diff mbox series

[v4,11/11] crypto: lib/poly1305 - Use block-only interface

Message ID 915c874caf5451d560bf26ff59f58177aa8b7c17.1745815528.git.herbert@gondor.apana.org.au
State New
Headers show
Series crypto: lib - Add partial block helper | expand

Commit Message

Herbert Xu April 28, 2025, 4:56 a.m. UTC 
Now that every architecture provides a block function, use that
to implement the lib/poly1305 and remove the old per-arch code.

Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 arch/arm/lib/crypto/poly1305-glue.c         | 57 -------------------
 arch/arm64/lib/crypto/poly1305-glue.c       | 58 -------------------
 arch/mips/lib/crypto/poly1305-glue.c        | 60 --------------------
 arch/powerpc/lib/crypto/poly1305-p10-glue.c | 63 ---------------------
 arch/x86/lib/crypto/poly1305_glue.c         | 60 --------------------
 include/crypto/poly1305.h                   | 53 ++---------------
 lib/crypto/poly1305.c                       | 39 ++++++++-----
 7 files changed, 32 insertions(+), 358 deletions(-)

Comments

Eric Biggers May 8, 2025, 4:29 p.m. UTC | #1 
On Thu, May 08, 2025 at 05:45:28PM +0800, Herbert Xu wrote:
> On Thu, May 08, 2025 at 02:46:06PM +0530, Venkat Rao Bagalkote wrote:
> >
> > I tested this patch by applying on next-20250507, though it fixes the build
> > issue, it has introduced a boot warning.
> 
> Looking at the history of this code it was never used as lib/crypto
> prior to commit 378a337ab40f88d63ba71d68ff578ead7f5ac8f1.  So either
> this code simply doesn't work as lib/crypto for some reason, or my
> subsequent blockhash change broke it.
> 
> Could you please revert back to commit 378a337ab40f and see if the
> lib/crypto chacha20poly1305 self-test passes with that?
> 

My patchsets "Remove per-architecture poly1305 shash glue code" and
"Finish disentangling ChaCha, Poly1305, and BLAKE2s from CRYPTO", which included
commit 378a337ab40f, passed testing with qemu-system-ppc64 with -M pseries and
-cpu in [POWER7, POWER8, POWER9, Power10].  These issues, both the build failure
and test failure, were introduced by your patchset
"crypto: lib - Add partial block helper".

- Eric
Herbert Xu May 9, 2025, 2:16 p.m. UTC | #2 
On Thu, May 08, 2025 at 08:23:17PM +0800, Herbert Xu wrote:
>
> @@ -51,7 +52,7 @@ void poly1305_blocks_arch(struct poly1305_block_state *state, const u8 *src,
>  	if (!static_key_enabled(&have_p10))
>  		return poly1305_blocks_generic(state, src, len, padbit);
>  	vsx_begin();
> -	if (len >= POLY1305_BLOCK_SIZE * 4) {
> +	if (crypto_simd_usable() && len >= POLY1305_BLOCK_SIZE * 4) {

This patch is obviously broken.  However, I think this code was
always broken in the SIMD-fallback case.  AFAICS the fallback
uses vector instructions so it can't be used in softirqs either.

A proper fallback would have to convert the state to the format
used by the generic poly1305 implementation, call that, and then
convert it back.

Of course it would be a lot easier if ppc could make VSX usable
in softirq context.

Cheers,
Eric Biggers May 10, 2025, 4:44 a.m. UTC | #3 
On Fri, May 09, 2025 at 08:29:00PM +0800, Herbert Xu wrote:
> On Thu, May 08, 2025 at 08:35:48PM +0530, Venkat Rao Bagalkote wrote:
> >
> > Unfortunately, above patch dosent fix the boot warning.
> 
> This works for me:
> 
> ---8<---
> Swap the order of the arguments in poly1305_emit_arch to match
> the prototype.
> 
> Fixes: 14d31979145d ("crypto: powerpc/poly1305 - Add block-only interface")
> Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>

This fixes "-cpu Power10", but older CPUs (e.g. "-cpu POWER9") are still
failing.

- Eric
diff mbox series

Patch

diff --git a/arch/arm/lib/crypto/poly1305-glue.c b/arch/arm/lib/crypto/poly1305-glue.c
index 3ee16048ec7c..91da42b26d9c 100644
--- a/arch/arm/lib/crypto/poly1305-glue.c
+++ b/arch/arm/lib/crypto/poly1305-glue.c
@@ -12,7 +12,6 @@ 
 #include <linux/jump_label.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
-#include <linux/string.h>
 #include <linux/unaligned.h>
 
 asmlinkage void poly1305_block_init_arch(
@@ -35,17 +34,6 @@  void __weak poly1305_blocks_neon(struct poly1305_block_state *state,
 
 static __ro_after_init DEFINE_STATIC_KEY_FALSE(have_neon);
 
-void poly1305_init_arch(struct poly1305_desc_ctx *dctx, const u8 key[POLY1305_KEY_SIZE])
-{
-	dctx->s[0] = get_unaligned_le32(key + 16);
-	dctx->s[1] = get_unaligned_le32(key + 20);
-	dctx->s[2] = get_unaligned_le32(key + 24);
-	dctx->s[3] = get_unaligned_le32(key + 28);
-	dctx->buflen = 0;
-	poly1305_block_init_arch(&dctx->state, key);
-}
-EXPORT_SYMBOL(poly1305_init_arch);
-
 void poly1305_blocks_arch(struct poly1305_block_state *state, const u8 *src,
 			  unsigned int len, u32 padbit)
 {
@@ -67,51 +55,6 @@  void poly1305_blocks_arch(struct poly1305_block_state *state, const u8 *src,
 }
 EXPORT_SYMBOL_GPL(poly1305_blocks_arch);
 
-void poly1305_update_arch(struct poly1305_desc_ctx *dctx, const u8 *src,
-			  unsigned int nbytes)
-{
-	if (unlikely(dctx->buflen)) {
-		u32 bytes = min(nbytes, POLY1305_BLOCK_SIZE - dctx->buflen);
-
-		memcpy(dctx->buf + dctx->buflen, src, bytes);
-		src += bytes;
-		nbytes -= bytes;
-		dctx->buflen += bytes;
-
-		if (dctx->buflen == POLY1305_BLOCK_SIZE) {
-			poly1305_blocks_arch(&dctx->state, dctx->buf,
-					     POLY1305_BLOCK_SIZE, 1);
-			dctx->buflen = 0;
-		}
-	}
-
-	if (likely(nbytes >= POLY1305_BLOCK_SIZE)) {
-		poly1305_blocks_arch(&dctx->state, src, nbytes, 1);
-		src += round_down(nbytes, POLY1305_BLOCK_SIZE);
-		nbytes %= POLY1305_BLOCK_SIZE;
-	}
-
-	if (unlikely(nbytes)) {
-		dctx->buflen = nbytes;
-		memcpy(dctx->buf, src, nbytes);
-	}
-}
-EXPORT_SYMBOL(poly1305_update_arch);
-
-void poly1305_final_arch(struct poly1305_desc_ctx *dctx, u8 *dst)
-{
-	if (unlikely(dctx->buflen)) {
-		dctx->buf[dctx->buflen++] = 1;
-		memset(dctx->buf + dctx->buflen, 0,
-		       POLY1305_BLOCK_SIZE - dctx->buflen);
-		poly1305_blocks_arch(&dctx->state, dctx->buf, POLY1305_BLOCK_SIZE, 0);
-	}
-
-	poly1305_emit_arch(&dctx->h, dst, dctx->s);
-	*dctx = (struct poly1305_desc_ctx){};
-}
-EXPORT_SYMBOL(poly1305_final_arch);
-
 bool poly1305_is_arch_optimized(void)
 {
 	/* We always can use at least the ARM scalar implementation. */
diff --git a/arch/arm64/lib/crypto/poly1305-glue.c b/arch/arm64/lib/crypto/poly1305-glue.c
index d66a820e32d5..681c26557336 100644
--- a/arch/arm64/lib/crypto/poly1305-glue.c
+++ b/arch/arm64/lib/crypto/poly1305-glue.c
@@ -12,7 +12,6 @@ 
 #include <linux/jump_label.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
-#include <linux/string.h>
 #include <linux/unaligned.h>
 
 asmlinkage void poly1305_block_init_arch(
@@ -30,17 +29,6 @@  EXPORT_SYMBOL_GPL(poly1305_emit_arch);
 
 static __ro_after_init DEFINE_STATIC_KEY_FALSE(have_neon);
 
-void poly1305_init_arch(struct poly1305_desc_ctx *dctx, const u8 key[POLY1305_KEY_SIZE])
-{
-	dctx->s[0] = get_unaligned_le32(key + 16);
-	dctx->s[1] = get_unaligned_le32(key + 20);
-	dctx->s[2] = get_unaligned_le32(key + 24);
-	dctx->s[3] = get_unaligned_le32(key + 28);
-	dctx->buflen = 0;
-	poly1305_block_init_arch(&dctx->state, key);
-}
-EXPORT_SYMBOL(poly1305_init_arch);
-
 void poly1305_blocks_arch(struct poly1305_block_state *state, const u8 *src,
 			  unsigned int len, u32 padbit)
 {
@@ -61,52 +49,6 @@  void poly1305_blocks_arch(struct poly1305_block_state *state, const u8 *src,
 }
 EXPORT_SYMBOL_GPL(poly1305_blocks_arch);
 
-void poly1305_update_arch(struct poly1305_desc_ctx *dctx, const u8 *src,
-			  unsigned int nbytes)
-{
-	if (unlikely(dctx->buflen)) {
-		u32 bytes = min(nbytes, POLY1305_BLOCK_SIZE - dctx->buflen);
-
-		memcpy(dctx->buf + dctx->buflen, src, bytes);
-		src += bytes;
-		nbytes -= bytes;
-		dctx->buflen += bytes;
-
-		if (dctx->buflen == POLY1305_BLOCK_SIZE) {
-			poly1305_blocks_arch(&dctx->state, dctx->buf,
-					     POLY1305_BLOCK_SIZE, 1);
-			dctx->buflen = 0;
-		}
-	}
-
-	if (likely(nbytes >= POLY1305_BLOCK_SIZE)) {
-		poly1305_blocks_arch(&dctx->state, src, nbytes, 1);
-		src += round_down(nbytes, POLY1305_BLOCK_SIZE);
-		nbytes %= POLY1305_BLOCK_SIZE;
-	}
-
-	if (unlikely(nbytes)) {
-		dctx->buflen = nbytes;
-		memcpy(dctx->buf, src, nbytes);
-	}
-}
-EXPORT_SYMBOL(poly1305_update_arch);
-
-void poly1305_final_arch(struct poly1305_desc_ctx *dctx, u8 *dst)
-{
-	if (unlikely(dctx->buflen)) {
-		dctx->buf[dctx->buflen++] = 1;
-		memset(dctx->buf + dctx->buflen, 0,
-		       POLY1305_BLOCK_SIZE - dctx->buflen);
-		poly1305_blocks_arch(&dctx->state, dctx->buf,
-				     POLY1305_BLOCK_SIZE, 0);
-	}
-
-	poly1305_emit_arch(&dctx->h, dst, dctx->s);
-	memzero_explicit(dctx, sizeof(*dctx));
-}
-EXPORT_SYMBOL(poly1305_final_arch);
-
 bool poly1305_is_arch_optimized(void)
 {
 	/* We always can use at least the ARM64 scalar implementation. */
diff --git a/arch/mips/lib/crypto/poly1305-glue.c b/arch/mips/lib/crypto/poly1305-glue.c
index 2fea4cacfe27..764a38a65200 100644
--- a/arch/mips/lib/crypto/poly1305-glue.c
+++ b/arch/mips/lib/crypto/poly1305-glue.c
@@ -9,7 +9,6 @@ 
 #include <linux/cpufeature.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
-#include <linux/string.h>
 #include <linux/unaligned.h>
 
 asmlinkage void poly1305_block_init_arch(
@@ -24,65 +23,6 @@  asmlinkage void poly1305_emit_arch(const struct poly1305_state *state,
 				   const u32 nonce[4]);
 EXPORT_SYMBOL_GPL(poly1305_emit_arch);
 
-void poly1305_init_arch(struct poly1305_desc_ctx *dctx, const u8 key[POLY1305_KEY_SIZE])
-{
-	dctx->s[0] = get_unaligned_le32(key + 16);
-	dctx->s[1] = get_unaligned_le32(key + 20);
-	dctx->s[2] = get_unaligned_le32(key + 24);
-	dctx->s[3] = get_unaligned_le32(key + 28);
-	dctx->buflen = 0;
-	poly1305_block_init_arch(&dctx->state, key);
-}
-EXPORT_SYMBOL(poly1305_init_arch);
-
-void poly1305_update_arch(struct poly1305_desc_ctx *dctx, const u8 *src,
-			  unsigned int nbytes)
-{
-	if (unlikely(dctx->buflen)) {
-		u32 bytes = min(nbytes, POLY1305_BLOCK_SIZE - dctx->buflen);
-
-		memcpy(dctx->buf + dctx->buflen, src, bytes);
-		src += bytes;
-		nbytes -= bytes;
-		dctx->buflen += bytes;
-
-		if (dctx->buflen == POLY1305_BLOCK_SIZE) {
-			poly1305_blocks_arch(&dctx->state, dctx->buf,
-					     POLY1305_BLOCK_SIZE, 1);
-			dctx->buflen = 0;
-		}
-	}
-
-	if (likely(nbytes >= POLY1305_BLOCK_SIZE)) {
-		unsigned int len = round_down(nbytes, POLY1305_BLOCK_SIZE);
-
-		poly1305_blocks_arch(&dctx->state, src, len, 1);
-		src += len;
-		nbytes %= POLY1305_BLOCK_SIZE;
-	}
-
-	if (unlikely(nbytes)) {
-		dctx->buflen = nbytes;
-		memcpy(dctx->buf, src, nbytes);
-	}
-}
-EXPORT_SYMBOL(poly1305_update_arch);
-
-void poly1305_final_arch(struct poly1305_desc_ctx *dctx, u8 *dst)
-{
-	if (unlikely(dctx->buflen)) {
-		dctx->buf[dctx->buflen++] = 1;
-		memset(dctx->buf + dctx->buflen, 0,
-		       POLY1305_BLOCK_SIZE - dctx->buflen);
-		poly1305_blocks_arch(&dctx->state, dctx->buf,
-				     POLY1305_BLOCK_SIZE, 0);
-	}
-
-	poly1305_emit_arch(&dctx->h, dst, dctx->s);
-	*dctx = (struct poly1305_desc_ctx){};
-}
-EXPORT_SYMBOL(poly1305_final_arch);
-
 bool poly1305_is_arch_optimized(void)
 {
 	return true;
diff --git a/arch/powerpc/lib/crypto/poly1305-p10-glue.c b/arch/powerpc/lib/crypto/poly1305-p10-glue.c
index 708435beaba6..50ac802220e0 100644
--- a/arch/powerpc/lib/crypto/poly1305-p10-glue.c
+++ b/arch/powerpc/lib/crypto/poly1305-p10-glue.c
@@ -10,7 +10,6 @@ 
 #include <linux/jump_label.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
-#include <linux/string.h>
 #include <linux/unaligned.h>
 
 asmlinkage void poly1305_p10le_4blocks(struct poly1305_block_state *state, const u8 *m, u32 mlen);
@@ -45,17 +44,6 @@  void poly1305_block_init_arch(struct poly1305_block_state *dctx,
 }
 EXPORT_SYMBOL_GPL(poly1305_block_init_arch);
 
-void poly1305_init_arch(struct poly1305_desc_ctx *dctx, const u8 key[POLY1305_KEY_SIZE])
-{
-	dctx->s[0] = get_unaligned_le32(key + 16);
-	dctx->s[1] = get_unaligned_le32(key + 20);
-	dctx->s[2] = get_unaligned_le32(key + 24);
-	dctx->s[3] = get_unaligned_le32(key + 28);
-	dctx->buflen = 0;
-	poly1305_block_init_arch(&dctx->state, key);
-}
-EXPORT_SYMBOL(poly1305_init_arch);
-
 void poly1305_blocks_arch(struct poly1305_block_state *state, const u8 *src,
 			  unsigned int len, u32 padbit)
 {
@@ -76,57 +64,6 @@  void poly1305_blocks_arch(struct poly1305_block_state *state, const u8 *src,
 }
 EXPORT_SYMBOL_GPL(poly1305_blocks_arch);
 
-void poly1305_update_arch(struct poly1305_desc_ctx *dctx,
-			  const u8 *src, unsigned int srclen)
-{
-	unsigned int bytes;
-
-	if (!static_key_enabled(&have_p10))
-		return poly1305_update_generic(dctx, src, srclen);
-
-	if (unlikely(dctx->buflen)) {
-		bytes = min(srclen, POLY1305_BLOCK_SIZE - dctx->buflen);
-		memcpy(dctx->buf + dctx->buflen, src, bytes);
-		src += bytes;
-		srclen -= bytes;
-		dctx->buflen += bytes;
-		if (dctx->buflen < POLY1305_BLOCK_SIZE)
-			return;
-		poly1305_blocks_arch(&dctx->state, dctx->buf,
-				     POLY1305_BLOCK_SIZE, 1);
-		dctx->buflen = 0;
-	}
-
-	if (likely(srclen >= POLY1305_BLOCK_SIZE)) {
-		poly1305_blocks_arch(&dctx->state, src, srclen, 1);
-		src += srclen - (srclen % POLY1305_BLOCK_SIZE);
-		srclen %= POLY1305_BLOCK_SIZE;
-	}
-
-	if (unlikely(srclen)) {
-		dctx->buflen = srclen;
-		memcpy(dctx->buf, src, srclen);
-	}
-}
-EXPORT_SYMBOL(poly1305_update_arch);
-
-void poly1305_final_arch(struct poly1305_desc_ctx *dctx, u8 *dst)
-{
-	if (!static_key_enabled(&have_p10))
-		return poly1305_final_generic(dctx, dst);
-
-	if (dctx->buflen) {
-		dctx->buf[dctx->buflen++] = 1;
-		memset(dctx->buf + dctx->buflen, 0,
-		       POLY1305_BLOCK_SIZE - dctx->buflen);
-		poly1305_blocks_arch(&dctx->state, dctx->buf,
-				     POLY1305_BLOCK_SIZE, 0);
-	}
-
-	poly1305_emit_arch(&dctx->h, dst, dctx->s);
-}
-EXPORT_SYMBOL(poly1305_final_arch);
-
 bool poly1305_is_arch_optimized(void)
 {
 	return static_key_enabled(&have_p10);
diff --git a/arch/x86/lib/crypto/poly1305_glue.c b/arch/x86/lib/crypto/poly1305_glue.c
index d98764ec3b47..f799828c5809 100644
--- a/arch/x86/lib/crypto/poly1305_glue.c
+++ b/arch/x86/lib/crypto/poly1305_glue.c
@@ -10,7 +10,6 @@ 
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/sizes.h>
-#include <linux/string.h>
 #include <linux/unaligned.h>
 
 struct poly1305_arch_internal {
@@ -96,65 +95,6 @@  void poly1305_emit_arch(const struct poly1305_state *ctx,
 }
 EXPORT_SYMBOL_GPL(poly1305_emit_arch);
 
-void poly1305_init_arch(struct poly1305_desc_ctx *dctx, const u8 key[POLY1305_KEY_SIZE])
-{
-	dctx->s[0] = get_unaligned_le32(&key[16]);
-	dctx->s[1] = get_unaligned_le32(&key[20]);
-	dctx->s[2] = get_unaligned_le32(&key[24]);
-	dctx->s[3] = get_unaligned_le32(&key[28]);
-	dctx->buflen = 0;
-	poly1305_block_init_arch(&dctx->state, key);
-}
-EXPORT_SYMBOL(poly1305_init_arch);
-
-void poly1305_update_arch(struct poly1305_desc_ctx *dctx, const u8 *src,
-			  unsigned int srclen)
-{
-	unsigned int bytes;
-
-	if (unlikely(dctx->buflen)) {
-		bytes = min(srclen, POLY1305_BLOCK_SIZE - dctx->buflen);
-		memcpy(dctx->buf + dctx->buflen, src, bytes);
-		src += bytes;
-		srclen -= bytes;
-		dctx->buflen += bytes;
-
-		if (dctx->buflen == POLY1305_BLOCK_SIZE) {
-			poly1305_blocks_arch(&dctx->state, dctx->buf,
-					     POLY1305_BLOCK_SIZE, 1);
-			dctx->buflen = 0;
-		}
-	}
-
-	if (likely(srclen >= POLY1305_BLOCK_SIZE)) {
-		bytes = round_down(srclen, POLY1305_BLOCK_SIZE);
-		poly1305_blocks_arch(&dctx->state, src, bytes, 1);
-		src += bytes;
-		srclen -= bytes;
-	}
-
-	if (unlikely(srclen)) {
-		dctx->buflen = srclen;
-		memcpy(dctx->buf, src, srclen);
-	}
-}
-EXPORT_SYMBOL(poly1305_update_arch);
-
-void poly1305_final_arch(struct poly1305_desc_ctx *dctx, u8 *dst)
-{
-	if (unlikely(dctx->buflen)) {
-		dctx->buf[dctx->buflen++] = 1;
-		memset(dctx->buf + dctx->buflen, 0,
-		       POLY1305_BLOCK_SIZE - dctx->buflen);
-		poly1305_blocks_arch(&dctx->state, dctx->buf,
-				     POLY1305_BLOCK_SIZE, 0);
-	}
-
-	poly1305_emit_arch(&dctx->h, dst, dctx->s);
-	memzero_explicit(dctx, sizeof(*dctx));
-}
-EXPORT_SYMBOL(poly1305_final_arch);
-
 bool poly1305_is_arch_optimized(void)
 {
 	return static_key_enabled(&poly1305_use_avx);
diff --git a/include/crypto/poly1305.h b/include/crypto/poly1305.h
index 027d74842cd5..e54abda8cfe9 100644
--- a/include/crypto/poly1305.h
+++ b/include/crypto/poly1305.h
@@ -55,55 +55,14 @@  struct poly1305_desc_ctx {
 	unsigned int buflen;
 	/* finalize key */
 	u32 s[4];
-	union {
-		struct {
-			struct poly1305_state h;
-			union {
-				struct poly1305_key opaque_r[CONFIG_CRYPTO_LIB_POLY1305_RSIZE];
-				struct poly1305_core_key core_r;
-			};
-		};
-		struct poly1305_block_state state;
-	};
+	struct poly1305_block_state state;
 };
 
-void poly1305_init_arch(struct poly1305_desc_ctx *desc,
-			const u8 key[POLY1305_KEY_SIZE]);
-void poly1305_init_generic(struct poly1305_desc_ctx *desc,
-			   const u8 key[POLY1305_KEY_SIZE]);
-
-static inline void poly1305_init(struct poly1305_desc_ctx *desc, const u8 *key)
-{
-	if (IS_ENABLED(CONFIG_CRYPTO_ARCH_HAVE_LIB_POLY1305))
-		poly1305_init_arch(desc, key);
-	else
-		poly1305_init_generic(desc, key);
-}
-
-void poly1305_update_arch(struct poly1305_desc_ctx *desc, const u8 *src,
-			  unsigned int nbytes);
-void poly1305_update_generic(struct poly1305_desc_ctx *desc, const u8 *src,
-			     unsigned int nbytes);
-
-static inline void poly1305_update(struct poly1305_desc_ctx *desc,
-				   const u8 *src, unsigned int nbytes)
-{
-	if (IS_ENABLED(CONFIG_CRYPTO_ARCH_HAVE_LIB_POLY1305))
-		poly1305_update_arch(desc, src, nbytes);
-	else
-		poly1305_update_generic(desc, src, nbytes);
-}
-
-void poly1305_final_arch(struct poly1305_desc_ctx *desc, u8 *digest);
-void poly1305_final_generic(struct poly1305_desc_ctx *desc, u8 *digest);
-
-static inline void poly1305_final(struct poly1305_desc_ctx *desc, u8 *digest)
-{
-	if (IS_ENABLED(CONFIG_CRYPTO_ARCH_HAVE_LIB_POLY1305))
-		poly1305_final_arch(desc, digest);
-	else
-		poly1305_final_generic(desc, digest);
-}
+void poly1305_init(struct poly1305_desc_ctx *desc,
+		   const u8 key[POLY1305_KEY_SIZE]);
+void poly1305_update(struct poly1305_desc_ctx *desc,
+		     const u8 *src, unsigned int nbytes);
+void poly1305_final(struct poly1305_desc_ctx *desc, u8 *digest);
 
 #if IS_ENABLED(CONFIG_CRYPTO_ARCH_HAVE_LIB_POLY1305)
 bool poly1305_is_arch_optimized(void);
diff --git a/lib/crypto/poly1305.c b/lib/crypto/poly1305.c
index 9fec64a599c1..4c9996864090 100644
--- a/lib/crypto/poly1305.c
+++ b/lib/crypto/poly1305.c
@@ -22,47 +22,60 @@  void poly1305_block_init_generic(struct poly1305_block_state *desc,
 }
 EXPORT_SYMBOL_GPL(poly1305_block_init_generic);
 
-void poly1305_init_generic(struct poly1305_desc_ctx *desc,
-			   const u8 key[POLY1305_KEY_SIZE])
+void poly1305_init(struct poly1305_desc_ctx *desc,
+		   const u8 key[POLY1305_KEY_SIZE])
 {
 	desc->s[0] = get_unaligned_le32(key + 16);
 	desc->s[1] = get_unaligned_le32(key + 20);
 	desc->s[2] = get_unaligned_le32(key + 24);
 	desc->s[3] = get_unaligned_le32(key + 28);
 	desc->buflen = 0;
-	poly1305_block_init_generic(&desc->state, key);
+	if (IS_ENABLED(CONFIG_CRYPTO_ARCH_HAVE_LIB_POLY1305))
+		poly1305_block_init_arch(&desc->state, key);
+	else
+		poly1305_block_init_generic(&desc->state, key);
 }
-EXPORT_SYMBOL_GPL(poly1305_init_generic);
+EXPORT_SYMBOL(poly1305_init);
 
 static inline void poly1305_blocks(struct poly1305_block_state *state,
 				   const u8 *src, unsigned int len)
 {
-	poly1305_blocks_generic(state, src, len, 1);
+	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_generic(struct poly1305_desc_ctx *desc, const u8 *src,
-			     unsigned int nbytes)
+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);
 }
-EXPORT_SYMBOL_GPL(poly1305_update_generic);
+EXPORT_SYMBOL(poly1305_update);
 
-void poly1305_final_generic(struct poly1305_desc_ctx *desc, u8 *dst)
+void poly1305_final(struct poly1305_desc_ctx *desc, u8 *dst)
 {
 	if (unlikely(desc->buflen)) {
 		desc->buf[desc->buflen++] = 1;
 		memset(desc->buf + desc->buflen, 0,
 		       POLY1305_BLOCK_SIZE - desc->buflen);
-		poly1305_blocks_generic(&desc->state, desc->buf,
-					POLY1305_BLOCK_SIZE, 0);
+		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_emit_generic(&desc->h, dst, desc->s);
+	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);
 	*desc = (struct poly1305_desc_ctx){};
 }
-EXPORT_SYMBOL_GPL(poly1305_final_generic);
+EXPORT_SYMBOL(poly1305_final);
 
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Martin Willi <martin@strongswan.org>");