crc32: add slice-by-8 algorithm to existing code

Add slicing-by-8 algorithm to the existing slicing-by-4 algorithm.  This
consists of:

- extend largest BITS size from 32 to 64
- extend tables from tab[4][256] to up to tab[8][256]
- Add code for inner loop.

[djwong@us.ibm.com: Minor changelog tweaks]
Signed-off-by: Bob Pearson <rpearson@systemfabricworks.com>
Signed-off-by: Darrick J. Wong <djwong@us.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 27 insertions, 16 deletions

diff --git a/lib/gen_crc32table.c b/lib/gen_crc32table.c
index 99ac744848fb..0d9edd17ee13 100644
--- a/lib/gen_crc32table.c
+++ b/lib/gen_crc32table.c
@@ -1,23 +1,28 @@
 #include <stdio.h>
+#include "../include/generated/autoconf.h"
 #include "crc32defs.h"
 #include <inttypes.h>
 
 #define ENTRIES_PER_LINE 4
 
-#if CRC_LE_BITS <= 8
-#define LE_TABLE_SIZE (1 << CRC_LE_BITS)
+#if CRC_LE_BITS > 8
+# define LE_TABLE_ROWS (CRC_LE_BITS/8)
+# define LE_TABLE_SIZE 256
 #else
-#define LE_TABLE_SIZE 256
+# define LE_TABLE_ROWS 1
+# define LE_TABLE_SIZE (1 << CRC_LE_BITS)
 #endif
 
-#if CRC_BE_BITS <= 8
-#define BE_TABLE_SIZE (1 << CRC_BE_BITS)
+#if CRC_BE_BITS > 8
+# define BE_TABLE_ROWS (CRC_BE_BITS/8)
+# define BE_TABLE_SIZE 256
 #else
-#define BE_TABLE_SIZE 256
+# define BE_TABLE_ROWS 1
+# define BE_TABLE_SIZE (1 << CRC_BE_BITS)
 #endif
 
-static uint32_t crc32table_le[4][256];
-static uint32_t crc32table_be[4][256];
+static uint32_t crc32table_le[LE_TABLE_ROWS][256];
+static uint32_t crc32table_be[BE_TABLE_ROWS][256];
 
 /**
  * crc32init_le() - allocate and initialize LE table data
@@ -40,7 +45,7 @@ static void crc32init_le(void)
 	}
 	for (i = 0; i < LE_TABLE_SIZE; i++) {
 		crc = crc32table_le[0][i];
-		for (j = 1; j < 4; j++) {
+		for (j = 1; j < LE_TABLE_ROWS; j++) {
 			crc = crc32table_le[0][crc & 0xff] ^ (crc >> 8);
 			crc32table_le[j][i] = crc;
 		}
@@ -64,18 +69,18 @@ static void crc32init_be(void)
 	}
 	for (i = 0; i < BE_TABLE_SIZE; i++) {
 		crc = crc32table_be[0][i];
-		for (j = 1; j < 4; j++) {
+		for (j = 1; j < BE_TABLE_ROWS; j++) {
 			crc = crc32table_be[0][(crc >> 24) & 0xff] ^ (crc << 8);
 			crc32table_be[j][i] = crc;
 		}
 	}
 }
 
-static void output_table(uint32_t (*table)[256], int len, char *trans)
+static void output_table(uint32_t (*table)[256], int rows, int len, char *trans)
 {
 	int i, j;
 
-	for (j = 0 ; j < 4; j++) {
+	for (j = 0 ; j < rows; j++) {
 		printf("{");
 		for (i = 0; i < len - 1; i++) {
 			if (i % ENTRIES_PER_LINE == 0)
@@ -92,15 +97,21 @@ int main(int argc, char** argv)
 
 	if (CRC_LE_BITS > 1) {
 		crc32init_le();
-		printf("static const u32 crc32table_le[4][256] = {");
-		output_table(crc32table_le, LE_TABLE_SIZE, "tole");
+		printf("static const u32 __cacheline_aligned "
+		       "crc32table_le[%d][%d] = {",
+		       LE_TABLE_ROWS, LE_TABLE_SIZE);
+		output_table(crc32table_le, LE_TABLE_ROWS,
+			     LE_TABLE_SIZE, "tole");
 		printf("};\n");
 	}
 
 	if (CRC_BE_BITS > 1) {
 		crc32init_be();
-		printf("static const u32 crc32table_be[4][256] = {");
-		output_table(crc32table_be, BE_TABLE_SIZE, "tobe");
+		printf("static const u32 __cacheline_aligned "
+		       "crc32table_be[%d][%d] = {",
+		       BE_TABLE_ROWS, BE_TABLE_SIZE);
+		output_table(crc32table_be, LE_TABLE_ROWS,
+			     BE_TABLE_SIZE, "tobe");
 		printf("};\n");
 	}