From 97362f6bec5a8d6e016d8a6b8700c2d3c7e7b877 Mon Sep 17 00:00:00 2001
From: John Naylor <john.naylor@2ndquadrant.com>
Date: Wed, 24 Feb 2021 11:39:42 -0400
Subject: [PATCH v7 3/4] Add an ASCII fast path to the fallback UTF-8
 validator.

Using bitwise operations, we can check an entire 8-byte
chunk for both valid ASCII and zero bytes.
---
 src/include/port/pg_utf8.h  | 33 +++++++++++++++++++++++++++++++++
 src/port/pg_utf8_fallback.c | 11 ++++++++++-
 2 files changed, 43 insertions(+), 1 deletion(-)

diff --git a/src/include/port/pg_utf8.h b/src/include/port/pg_utf8.h
index 636c637706..a19fc55c1e 100644
--- a/src/include/port/pg_utf8.h
+++ b/src/include/port/pg_utf8.h
@@ -48,4 +48,37 @@ extern int	pg_validate_utf8_fallback(const unsigned char *s, int len);
 #define IS_THREE_BYTE_LEAD(c)	(((c) & 0xF0) == 0xE0)
 #define IS_FOUR_BYTE_LEAD(c)	(((c) & 0xF8) == 0xF0)
 
+/* from https://graphics.stanford.edu/~seander/bithacks.html#ZeroInWord */
+#define HAS_ZERO(chunk) ( \
+	((chunk) - UINT64CONST(0x0101010101010101)) & \
+	 ~(chunk) & \
+	 UINT64CONST(0x8080808080808080))
+
+/* Verify a chunk of bytes for valid ASCII including a zero-byte check. */
+static inline int
+check_ascii(const unsigned char *s, int len)
+{
+	uint64		chunk,
+				highbits_set;
+
+	if (len >= sizeof(uint64))
+	{
+		memcpy(&chunk, s, sizeof(uint64));
+
+		/* If there are zero bytes, bail and let the slow path handle it. */
+		if (HAS_ZERO(chunk))
+			return 0;
+
+		/* Check if any bytes in this chunk have the high bit set. */
+		highbits_set = (chunk & UINT64CONST(0x8080808080808080));
+
+		if (!highbits_set)
+			return sizeof(uint64);
+		else
+			return 0;
+	}
+	else
+		return 0;
+}
+
 #endif							/* PG_UTF8_H */
diff --git a/src/port/pg_utf8_fallback.c b/src/port/pg_utf8_fallback.c
index 85a6bbd0eb..9a29d909ef 100644
--- a/src/port/pg_utf8_fallback.c
+++ b/src/port/pg_utf8_fallback.c
@@ -34,7 +34,16 @@ pg_validate_utf8_fallback(const unsigned char *s, int len)
 	{
 		int			l;
 
-		/* ASCII */
+		/* fast path for ASCII-subset characters */
+		l = check_ascii(s, len);
+		if (l)
+		{
+			s += l;
+			len -= l;
+			continue;
+		}
+
+		/* Found non-ASCII or zero above, so verify a single character. */
 		if (!IS_HIGHBIT_SET(*s))
 		{
 			if (*s == '\0')
-- 
2.22.0