"
 	select CRYPTO_ALGAPI
diff --git a/arch/arm/crypto/Makefile b/arch/arm/crypto/Makefile
index 8479137c6e80..78a4042d8761 100644
--- a/arch/arm/crypto/Makefile
+++ b/arch/arm/crypto/Makefile
@@ -7,7 +7,6 @@ obj-$(CONFIG_CRYPTO_AES_ARM) += aes-arm.o
 obj-$(CONFIG_CRYPTO_AES_ARM_BS) += aes-arm-bs.o
 obj-$(CONFIG_CRYPTO_SHA1_ARM) += sha1-arm.o
 obj-$(CONFIG_CRYPTO_SHA1_ARM_NEON) += sha1-arm-neon.o
-obj-$(CONFIG_CRYPTO_SHA512_ARM) += sha512-arm.o
 obj-$(CONFIG_CRYPTO_BLAKE2B_NEON) += blake2b-neon.o
 obj-$(CONFIG_CRYPTO_NHPOLY1305_NEON) += nhpoly1305-neon.o
 obj-$(CONFIG_CRYPTO_CURVE25519_NEON) += curve25519-neon.o
@@ -20,23 +19,9 @@ aes-arm-y	:= aes-cipher-core.o aes-cipher-glue.o
 aes-arm-bs-y	:= aes-neonbs-core.o aes-neonbs-glue.o
 sha1-arm-y	:= sha1-armv4-large.o sha1_glue.o
 sha1-arm-neon-y	:= sha1-armv7-neon.o sha1_neon_glue.o
-sha512-arm-neon-$(CONFIG_KERNEL_MODE_NEON) := sha512-neon-glue.o
-sha512-arm-y	:= sha512-core.o sha512-glue.o $(sha512-arm-neon-y)
 blake2b-neon-y  := blake2b-neon-core.o blake2b-neon-glue.o
 sha1-arm-ce-y	:= sha1-ce-core.o sha1-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
 nhpoly1305-neon-y := nh-neon-core.o nhpoly1305-neon-glue.o
 curve25519-neon-y := curve25519-core.o curve25519-glue.o
-
-quiet_cmd_perl = PERL    $@
-      cmd_perl = $(PERL) $(<) > $(@)
-
-$(obj)/%-core.S: $(src)/%-armv4.pl
-	$(call cmd,perl)
-
-clean-files += sha512-core.S
-
-aflags-thumb2-$(CONFIG_THUMB2_KERNEL)  := -U__thumb2__ -D__thumb2__=1
-
-AFLAGS_sha512-core.o += $(aflags-thumb2-y)
diff --git a/arch/arm/crypto/sha512-glue.c b/arch/arm/crypto/sha512-glue.c
deleted file mode 100644
index f8a6480889b1..000000000000
--- a/arch/arm/crypto/sha512-glue.c
+++ /dev/null
@@ -1,110 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * sha512-glue.c - accelerated SHA-384/512 for ARM
- *
- * Copyright (C) 2015 Linaro Ltd <ard.biesheuvel@linaro.org>
- */
-
-#include <asm/hwcap.h>
-#include <asm/neon.h>
-#include <crypto/internal/hash.h>
-#include <crypto/sha2.h>
-#include <crypto/sha512_base.h>
-#include <linux/kernel.h>
-#include <linux/module.h>
-
-#include "sha512.h"
-
-MODULE_DESCRIPTION("Accelerated SHA-384/SHA-512 secure hash for ARM");
-MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>");
-MODULE_LICENSE("GPL v2");
-
-MODULE_ALIAS_CRYPTO("sha384");
-MODULE_ALIAS_CRYPTO("sha512");
-MODULE_ALIAS_CRYPTO("sha384-arm");
-MODULE_ALIAS_CRYPTO("sha512-arm");
-
-asmlinkage void sha512_block_data_order(struct sha512_state *state,
-					u8 const *src, int blocks);
-
-static int sha512_arm_update(struct shash_desc *desc, const u8 *data,
-			     unsigned int len)
-{
-	return sha512_base_do_update_blocks(desc, data, len,
-					    sha512_block_data_order);
-}
-
-static int sha512_arm_finup(struct shash_desc *desc, const u8 *data,
-			    unsigned int len, u8 *out)
-{
-	sha512_base_do_finup(desc, data, len, sha512_block_data_order);
-	return sha512_base_finish(desc, out);
-}
-
-static struct shash_alg sha512_arm_algs[] = { {
-	.init			= sha384_base_init,
-	.update			= sha512_arm_update,
-	.finup			= sha512_arm_finup,
-	.descsize		= SHA512_STATE_SIZE,
-	.digestsize		= SHA384_DIGEST_SIZE,
-	.base			= {
-		.cra_name		= "sha384",
-		.cra_driver_name	= "sha384-arm",
-		.cra_priority		= 250,
-		.cra_flags		= CRYPTO_AHASH_ALG_BLOCK_ONLY |
-					  CRYPTO_AHASH_ALG_FINUP_MAX,
-		.cra_blocksize		= SHA512_BLOCK_SIZE,
-		.cra_module		= THIS_MODULE,
-	}
-},  {
-	.init			= sha512_base_init,
-	.update			= sha512_arm_update,
-	.finup			= sha512_arm_finup,
-	.descsize		= SHA512_STATE_SIZE,
-	.digestsize		= SHA512_DIGEST_SIZE,
-	.base			= {
-		.cra_name		= "sha512",
-		.cra_driver_name	= "sha512-arm",
-		.cra_priority		= 250,
-		.cra_flags		= CRYPTO_AHASH_ALG_BLOCK_ONLY |
-					  CRYPTO_AHASH_ALG_FINUP_MAX,
-		.cra_blocksize		= SHA512_BLOCK_SIZE,
-		.cra_module		= THIS_MODULE,
-	}
-} };
-
-static int __init sha512_arm_mod_init(void)
-{
-	int err;
-
-	err = crypto_register_shashes(sha512_arm_algs,
-				      ARRAY_SIZE(sha512_arm_algs));
-	if (err)
-		return err;
-
-	if (IS_ENABLED(CONFIG_KERNEL_MODE_NEON) && cpu_has_neon()) {
-		err = crypto_register_shashes(sha512_neon_algs,
-					      ARRAY_SIZE(sha512_neon_algs));
-		if (err)
-			goto err_unregister;
-	}
-	return 0;
-
-err_unregister:
-	crypto_unregister_shashes(sha512_arm_algs,
-				  ARRAY_SIZE(sha512_arm_algs));
-
-	return err;
-}
-
-static void __exit sha512_arm_mod_fini(void)
-{
-	crypto_unregister_shashes(sha512_arm_algs,
-				  ARRAY_SIZE(sha512_arm_algs));
-	if (IS_ENABLED(CONFIG_KERNEL_MODE_NEON) && cpu_has_neon())
-		crypto_unregister_shashes(sha512_neon_algs,
-					  ARRAY_SIZE(sha512_neon_algs));
-}
-
-module_init(sha512_arm_mod_init);
-module_exit(sha512_arm_mod_fini);
diff --git a/arch/arm/crypto/sha512-neon-glue.c b/arch/arm/crypto/sha512-neon-glue.c
deleted file mode 100644
index bd528077fefb..000000000000
--- a/arch/arm/crypto/sha512-neon-glue.c
+++ /dev/null
@@ -1,75 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * sha512-neon-glue.c - accelerated SHA-384/512 for ARM NEON
- *
- * Copyright (C) 2015 Linaro Ltd <ard.biesheuvel@linaro.org>
- */
-
-#include <asm/neon.h>
-#include <crypto/internal/hash.h>
-#include <crypto/sha2.h>
-#include <crypto/sha512_base.h>
-#include <linux/kernel.h>
-#include <linux/module.h>
-
-#include "sha512.h"
-
-MODULE_ALIAS_CRYPTO("sha384-neon");
-MODULE_ALIAS_CRYPTO("sha512-neon");
-
-asmlinkage void sha512_block_data_order_neon(struct sha512_state *state,
-					     const u8 *src, int blocks);
-
-static int sha512_neon_update(struct shash_desc *desc, const u8 *data,
-			      unsigned int len)
-{
-	int remain;
-
-	kernel_neon_begin();
-	remain = sha512_base_do_update_blocks(desc, data, len,
-					      sha512_block_data_order_neon);
-	kernel_neon_end();
-	return remain;
-}
-
-static int sha512_neon_finup(struct shash_desc *desc, const u8 *data,
-			     unsigned int len, u8 *out)
-{
-	kernel_neon_begin();
-	sha512_base_do_finup(desc, data, len, sha512_block_data_order_neon);
-	kernel_neon_end();
-	return sha512_base_finish(desc, out);
-}
-
-struct shash_alg sha512_neon_algs[] = { {
-	.init			= sha384_base_init,
-	.update			= sha512_neon_update,
-	.finup			= sha512_neon_finup,
-	.descsize		= SHA512_STATE_SIZE,
-	.digestsize		= SHA384_DIGEST_SIZE,
-	.base			= {
-		.cra_name		= "sha384",
-		.cra_driver_name	= "sha384-neon",
-		.cra_priority		= 300,
-		.cra_flags		= CRYPTO_AHASH_ALG_BLOCK_ONLY |
-					  CRYPTO_AHASH_ALG_FINUP_MAX,
-		.cra_blocksize		= SHA384_BLOCK_SIZE,
-		.cra_module		= THIS_MODULE,
-
-	}
-},  {
-	.init			= sha512_base_init,
-	.update			= sha512_neon_update,
-	.finup			= sha512_neon_finup,
-	.descsize		= SHA512_STATE_SIZE,
-	.digestsize		= SHA512_DIGEST_SIZE,
-	.base			= {
-		.cra_name		= "sha512",
-		.cra_driver_name	= "sha512-neon",
-		.cra_priority		= 300,
-		.cra_flags		= CRYPTO_AHASH_ALG_BLOCK_ONLY |
-					  CRYPTO_AHASH_ALG_FINUP_MAX,
-		.cra_blocksize		= SHA512_BLOCK_SIZE,
-		.cra_module		= THIS_MODULE,
-	}
-} };
diff --git a/arch/arm/crypto/sha512.h b/arch/arm/crypto/sha512.h
deleted file mode 100644
index eeaee52cda69..000000000000
--- a/arch/arm/crypto/sha512.h
+++ /dev/null
@@ -1,3 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-
-extern struct shash_alg sha512_neon_algs[2];
diff --git a/lib/crypto/Kconfig b/lib/crypto/Kconfig
index d1bee3787eb3..dac6356ba0aa 100644
--- a/lib/crypto/Kconfig
+++ b/lib/crypto/Kconfig
@@ -177,6 +177,7 @@ config CRYPTO_LIB_SHA512
 config CRYPTO_LIB_SHA512_ARCH
 	bool
 	depends on CRYPTO_LIB_SHA512 && !UML
+	default y if ARM && !CPU_V7M
 
 config CRYPTO_LIB_SM3
 	tristate
diff --git a/lib/crypto/Makefile b/lib/crypto/Makefile
index f6b6f370451e..67008a1612c6 100644
--- a/lib/crypto/Makefile
+++ b/lib/crypto/Makefile
@@ -1,5 +1,10 @@
 # SPDX-License-Identifier: GPL-2.0
 
+aflags-thumb2-$(CONFIG_THUMB2_KERNEL)  := -U__thumb2__ -D__thumb2__=1
+
+quiet_cmd_perlasm = PERLASM $@
+      cmd_perlasm = $(PERL) $(<) > $(@)
+
 obj-$(CONFIG_CRYPTO_LIB_UTILS)			+= libcryptoutils.o
 libcryptoutils-y				:= memneq.o utils.o
 
@@ -68,6 +73,15 @@ obj-$(CONFIG_CRYPTO_LIB_SHA512) += libsha512.o
 libsha512-y := sha512.o
 ifeq ($(CONFIG_CRYPTO_LIB_SHA512_ARCH),y)
 CFLAGS_sha512.o += -I$(src)/$(SRCARCH)
+
+ifeq ($(CONFIG_ARM),y)
+libsha512-y += arm/sha512-core.o
+$(obj)/arm/sha512-core.S: $(src)/arm/sha512-armv4.pl
+	$(call cmd,perlasm)
+clean-files += arm/sha512-core.S
+AFLAGS_arm/sha512-core.o += $(aflags-thumb2-y)
+endif
+
 endif # CONFIG_CRYPTO_LIB_SHA512_ARCH
 
 obj-$(CONFIG_MPILIB) += mpi/
diff --git a/lib/crypto/arm/.gitignore b/lib/crypto/arm/.gitignore
new file mode 100644
index 000000000000..670a4d97b568
--- /dev/null
+++ b/lib/crypto/arm/.gitignore
@@ -0,0 +1,2 @@
+# SPDX-License-Identifier: GPL-2.0-only
+sha512-core.S
diff --git a/arch/arm/crypto/sha512-armv4.pl b/lib/crypto/arm/sha512-armv4.pl
index 2fc3516912fa..2fc3516912fa 100644
--- a/arch/arm/crypto/sha512-armv4.pl
+++ b/lib/crypto/arm/sha512-armv4.pl
diff --git a/lib/crypto/arm/sha512.h b/lib/crypto/arm/sha512.h
new file mode 100644
index 000000000000..f147b6490d6c
--- /dev/null
+++ b/lib/crypto/arm/sha512.h
@@ -0,0 +1,38 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * arm32-optimized SHA-512 block function
+ *
+ * Copyright 2025 Google LLC
+ */
+
+#include <asm/neon.h>
+#include <crypto/internal/simd.h>
+
+static __ro_after_init DEFINE_STATIC_KEY_FALSE(have_neon);
+
+asmlinkage void sha512_block_data_order(struct sha512_block_state *state,
+					const u8 *data, size_t nblocks);
+asmlinkage void sha512_block_data_order_neon(struct sha512_block_state *state,
+					     const u8 *data, size_t nblocks);
+
+static void sha512_blocks(struct sha512_block_state *state,
+			  const u8 *data, size_t nblocks)
+{
+	if (IS_ENABLED(CONFIG_KERNEL_MODE_NEON) &&
+	    static_branch_likely(&have_neon) && likely(crypto_simd_usable())) {
+		kernel_neon_begin();
+		sha512_block_data_order_neon(state, data, nblocks);
+		kernel_neon_end();
+	} else {
+		sha512_block_data_order(state, data, nblocks);
+	}
+}
+
+#ifdef CONFIG_KERNEL_MODE_NEON
+#define sha512_mod_init_arch sha512_mod_init_arch
+static inline void sha512_mod_init_arch(void)
+{
+	if (cpu_has_neon())
+		static_branch_enable(&have_neon);
+}
+#endif /* CONFIG_KERNEL_MODE_NEON */