lib/crypto: poly1305: Consolidate into single module

Consolidate the Poly1305 code into a single module, similar to various
other algorithms (SHA-1, SHA-256, SHA-512, etc.):

- Each arch now provides a header file lib/crypto/$(SRCARCH)/poly1305.h,
  replacing lib/crypto/$(SRCARCH)/poly1305*.c.  The header defines
  poly1305_block_init(), poly1305_blocks(), poly1305_emit(), and
  optionally poly1305_mod_init_arch().  It is included by
  lib/crypto/poly1305.c, and thus the code gets built into the single
  libpoly1305 module, with improved inlining in some cases.

- Whether arch-optimized Poly1305 is buildable is now controlled
  centrally by lib/crypto/Kconfig instead of by
  lib/crypto/$(SRCARCH)/Kconfig.  The conditions for enabling it remain
  the same as before, and it remains enabled by default.  (The PPC64 one
  remains unconditionally disabled due to 'depends on BROKEN'.)

- Any additional arch-specific translation units for the optimized
  Poly1305 code, such as assembly files, are now compiled by
  lib/crypto/Makefile instead of lib/crypto/$(SRCARCH)/Makefile.

A special consideration is needed because the Adiantum code uses the
poly1305_core_*() functions directly.  For now, just carry forward that
approach.  This means retaining the CRYPTO_LIB_POLY1305_GENERIC kconfig
symbol, and keeping the poly1305_core_*() functions in separate
translation units.  So it's not quite as streamlined I've done with the
other hash functions, but we still get a single libpoly1305 module.

Note: to see the diff from the arm, arm64, and x86 .c files to the new
.h files, view this commit with 'git show -M10'.

Reviewed-by: Ard Biesheuvel <ardb@kernel.org>
Link: https://lore.kernel.org/r/20250829152513.92459-3-ebiggers@kernel.org
Signed-off-by: Eric Biggers <ebiggers@kernel.org>

26 files changed, 290 insertions, 415 deletions

diff --git a/lib/crypto/Kconfig b/lib/crypto/Kconfig
index 79b848448e07..9991118c41a9 100644
--- a/lib/crypto/Kconfig
+++ b/lib/crypto/Kconfig
@@ -114,6 +114,33 @@ config CRYPTO_LIB_MD5_ARCH
 	default y if PPC
 	default y if SPARC64
 
+config CRYPTO_LIB_POLY1305
+	tristate
+	help
+	  The Poly1305 library functions.  Select this if your module uses any
+	  of the functions from <crypto/poly1305.h>.
+
+config CRYPTO_LIB_POLY1305_ARCH
+	bool
+	depends on CRYPTO_LIB_POLY1305 && !UML
+	default y if ARM
+	default y if ARM64 && KERNEL_MODE_NEON
+	default y if MIPS
+	# The PPC64 code needs to be fixed to work in softirq context.
+	default y if PPC64 && CPU_LITTLE_ENDIAN && VSX && BROKEN
+	default y if X86_64
+
+# This symbol controls the inclusion of the Poly1305 generic code.  This differs
+# from most of the other algorithms, which handle the generic code
+# "automatically" via __maybe_unused.  This is needed so that the Adiantum code,
+# which calls the poly1305_core_*() functions directly, can enable them.
+config CRYPTO_LIB_POLY1305_GENERIC
+	bool
+	depends on CRYPTO_LIB_POLY1305
+	# Enable if there's no arch impl or the arch impl requires the generic
+	# impl as a fallback.  (Or if selected explicitly.)
+	default y if !CRYPTO_LIB_POLY1305_ARCH || PPC64
+
 config CRYPTO_LIB_POLY1305_RSIZE
 	int
 	default 2 if MIPS
@@ -121,29 +148,6 @@ config CRYPTO_LIB_POLY1305_RSIZE
 	default 9 if ARM || ARM64
 	default 1
 
-config CRYPTO_ARCH_HAVE_LIB_POLY1305
-	bool
-	help
-	  Declares whether the architecture provides an arch-specific
-	  accelerated implementation of the Poly1305 library interface,
-	  either builtin or as a module.
-
-config CRYPTO_LIB_POLY1305_GENERIC
-	tristate
-	default CRYPTO_LIB_POLY1305 if !CRYPTO_ARCH_HAVE_LIB_POLY1305
-	help
-	  This symbol can be selected by arch implementations of the Poly1305
-	  library interface that require the generic code as a fallback, e.g.,
-	  for SIMD implementations. If no arch specific implementation is
-	  enabled, this implementation serves the users of CRYPTO_LIB_POLY1305.
-
-config CRYPTO_LIB_POLY1305
-	tristate
-	help
-	  Enable the Poly1305 library interface. This interface may be fulfilled
-	  by either the generic implementation or an arch-specific one, if one
-	  is available and enabled.
-
 config CRYPTO_LIB_CHACHA20POLY1305
 	tristate
 	select CRYPTO_LIB_CHACHA
diff --git a/lib/crypto/Makefile b/lib/crypto/Makefile
index d362636a22d3..e0536e3b3a04 100644
--- a/lib/crypto/Makefile
+++ b/lib/crypto/Makefile
@@ -71,13 +71,60 @@ endif # CONFIG_CRYPTO_LIB_MD5_ARCH
 
 ################################################################################
 
-obj-$(CONFIG_CRYPTO_LIB_POLY1305)		+= libpoly1305.o
-libpoly1305-y					+= poly1305.o
+obj-$(CONFIG_CRYPTO_LIB_POLY1305) += libpoly1305.o
+libpoly1305-y := poly1305.o
+ifeq ($(CONFIG_ARCH_SUPPORTS_INT128),y)
+libpoly1305-$(CONFIG_CRYPTO_LIB_POLY1305_GENERIC) += poly1305-donna64.o
+else
+libpoly1305-$(CONFIG_CRYPTO_LIB_POLY1305_GENERIC) += poly1305-donna32.o
+endif
+
+ifeq ($(CONFIG_CRYPTO_LIB_POLY1305_ARCH),y)
+CFLAGS_poly1305.o += -I$(src)/$(SRCARCH)
+
+ifeq ($(CONFIG_ARM),y)
+libpoly1305-y += arm/poly1305-core.o
+$(obj)/arm/poly1305-core.S: $(src)/arm/poly1305-armv4.pl
+	$(call cmd,perlasm)
+# massage the perlasm code a bit so we only get the NEON routine if we need it
+poly1305-aflags-$(CONFIG_CPU_V7) := -U__LINUX_ARM_ARCH__ -D__LINUX_ARM_ARCH__=5
+poly1305-aflags-$(CONFIG_KERNEL_MODE_NEON) := -U__LINUX_ARM_ARCH__ -D__LINUX_ARM_ARCH__=7
+AFLAGS_arm/poly1305-core.o += $(poly1305-aflags-y) $(aflags-thumb2-y)
+endif
+
+ifeq ($(CONFIG_ARM64),y)
+libpoly1305-y += arm64/poly1305-core.o
+$(obj)/arm64/poly1305-core.S: $(src)/arm64/poly1305-armv8.pl
+	$(call cmd,perlasm_with_args)
+endif
+
+ifeq ($(CONFIG_MIPS),y)
+libpoly1305-y += mips/poly1305-core.o
+poly1305-perlasm-flavour-$(CONFIG_32BIT) := o32
+poly1305-perlasm-flavour-$(CONFIG_64BIT) := 64
+quiet_cmd_perlasm_poly1305 = PERLASM $@
+      cmd_perlasm_poly1305 = $(PERL) $< $(poly1305-perlasm-flavour-y) $@
+# Use if_changed instead of cmd, in case the flavour changed.
+$(obj)/mips/poly1305-core.S: $(src)/mips/poly1305-mips.pl FORCE
+	$(call if_changed,perlasm_poly1305)
+targets += mips/poly1305-core.S
+endif
 
-obj-$(CONFIG_CRYPTO_LIB_POLY1305_GENERIC)	+= libpoly1305-generic.o
-libpoly1305-generic-y				:= poly1305-donna32.o
-libpoly1305-generic-$(CONFIG_ARCH_SUPPORTS_INT128) := poly1305-donna64.o
-libpoly1305-generic-y				+= poly1305-generic.o
+libpoly1305-$(CONFIG_PPC) += powerpc/poly1305-p10le_64.o
+
+ifeq ($(CONFIG_X86),y)
+libpoly1305-y += x86/poly1305-x86_64-cryptogams.o
+$(obj)/x86/poly1305-x86_64-cryptogams.S: $(src)/x86/poly1305-x86_64-cryptogams.pl
+	$(call cmd,perlasm)
+endif
+
+endif # CONFIG_CRYPTO_LIB_POLY1305_ARCH
+
+# clean-files must be defined unconditionally
+clean-files += arm/poly1305-core.S \
+	       arm64/poly1305-core.S \
+	       mips/poly1305-core.S \
+	       x86/poly1305-x86_64-cryptogams.S
 
 ################################################################################
 
diff --git a/lib/crypto/arm/Kconfig b/lib/crypto/arm/Kconfig
index e8444fd0aae3..0d821e282c64 100644
--- a/lib/crypto/arm/Kconfig
+++ b/lib/crypto/arm/Kconfig
@@ -17,8 +17,3 @@ config CRYPTO_CHACHA20_NEON
 	tristate
 	default CRYPTO_LIB_CHACHA
 	select CRYPTO_ARCH_HAVE_LIB_CHACHA
-
-config CRYPTO_POLY1305_ARM
-	tristate
-	default CRYPTO_LIB_POLY1305
-	select CRYPTO_ARCH_HAVE_LIB_POLY1305
diff --git a/lib/crypto/arm/Makefile b/lib/crypto/arm/Makefile
index 4c042a4c77ed..9f70e61d419e 100644
--- a/lib/crypto/arm/Makefile
+++ b/lib/crypto/arm/Makefile
@@ -6,21 +6,3 @@ libblake2s-arm-y := blake2s-core.o blake2s-glue.o
 obj-$(CONFIG_CRYPTO_CHACHA20_NEON) += chacha-neon.o
 chacha-neon-y := chacha-scalar-core.o chacha-glue.o
 chacha-neon-$(CONFIG_KERNEL_MODE_NEON) += chacha-neon-core.o
-
-obj-$(CONFIG_CRYPTO_POLY1305_ARM) += poly1305-arm.o
-poly1305-arm-y := poly1305-core.o poly1305-glue.o
-
-quiet_cmd_perl = PERL    $@
-      cmd_perl = $(PERL) $(<) > $(@)
-
-$(obj)/%-core.S: $(src)/%-armv4.pl
-	$(call cmd,perl)
-
-clean-files += poly1305-core.S
-
-aflags-thumb2-$(CONFIG_THUMB2_KERNEL)  := -U__thumb2__ -D__thumb2__=1
-
-# massage the perlasm code a bit so we only get the NEON routine if we need it
-poly1305-aflags-$(CONFIG_CPU_V7) := -U__LINUX_ARM_ARCH__ -D__LINUX_ARM_ARCH__=5
-poly1305-aflags-$(CONFIG_KERNEL_MODE_NEON) := -U__LINUX_ARM_ARCH__ -D__LINUX_ARM_ARCH__=7
-AFLAGS_poly1305-core.o += $(poly1305-aflags-y) $(aflags-thumb2-y)
diff --git a/lib/crypto/arm/poly1305-armv4.pl b/lib/crypto/arm/poly1305-armv4.pl
index dd7a996361a7..34c11b7b44bd 100644
--- a/lib/crypto/arm/poly1305-armv4.pl
+++ b/lib/crypto/arm/poly1305-armv4.pl
@@ -43,9 +43,8 @@ $code.=<<___;
 #else
 # define __ARM_ARCH__ __LINUX_ARM_ARCH__
 # define __ARM_MAX_ARCH__ __LINUX_ARM_ARCH__
-# define poly1305_init   poly1305_block_init_arch
+# define poly1305_init   poly1305_block_init
 # define poly1305_blocks poly1305_blocks_arm
-# define poly1305_emit   poly1305_emit_arch
 #endif
 
 #if defined(__thumb2__)
diff --git a/lib/crypto/arm/poly1305-glue.c b/lib/crypto/arm/poly1305-glue.c
deleted file mode 100644
index 9e513e319e37..000000000000
--- a/lib/crypto/arm/poly1305-glue.c
+++ /dev/null
@@ -1,69 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * OpenSSL/Cryptogams accelerated Poly1305 transform for ARM
- *
- * Copyright (C) 2019 Linaro Ltd. <ard.biesheuvel@linaro.org>
- */
-
-#include <asm/hwcap.h>
-#include <asm/neon.h>
-#include <asm/simd.h>
-#include <crypto/internal/poly1305.h>
-#include <linux/cpufeature.h>
-#include <linux/jump_label.h>
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/unaligned.h>
-
-asmlinkage void poly1305_block_init_arch(
-	struct poly1305_block_state *state,
-	const u8 raw_key[POLY1305_BLOCK_SIZE]);
-EXPORT_SYMBOL_GPL(poly1305_block_init_arch);
-asmlinkage void poly1305_blocks_arm(struct poly1305_block_state *state,
-				    const u8 *src, u32 len, u32 hibit);
-asmlinkage void poly1305_blocks_neon(struct poly1305_block_state *state,
-				     const u8 *src, u32 len, u32 hibit);
-asmlinkage void poly1305_emit_arch(const struct poly1305_state *state,
-				   u8 digest[POLY1305_DIGEST_SIZE],
-				   const u32 nonce[4]);
-EXPORT_SYMBOL_GPL(poly1305_emit_arch);
-
-static __ro_after_init DEFINE_STATIC_KEY_FALSE(have_neon);
-
-void poly1305_blocks_arch(struct poly1305_block_state *state, const u8 *src,
-			  unsigned int len, u32 padbit)
-{
-	len = round_down(len, POLY1305_BLOCK_SIZE);
-	if (IS_ENABLED(CONFIG_KERNEL_MODE_NEON) &&
-	    static_branch_likely(&have_neon) && likely(may_use_simd())) {
-		do {
-			unsigned int todo = min_t(unsigned int, len, SZ_4K);
-
-			kernel_neon_begin();
-			poly1305_blocks_neon(state, src, todo, padbit);
-			kernel_neon_end();
-
-			len -= todo;
-			src += todo;
-		} while (len);
-	} else
-		poly1305_blocks_arm(state, src, len, padbit);
-}
-EXPORT_SYMBOL_GPL(poly1305_blocks_arch);
-
-static int __init arm_poly1305_mod_init(void)
-{
-	if (IS_ENABLED(CONFIG_KERNEL_MODE_NEON) &&
-	    (elf_hwcap & HWCAP_NEON))
-		static_branch_enable(&have_neon);
-	return 0;
-}
-subsys_initcall(arm_poly1305_mod_init);
-
-static void __exit arm_poly1305_mod_exit(void)
-{
-}
-module_exit(arm_poly1305_mod_exit);
-
-MODULE_DESCRIPTION("Accelerated Poly1305 transform for ARM");
-MODULE_LICENSE("GPL v2");
diff --git a/lib/crypto/arm/poly1305.h b/lib/crypto/arm/poly1305.h
new file mode 100644
index 000000000000..0021cf368307
--- /dev/null
+++ b/lib/crypto/arm/poly1305.h
@@ -0,0 +1,53 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * OpenSSL/Cryptogams accelerated Poly1305 transform for ARM
+ *
+ * Copyright (C) 2019 Linaro Ltd. <ard.biesheuvel@linaro.org>
+ */
+
+#include <asm/hwcap.h>
+#include <asm/neon.h>
+#include <asm/simd.h>
+#include <linux/cpufeature.h>
+#include <linux/jump_label.h>
+#include <linux/kernel.h>
+
+asmlinkage void poly1305_block_init(struct poly1305_block_state *state,
+				    const u8 raw_key[POLY1305_BLOCK_SIZE]);
+asmlinkage void poly1305_blocks_arm(struct poly1305_block_state *state,
+				    const u8 *src, u32 len, u32 hibit);
+asmlinkage void poly1305_blocks_neon(struct poly1305_block_state *state,
+				     const u8 *src, u32 len, u32 hibit);
+asmlinkage void poly1305_emit(const struct poly1305_state *state,
+			      u8 digest[POLY1305_DIGEST_SIZE],
+			      const u32 nonce[4]);
+
+static __ro_after_init DEFINE_STATIC_KEY_FALSE(have_neon);
+
+static void poly1305_blocks(struct poly1305_block_state *state, const u8 *src,
+			    unsigned int len, u32 padbit)
+{
+	if (IS_ENABLED(CONFIG_KERNEL_MODE_NEON) &&
+	    static_branch_likely(&have_neon) && likely(may_use_simd())) {
+		do {
+			unsigned int todo = min_t(unsigned int, len, SZ_4K);
+
+			kernel_neon_begin();
+			poly1305_blocks_neon(state, src, todo, padbit);
+			kernel_neon_end();
+
+			len -= todo;
+			src += todo;
+		} while (len);
+	} else
+		poly1305_blocks_arm(state, src, len, padbit);
+}
+
+#ifdef CONFIG_KERNEL_MODE_NEON
+#define poly1305_mod_init_arch poly1305_mod_init_arch
+static void poly1305_mod_init_arch(void)
+{
+	if (elf_hwcap & HWCAP_NEON)
+		static_branch_enable(&have_neon);
+}
+#endif /* CONFIG_KERNEL_MODE_NEON */
diff --git a/lib/crypto/arm64/Kconfig b/lib/crypto/arm64/Kconfig
index 0b903ef524d8..07c8a4f0ab03 100644
--- a/lib/crypto/arm64/Kconfig
+++ b/lib/crypto/arm64/Kconfig
@@ -6,9 +6,3 @@ config CRYPTO_CHACHA20_NEON
 	default CRYPTO_LIB_CHACHA
 	select CRYPTO_LIB_CHACHA_GENERIC
 	select CRYPTO_ARCH_HAVE_LIB_CHACHA
-
-config CRYPTO_POLY1305_NEON
-	tristate
-	depends on KERNEL_MODE_NEON
-	default CRYPTO_LIB_POLY1305
-	select CRYPTO_ARCH_HAVE_LIB_POLY1305
diff --git a/lib/crypto/arm64/Makefile b/lib/crypto/arm64/Makefile
index 6207088397a7..d49cceca3d1c 100644
--- a/lib/crypto/arm64/Makefile
+++ b/lib/crypto/arm64/Makefile
@@ -2,16 +2,3 @@
 
 obj-$(CONFIG_CRYPTO_CHACHA20_NEON) += chacha-neon.o
 chacha-neon-y := chacha-neon-core.o chacha-neon-glue.o
-
-obj-$(CONFIG_CRYPTO_POLY1305_NEON) += poly1305-neon.o
-poly1305-neon-y := poly1305-core.o poly1305-glue.o
-AFLAGS_poly1305-core.o += -Dpoly1305_init=poly1305_block_init_arch
-AFLAGS_poly1305-core.o += -Dpoly1305_emit=poly1305_emit_arch
-
-quiet_cmd_perlasm = PERLASM $@
-      cmd_perlasm = $(PERL) $(<) void $(@)
-
-$(obj)/%-core.S: $(src)/%-armv8.pl
-	$(call cmd,perlasm)
-
-clean-files += poly1305-core.S
diff --git a/lib/crypto/arm64/poly1305-armv8.pl b/lib/crypto/arm64/poly1305-armv8.pl
index 22c9069c0650..f1930c6b55ce 100644
--- a/lib/crypto/arm64/poly1305-armv8.pl
+++ b/lib/crypto/arm64/poly1305-armv8.pl
@@ -50,6 +50,9 @@ $code.=<<___;
 #ifndef __KERNEL__
 # include "arm_arch.h"
 .extern	OPENSSL_armcap_P
+#else
+# define poly1305_init   poly1305_block_init
+# define poly1305_blocks poly1305_blocks_arm64
 #endif
 
 .text
diff --git a/lib/crypto/arm64/poly1305-glue.c b/lib/crypto/arm64/poly1305-glue.c
deleted file mode 100644
index d4a522e7d25a..000000000000
--- a/lib/crypto/arm64/poly1305-glue.c
+++ /dev/null
@@ -1,67 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * OpenSSL/Cryptogams accelerated Poly1305 transform for arm64
- *
- * Copyright (C) 2019 Linaro Ltd. <ard.biesheuvel@linaro.org>
- */
-
-#include <asm/hwcap.h>
-#include <asm/neon.h>
-#include <asm/simd.h>
-#include <crypto/internal/poly1305.h>
-#include <linux/cpufeature.h>
-#include <linux/jump_label.h>
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/unaligned.h>
-
-asmlinkage void poly1305_block_init_arch(
-	struct poly1305_block_state *state,
-	const u8 raw_key[POLY1305_BLOCK_SIZE]);
-EXPORT_SYMBOL_GPL(poly1305_block_init_arch);
-asmlinkage void poly1305_blocks(struct poly1305_block_state *state,
-				const u8 *src, u32 len, u32 hibit);
-asmlinkage void poly1305_blocks_neon(struct poly1305_block_state *state,
-				     const u8 *src, u32 len, u32 hibit);
-asmlinkage void poly1305_emit_arch(const struct poly1305_state *state,
-				   u8 digest[POLY1305_DIGEST_SIZE],
-				   const u32 nonce[4]);
-EXPORT_SYMBOL_GPL(poly1305_emit_arch);
-
-static __ro_after_init DEFINE_STATIC_KEY_FALSE(have_neon);
-
-void poly1305_blocks_arch(struct poly1305_block_state *state, const u8 *src,
-			  unsigned int len, u32 padbit)
-{
-	len = round_down(len, POLY1305_BLOCK_SIZE);
-	if (static_branch_likely(&have_neon) && likely(may_use_simd())) {
-		do {
-			unsigned int todo = min_t(unsigned int, len, SZ_4K);
-
-			kernel_neon_begin();
-			poly1305_blocks_neon(state, src, todo, padbit);
-			kernel_neon_end();
-
-			len -= todo;
-			src += todo;
-		} while (len);
-	} else
-		poly1305_blocks(state, src, len, padbit);
-}
-EXPORT_SYMBOL_GPL(poly1305_blocks_arch);
-
-static int __init neon_poly1305_mod_init(void)
-{
-	if (cpu_have_named_feature(ASIMD))
-		static_branch_enable(&have_neon);
-	return 0;
-}
-subsys_initcall(neon_poly1305_mod_init);
-
-static void __exit neon_poly1305_mod_exit(void)
-{
-}
-module_exit(neon_poly1305_mod_exit);
-
-MODULE_DESCRIPTION("Poly1305 authenticator (ARM64 optimized)");
-MODULE_LICENSE("GPL v2");
diff --git a/lib/crypto/arm64/poly1305.h b/lib/crypto/arm64/poly1305.h
new file mode 100644
index 000000000000..aed5921ccd9a
--- /dev/null
+++ b/lib/crypto/arm64/poly1305.h
@@ -0,0 +1,50 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * OpenSSL/Cryptogams accelerated Poly1305 transform for arm64
+ *
+ * Copyright (C) 2019 Linaro Ltd. <ard.biesheuvel@linaro.org>
+ */
+
+#include <asm/hwcap.h>
+#include <asm/neon.h>
+#include <asm/simd.h>
+#include <linux/cpufeature.h>
+#include <linux/jump_label.h>
+#include <linux/kernel.h>
+
+asmlinkage void poly1305_block_init(struct poly1305_block_state *state,
+				    const u8 raw_key[POLY1305_BLOCK_SIZE]);
+asmlinkage void poly1305_blocks_arm64(struct poly1305_block_state *state,
+				      const u8 *src, u32 len, u32 hibit);
+asmlinkage void poly1305_blocks_neon(struct poly1305_block_state *state,
+				     const u8 *src, u32 len, u32 hibit);
+asmlinkage void poly1305_emit(const struct poly1305_state *state,
+			      u8 digest[POLY1305_DIGEST_SIZE],
+			      const u32 nonce[4]);
+
+static __ro_after_init DEFINE_STATIC_KEY_FALSE(have_neon);
+
+static void poly1305_blocks(struct poly1305_block_state *state, const u8 *src,
+			    unsigned int len, u32 padbit)
+{
+	if (static_branch_likely(&have_neon) && likely(may_use_simd())) {
+		do {
+			unsigned int todo = min_t(unsigned int, len, SZ_4K);
+
+			kernel_neon_begin();
+			poly1305_blocks_neon(state, src, todo, padbit);
+			kernel_neon_end();
+
+			len -= todo;
+			src += todo;
+		} while (len);
+	} else
+		poly1305_blocks_arm64(state, src, len, padbit);
+}
+
+#define poly1305_mod_init_arch poly1305_mod_init_arch
+static void poly1305_mod_init_arch(void)
+{
+	if (cpu_have_named_feature(ASIMD))
+		static_branch_enable(&have_neon);
+}
diff --git a/lib/crypto/mips/Kconfig b/lib/crypto/mips/Kconfig
index 0670a170c1be..94c1a0892c20 100644
--- a/lib/crypto/mips/Kconfig
+++ b/lib/crypto/mips/Kconfig
@@ -5,8 +5,3 @@ config CRYPTO_CHACHA_MIPS
 	depends on CPU_MIPS32_R2
 	default CRYPTO_LIB_CHACHA
 	select CRYPTO_ARCH_HAVE_LIB_CHACHA
-
-config CRYPTO_POLY1305_MIPS
-	tristate
-	default CRYPTO_LIB_POLY1305
-	select CRYPTO_ARCH_HAVE_LIB_POLY1305
diff --git a/lib/crypto/mips/Makefile b/lib/crypto/mips/Makefile
index 804488c7aded..b5ea0e25c21e 100644
--- a/lib/crypto/mips/Makefile
+++ b/lib/crypto/mips/Makefile
@@ -3,17 +3,3 @@
 obj-$(CONFIG_CRYPTO_CHACHA_MIPS) += chacha-mips.o
 chacha-mips-y := chacha-core.o chacha-glue.o
 AFLAGS_chacha-core.o += -O2 # needed to fill branch delay slots
-
-obj-$(CONFIG_CRYPTO_POLY1305_MIPS) += poly1305-mips.o
-poly1305-mips-y := poly1305-core.o poly1305-glue.o
-
-perlasm-flavour-$(CONFIG_32BIT) := o32
-perlasm-flavour-$(CONFIG_64BIT) := 64
-
-quiet_cmd_perlasm = PERLASM $@
-      cmd_perlasm = $(PERL) $(<) $(perlasm-flavour-y) $(@)
-
-$(obj)/poly1305-core.S: $(src)/poly1305-mips.pl FORCE
-	$(call if_changed,perlasm)
-
-targets += poly1305-core.S
diff --git a/lib/crypto/mips/poly1305-glue.c b/lib/crypto/mips/poly1305-glue.c
deleted file mode 100644
index 002f50f710ab..000000000000
--- a/lib/crypto/mips/poly1305-glue.c
+++ /dev/null
@@ -1,27 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * OpenSSL/Cryptogams accelerated Poly1305 transform for MIPS
- *
- * Copyright (C) 2019 Linaro Ltd. <ard.biesheuvel@linaro.org>
- */
-
-#include <crypto/internal/poly1305.h>
-#include <linux/cpufeature.h>
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/unaligned.h>
-
-asmlinkage void poly1305_block_init_arch(
-	struct poly1305_block_state *state,
-	const u8 raw_key[POLY1305_BLOCK_SIZE]);
-EXPORT_SYMBOL_GPL(poly1305_block_init_arch);
-asmlinkage void poly1305_blocks_arch(struct poly1305_block_state *state,
-				     const u8 *src, u32 len, u32 hibit);
-EXPORT_SYMBOL_GPL(poly1305_blocks_arch);
-asmlinkage void poly1305_emit_arch(const struct poly1305_state *state,
-				   u8 digest[POLY1305_DIGEST_SIZE],
-				   const u32 nonce[4]);
-EXPORT_SYMBOL_GPL(poly1305_emit_arch);
-
-MODULE_DESCRIPTION("Poly1305 transform (MIPS accelerated");
-MODULE_LICENSE("GPL v2");
diff --git a/lib/crypto/mips/poly1305-mips.pl b/lib/crypto/mips/poly1305-mips.pl
index 399f10c3e385..71347f34f4f9 100644
--- a/lib/crypto/mips/poly1305-mips.pl
+++ b/lib/crypto/mips/poly1305-mips.pl
@@ -93,9 +93,7 @@ $code.=<<___;
 #endif
 
 #ifdef	__KERNEL__
-# define poly1305_init   poly1305_block_init_arch
-# define poly1305_blocks poly1305_blocks_arch
-# define poly1305_emit   poly1305_emit_arch
+# define poly1305_init   poly1305_block_init
 #endif
 
 #if defined(__MIPSEB__) && !defined(MIPSEB)
@@ -565,9 +563,7 @@ $code.=<<___;
 #endif
 
 #ifdef	__KERNEL__
-# define poly1305_init   poly1305_block_init_arch
-# define poly1305_blocks poly1305_blocks_arch
-# define poly1305_emit   poly1305_emit_arch
+# define poly1305_init   poly1305_block_init
 #endif
 
 #if defined(__MIPSEB__) && !defined(MIPSEB)
diff --git a/lib/crypto/mips/poly1305.h b/lib/crypto/mips/poly1305.h
new file mode 100644
index 000000000000..85de450f1a93
--- /dev/null
+++ b/lib/crypto/mips/poly1305.h
@@ -0,0 +1,14 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * OpenSSL/Cryptogams accelerated Poly1305 transform for MIPS
+ *
+ * Copyright (C) 2019 Linaro Ltd. <ard.biesheuvel@linaro.org>
+ */
+
+asmlinkage void poly1305_block_init(struct poly1305_block_state *state,
+				    const u8 raw_key[POLY1305_BLOCK_SIZE]);
+asmlinkage void poly1305_blocks(struct poly1305_block_state *state,
+				const u8 *src, u32 len, u32 hibit);
+asmlinkage void poly1305_emit(const struct poly1305_state *state,
+			      u8 digest[POLY1305_DIGEST_SIZE],
+			      const u32 nonce[4]);
diff --git a/lib/crypto/poly1305-generic.c b/lib/crypto/poly1305-generic.c
deleted file mode 100644
index 71a16c5c538b..000000000000
--- a/lib/crypto/poly1305-generic.c
+++ /dev/null
@@ -1,25 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * Poly1305 authenticator algorithm, RFC7539
- *
- * Copyright (C) 2015 Martin Willi
- *
- * Based on public domain code by Andrew Moon and Daniel J. Bernstein.
- */
-
-#include <crypto/internal/poly1305.h>
-#include <linux/export.h>
-#include <linux/kernel.h>
-#include <linux/module.h>
-
-void poly1305_block_init_generic(struct poly1305_block_state *desc,
-				 const u8 raw_key[POLY1305_BLOCK_SIZE])
-{
-	poly1305_core_init(&desc->h);
-	poly1305_core_setkey(&desc->core_r, raw_key);
-}
-EXPORT_SYMBOL_GPL(poly1305_block_init_generic);
-
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Martin Willi <martin@strongswan.org>");
-MODULE_DESCRIPTION("Poly1305 algorithm (generic implementation)");
diff --git a/lib/crypto/poly1305.c b/lib/crypto/poly1305.c
index a6dc182b6c22..f313ccc4b4dd 100644
--- a/lib/crypto/poly1305.c
+++ b/lib/crypto/poly1305.c
@@ -7,7 +7,6 @@
  * Based on public domain code by Andrew Moon and Daniel J. Bernstein.
  */
 
-#include <crypto/internal/blockhash.h>
 #include <crypto/internal/poly1305.h>
 #include <linux/export.h>
 #include <linux/kernel.h>
@@ -15,6 +14,14 @@
 #include <linux/string.h>
 #include <linux/unaligned.h>
 
+#ifdef CONFIG_CRYPTO_LIB_POLY1305_ARCH
+#include "poly1305.h" /* $(SRCARCH)/poly1305.h */
+#else
+#define poly1305_block_init	poly1305_block_init_generic
+#define poly1305_blocks		poly1305_blocks_generic
+#define poly1305_emit		poly1305_emit_generic
+#endif
+
 void poly1305_init(struct poly1305_desc_ctx *desc,
 		   const u8 key[POLY1305_KEY_SIZE])
 {
@@ -23,28 +30,40 @@ void poly1305_init(struct poly1305_desc_ctx *desc,
 	desc->s[2] = get_unaligned_le32(key + 24);
 	desc->s[3] = get_unaligned_le32(key + 28);
 	desc->buflen = 0;
-	if (IS_ENABLED(CONFIG_CRYPTO_ARCH_HAVE_LIB_POLY1305))
-		poly1305_block_init_arch(&desc->state, key);
-	else
-		poly1305_block_init_generic(&desc->state, key);
+	poly1305_block_init(&desc->state, key);
 }
 EXPORT_SYMBOL(poly1305_init);
 
-static inline void poly1305_blocks(struct poly1305_block_state *state,
-				   const u8 *src, unsigned int len)
-{
-	if (IS_ENABLED(CONFIG_CRYPTO_ARCH_HAVE_LIB_POLY1305))
-		poly1305_blocks_arch(state, src, len, 1);
-	else
-		poly1305_blocks_generic(state, src, len, 1);
-}
-
 void poly1305_update(struct poly1305_desc_ctx *desc,
 		     const u8 *src, unsigned int nbytes)
 {
-	desc->buflen = BLOCK_HASH_UPDATE(poly1305_blocks, &desc->state,
-					 src, nbytes, POLY1305_BLOCK_SIZE,
-					 desc->buf, desc->buflen);
+	if (desc->buflen + nbytes >= POLY1305_BLOCK_SIZE) {
+		unsigned int bulk_len;
+
+		if (desc->buflen) {
+			unsigned int l = POLY1305_BLOCK_SIZE - desc->buflen;
+
+			memcpy(&desc->buf[desc->buflen], src, l);
+			src += l;
+			nbytes -= l;
+
+			poly1305_blocks(&desc->state, desc->buf,
+					POLY1305_BLOCK_SIZE, 1);
+			desc->buflen = 0;
+		}
+
+		bulk_len = round_down(nbytes, POLY1305_BLOCK_SIZE);
+		nbytes %= POLY1305_BLOCK_SIZE;
+
+		if (bulk_len) {
+			poly1305_blocks(&desc->state, src, bulk_len, 1);
+			src += bulk_len;
+		}
+	}
+	if (nbytes) {
+		memcpy(&desc->buf[desc->buflen], src, nbytes);
+		desc->buflen += nbytes;
+	}
 }
 EXPORT_SYMBOL(poly1305_update);
 
@@ -54,22 +73,28 @@ void poly1305_final(struct poly1305_desc_ctx *desc, u8 *dst)
 		desc->buf[desc->buflen++] = 1;
 		memset(desc->buf + desc->buflen, 0,
 		       POLY1305_BLOCK_SIZE - desc->buflen);
-		if (IS_ENABLED(CONFIG_CRYPTO_ARCH_HAVE_LIB_POLY1305))
-			poly1305_blocks_arch(&desc->state, desc->buf,
-					     POLY1305_BLOCK_SIZE, 0);
-		else
-			poly1305_blocks_generic(&desc->state, desc->buf,
-						POLY1305_BLOCK_SIZE, 0);
+		poly1305_blocks(&desc->state, desc->buf, POLY1305_BLOCK_SIZE,
+				0);
 	}
 
-	if (IS_ENABLED(CONFIG_CRYPTO_ARCH_HAVE_LIB_POLY1305))
-		poly1305_emit_arch(&desc->state.h, dst, desc->s);
-	else
-		poly1305_emit_generic(&desc->state.h, dst, desc->s);
+	poly1305_emit(&desc->state.h, dst, desc->s);
 	*desc = (struct poly1305_desc_ctx){};
 }
 EXPORT_SYMBOL(poly1305_final);