v14-0004-Always-do-runtime-check-for-x86-to-simplify-PCLM.patch

From adfe02a6d169be865937b567bc1b2b2ffde60631 Mon Sep 17 00:00:00 2001
From: John Naylor <john.naylor@postgresql.org>
Date: Tue, 11 Mar 2025 11:20:20 +0700
Subject: [PATCH v14 4/8] Always do runtime check for x86 to simplify PCLMUL

---
 configure                         |  2 +-
 configure.ac                      |  2 +-
 src/include/port/pg_crc32c.h      | 20 ++++++++++++++------
 src/port/meson.build              |  1 +
 src/port/pg_crc32c_sse42.c        |  2 +-
 src/port/pg_crc32c_sse42_choose.c |  2 ++
 6 files changed, 20 insertions(+), 9 deletions(-)

diff --git a/configure b/configure
index 93fddd69981..91c0ffc8272 100755
--- a/configure
+++ b/configure
@@ -17684,7 +17684,7 @@ if test x"$USE_SSE42_CRC32C" = x"1"; then
 
 $as_echo "#define USE_SSE42_CRC32C 1" >>confdefs.h
 
-  PG_CRC32C_OBJS="pg_crc32c_sse42.o"
+  PG_CRC32C_OBJS="pg_crc32c_sse42.o pg_crc32c_sse42_choose.o"
   { $as_echo "$as_me:${as_lineno-$LINENO}: result: SSE 4.2" >&5
 $as_echo "SSE 4.2" >&6; }
 else
diff --git a/configure.ac b/configure.ac
index b6d02f5ecc7..a85bdbd4ff6 100644
--- a/configure.ac
+++ b/configure.ac
@@ -2151,7 +2151,7 @@ fi
 AC_MSG_CHECKING([which CRC-32C implementation to use])
 if test x"$USE_SSE42_CRC32C" = x"1"; then
   AC_DEFINE(USE_SSE42_CRC32C, 1, [Define to 1 use Intel SSE 4.2 CRC instructions.])
-  PG_CRC32C_OBJS="pg_crc32c_sse42.o"
+  PG_CRC32C_OBJS="pg_crc32c_sse42.o pg_crc32c_sse42_choose.o"
   AC_MSG_RESULT(SSE 4.2)
 else
   if test x"$USE_SSE42_CRC32C_WITH_RUNTIME_CHECK" = x"1"; then
diff --git a/src/include/port/pg_crc32c.h b/src/include/port/pg_crc32c.h
index 229f4f6a65a..28253b48018 100644
--- a/src/include/port/pg_crc32c.h
+++ b/src/include/port/pg_crc32c.h
@@ -47,7 +47,10 @@ typedef uint32 pg_crc32c;
 #define EQ_CRC32C(c1, c2) ((c1) == (c2))
 
 #if defined(USE_SSE42_CRC32C)
-/* Use Intel SSE4.2 instructions. */
+/*
+ * Use either Intel SSE 4.2 or PCLMUL instructions. We don't need a runtime check
+ * for SSE 4.2, so we can inline those in some cases.
+ */
 
 #include <nmmintrin.h>
 
@@ -55,7 +58,11 @@ typedef uint32 pg_crc32c;
 	((crc) = pg_comp_crc32c_dispatch((crc), (data), (len)))
 #define FIN_CRC32C(crc) ((crc) ^= 0xFFFFFFFF)
 
+extern pg_crc32c (*pg_comp_crc32c) (pg_crc32c crc, const void *data, size_t len);
 extern pg_crc32c pg_comp_crc32c_sse42(pg_crc32c crc, const void *data, size_t len);
+#ifdef USE_PCLMUL_WITH_RUNTIME_CHECK
+extern pg_crc32c pg_comp_crc32c_pclmul(pg_crc32c crc, const void *data, size_t len);
+#endif
 
 pg_attribute_no_sanitize_alignment()
 static inline
@@ -67,9 +74,9 @@ pg_comp_crc32c_dispatch(pg_crc32c crc, const void *data, size_t len)
 		const unsigned char *p = data;
 
 		/*
-		 * For constant inputs, inline the computation to avoid the
-		 * indirect function call. This also allows the compiler to unroll
-		 * loops for small inputs.
+		 * For constant inputs, inline the computation to avoid the indirect
+		 * function call. This also allows the compiler to unroll loops for
+		 * small inputs.
 		 */
 #if SIZEOF_VOID_P >= 8
 		for (; len >= 8; p += 8, len -= 8)
@@ -82,7 +89,8 @@ pg_comp_crc32c_dispatch(pg_crc32c crc, const void *data, size_t len)
 		return crc;
 	}
 	else
-		return pg_comp_crc32c_sse42(crc, data, len);
+		/* Otherwise, use a runtime check for PCLMUL instructions. */
+		return pg_comp_crc32c(crc, data, len);
 }
 
 #elif defined(USE_SSE42_CRC32C_WITH_RUNTIME_CHECK)
@@ -123,7 +131,7 @@ extern pg_crc32c pg_comp_crc32c_loongarch(pg_crc32c crc, const void *data, size_
 #elif defined(USE_ARMV8_CRC32C_WITH_RUNTIME_CHECK)
 
 /*
- * Use Intel SSE 4.2 or ARMv8 instructions, but perform a runtime check first
+ * Use ARMv8 instructions, but perform a runtime check first
  * to check that they are available.
  */
 #define COMP_CRC32C(crc, data, len) \
diff --git a/src/port/meson.build b/src/port/meson.build
index 7fcfa728d43..8d70a4d510e 100644
--- a/src/port/meson.build
+++ b/src/port/meson.build
@@ -83,6 +83,7 @@ replace_funcs_pos = [
   # x86/x64
   ['pg_crc32c_sse42', 'USE_SSE42_CRC32C'],
   ['pg_crc32c_sse42', 'USE_SSE42_CRC32C_WITH_RUNTIME_CHECK'],
+  ['pg_crc32c_sse42_choose', 'USE_SSE42_CRC32C'],
   ['pg_crc32c_sse42_choose', 'USE_SSE42_CRC32C_WITH_RUNTIME_CHECK'],
   ['pg_crc32c_sb8', 'USE_SSE42_CRC32C_WITH_RUNTIME_CHECK'],
 
diff --git a/src/port/pg_crc32c_sse42.c b/src/port/pg_crc32c_sse42.c
index 2001e69850b..c57d6c6293b 100644
--- a/src/port/pg_crc32c_sse42.c
+++ b/src/port/pg_crc32c_sse42.c
@@ -152,7 +152,7 @@ pg_comp_crc32c_pclmul(pg_crc32c crc, const void *data, size_t length)
 		len = end - buf;
 	}
 
-	return pg_comp_crc32c_sse42_inline(crc0, buf, len);
+	return pg_comp_crc32c_sse42(crc0, buf, len);
 }
 
 #endif
diff --git a/src/port/pg_crc32c_sse42_choose.c b/src/port/pg_crc32c_sse42_choose.c
index abea0f90eb3..89a48c76894 100644
--- a/src/port/pg_crc32c_sse42_choose.c
+++ b/src/port/pg_crc32c_sse42_choose.c
@@ -55,8 +55,10 @@ pg_comp_crc32c_choose(pg_crc32c crc, const void *data, size_t len)
 			pg_comp_crc32c = pg_comp_crc32c_pclmul;
 #endif
 	}
+#ifdef USE_SSE42_CRC32C_WITH_RUNTIME_CHECK
 	else
 		pg_comp_crc32c = pg_comp_crc32c_sb8;
+#endif
 
 	return pg_comp_crc32c(crc, data, len);
 }
-- 
2.48.1