[PATCH v4 06/24] crypto: x86/sm3 - limit FPU preemption

[Robert Elliott <elliott@xxxxxxx>]

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@xxxxxxxxxxxxxxxxxxx>
Signed-off-by: Robert Elliott <elliott@xxxxxxx>

---
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();
 
-- 
2.38.1