crc32: bolt on crc32c

Reuse the existing crc32 code to stamp out a crc32c implementation.

Signed-off-by: Darrick J. Wong <[e-mail]>
Cc: Herbert Xu <[e-mail]>
Cc: Bob Pearson <[e-mail]>
Cc: Randy Dunlap <[e-mail]>
Signed-off-by: Andrew Morton <[e-mail]>
Signed-off-by: Linus Torvalds <[e-mail]>

include/linux/crc32.h

···
 extern u32  crc32_le(u32 crc, unsigned char const *p, size_t len);
 extern u32  crc32_be(u32 crc, unsigned char const *p, size_t len);
 
+extern u32  __crc32c_le(u32 crc, unsigned char const *p, size_t len);
+
 #define crc32(seed, data, length)  crc32_le(seed, (unsigned char const *)(data), length)
 
 /*

lib/Kconfig

···
 	  functions require M here.
 
 config CRC32
-	tristate "CRC32 functions"
+	tristate "CRC32/CRC32c functions"
 	default y
 	select BITREVERSE
 	help
 	  This option is provided for the case where no in-kernel-tree
-	  modules require CRC32 functions, but a module built outside the
-	  kernel tree does. Such modules that use library CRC32 functions
-	  require M here.
+	  modules require CRC32/CRC32c functions, but a module built outside
+	  the kernel tree does. Such modules that use library CRC32/CRC32c
+	  functions require M here.
 
 config CRC32_SELFTEST
 	bool "CRC32 perform self test on init"

lib/crc32.c

···
 #include "crc32table.h"
 
 MODULE_AUTHOR("Matt Domsch <[e-mail]>");
-MODULE_DESCRIPTION("Ethernet CRC32 calculations");
+MODULE_DESCRIPTION("Various CRC32 calculations");
 MODULE_LICENSE("GPL");
 
 #if CRC_LE_BITS > 8 || CRC_BE_BITS > 8
···
  * @p: pointer to buffer over which CRC is run
  * @len: length of buffer @p
  */
-u32 __pure crc32_le(u32 crc, unsigned char const *p, size_t len)
+static inline u32 __pure crc32_le_generic(u32 crc, unsigned char const *p,
+					  size_t len, const u32 (*tab)[256],
+					  u32 polynomial)
 {
 #if CRC_LE_BITS == 1
 	int i;
 	while (len--) {
 		crc ^= *p++;
 		for (i = 0; i < 8; i++)
-			crc = (crc >> 1) ^ ((crc & 1) ? CRCPOLY_LE : 0);
+			crc = (crc >> 1) ^ ((crc & 1) ? polynomial : 0);
 	}
 # elif CRC_LE_BITS == 2
 	while (len--) {
 		crc ^= *p++;
-		crc = (crc >> 2) ^ crc32table_le[0][crc & 3];
-		crc = (crc >> 2) ^ crc32table_le[0][crc & 3];
-		crc = (crc >> 2) ^ crc32table_le[0][crc & 3];
-		crc = (crc >> 2) ^ crc32table_le[0][crc & 3];
+		crc = (crc >> 2) ^ tab[0][crc & 3];
+		crc = (crc >> 2) ^ tab[0][crc & 3];
+		crc = (crc >> 2) ^ tab[0][crc & 3];
+		crc = (crc >> 2) ^ tab[0][crc & 3];
 	}
 # elif CRC_LE_BITS == 4
 	while (len--) {
 		crc ^= *p++;
-		crc = (crc >> 4) ^ crc32table_le[0][crc & 15];
-		crc = (crc >> 4) ^ crc32table_le[0][crc & 15];
+		crc = (crc >> 4) ^ tab[0][crc & 15];
+		crc = (crc >> 4) ^ tab[0][crc & 15];
 	}
 # elif CRC_LE_BITS == 8
 	/* aka Sarwate algorithm */
 	while (len--) {
 		crc ^= *p++;
-		crc = (crc >> 8) ^ crc32table_le[0][crc & 255];
+		crc = (crc >> 8) ^ tab[0][crc & 255];
 	}
 # else
-	const u32      (*tab)[] = crc32table_le;
-
 	crc = (__force u32) __cpu_to_le32(crc);
 	crc = crc32_body(crc, p, len, tab);
 	crc = __le32_to_cpu((__force __le32)crc);
 #endif
 	return crc;
 }
+
+#if CRC_LE_BITS == 1
+u32 __pure crc32_le(u32 crc, unsigned char const *p, size_t len)
+{
+	return crc32_le_generic(crc, p, len, NULL, CRCPOLY_LE);
+}
+u32 __pure __crc32c_le(u32 crc, unsigned char const *p, size_t len)
+{
+	return crc32_le_generic(crc, p, len, NULL, CRC32C_POLY_LE);
+}
+#else
+u32 __pure crc32_le(u32 crc, unsigned char const *p, size_t len)
+{
+	return crc32_le_generic(crc, p, len, crc32table_le, CRCPOLY_LE);
+}
+u32 __pure __crc32c_le(u32 crc, unsigned char const *p, size_t len)
+{
+	return crc32_le_generic(crc, p, len, crc32ctable_le, CRC32C_POLY_LE);
+}
+#endif
 EXPORT_SYMBOL(crc32_le);
+EXPORT_SYMBOL(__crc32c_le);
 
 /**
  * crc32_be() - Calculate bitwise big-endian Ethernet AUTODIN II CRC32
···
  * @p: pointer to buffer over which CRC is run
  * @len: length of buffer @p
  */
-u32 __pure crc32_be(u32 crc, unsigned char const *p, size_t len)
+static inline u32 __pure crc32_be_generic(u32 crc, unsigned char const *p,
+					  size_t len, const u32 (*tab)[256],
+					  u32 polynomial)
 {
 #if CRC_BE_BITS == 1
 	int i;
···
 		crc ^= *p++ << 24;
 		for (i = 0; i < 8; i++)
 			crc =
-			    (crc << 1) ^ ((crc & 0x80000000) ? CRCPOLY_BE :
+			    (crc << 1) ^ ((crc & 0x80000000) ? polynomial :
 					  0);
 	}
 # elif CRC_BE_BITS == 2
 	while (len--) {
 		crc ^= *p++ << 24;
-		crc = (crc << 2) ^ crc32table_be[0][crc >> 30];
-		crc = (crc << 2) ^ crc32table_be[0][crc >> 30];
-		crc = (crc << 2) ^ crc32table_be[0][crc >> 30];
-		crc = (crc << 2) ^ crc32table_be[0][crc >> 30];
+		crc = (crc << 2) ^ tab[0][crc >> 30];
+		crc = (crc << 2) ^ tab[0][crc >> 30];
+		crc = (crc << 2) ^ tab[0][crc >> 30];
+		crc = (crc << 2) ^ tab[0][crc >> 30];
 	}
 # elif CRC_BE_BITS == 4
 	while (len--) {
 		crc ^= *p++ << 24;
-		crc = (crc << 4) ^ crc32table_be[0][crc >> 28];
-		crc = (crc << 4) ^ crc32table_be[0][crc >> 28];
+		crc = (crc << 4) ^ tab[0][crc >> 28];
+		crc = (crc << 4) ^ tab[0][crc >> 28];
 	}
 # elif CRC_BE_BITS == 8
 	while (len--) {
 		crc ^= *p++ << 24;
-		crc = (crc << 8) ^ crc32table_be[0][crc >> 24];
+		crc = (crc << 8) ^ tab[0][crc >> 24];
 	}
 # else
-	const u32      (*tab)[] = crc32table_be;
-
 	crc = (__force u32) __cpu_to_be32(crc);
 	crc = crc32_body(crc, p, len, tab);
 	crc = __be32_to_cpu((__force __be32)crc);
 # endif
 	return crc;
 }
+
+#if CRC_LE_BITS == 1
+u32 __pure crc32_be(u32 crc, unsigned char const *p, size_t len)
+{
+	return crc32_be_generic(crc, p, len, NULL, CRCPOLY_BE);
+}
+#else
+u32 __pure crc32_be(u32 crc, unsigned char const *p, size_t len)
+{
+	return crc32_be_generic(crc, p, len, crc32table_be, CRCPOLY_BE);
+}
+#endif
 EXPORT_SYMBOL(crc32_be);
 
 #ifdef CONFIG_CRC32_SELFTEST

lib/crc32defs.h

···
 #define CRCPOLY_BE 0x04c11db7
 
 /*
+ * This is the CRC32c polynomial, as outlined by Castagnoli.
+ * x^32+x^28+x^27+x^26+x^25+x^23+x^22+x^20+x^19+x^18+x^14+x^13+x^11+x^10+x^9+
+ * x^8+x^6+x^0
+ */
+#define CRC32C_POLY_LE 0x82F63B78
+
+/*
  * How many bits at a time to use.  Valid values are 1, 2, 4, 8, 32 and 64.
  * For less performance-sensitive, use 4 or 8 to save table size.
  * For larger systems choose same as CPU architecture as default.

lib/gen_crc32table.c

···
 
 static uint32_t crc32table_le[LE_TABLE_ROWS][256];
 static uint32_t crc32table_be[BE_TABLE_ROWS][256];
+static uint32_t crc32ctable_le[LE_TABLE_ROWS][256];
 
 /**
  * crc32init_le() - allocate and initialize LE table data
···
  * fact that crctable[i^j] = crctable[i] ^ crctable[j].
  *
  */
-static void crc32init_le(void)
+static void crc32init_le_generic(const uint32_t polynomial,
+				 uint32_t (*tab)[256])
 {
 	unsigned i, j;
 	uint32_t crc = 1;
 
-	crc32table_le[0][0] = 0;
+	tab[0][0] = 0;
 
 	for (i = LE_TABLE_SIZE >> 1; i; i >>= 1) {
-		crc = (crc >> 1) ^ ((crc & 1) ? CRCPOLY_LE : 0);
+		crc = (crc >> 1) ^ ((crc & 1) ? polynomial : 0);
 		for (j = 0; j < LE_TABLE_SIZE; j += 2 * i)
-			crc32table_le[0][i + j] = crc ^ crc32table_le[0][j];
+			tab[0][i + j] = crc ^ tab[0][j];
 	}
 	for (i = 0; i < LE_TABLE_SIZE; i++) {
-		crc = crc32table_le[0][i];
+		crc = tab[0][i];
 		for (j = 1; j < LE_TABLE_ROWS; j++) {
-			crc = crc32table_le[0][crc & 0xff] ^ (crc >> 8);
-			crc32table_le[j][i] = crc;
+			crc = tab[0][crc & 0xff] ^ (crc >> 8);
+			tab[j][i] = crc;
 		}
 	}
+}
+
+static void crc32init_le(void)
+{
+	crc32init_le_generic(CRCPOLY_LE, crc32table_le);
+}
+
+static void crc32cinit_le(void)
+{
+	crc32init_le_generic(CRC32C_POLY_LE, crc32ctable_le);
 }
 
 /**
···
 		       BE_TABLE_ROWS, BE_TABLE_SIZE);
 		output_table(crc32table_be, LE_TABLE_ROWS,
 			     BE_TABLE_SIZE, "tobe");
+		printf("};\n");
+	}
+	if (CRC_LE_BITS > 1) {
+		crc32cinit_le();
+		printf("static const u32 __cacheline_aligned "
+		       "crc32ctable_le[%d][%d] = {",
+		       LE_TABLE_ROWS, LE_TABLE_SIZE);
+		output_table(crc32ctable_le, LE_TABLE_ROWS,
+			     LE_TABLE_SIZE, "tole");
 		printf("};\n");
 	}