Re: [PATCH v5 7/8] crypto: arm64/polyval: Add PMULL accelerated implementation of POLYVAL

quoted

+static int polyval_arm64_update(struct shash_desc *desc,
+			 const u8 *src, unsigned int srclen)
+{
+	struct polyval_desc_ctx *dctx = shash_desc_ctx(desc);
+	struct polyval_tfm_ctx *ctx = crypto_shash_ctx(desc->tfm);
+	u8 *pos;
+	unsigned int nblocks;
+	unsigned int n;
+
+	if (dctx->bytes) {
+		n = min(srclen, dctx->bytes);
+		pos = dctx->buffer + POLYVAL_BLOCK_SIZE - dctx->bytes;
+
+		dctx->bytes -= n;
+		srclen -= n;
+
+		while (n--)
+			*pos++ ^= *src++;
+
+		if (!dctx->bytes)
+			internal_polyval_mul(dctx->buffer,
+				ctx->key_powers[NUM_KEY_POWERS-1]);
+	}
+
+	nblocks = srclen/POLYVAL_BLOCK_SIZE;
+	internal_polyval_update(ctx, src, nblocks, dctx->buffer);
+	srclen -= nblocks*POLYVAL_BLOCK_SIZE;

This is executing a kernel_neon_begin()/kernel_neon_end() section of unbounded
length.  To allow the task to be preempted occasionally, it needs to handle the
input in chunks, e.g. 4K at a time, like the existing code for other algorithms
does.  Something like the following would work:

@@ -122,13 +118,16 @@ static int polyval_arm64_update(struct shash_desc *desc,
 				ctx->key_powers[NUM_KEY_POWERS-1]);
 	}
 
-	nblocks = srclen/POLYVAL_BLOCK_SIZE;
-	internal_polyval_update(ctx, src, nblocks, dctx->buffer);
-	srclen -= nblocks*POLYVAL_BLOCK_SIZE;
+	while (srclen >= POLYVAL_BLOCK_SIZE) {
+		/* Allow rescheduling every 4K bytes. */
+		nblocks = min(srclen, 4096U) / POLYVAL_BLOCK_SIZE;
+		internal_polyval_update(ctx, src, nblocks, dctx->buffer);
+		srclen -= nblocks * POLYVAL_BLOCK_SIZE;
+		src += nblocks * POLYVAL_BLOCK_SIZE;
+	}
 
 	if (srclen) {
 		dctx->bytes = POLYVAL_BLOCK_SIZE - srclen;
-		src += nblocks*POLYVAL_BLOCK_SIZE;
 		pos = dctx->buffer;
 		while (srclen--)
 			*pos++ ^= *src++;