[PATCH resend 10/18] crypto: arm64/aes-ce-ccm: add non-SIMD generic fallback

[Ard Biesheuvel <ard.biesheuvel@linaro.org>]

The arm64 kernel will shortly disallow nested kernel mode NEON.

So honour this in the ARMv8 Crypto Extensions implementation of
CCM-AES, and fall back to a scalar implementation using the generic
crypto helpers for AES, XOR and incrementing the CTR counter.

Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
---
 arch/arm64/crypto/Kconfig           |   1 +
 arch/arm64/crypto/aes-ce-ccm-glue.c | 174 ++++++++++++++++----
 2 files changed, 140 insertions(+), 35 deletions(-)

diff --git a/arch/arm64/crypto/Kconfig b/arch/arm64/crypto/Kconfig
index 2fd4bb6d0b5a..ba637765c19a 100644
--- a/arch/arm64/crypto/Kconfig
+++ b/arch/arm64/crypto/Kconfig
@@ -59,6 +59,7 @@ config CRYPTO_AES_ARM64_CE_CCM
 	depends on ARM64 && KERNEL_MODE_NEON
 	select CRYPTO_ALGAPI
 	select CRYPTO_AES_ARM64_CE
+	select CRYPTO_AES_ARM64
 	select CRYPTO_AEAD
 
 config CRYPTO_AES_ARM64_CE_BLK
diff --git a/arch/arm64/crypto/aes-ce-ccm-glue.c b/arch/arm64/crypto/aes-ce-ccm-glue.c
index 6a7dbc7c83a6..a1254036f2b1 100644
--- a/arch/arm64/crypto/aes-ce-ccm-glue.c
+++ b/arch/arm64/crypto/aes-ce-ccm-glue.c
@@ -1,7 +1,7 @@
 /*
  * aes-ccm-glue.c - AES-CCM transform for ARMv8 with Crypto Extensions
  *
- * Copyright (C) 2013 - 2014 Linaro Ltd <ard.biesheuvel@linaro.org>
+ * Copyright (C) 2013 - 2017 Linaro Ltd <ard.biesheuvel@linaro.org>
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
@@ -9,6 +9,7 @@
  */
 
 #include <asm/neon.h>
+#include <asm/simd.h>
 #include <asm/unaligned.h>
 #include <crypto/aes.h>
 #include <crypto/scatterwalk.h>
@@ -44,6 +45,8 @@ asmlinkage void ce_aes_ccm_decrypt(u8 out[], u8 const in[], u32 cbytes,
 asmlinkage void ce_aes_ccm_final(u8 mac[], u8 const ctr[], u32 const rk[],
 				 u32 rounds);
 
+asmlinkage void __aes_arm64_encrypt(u32 *rk, u8 *out, const u8 *in, int rounds);
+
 static int ccm_setkey(struct crypto_aead *tfm, const u8 *in_key,
 		      unsigned int key_len)
 {
@@ -103,7 +106,45 @@ static int ccm_init_mac(struct aead_request *req, u8 maciv[], u32 msglen)
 	return 0;
 }
 
-static void ccm_calculate_auth_mac(struct aead_request *req, u8 mac[])
+static void ccm_update_mac(struct crypto_aes_ctx *key, u8 mac[], u8 const in[],
+			   u32 abytes, u32 *macp, bool use_neon)
+{
+	if (likely(use_neon)) {
+		ce_aes_ccm_auth_data(mac, in, abytes, macp, key->key_enc,
+				     num_rounds(key));
+	} else {
+		if (*macp > 0 && *macp < AES_BLOCK_SIZE) {
+			int added = min(abytes, AES_BLOCK_SIZE - *macp);
+
+			crypto_xor(&mac[*macp], in, added);
+
+			*macp += added;
+			in += added;
+			abytes -= added;
+		}
+
+		while (abytes > AES_BLOCK_SIZE) {
+			__aes_arm64_encrypt(key->key_enc, mac, mac,
+					    num_rounds(key));
+			crypto_xor(mac, in, AES_BLOCK_SIZE);
+
+			in += AES_BLOCK_SIZE;
+			abytes -= AES_BLOCK_SIZE;
+		}
+
+		if (abytes > 0) {
+			__aes_arm64_encrypt(key->key_enc, mac, mac,
+					    num_rounds(key));
+			crypto_xor(mac, in, abytes);
+			*macp = abytes;
+		} else {
+			*macp = 0;
+		}
+	}
+}
+
+static void ccm_calculate_auth_mac(struct aead_request *req, u8 mac[],
+				   bool use_neon)
 {
 	struct crypto_aead *aead = crypto_aead_reqtfm(req);
 	struct crypto_aes_ctx *ctx = crypto_aead_ctx(aead);
@@ -122,8 +163,7 @@ static void ccm_calculate_auth_mac(struct aead_request *req, u8 mac[])
 		ltag.len = 6;
 	}
 
-	ce_aes_ccm_auth_data(mac, (u8 *)&ltag, ltag.len, &macp, ctx->key_enc,
-			     num_rounds(ctx));
+	ccm_update_mac(ctx, mac, (u8 *)&ltag, ltag.len, &macp, use_neon);
 	scatterwalk_start(&walk, req->src);
 
 	do {
@@ -135,8 +175,7 @@ static void ccm_calculate_auth_mac(struct aead_request *req, u8 mac[])
 			n = scatterwalk_clamp(&walk, len);
 		}
 		p = scatterwalk_map(&walk);
-		ce_aes_ccm_auth_data(mac, p, n, &macp, ctx->key_enc,
-				     num_rounds(ctx));
+		ccm_update_mac(ctx, mac, p, n, &macp, use_neon);
 		len -= n;
 
 		scatterwalk_unmap(p);
@@ -145,6 +184,56 @@ static void ccm_calculate_auth_mac(struct aead_request *req, u8 mac[])
 	} while (len);
 }
 
+static int ccm_crypt_fallback(struct skcipher_walk *walk, u8 mac[], u8 iv0[],
+			      struct crypto_aes_ctx *ctx, bool enc)
+{
+	u8 buf[AES_BLOCK_SIZE];
+	int err = 0;
+
+	while (walk->nbytes) {
+		int blocks = walk->nbytes / AES_BLOCK_SIZE;
+		u32 tail = walk->nbytes % AES_BLOCK_SIZE;
+		u8 *dst = walk->dst.virt.addr;
+		u8 *src = walk->src.virt.addr;
+		u32 nbytes = walk->nbytes;
+
+		if (nbytes == walk->total && tail > 0) {
+			blocks++;
+			tail = 0;
+		}
+
+		do {
+			u32 bsize = AES_BLOCK_SIZE;
+
+			if (nbytes < AES_BLOCK_SIZE)
+				bsize = nbytes;
+
+			crypto_inc(walk->iv, AES_BLOCK_SIZE);
+			__aes_arm64_encrypt(ctx->key_enc, buf, walk->iv,
+					    num_rounds(ctx));
+			__aes_arm64_encrypt(ctx->key_enc, mac, mac,
+					    num_rounds(ctx));
+			if (enc)
+				crypto_xor(mac, src, bsize);
+			crypto_xor_cpy(dst, src, buf, bsize);
+			if (!enc)
+				crypto_xor(mac, dst, bsize);
+			dst += bsize;
+			src += bsize;
+			nbytes -= bsize;
+		} while (--blocks);
+
+		err = skcipher_walk_done(walk, tail);
+	}
+
+	if (!err) {
+		__aes_arm64_encrypt(ctx->key_enc, buf, iv0, num_rounds(ctx));
+		__aes_arm64_encrypt(ctx->key_enc, mac, mac, num_rounds(ctx));
+		crypto_xor(mac, buf, AES_BLOCK_SIZE);
+	}
+	return err;
+}
+
 static int ccm_encrypt(struct aead_request *req)
 {
 	struct crypto_aead *aead = crypto_aead_reqtfm(req);
@@ -153,39 +242,46 @@ static int ccm_encrypt(struct aead_request *req)
 	u8 __aligned(8) mac[AES_BLOCK_SIZE];
 	u8 buf[AES_BLOCK_SIZE];
 	u32 len = req->cryptlen;
+	bool use_neon = may_use_simd();
 	int err;
 
 	err = ccm_init_mac(req, mac, len);
 	if (err)
 		return err;
 
-	kernel_neon_begin_partial(6);
+	if (likely(use_neon))
+		kernel_neon_begin();
 
 	if (req->assoclen)
-		ccm_calculate_auth_mac(req, mac);
+		ccm_calculate_auth_mac(req, mac, use_neon);
 
 	/* preserve the original iv for the final round */
 	memcpy(buf, req->iv, AES_BLOCK_SIZE);
 
 	err = skcipher_walk_aead_encrypt(&walk, req, true);
 
-	while (walk.nbytes) {
-		u32 tail = walk.nbytes % AES_BLOCK_SIZE;
-
-		if (walk.nbytes == walk.total)
-			tail = 0;
+	if (likely(use_neon)) {
+		while (walk.nbytes) {
+			u32 tail = walk.nbytes % AES_BLOCK_SIZE;
 
-		ce_aes_ccm_encrypt(walk.dst.virt.addr, walk.src.virt.addr,
-				   walk.nbytes - tail, ctx->key_enc,
-				   num_rounds(ctx), mac, walk.iv);
+			if (walk.nbytes == walk.total)
+				tail = 0;
 
-		err = skcipher_walk_done(&walk, tail);
-	}
-	if (!err)
-		ce_aes_ccm_final(mac, buf, ctx->key_enc, num_rounds(ctx));
+			ce_aes_ccm_encrypt(walk.dst.virt.addr,
+					   walk.src.virt.addr,
+					   walk.nbytes - tail, ctx->key_enc,
+					   num_rounds(ctx), mac, walk.iv);
 
-	kernel_neon_end();
+			err = skcipher_walk_done(&walk, tail);
+		}
+		if (!err)
+			ce_aes_ccm_final(mac, buf, ctx->key_enc,
+					 num_rounds(ctx));
 
+		kernel_neon_end();
+	} else {
+		err = ccm_crypt_fallback(&walk, mac, buf, ctx, true);
+	}
 	if (err)
 		return err;
 
@@ -205,38 +301,46 @@ static int ccm_decrypt(struct aead_request *req)
 	u8 __aligned(8) mac[AES_BLOCK_SIZE];
 	u8 buf[AES_BLOCK_SIZE];
 	u32 len = req->cryptlen - authsize;
+	bool use_neon = may_use_simd();
 	int err;
 
 	err = ccm_init_mac(req, mac, len);
 	if (err)
 		return err;
 
-	kernel_neon_begin_partial(6);
+	if (likely(use_neon))
+		kernel_neon_begin();
 
 	if (req->assoclen)
-		ccm_calculate_auth_mac(req, mac);
+		ccm_calculate_auth_mac(req, mac, use_neon);
 
 	/* preserve the original iv for the final round */
 	memcpy(buf, req->iv, AES_BLOCK_SIZE);
 
 	err = skcipher_walk_aead_decrypt(&walk, req, true);
 
-	while (walk.nbytes) {
-		u32 tail = walk.nbytes % AES_BLOCK_SIZE;
+	if (likely(use_neon)) {
+		while (walk.nbytes) {
+			u32 tail = walk.nbytes % AES_BLOCK_SIZE;
 
-		if (walk.nbytes == walk.total)
-			tail = 0;
+			if (walk.nbytes == walk.total)
+				tail = 0;
 
-		ce_aes_ccm_decrypt(walk.dst.virt.addr, walk.src.virt.addr,
-				   walk.nbytes - tail, ctx->key_enc,
-				   num_rounds(ctx), mac, walk.iv);
+			ce_aes_ccm_decrypt(walk.dst.virt.addr,
+					   walk.src.virt.addr,
+					   walk.nbytes - tail, ctx->key_enc,
+					   num_rounds(ctx), mac, walk.iv);
 
-		err = skcipher_walk_done(&walk, tail);
-	}
-	if (!err)
-		ce_aes_ccm_final(mac, buf, ctx->key_enc, num_rounds(ctx));
+			err = skcipher_walk_done(&walk, tail);
+		}
+		if (!err)
+			ce_aes_ccm_final(mac, buf, ctx->key_enc,
+					 num_rounds(ctx));
 
-	kernel_neon_end();
+		kernel_neon_end();
+	} else {
+		err = ccm_crypt_fallback(&walk, mac, buf, ctx, false);
+	}
 
 	if (err)
 		return err;
-- 
2.9.3