crypto/arm64: sm4-ce-gcm - Avoid pointless yield of the NEON unit

Kernel mode NEON sections are now preemptible on arm64, and so there is
no need to yield it when calling APIs that may sleep.

Also, move the calls to kernel_neon_end() to the same scope as
kernel_neon_begin(). This is needed for a subsequent change where a
stack buffer is allocated transparently and passed to
kernel_neon_begin().

While at it, simplify the logic.

Reviewed-by: Eric Biggers <[e-mail]>
Acked-by: Herbert Xu <[e-mail]>
Acked-by: Catalin Marinas <[e-mail]>
Signed-off-by: Ard Biesheuvel <[e-mail]>

arch/arm64/crypto/sm4-ce-gcm-glue.c

···
 	if (req->assoclen)
 		gcm_calculate_auth_mac(req, ghash);
 
-	while (walk->nbytes) {
+	do {
 		unsigned int tail = walk->nbytes % SM4_BLOCK_SIZE;
 		const u8 *src = walk->src.virt.addr;
 		u8 *dst = walk->dst.virt.addr;
+		const u8 *l = NULL;
 
 		if (walk->nbytes == walk->total) {
-			sm4_ce_pmull_gcm_crypt(ctx->key.rkey_enc, dst, src, iv,
-					       walk->nbytes, ghash,
-					       ctx->ghash_table,
-					       (const u8 *)&lengths);
-
-			kernel_neon_end();
-
-			return skcipher_walk_done(walk, 0);
+			l = (const u8 *)&lengths;
+			tail = 0;
 		}
 
 		sm4_ce_pmull_gcm_crypt(ctx->key.rkey_enc, dst, src, iv,
 				       walk->nbytes - tail, ghash,
-				       ctx->ghash_table, NULL);
-
-		kernel_neon_end();
+				       ctx->ghash_table, l);
 
 		err = skcipher_walk_done(walk, tail);
-
-		kernel_neon_begin();
-	}
-
-	sm4_ce_pmull_gcm_crypt(ctx->key.rkey_enc, NULL, NULL, iv,
-			       walk->nbytes, ghash, ctx->ghash_table,
-			       (const u8 *)&lengths);
+	} while (walk->nbytes);
 
 	kernel_neon_end();