[PATCH] crc32 speedup/use anywhere

This patch combines my patch which statically initialises the crc32
tables so they can be used at any time (during initialisation) and
Joakim Tjernlund's patch to speed up the crc calculations by doing word
operations instead of exclusively byte.

The crc routines are used extensively in jffs2 where speed is very
important.

I need the crc32 routines to calculate a checksum on values read from an
eeprom which contain cpu speed and memory size information - so they are
needed very much earlier in the initialisation process than they are
currently available.

lib/Makefile

@@ -31,3 +31,11 @@ include $(TOPDIR)/drivers/net/Makefile.lib
 include $(TOPDIR)/drivers/usb/class/Makefile.lib
 include $(TOPDIR)/fs/Makefile.lib
 include $(TOPDIR)/net/bluetooth/bnep/Makefile.lib
+
+host-progs := gen_crc32table
+clean-files := crc32table.h
+
+$(obj)/crc32.o: $(obj)/crc32table.h
+
+$(obj)/crc32table.h: $(obj)/gen_crc32table
+	./$< > $@

lib/crc32defs.h

+/*
+ * There are multiple 16-bit CRC polynomials in common use, but this is
+ * *the* standard CRC-32 polynomial, first popularized by Ethernet.
+ * x^32+x^26+x^23+x^22+x^16+x^12+x^11+x^10+x^8+x^7+x^5+x^4+x^2+x^1+x^0
+ */
+#define CRCPOLY_LE 0xedb88320
+#define CRCPOLY_BE 0x04c11db7
+
+/* How many bits at a time to use.  Requires a table of 4<<CRC_xx_BITS bytes. */
+/* For less performance-sensitive, use 4 */
+#define CRC_LE_BITS 8
+#define CRC_BE_BITS 8
+
+/*
+ * Little-endian CRC computation.  Used with serial bit streams sent
+ * lsbit-first.  Be sure to use cpu_to_le32() to append the computed CRC.
+ */
+#if CRC_LE_BITS > 8 || CRC_LE_BITS < 1 || CRC_LE_BITS & CRC_LE_BITS-1
+# error CRC_LE_BITS must be a power of 2 between 1 and 8
+#endif
+
+/*
+ * Big-endian CRC computation.  Used with serial bit streams sent
+ * msbit-first.  Be sure to use cpu_to_be32() to append the computed CRC.
+ */
+#if CRC_BE_BITS > 8 || CRC_BE_BITS < 1 || CRC_BE_BITS & CRC_BE_BITS-1
+# error CRC_BE_BITS must be a power of 2 between 1 and 8
+#endif

lib/gen_crc32table.c

+#include <stdio.h>
+#include "crc32defs.h"
+#include <sys/types.h>
+
+#define ENTRIES_PER_LINE 4
+
+#define LE_TABLE_SIZE (1 << CRC_LE_BITS)
+#define BE_TABLE_SIZE (1 << CRC_BE_BITS)
+
+static u_int32_t crc32table_le[LE_TABLE_SIZE];
+static u_int32_t crc32table_be[BE_TABLE_SIZE];
+
+/**
+ * crc32init_le() - allocate and initialize LE table data
+ *
+ * crc is the crc of the byte i; other entries are filled in based on the
+ * fact that crctable[i^j] = crctable[i] ^ crctable[j].
+ *
+ */
+static void crc32init_le(void)
+{
+	unsigned i, j;
+	u_int32_t crc = 1;
+
+	crc32table_le[0] = 0;
+
+	for (i = 1 << (CRC_LE_BITS - 1); i; i >>= 1) {
+		crc = (crc >> 1) ^ ((crc & 1) ? CRCPOLY_LE : 0);
+		for (j = 0; j < LE_TABLE_SIZE; j += 2 * i)
+			crc32table_le[i + j] = crc ^ crc32table_le[j];
+	}
+}
+
+/**
+ * crc32init_be() - allocate and initialize BE table data
+ */
+static void crc32init_be(void)
+{
+	unsigned i, j;
+	u_int32_t crc = 0x80000000;
+
+	crc32table_be[0] = 0;
+
+	for (i = 1; i < BE_TABLE_SIZE; i <<= 1) {
+		crc = (crc << 1) ^ ((crc & 0x80000000) ? CRCPOLY_BE : 0);
+		for (j = 0; j < i; j++)
+			crc32table_be[i + j] = crc ^ crc32table_be[j];
+	}
+}
+
+static void output_table(u_int32_t table[], int len, char *trans)
+{
+	int i;
+
+	for (i = 0; i < len - 1; i++) {
+		if (i % ENTRIES_PER_LINE == 0)
+			printf("\n");
+		printf("%s(0x%8.8xL), ", trans, table[i]);
+	}
+	printf("%s(0x%8.8xL)\n", trans, table[len - 1]);
+}
+
+int main(int argc, char** argv)
+{
+	printf("/* this file is generated - do not edit */\n\n");
+
+	if (CRC_LE_BITS > 1) {
+		crc32init_le();
+		printf("static const u32 crc32table_le[] = {");
+		output_table(crc32table_le, LE_TABLE_SIZE, "tole");
+		printf("};\n");
+	}
+
+	if (CRC_BE_BITS > 1) {
+		crc32init_be();
+		printf("static const u32 crc32table_be[] = {");
+		output_table(crc32table_be, BE_TABLE_SIZE, "tobe");
+		printf("};\n");
+	}
+
+	return 0;
+}