diff mbox series

[crypto-next,v2,3/3] crypto: arm/arm64/mips/poly1305 - remove redundant non-reduction from emit

Message ID 20191212093008.217086-3-Jason@zx2c4.com
State Superseded
Headers show
Series [crypto-next,v2,1/3] crypto: poly1305 - add new 32 and 64-bit generic versions | expand

Commit Message

Jason A. Donenfeld Dec. 12, 2019, 9:30 a.m. UTC
This appears to be some kind of copy and paste error, and is actually
dead code.

Pre: f = 0 ⇒ (f >> 32) = 0
    f = (f >> 32) + le32_to_cpu(digest[0]);
Post: 0 ≤ f < 2³²
    put_unaligned_le32(f, dst);

Pre: 0 ≤ f < 2³² ⇒ (f >> 32) = 0
    f = (f >> 32) + le32_to_cpu(digest[1]);
Post: 0 ≤ f < 2³²
    put_unaligned_le32(f, dst + 4);

Pre: 0 ≤ f < 2³² ⇒ (f >> 32) = 0
    f = (f >> 32) + le32_to_cpu(digest[2]);
Post: 0 ≤ f < 2³²
    put_unaligned_le32(f, dst + 8);

Pre: 0 ≤ f < 2³² ⇒ (f >> 32) = 0
    f = (f >> 32) + le32_to_cpu(digest[3]);
Post: 0 ≤ f < 2³²
    put_unaligned_le32(f, dst + 12);

Therefore this sequence is redundant. And Andy's code appears to handle
misalignment acceptably.

Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>

Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org>
---
 arch/arm/crypto/poly1305-glue.c   | 18 ++----------------
 arch/arm64/crypto/poly1305-glue.c | 18 ++----------------
 arch/mips/crypto/poly1305-glue.c  | 18 ++----------------
 3 files changed, 6 insertions(+), 48 deletions(-)

-- 
2.24.0

Comments

Ard Biesheuvel Dec. 12, 2019, 2:59 p.m. UTC | #1
On Thu, 12 Dec 2019 at 10:30, Jason A. Donenfeld <Jason@zx2c4.com> wrote:
>

> This appears to be some kind of copy and paste error, and is actually

> dead code.

>

> Pre: f = 0 ⇒ (f >> 32) = 0

>     f = (f >> 32) + le32_to_cpu(digest[0]);

> Post: 0 ≤ f < 2³²

>     put_unaligned_le32(f, dst);

>

> Pre: 0 ≤ f < 2³² ⇒ (f >> 32) = 0

>     f = (f >> 32) + le32_to_cpu(digest[1]);

> Post: 0 ≤ f < 2³²

>     put_unaligned_le32(f, dst + 4);

>

> Pre: 0 ≤ f < 2³² ⇒ (f >> 32) = 0

>     f = (f >> 32) + le32_to_cpu(digest[2]);

> Post: 0 ≤ f < 2³²

>     put_unaligned_le32(f, dst + 8);

>

> Pre: 0 ≤ f < 2³² ⇒ (f >> 32) = 0

>     f = (f >> 32) + le32_to_cpu(digest[3]);

> Post: 0 ≤ f < 2³²

>     put_unaligned_le32(f, dst + 12);

>

> Therefore this sequence is redundant. And Andy's code appears to handle

> misalignment acceptably.

>

> Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>

> Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org>

> ---


The change is obviously correct, but I ran it on a big-endian system
just to be sure.

Tested-by: Ard Biesheuvel <ardb@kernel.org>

Reviewed-by: Ard Biesheuvel <ardb@kernel.org>


>  arch/arm/crypto/poly1305-glue.c   | 18 ++----------------

>  arch/arm64/crypto/poly1305-glue.c | 18 ++----------------

>  arch/mips/crypto/poly1305-glue.c  | 18 ++----------------

>  3 files changed, 6 insertions(+), 48 deletions(-)

>

> diff --git a/arch/arm/crypto/poly1305-glue.c b/arch/arm/crypto/poly1305-glue.c

> index abe3f2d587dc..ceec04ec2f40 100644

> --- a/arch/arm/crypto/poly1305-glue.c

> +++ b/arch/arm/crypto/poly1305-glue.c

> @@ -20,7 +20,7 @@

>

>  void poly1305_init_arm(void *state, const u8 *key);

>  void poly1305_blocks_arm(void *state, const u8 *src, u32 len, u32 hibit);

> -void poly1305_emit_arm(void *state, __le32 *digest, const u32 *nonce);

> +void poly1305_emit_arm(void *state, u8 *digest, const u32 *nonce);

>

>  void __weak poly1305_blocks_neon(void *state, const u8 *src, u32 len, u32 hibit)

>  {

> @@ -179,9 +179,6 @@ EXPORT_SYMBOL(poly1305_update_arch);

>

>  void poly1305_final_arch(struct poly1305_desc_ctx *dctx, u8 *dst)

>  {

> -       __le32 digest[4];

> -       u64 f = 0;

> -

>         if (unlikely(dctx->buflen)) {

>                 dctx->buf[dctx->buflen++] = 1;

>                 memset(dctx->buf + dctx->buflen, 0,

> @@ -189,18 +186,7 @@ void poly1305_final_arch(struct poly1305_desc_ctx *dctx, u8 *dst)

>                 poly1305_blocks_arm(&dctx->h, dctx->buf, POLY1305_BLOCK_SIZE, 0);

>         }

>

> -       poly1305_emit_arm(&dctx->h, digest, dctx->s);

> -

> -       /* mac = (h + s) % (2^128) */

> -       f = (f >> 32) + le32_to_cpu(digest[0]);

> -       put_unaligned_le32(f, dst);

> -       f = (f >> 32) + le32_to_cpu(digest[1]);

> -       put_unaligned_le32(f, dst + 4);

> -       f = (f >> 32) + le32_to_cpu(digest[2]);

> -       put_unaligned_le32(f, dst + 8);

> -       f = (f >> 32) + le32_to_cpu(digest[3]);

> -       put_unaligned_le32(f, dst + 12);

> -

> +       poly1305_emit_arm(&dctx->h, dst, dctx->s);

>         *dctx = (struct poly1305_desc_ctx){};

>  }

>  EXPORT_SYMBOL(poly1305_final_arch);

> diff --git a/arch/arm64/crypto/poly1305-glue.c b/arch/arm64/crypto/poly1305-glue.c

> index 83a2338a8826..e97b092f56b8 100644

> --- a/arch/arm64/crypto/poly1305-glue.c

> +++ b/arch/arm64/crypto/poly1305-glue.c

> @@ -21,7 +21,7 @@

>  asmlinkage void poly1305_init_arm64(void *state, const u8 *key);

>  asmlinkage void poly1305_blocks(void *state, const u8 *src, u32 len, u32 hibit);

>  asmlinkage void poly1305_blocks_neon(void *state, const u8 *src, u32 len, u32 hibit);

> -asmlinkage void poly1305_emit(void *state, __le32 *digest, const u32 *nonce);

> +asmlinkage void poly1305_emit(void *state, u8 *digest, const u32 *nonce);

>

>  static __ro_after_init DEFINE_STATIC_KEY_FALSE(have_neon);

>

> @@ -162,9 +162,6 @@ EXPORT_SYMBOL(poly1305_update_arch);

>

>  void poly1305_final_arch(struct poly1305_desc_ctx *dctx, u8 *dst)

>  {

> -       __le32 digest[4];

> -       u64 f = 0;

> -

>         if (unlikely(dctx->buflen)) {

>                 dctx->buf[dctx->buflen++] = 1;

>                 memset(dctx->buf + dctx->buflen, 0,

> @@ -172,18 +169,7 @@ void poly1305_final_arch(struct poly1305_desc_ctx *dctx, u8 *dst)

>                 poly1305_blocks(&dctx->h, dctx->buf, POLY1305_BLOCK_SIZE, 0);

>         }

>

> -       poly1305_emit(&dctx->h, digest, dctx->s);

> -

> -       /* mac = (h + s) % (2^128) */

> -       f = (f >> 32) + le32_to_cpu(digest[0]);

> -       put_unaligned_le32(f, dst);

> -       f = (f >> 32) + le32_to_cpu(digest[1]);

> -       put_unaligned_le32(f, dst + 4);

> -       f = (f >> 32) + le32_to_cpu(digest[2]);

> -       put_unaligned_le32(f, dst + 8);

> -       f = (f >> 32) + le32_to_cpu(digest[3]);

> -       put_unaligned_le32(f, dst + 12);

> -

> +       poly1305_emit(&dctx->h, dst, dctx->s);

>         *dctx = (struct poly1305_desc_ctx){};

>  }

>  EXPORT_SYMBOL(poly1305_final_arch);

> diff --git a/arch/mips/crypto/poly1305-glue.c b/arch/mips/crypto/poly1305-glue.c

> index b37d29cf5d0a..fc881b46d911 100644

> --- a/arch/mips/crypto/poly1305-glue.c

> +++ b/arch/mips/crypto/poly1305-glue.c

> @@ -15,7 +15,7 @@

>

>  asmlinkage void poly1305_init_mips(void *state, const u8 *key);

>  asmlinkage void poly1305_blocks_mips(void *state, const u8 *src, u32 len, u32 hibit);

> -asmlinkage void poly1305_emit_mips(void *state, __le32 *digest, const u32 *nonce);

> +asmlinkage void poly1305_emit_mips(void *state, u8 *digest, const u32 *nonce);

>

>  void poly1305_init_arch(struct poly1305_desc_ctx *dctx, const u8 *key)

>  {

> @@ -134,9 +134,6 @@ EXPORT_SYMBOL(poly1305_update_arch);

>

>  void poly1305_final_arch(struct poly1305_desc_ctx *dctx, u8 *dst)

>  {

> -       __le32 digest[4];

> -       u64 f = 0;

> -

>         if (unlikely(dctx->buflen)) {

>                 dctx->buf[dctx->buflen++] = 1;

>                 memset(dctx->buf + dctx->buflen, 0,

> @@ -144,18 +141,7 @@ void poly1305_final_arch(struct poly1305_desc_ctx *dctx, u8 *dst)

>                 poly1305_blocks_mips(&dctx->h, dctx->buf, POLY1305_BLOCK_SIZE, 0);

>         }

>

> -       poly1305_emit_mips(&dctx->h, digest, dctx->s);

> -

> -       /* mac = (h + s) % (2^128) */

> -       f = (f >> 32) + le32_to_cpu(digest[0]);

> -       put_unaligned_le32(f, dst);

> -       f = (f >> 32) + le32_to_cpu(digest[1]);

> -       put_unaligned_le32(f, dst + 4);

> -       f = (f >> 32) + le32_to_cpu(digest[2]);

> -       put_unaligned_le32(f, dst + 8);

> -       f = (f >> 32) + le32_to_cpu(digest[3]);

> -       put_unaligned_le32(f, dst + 12);

> -

> +       poly1305_emit_mips(&dctx->h, dst, dctx->s);

>         *dctx = (struct poly1305_desc_ctx){};

>  }

>  EXPORT_SYMBOL(poly1305_final_arch);

> --

> 2.24.0

>
diff mbox series

Patch

diff --git a/arch/arm/crypto/poly1305-glue.c b/arch/arm/crypto/poly1305-glue.c
index abe3f2d587dc..ceec04ec2f40 100644
--- a/arch/arm/crypto/poly1305-glue.c
+++ b/arch/arm/crypto/poly1305-glue.c
@@ -20,7 +20,7 @@ 
 
 void poly1305_init_arm(void *state, const u8 *key);
 void poly1305_blocks_arm(void *state, const u8 *src, u32 len, u32 hibit);
-void poly1305_emit_arm(void *state, __le32 *digest, const u32 *nonce);
+void poly1305_emit_arm(void *state, u8 *digest, const u32 *nonce);
 
 void __weak poly1305_blocks_neon(void *state, const u8 *src, u32 len, u32 hibit)
 {
@@ -179,9 +179,6 @@  EXPORT_SYMBOL(poly1305_update_arch);
 
 void poly1305_final_arch(struct poly1305_desc_ctx *dctx, u8 *dst)
 {
-	__le32 digest[4];
-	u64 f = 0;
-
 	if (unlikely(dctx->buflen)) {
 		dctx->buf[dctx->buflen++] = 1;
 		memset(dctx->buf + dctx->buflen, 0,
@@ -189,18 +186,7 @@  void poly1305_final_arch(struct poly1305_desc_ctx *dctx, u8 *dst)
 		poly1305_blocks_arm(&dctx->h, dctx->buf, POLY1305_BLOCK_SIZE, 0);
 	}
 
-	poly1305_emit_arm(&dctx->h, digest, dctx->s);
-
-	/* mac = (h + s) % (2^128) */
-	f = (f >> 32) + le32_to_cpu(digest[0]);
-	put_unaligned_le32(f, dst);
-	f = (f >> 32) + le32_to_cpu(digest[1]);
-	put_unaligned_le32(f, dst + 4);
-	f = (f >> 32) + le32_to_cpu(digest[2]);
-	put_unaligned_le32(f, dst + 8);
-	f = (f >> 32) + le32_to_cpu(digest[3]);
-	put_unaligned_le32(f, dst + 12);
-
+	poly1305_emit_arm(&dctx->h, dst, dctx->s);
 	*dctx = (struct poly1305_desc_ctx){};
 }
 EXPORT_SYMBOL(poly1305_final_arch);
diff --git a/arch/arm64/crypto/poly1305-glue.c b/arch/arm64/crypto/poly1305-glue.c
index 83a2338a8826..e97b092f56b8 100644
--- a/arch/arm64/crypto/poly1305-glue.c
+++ b/arch/arm64/crypto/poly1305-glue.c
@@ -21,7 +21,7 @@ 
 asmlinkage void poly1305_init_arm64(void *state, const u8 *key);
 asmlinkage void poly1305_blocks(void *state, const u8 *src, u32 len, u32 hibit);
 asmlinkage void poly1305_blocks_neon(void *state, const u8 *src, u32 len, u32 hibit);
-asmlinkage void poly1305_emit(void *state, __le32 *digest, const u32 *nonce);
+asmlinkage void poly1305_emit(void *state, u8 *digest, const u32 *nonce);
 
 static __ro_after_init DEFINE_STATIC_KEY_FALSE(have_neon);
 
@@ -162,9 +162,6 @@  EXPORT_SYMBOL(poly1305_update_arch);
 
 void poly1305_final_arch(struct poly1305_desc_ctx *dctx, u8 *dst)
 {
-	__le32 digest[4];
-	u64 f = 0;
-
 	if (unlikely(dctx->buflen)) {
 		dctx->buf[dctx->buflen++] = 1;
 		memset(dctx->buf + dctx->buflen, 0,
@@ -172,18 +169,7 @@  void poly1305_final_arch(struct poly1305_desc_ctx *dctx, u8 *dst)
 		poly1305_blocks(&dctx->h, dctx->buf, POLY1305_BLOCK_SIZE, 0);
 	}
 
-	poly1305_emit(&dctx->h, digest, dctx->s);
-
-	/* mac = (h + s) % (2^128) */
-	f = (f >> 32) + le32_to_cpu(digest[0]);
-	put_unaligned_le32(f, dst);
-	f = (f >> 32) + le32_to_cpu(digest[1]);
-	put_unaligned_le32(f, dst + 4);
-	f = (f >> 32) + le32_to_cpu(digest[2]);
-	put_unaligned_le32(f, dst + 8);
-	f = (f >> 32) + le32_to_cpu(digest[3]);
-	put_unaligned_le32(f, dst + 12);
-
+	poly1305_emit(&dctx->h, dst, dctx->s);
 	*dctx = (struct poly1305_desc_ctx){};
 }
 EXPORT_SYMBOL(poly1305_final_arch);
diff --git a/arch/mips/crypto/poly1305-glue.c b/arch/mips/crypto/poly1305-glue.c
index b37d29cf5d0a..fc881b46d911 100644
--- a/arch/mips/crypto/poly1305-glue.c
+++ b/arch/mips/crypto/poly1305-glue.c
@@ -15,7 +15,7 @@ 
 
 asmlinkage void poly1305_init_mips(void *state, const u8 *key);
 asmlinkage void poly1305_blocks_mips(void *state, const u8 *src, u32 len, u32 hibit);
-asmlinkage void poly1305_emit_mips(void *state, __le32 *digest, const u32 *nonce);
+asmlinkage void poly1305_emit_mips(void *state, u8 *digest, const u32 *nonce);
 
 void poly1305_init_arch(struct poly1305_desc_ctx *dctx, const u8 *key)
 {
@@ -134,9 +134,6 @@  EXPORT_SYMBOL(poly1305_update_arch);
 
 void poly1305_final_arch(struct poly1305_desc_ctx *dctx, u8 *dst)
 {
-	__le32 digest[4];
-	u64 f = 0;
-
 	if (unlikely(dctx->buflen)) {
 		dctx->buf[dctx->buflen++] = 1;
 		memset(dctx->buf + dctx->buflen, 0,
@@ -144,18 +141,7 @@  void poly1305_final_arch(struct poly1305_desc_ctx *dctx, u8 *dst)
 		poly1305_blocks_mips(&dctx->h, dctx->buf, POLY1305_BLOCK_SIZE, 0);
 	}
 
-	poly1305_emit_mips(&dctx->h, digest, dctx->s);
-
-	/* mac = (h + s) % (2^128) */
-	f = (f >> 32) + le32_to_cpu(digest[0]);
-	put_unaligned_le32(f, dst);
-	f = (f >> 32) + le32_to_cpu(digest[1]);
-	put_unaligned_le32(f, dst + 4);
-	f = (f >> 32) + le32_to_cpu(digest[2]);
-	put_unaligned_le32(f, dst + 8);
-	f = (f >> 32) + le32_to_cpu(digest[3]);
-	put_unaligned_le32(f, dst + 12);
-
+	poly1305_emit_mips(&dctx->h, dst, dctx->s);
 	*dctx = (struct poly1305_desc_ctx){};
 }
 EXPORT_SYMBOL(poly1305_final_arch);