From mboxrd@z Thu Jan 1 00:00:00 1970 From: Ard Biesheuvel Subject: [PATCH v5 05/23] crypto: arm64/chacha20 - move kernel mode neon en/disable into loop Date: Sat, 10 Mar 2018 15:21:50 +0000 Message-ID: <20180310152208.10369-6-ard.biesheuvel@linaro.org> References: <20180310152208.10369-1-ard.biesheuvel@linaro.org> Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit Cc: Mark Rutland , herbert@gondor.apana.org.au, Ard Biesheuvel , Peter Zijlstra , Catalin Marinas , Sebastian Andrzej Siewior , Will Deacon , Russell King - ARM Linux , Steven Rostedt , Thomas Gleixner , Dave Martin , linux-arm-kernel@lists.infradead.org, linux-rt-users@vger.kernel.org To: linux-crypto@vger.kernel.org Return-path: In-Reply-To: <20180310152208.10369-1-ard.biesheuvel@linaro.org> List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Sender: "linux-arm-kernel" Errors-To: linux-arm-kernel-bounces+linux-arm-kernel=m.gmane.org@lists.infradead.org List-Id: linux-crypto.vger.kernel.org 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/chacha20-neon-glue.c | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) diff --git a/arch/arm64/crypto/chacha20-neon-glue.c b/arch/arm64/crypto/chacha20-neon-glue.c index cbdb75d15cd0..727579c93ded 100644 --- a/arch/arm64/crypto/chacha20-neon-glue.c +++ b/arch/arm64/crypto/chacha20-neon-glue.c @@ -37,12 +37,19 @@ static void chacha20_doneon(u32 *state, u8 *dst, const u8 *src, u8 buf[CHACHA20_BLOCK_SIZE]; while (bytes >= CHACHA20_BLOCK_SIZE * 4) { + kernel_neon_begin(); chacha20_4block_xor_neon(state, dst, src); + kernel_neon_end(); bytes -= CHACHA20_BLOCK_SIZE * 4; src += CHACHA20_BLOCK_SIZE * 4; dst += CHACHA20_BLOCK_SIZE * 4; state[12] += 4; } + + if (!bytes) + return; + + kernel_neon_begin(); while (bytes >= CHACHA20_BLOCK_SIZE) { chacha20_block_xor_neon(state, dst, src); bytes -= CHACHA20_BLOCK_SIZE; @@ -55,6 +62,7 @@ static void chacha20_doneon(u32 *state, u8 *dst, const u8 *src, chacha20_block_xor_neon(state, buf, buf); memcpy(dst, buf, bytes); } + kernel_neon_end(); } static int chacha20_neon(struct skcipher_request *req) @@ -68,11 +76,10 @@ static int chacha20_neon(struct skcipher_request *req) if (!may_use_simd() || req->cryptlen <= CHACHA20_BLOCK_SIZE) return crypto_chacha20_crypt(req); - err = skcipher_walk_virt(&walk, req, true); + err = skcipher_walk_virt(&walk, req, false); crypto_chacha20_init(state, ctx, walk.iv); - kernel_neon_begin(); while (walk.nbytes > 0) { unsigned int nbytes = walk.nbytes; @@ -83,7 +90,6 @@ static int chacha20_neon(struct skcipher_request *req) nbytes); err = skcipher_walk_done(&walk, walk.nbytes - nbytes); } - kernel_neon_end(); return err; } -- 2.15.1 From mboxrd@z Thu Jan 1 00:00:00 1970 From: ard.biesheuvel@linaro.org (Ard Biesheuvel) Date: Sat, 10 Mar 2018 15:21:50 +0000 Subject: [PATCH v5 05/23] crypto: arm64/chacha20 - move kernel mode neon en/disable into loop In-Reply-To: <20180310152208.10369-1-ard.biesheuvel@linaro.org> References: <20180310152208.10369-1-ard.biesheuvel@linaro.org> Message-ID: <20180310152208.10369-6-ard.biesheuvel@linaro.org> To: linux-arm-kernel@lists.infradead.org List-Id: linux-arm-kernel.lists.infradead.org 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/chacha20-neon-glue.c | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) diff --git a/arch/arm64/crypto/chacha20-neon-glue.c b/arch/arm64/crypto/chacha20-neon-glue.c index cbdb75d15cd0..727579c93ded 100644 --- a/arch/arm64/crypto/chacha20-neon-glue.c +++ b/arch/arm64/crypto/chacha20-neon-glue.c @@ -37,12 +37,19 @@ static void chacha20_doneon(u32 *state, u8 *dst, const u8 *src, u8 buf[CHACHA20_BLOCK_SIZE]; while (bytes >= CHACHA20_BLOCK_SIZE * 4) { + kernel_neon_begin(); chacha20_4block_xor_neon(state, dst, src); + kernel_neon_end(); bytes -= CHACHA20_BLOCK_SIZE * 4; src += CHACHA20_BLOCK_SIZE * 4; dst += CHACHA20_BLOCK_SIZE * 4; state[12] += 4; } + + if (!bytes) + return; + + kernel_neon_begin(); while (bytes >= CHACHA20_BLOCK_SIZE) { chacha20_block_xor_neon(state, dst, src); bytes -= CHACHA20_BLOCK_SIZE; @@ -55,6 +62,7 @@ static void chacha20_doneon(u32 *state, u8 *dst, const u8 *src, chacha20_block_xor_neon(state, buf, buf); memcpy(dst, buf, bytes); } + kernel_neon_end(); } static int chacha20_neon(struct skcipher_request *req) @@ -68,11 +76,10 @@ static int chacha20_neon(struct skcipher_request *req) if (!may_use_simd() || req->cryptlen <= CHACHA20_BLOCK_SIZE) return crypto_chacha20_crypt(req); - err = skcipher_walk_virt(&walk, req, true); + err = skcipher_walk_virt(&walk, req, false); crypto_chacha20_init(state, ctx, walk.iv); - kernel_neon_begin(); while (walk.nbytes > 0) { unsigned int nbytes = walk.nbytes; @@ -83,7 +90,6 @@ static int chacha20_neon(struct skcipher_request *req) nbytes); err = skcipher_walk_done(&walk, walk.nbytes - nbytes); } - kernel_neon_end(); return err; } -- 2.15.1