Received-SPF: pass (google.com: domain of linux-crypto-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
From:   Robert Elliott <elliott@hpe.com>
To:     herbert@gondor.apana.org.au, davem@davemloft.net,
        tim.c.chen@linux.intel.com, ap420073@gmail.com, ardb@kernel.org,
        Jason@zx2c4.com, David.Laight@ACULAB.COM, ebiggers@kernel.org,
        linux-crypto@vger.kernel.org, linux-kernel@vger.kernel.org
Cc:     Robert Elliott <elliott@hpe.com>
Subject: [PATCH v3 06/17] crypto: x86/sm3 - limit FPU preemption
Date:   Wed,  2 Nov 2022 23:27:29 -0500
Message-Id: <20221103042740.6556-7-elliott@hpe.com>
In-Reply-To: <20221103042740.6556-1-elliott@hpe.com>
References: <20221012215931.3896-1-elliott@hpe.com>
 <20221103042740.6556-1-elliott@hpe.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

Limit the number of bytes processed between kernel_fpu_begin() and
kernel_fpu_end() calls.

Those functions call preempt_disable() and preempt_enable(), so
the CPU core is unavailable for scheduling while running, causing:
    rcu: INFO: rcu_preempt detected expedited stalls on CPUs/tasks: ...

Fixes: 930ab34d906d ("crypto: x86/sm3 - add AVX assembly implementation")
Suggested-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: Robert Elliott <elliott@hpe.com>

---
v3 use while loop, static int
---
 arch/x86/crypto/sm3_avx_glue.c | 35 ++++++++++++++++++++++++++++------
 1 file changed, 29 insertions(+), 6 deletions(-)

diff --git a/arch/x86/crypto/sm3_avx_glue.c b/arch/x86/crypto/sm3_avx_glue.c
index 661b6f22ffcd..483aaed996ba 100644
--- a/arch/x86/crypto/sm3_avx_glue.c
+++ b/arch/x86/crypto/sm3_avx_glue.c
@@ -17,6 +17,9 @@
 #include <crypto/sm3_base.h>
 #include <asm/simd.h>
 
+/* avoid kernel_fpu_begin/end scheduler/rcu stalls */
+static const unsigned int bytes_per_fpu = 11 * 1024;
+
 asmlinkage void sm3_transform_avx(struct sm3_state *state,
 			const u8 *data, int nblocks);
 
@@ -25,8 +28,10 @@ static int sm3_avx_update(struct shash_desc *desc, const u8 *data,
 {
 	struct sm3_state *sctx = shash_desc_ctx(desc);
 
+	BUILD_BUG_ON(bytes_per_fpu == 0);
+
 	if (!crypto_simd_usable() ||
-			(sctx->count % SM3_BLOCK_SIZE) + len < SM3_BLOCK_SIZE) {
+	    (sctx->count % SM3_BLOCK_SIZE) + len < SM3_BLOCK_SIZE) {
 		sm3_update(sctx, data, len);
 		return 0;
 	}
@@ -37,9 +42,16 @@ static int sm3_avx_update(struct shash_desc *desc, const u8 *data,
 	 */
 	BUILD_BUG_ON(offsetof(struct sm3_state, state) != 0);
 
-	kernel_fpu_begin();
-	sm3_base_do_update(desc, data, len, sm3_transform_avx);
-	kernel_fpu_end();
+	while (len) {
+		unsigned int chunk = min(len, bytes_per_fpu);
+
+		kernel_fpu_begin();
+		sm3_base_do_update(desc, data, chunk, sm3_transform_avx);
+		kernel_fpu_end();
+
+		len -= chunk;
+		data += chunk;
+	}
 
 	return 0;
 }
@@ -47,6 +59,8 @@ static int sm3_avx_update(struct shash_desc *desc, const u8 *data,
 static int sm3_avx_finup(struct shash_desc *desc, const u8 *data,
 		      unsigned int len, u8 *out)
 {
+	BUILD_BUG_ON(bytes_per_fpu == 0);
+
 	if (!crypto_simd_usable()) {
 		struct sm3_state *sctx = shash_desc_ctx(desc);
 
@@ -57,9 +71,18 @@ static int sm3_avx_finup(struct shash_desc *desc, const u8 *data,
 		return 0;
 	}
 
+	while (len) {
+		unsigned int chunk = min(len, bytes_per_fpu);
+
+		kernel_fpu_begin();
+		sm3_base_do_update(desc, data, chunk, sm3_transform_avx);
+		kernel_fpu_end();
+
+		len -= chunk;
+		data += chunk;
+	}
+
 	kernel_fpu_begin();
-	if (len)
-		sm3_base_do_update(desc, data, len, sm3_transform_avx);
 	sm3_base_do_finalize(desc, sm3_transform_avx);
 	kernel_fpu_end();
 
-- 
2.37.3