crypto: arm64/aes-neon-ctr - improve handling of single tail block

Instead of falling back to C code to do a memcpy of the output of the
last block, handle this in the asm code directly if possible, which is
the case if the entire input is longer than 16 bytes.

Cc: Nathan Huckleberry <[email protected]>
Cc: Eric Biggers <[email protected]>
Signed-off-by: Ard Biesheuvel <[email protected]>
Signed-off-by: Herbert Xu <[email protected]>

1 files changed, 7 insertions, 14 deletions

diff --git a/arch/arm64/crypto/aes-glue.c b/arch/arm64/crypto/aes-glue.c
index 30b7cc6a7079..7d66f8babb1d 100644
--- a/arch/arm64/crypto/aes-glue.c
+++ b/arch/arm64/crypto/aes-glue.c
@@ -24,7 +24,6 @@
 #ifdef USE_V8_CRYPTO_EXTENSIONS
 #define MODE			"ce"
 #define PRIO			300
-#define STRIDE			5
 #define aes_expandkey		ce_aes_expandkey
 #define aes_ecb_encrypt		ce_aes_ecb_encrypt
 #define aes_ecb_decrypt		ce_aes_ecb_decrypt
@@ -42,7 +41,6 @@ MODULE_DESCRIPTION("AES-ECB/CBC/CTR/XTS using ARMv8 Crypto Extensions");
 #else
 #define MODE			"neon"
 #define PRIO			200
-#define STRIDE			4
 #define aes_ecb_encrypt		neon_aes_ecb_encrypt
 #define aes_ecb_decrypt		neon_aes_ecb_decrypt
 #define aes_cbc_encrypt		neon_aes_cbc_encrypt
@@ -89,7 +87,7 @@ asmlinkage void aes_cbc_cts_decrypt(u8 out[], u8 const in[], u32 const rk[],
 				int rounds, int bytes, u8 const iv[]);
 
 asmlinkage void aes_ctr_encrypt(u8 out[], u8 const in[], u32 const rk[],
-				int rounds, int bytes, u8 ctr[], u8 finalbuf[]);
+				int rounds, int bytes, u8 ctr[]);
 
 asmlinkage void aes_xts_encrypt(u8 out[], u8 const in[], u32 const rk1[],
 				int rounds, int bytes, u32 const rk2[], u8 iv[],
@@ -458,26 +456,21 @@ static int __maybe_unused ctr_encrypt(struct skcipher_request *req)
 		unsigned int nbytes = walk.nbytes;
 		u8 *dst = walk.dst.virt.addr;
 		u8 buf[AES_BLOCK_SIZE];
-		unsigned int tail;
 
 		if (unlikely(nbytes < AES_BLOCK_SIZE))
-			src = memcpy(buf, src, nbytes);
+			src = dst = memcpy(buf + sizeof(buf) - nbytes,
+					   src, nbytes);
 		else if (nbytes < walk.total)
 			nbytes &= ~(AES_BLOCK_SIZE - 1);
 
 		kernel_neon_begin();
 		aes_ctr_encrypt(dst, src, ctx->key_enc, rounds, nbytes,
-				walk.iv, buf);
+				walk.iv);
 		kernel_neon_end();
 
-		tail = nbytes % (STRIDE * AES_BLOCK_SIZE);
-		if (tail > 0 && tail < AES_BLOCK_SIZE)
-			/*
-			 * The final partial block could not be returned using
-			 * an overlapping store, so it was passed via buf[]
-			 * instead.
-			 */
-			memcpy(dst + nbytes - tail, buf, tail);
+		if (unlikely(nbytes < AES_BLOCK_SIZE))
+			memcpy(walk.dst.virt.addr,
+			       buf + sizeof(buf) - nbytes, nbytes);
 
 		err = skcipher_walk_done(&walk, walk.nbytes - nbytes);
 	}