From mboxrd@z Thu Jan 1 00:00:00 1970 From: Ard Biesheuvel Subject: [PATCH 3/5] crypto: arm64/aes-bs - move kernel mode neon en/disable into loop Date: Fri, 1 Dec 2017 21:19:25 +0000 Message-ID: <20171201211927.24653-4-ard.biesheuvel@linaro.org> References: <20171201211927.24653-1-ard.biesheuvel@linaro.org> Cc: herbert@gondor.apana.org.au, linux-arm-kernel@lists.infradead.org, Ard Biesheuvel , Dave Martin , Russell King - ARM Linux , Sebastian Andrzej Siewior , Mark Rutland , linux-rt-users@vger.kernel.org, Peter Zijlstra , Catalin Marinas , Will Deacon , Steven Rostedt , Thomas Gleixner To: linux-crypto@vger.kernel.org Return-path: Received: from mail-wr0-f193.google.com ([209.85.128.193]:38556 "EHLO mail-wr0-f193.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751169AbdLAV0H (ORCPT ); Fri, 1 Dec 2017 16:26:07 -0500 Received: by mail-wr0-f193.google.com with SMTP id o2so11448895wro.5 for ; Fri, 01 Dec 2017 13:26:06 -0800 (PST) In-Reply-To: <20171201211927.24653-1-ard.biesheuvel@linaro.org> Sender: linux-rt-users-owner@vger.kernel.org List-ID: When kernel mode NEON was first introduced on arm64, the preserve and restore of the userland NEON state was completely unoptimized, and involved saving all registers on each call to kernel_neon_begin(), and restoring them on each call to kernel_neon_end(). For this reason, the NEON crypto code that was introduced at the time keeps the NEON enabled throughout the execution of the crypto API methods, which may include calls back into the crypto API that could result in memory allocation or other actions that we should avoid when running with preemption disabled. Since then, we have optimized the kernel mode NEON handling, which now restores lazily (upon return to userland), and so the preserve action is only costly the first time it is called after entering the kernel. So let's put the kernel_neon_begin() and kernel_neon_end() calls around the actual invocations of the NEON crypto code, and run the remainder of the code with kernel mode NEON disabled (and preemption enabled) Signed-off-by: Ard Biesheuvel --- arch/arm64/crypto/aes-neonbs-glue.c | 26 +++++++++----------- 1 file changed, 12 insertions(+), 14 deletions(-) diff --git a/arch/arm64/crypto/aes-neonbs-glue.c b/arch/arm64/crypto/aes-neonbs-glue.c index 9d823c77ec84..fa09dc340a1e 100644 --- a/arch/arm64/crypto/aes-neonbs-glue.c +++ b/arch/arm64/crypto/aes-neonbs-glue.c @@ -101,7 +101,6 @@ static int __ecb_crypt(struct skcipher_request *req, err = skcipher_walk_virt(&walk, req, true); - kernel_neon_begin(); while (walk.nbytes >= AES_BLOCK_SIZE) { unsigned int blocks = walk.nbytes / AES_BLOCK_SIZE; @@ -109,12 +108,13 @@ static int __ecb_crypt(struct skcipher_request *req, blocks = round_down(blocks, walk.stride / AES_BLOCK_SIZE); + kernel_neon_begin(); fn(walk.dst.virt.addr, walk.src.virt.addr, ctx->rk, ctx->rounds, blocks); + kernel_neon_end(); err = skcipher_walk_done(&walk, walk.nbytes - blocks * AES_BLOCK_SIZE); } - kernel_neon_end(); return err; } @@ -160,17 +160,17 @@ static int cbc_encrypt(struct skcipher_request *req) err = skcipher_walk_virt(&walk, req, true); - kernel_neon_begin(); while (walk.nbytes >= AES_BLOCK_SIZE) { unsigned int blocks = walk.nbytes / AES_BLOCK_SIZE; /* fall back to the non-bitsliced NEON implementation */ + kernel_neon_begin(); neon_aes_cbc_encrypt(walk.dst.virt.addr, walk.src.virt.addr, ctx->enc, ctx->key.rounds, blocks, walk.iv); + kernel_neon_end(); err = skcipher_walk_done(&walk, walk.nbytes % AES_BLOCK_SIZE); } - kernel_neon_end(); return err; } @@ -183,7 +183,6 @@ static int cbc_decrypt(struct skcipher_request *req) err = skcipher_walk_virt(&walk, req, true); - kernel_neon_begin(); while (walk.nbytes >= AES_BLOCK_SIZE) { unsigned int blocks = walk.nbytes / AES_BLOCK_SIZE; @@ -191,13 +190,14 @@ static int cbc_decrypt(struct skcipher_request *req) blocks = round_down(blocks, walk.stride / AES_BLOCK_SIZE); + kernel_neon_begin(); aesbs_cbc_decrypt(walk.dst.virt.addr, walk.src.virt.addr, ctx->key.rk, ctx->key.rounds, blocks, walk.iv); + kernel_neon_end(); err = skcipher_walk_done(&walk, walk.nbytes - blocks * AES_BLOCK_SIZE); } - kernel_neon_end(); return err; } @@ -231,7 +231,6 @@ static int ctr_encrypt(struct skcipher_request *req) err = skcipher_walk_virt(&walk, req, true); - kernel_neon_begin(); while (walk.nbytes > 0) { unsigned int blocks = walk.nbytes / AES_BLOCK_SIZE; u8 *final = (walk.total % AES_BLOCK_SIZE) ? buf : NULL; @@ -242,8 +241,10 @@ static int ctr_encrypt(struct skcipher_request *req) final = NULL; } + kernel_neon_begin(); aesbs_ctr_encrypt(walk.dst.virt.addr, walk.src.virt.addr, ctx->rk, ctx->rounds, blocks, walk.iv, final); + kernel_neon_end(); if (final) { u8 *dst = walk.dst.virt.addr + blocks * AES_BLOCK_SIZE; @@ -258,8 +259,6 @@ static int ctr_encrypt(struct skcipher_request *req) err = skcipher_walk_done(&walk, walk.nbytes - blocks * AES_BLOCK_SIZE); } - kernel_neon_end(); - return err; } @@ -307,9 +306,8 @@ static int __xts_crypt(struct skcipher_request *req, err = skcipher_walk_virt(&walk, req, true); kernel_neon_begin(); - - neon_aes_ecb_encrypt(walk.iv, walk.iv, ctx->twkey, - ctx->key.rounds, 1); + neon_aes_ecb_encrypt(walk.iv, walk.iv, ctx->twkey, ctx->key.rounds, 1); + kernel_neon_end(); while (walk.nbytes >= AES_BLOCK_SIZE) { unsigned int blocks = walk.nbytes / AES_BLOCK_SIZE; @@ -318,13 +316,13 @@ static int __xts_crypt(struct skcipher_request *req, blocks = round_down(blocks, walk.stride / AES_BLOCK_SIZE); + kernel_neon_begin(); fn(walk.dst.virt.addr, walk.src.virt.addr, ctx->key.rk, ctx->key.rounds, blocks, walk.iv); + kernel_neon_end(); err = skcipher_walk_done(&walk, walk.nbytes - blocks * AES_BLOCK_SIZE); } - kernel_neon_end(); - return err; } -- 2.11.0