From:   Peter Lafreniere <peter@n8pjl.ca>
To:     linux-crypto@vger.kernel.org
Cc:     Peter Lafreniere <peter@n8pjl.ca>, ardb@kernel.org,
        linux-kernel@vger.kernel.org, conor.dooley@microchip.com,
        x86@kernel.org
Subject: [PATCH RESEND] crypto: x86 - exit fpu context earlier in ECB/CBC macros
Date:   Sat, 21 Jan 2023 13:34:50 -0500
Message-id: <20230121183450.14570-1-peter@n8pjl.ca>
MIME-version: 1.0
Content-transfer-encoding: 8bit
Reporting-Meta: AAHti/A/VBUEry6Wh9cg4KLobGKhnYtxA2zEdZswC1iVMoZYeOrD2P26pp6VvkhJ
 hDYDYUod6foXe7OH+gHG77bs70d6kWYZ9KGp7Sx74onuCan0nX30JUbqyshI3cqm
 nF//p+CXGcAKXbyjOZQpfiNgU7iA8TwBDHXd8SmxSIBBzn0ApxaT4K6HybHk5gdg
 e5ca06Vwd+LKdHfDS326/Wtu/9w4ut+RtK3mqSwbX4pNS7eKtDeuf3L5cBy2/yoV
 rLALK97FJcVPyLVHvHSQX65/EDqIDxmfQY5ZzsJ7i3j9uSxz/e7TddJrdWCoaqeV
 8aBHkG0+volwZPFIrB1iSwJVcdC4tnCLQUaQGwSqouW4ZtMbwBwXqWOKzLPtXSpd
 93hf23zFW3g6IWSIcKw2XSHlczGLnGq2lfP4Z9DjRBMTKreR2hjBy4J4fQ4o6g==
Precedence: bulk

Currently the ecb/cbc macros hold fpu context unnecessarily when using
scalar cipher routines (e.g. when handling odd sizes of blocks per walk).

Change the macros to drop fpu context as soon as the fpu is out of use.

No performance impact found (on Intel Haswell).

Signed-off-by: Peter Lafreniere <peter@n8pjl.ca>
---
 arch/x86/crypto/ecb_cbc_helpers.h | 19 +++++++++++++++----
 1 file changed, 15 insertions(+), 4 deletions(-)

diff --git a/arch/x86/crypto/ecb_cbc_helpers.h b/arch/x86/crypto/ecb_cbc_helpers.h
index eaa15c7b29d6..11955bd01af1 100644
--- a/arch/x86/crypto/ecb_cbc_helpers.h
+++ b/arch/x86/crypto/ecb_cbc_helpers.h
@@ -13,13 +13,14 @@
 
 #define ECB_WALK_START(req, bsize, fpu_blocks) do {			\
 	void *ctx = crypto_skcipher_ctx(crypto_skcipher_reqtfm(req));	\
+	const int __fpu_blocks = (fpu_blocks);				\
 	const int __bsize = (bsize);					\
 	struct skcipher_walk walk;					\
 	int err = skcipher_walk_virt(&walk, (req), false);		\
 	while (walk.nbytes > 0) {					\
 		unsigned int nbytes = walk.nbytes;			\
-		bool do_fpu = (fpu_blocks) != -1 &&			\
-			      nbytes >= (fpu_blocks) * __bsize;		\
+		bool do_fpu = __fpu_blocks != -1 &&			\
+			      nbytes >= __fpu_blocks * __bsize;		\
 		const u8 *src = walk.src.virt.addr;			\
 		u8 *dst = walk.dst.virt.addr;				\
 		u8 __maybe_unused buf[(bsize)];				\
@@ -35,7 +36,12 @@
 } while (0)
 
 #define ECB_BLOCK(blocks, func) do {					\
-	while (nbytes >= (blocks) * __bsize) {				\
+	const int __blocks = (blocks);					\
+	if (do_fpu && __blocks < __fpu_blocks) {			\
+		kernel_fpu_end();					\
+		do_fpu = false;						\
+	}								\
+	while (nbytes >= __blocks * __bsize) {				\
 		(func)(ctx, dst, src);					\
 		ECB_WALK_ADVANCE(blocks);				\
 	}								\
@@ -53,7 +59,12 @@
 } while (0)
 
 #define CBC_DEC_BLOCK(blocks, func) do {				\
-	while (nbytes >= (blocks) * __bsize) {				\
+	const int __blocks = (blocks);					\
+	if (do_fpu && __blocks <  __fpu_blocks) {			\
+		kernel_fpu_end();					\
+		do_fpu = false;						\
+	}								\
+	while (nbytes >= __blocks * __bsize) {				\
 		const u8 *__iv = src + ((blocks) - 1) * __bsize;	\
 		if (dst == src)						\
 			__iv = memcpy(buf, __iv, __bsize);		\
-- 
2.39.0