openwrt/target/linux/ipq40xx/patches-5.4/0015-v5.7-crypto-qce-use-AES-fallback-for-small-requests.patch

From ce163ba0bf298f1707321ac025ef639f88e62801 Mon Sep 17 00:00:00 2001
From: Eneas U de Queiroz <cotequeiroz@gmail.com>
Date: Fri, 7 Feb 2020 12:02:26 -0300
Subject: [PATCH 10/11] crypto: qce - use AES fallback for small requests

Process small blocks using the fallback cipher, as a workaround for an
observed failure (DMA-related, apparently) when computing the GCM ghash
key.  This brings a speed gain as well, since it avoids the latency of
using the hardware engine to process small blocks.

Using software for all 16-byte requests would be enough to make GCM
work, but to increase performance, a larger threshold would be better.
Measuring the performance of supported ciphers with openssl speed,
software matches hardware at around 768-1024 bytes.

Considering the 256-bit ciphers, software is 2-3 times faster than qce
at 256-bytes, 30% faster at 512, and about even at 768-bytes.  With
128-bit keys, the break-even point would be around 1024-bytes.

This adds the 'aes_sw_max_len' parameter, to set the largest request
length processed by the software fallback.  Its default is being set to
512 bytes, a little lower than the break-even point, to balance the cost
in CPU usage.

Signed-off-by: Eneas U de Queiroz <cotequeiroz@gmail.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---

--- a/drivers/crypto/Kconfig
+++ b/drivers/crypto/Kconfig
@@ -684,6 +684,29 @@ choice
 
 endchoice
 
+config CRYPTO_DEV_QCE_SW_MAX_LEN
+	int "Default maximum request size to use software for AES"
+	depends on CRYPTO_DEV_QCE && CRYPTO_DEV_QCE_SKCIPHER
+	default 512
+	help
+	  This sets the default maximum request size to perform AES requests
+	  using software instead of the crypto engine.  It can be changed by
+	  setting the aes_sw_max_len parameter.
+
+	  Small blocks are processed faster in software than hardware.
+	  Considering the 256-bit ciphers, software is 2-3 times faster than
+	  qce at 256-bytes, 30% faster at 512, and about even at 768-bytes.
+	  With 128-bit keys, the break-even point would be around 1024-bytes.
+
+	  The default is set a little lower, to 512 bytes, to balance the
+	  cost in CPU usage.  The minimum recommended setting is 16-bytes
+	  (1 AES block), since AES-GCM will fail if you set it lower.
+	  Setting this to zero will send all requests to the hardware.
+
+	  Note that 192-bit keys are not supported by the hardware and are
+	  always processed by the software fallback, and all DES requests
+	  are done by the hardware.
+
 config CRYPTO_DEV_QCOM_RNG
 	tristate "Qualcomm Random Number Generator Driver"
 	depends on ARCH_QCOM || COMPILE_TEST
--- a/drivers/crypto/qce/skcipher.c
+++ b/drivers/crypto/qce/skcipher.c
@@ -5,6 +5,7 @@
 
 #include <linux/device.h>
 #include <linux/interrupt.h>
+#include <linux/moduleparam.h>
 #include <linux/types.h>
 #include <crypto/aes.h>
 #include <crypto/internal/des.h>
@@ -12,6 +13,13 @@
 
 #include "cipher.h"
 
+static unsigned int aes_sw_max_len = CONFIG_CRYPTO_DEV_QCE_SW_MAX_LEN;
+module_param(aes_sw_max_len, uint, 0644);
+MODULE_PARM_DESC(aes_sw_max_len,
+		 "Only use hardware for AES requests larger than this "
+		 "[0=always use hardware; anything <16 breaks AES-GCM; default="
+		 __stringify(CONFIG_CRYPTO_DEV_QCE_SOFT_THRESHOLD)"]");
+
 static LIST_HEAD(skcipher_algs);
 
 static void qce_skcipher_done(void *data)
@@ -166,15 +174,10 @@ static int qce_skcipher_setkey(struct cr
 	switch (IS_XTS(flags) ? keylen >> 1 : keylen) {
 	case AES_KEYSIZE_128:
 	case AES_KEYSIZE_256:
+		memcpy(ctx->enc_key, key, keylen);
 		break;
-	default:
-		goto fallback;
 	}
 
-	ctx->enc_keylen = keylen;
-	memcpy(ctx->enc_key, key, keylen);
-	return 0;
-fallback:
 	ret = crypto_sync_skcipher_setkey(ctx->fallback, key, keylen);
 	if (!ret)
 		ctx->enc_keylen = keylen;
@@ -224,8 +227,9 @@ static int qce_skcipher_crypt(struct skc
 	rctx->flags |= encrypt ? QCE_ENCRYPT : QCE_DECRYPT;
 	keylen = IS_XTS(rctx->flags) ? ctx->enc_keylen >> 1 : ctx->enc_keylen;
 
-	if (IS_AES(rctx->flags) && keylen != AES_KEYSIZE_128 &&
-	    keylen != AES_KEYSIZE_256) {
+	if (IS_AES(rctx->flags) &&
+	    ((keylen != AES_KEYSIZE_128 && keylen != AES_KEYSIZE_256) ||
+	     req->cryptlen <= aes_sw_max_len)) {
 		SYNC_SKCIPHER_REQUEST_ON_STACK(subreq, ctx->fallback);
 
 		skcipher_request_set_sync_tfm(subreq, ctx->fallback);