1 files changed, 15 insertions, 21 deletions

diff --git a/arch/arm/crypto/poly1305-glue.c b/arch/arm/crypto/poly1305-glue.c
index abe3f2d587dc..c31bd8f7c092 100644
--- a/arch/arm/crypto/poly1305-glue.c
+++ b/arch/arm/crypto/poly1305-glue.c
@@ -20,7 +20,8 @@
 
 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_blocks_neon(void *state, const u8 *src, u32 len, u32 hibit);
+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)
 {
@@ -28,7 +29,7 @@ void __weak poly1305_blocks_neon(void *state, const u8 *src, u32 len, u32 hibit)
 
 static __ro_after_init DEFINE_STATIC_KEY_FALSE(have_neon);
 
-void poly1305_init_arch(struct poly1305_desc_ctx *dctx, const u8 *key)
+void poly1305_init_arch(struct poly1305_desc_ctx *dctx, const u8 key[POLY1305_KEY_SIZE])
 {
 	poly1305_init_arm(&dctx->h, key);
 	dctx->s[0] = get_unaligned_le32(key + 16);
@@ -160,13 +161,20 @@ void poly1305_update_arch(struct poly1305_desc_ctx *dctx, const u8 *src,
 		unsigned int len = round_down(nbytes, POLY1305_BLOCK_SIZE);
 
 		if (static_branch_likely(&have_neon) && do_neon) {
-			kernel_neon_begin();
-			poly1305_blocks_neon(&dctx->h, src, len, 1);
-			kernel_neon_end();
+			do {
+				unsigned int todo = min_t(unsigned int, len, SZ_4K);
+
+				kernel_neon_begin();
+				poly1305_blocks_neon(&dctx->h, src, todo, 1);
+				kernel_neon_end();
+
+				len -= todo;
+				src += todo;
+			} while (len);
 		} else {
 			poly1305_blocks_arm(&dctx->h, src, len, 1);
+			src += len;
 		}
-		src += len;
 		nbytes %= POLY1305_BLOCK_SIZE;
 	}
 
@@ -179,9 +187,6 @@ 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 +194,7 @@ 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);