lib/crc32: remove other generic implementations

Now that we've standardized on the byte-by-byte implementation of CRC32
as the only generic implementation (see previous commit for the
rationale), remove the code for the other implementations.

Tested with crc_kunit.

Link: https://lore.kernel.org/r/20250123212904.118683-3-ebiggers@kernel.org
Reviewed-by: Ard Biesheuvel <ardb@kernel.org>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Eric Biggers <ebiggers@google.com>

Author: ebiggers

lib/Kconfig

@@ -189,7 +189,6 @@ config CRC32
 	tristate "CRC32/CRC32c functions"
 	default y
 	select BITREVERSE
-	select CRC32_SARWATE
 	help
 	  This option is provided for the case where no in-kernel-tree
 	  modules require CRC32/CRC32c functions, but a module built outside
@@ -203,9 +202,6 @@ config CRC32_ARCH
 	tristate
 	default CRC32 if ARCH_HAS_CRC32 && CRC_OPTIMIZATIONS
 
-config CRC32_SARWATE
-	bool
-
 config CRC64
 	tristate "CRC64 functions"
 	help

lib/crc32.c

@@ -30,178 +30,27 @@
 #include <linux/crc32poly.h>
 #include <linux/module.h>
 #include <linux/types.h>
-#include <linux/sched.h>
-#include "crc32defs.h"
-
-#if CRC_LE_BITS > 8
-# define tole(x) ((__force u32) cpu_to_le32(x))
-#else
-# define tole(x) (x)
-#endif
-
-#if CRC_BE_BITS > 8
-# define tobe(x) ((__force u32) cpu_to_be32(x))
-#else
-# define tobe(x) (x)
-#endif
 
 #include "crc32table.h"
 
 MODULE_AUTHOR("Matt Domsch <Matt_Domsch@dell.com>");
 MODULE_DESCRIPTION("Various CRC32 calculations");
 MODULE_LICENSE("GPL");
 
-#if CRC_LE_BITS > 8 || CRC_BE_BITS > 8
-
-/* implements slicing-by-4 or slicing-by-8 algorithm */
-static inline u32 __pure
-crc32_body(u32 crc, unsigned char const *buf, size_t len, const u32 (*tab)[256])
-{
-# ifdef __LITTLE_ENDIAN
-#  define DO_CRC(x) crc = t0[(crc ^ (x)) & 255] ^ (crc >> 8)
-#  define DO_CRC4 (t3[(q) & 255] ^ t2[(q >> 8) & 255] ^ \
-		   t1[(q >> 16) & 255] ^ t0[(q >> 24) & 255])
-#  define DO_CRC8 (t7[(q) & 255] ^ t6[(q >> 8) & 255] ^ \
-		   t5[(q >> 16) & 255] ^ t4[(q >> 24) & 255])
-# else
-#  define DO_CRC(x) crc = t0[((crc >> 24) ^ (x)) & 255] ^ (crc << 8)
-#  define DO_CRC4 (t0[(q) & 255] ^ t1[(q >> 8) & 255] ^ \
-		   t2[(q >> 16) & 255] ^ t3[(q >> 24) & 255])
-#  define DO_CRC8 (t4[(q) & 255] ^ t5[(q >> 8) & 255] ^ \
-		   t6[(q >> 16) & 255] ^ t7[(q >> 24) & 255])
-# endif
-	const u32 *b;
-	size_t    rem_len;
-# ifdef CONFIG_X86
-	size_t i;
-# endif
-	const u32 *t0=tab[0], *t1=tab[1], *t2=tab[2], *t3=tab[3];
-# if CRC_LE_BITS != 32
-	const u32 *t4 = tab[4], *t5 = tab[5], *t6 = tab[6], *t7 = tab[7];
-# endif
-	u32 q;
-
-	/* Align it */
-	if (unlikely((long)buf & 3 && len)) {
-		do {
-			DO_CRC(*buf++);
-		} while ((--len) && ((long)buf)&3);
-	}
-
-# if CRC_LE_BITS == 32
-	rem_len = len & 3;
-	len = len >> 2;
-# else
-	rem_len = len & 7;
-	len = len >> 3;
-# endif
-
-	b = (const u32 *)buf;
-# ifdef CONFIG_X86
-	--b;
-	for (i = 0; i < len; i++) {
-# else
-	for (--b; len; --len) {
-# endif
-		q = crc ^ *++b; /* use pre increment for speed */
-# if CRC_LE_BITS == 32
-		crc = DO_CRC4;
-# else
-		crc = DO_CRC8;
-		q = *++b;
-		crc ^= DO_CRC4;
-# endif
-	}
-	len = rem_len;
-	/* And the last few bytes */
-	if (len) {
-		u8 *p = (u8 *)(b + 1) - 1;
-# ifdef CONFIG_X86
-		for (i = 0; i < len; i++)
-			DO_CRC(*++p); /* use pre increment for speed */
-# else
-		do {
-			DO_CRC(*++p); /* use pre increment for speed */
-		} while (--len);
-# endif
-	}
-	return crc;
-#undef DO_CRC
-#undef DO_CRC4
-#undef DO_CRC8
-}
-#endif
-
-
-/**
- * crc32_le_generic() - Calculate bitwise little-endian Ethernet AUTODIN II
- *			CRC32/CRC32C
- * @crc: seed value for computation.  ~0 for Ethernet, sometimes 0 for other
- *	 uses, or the previous crc32/crc32c value if computing incrementally.
- * @p: pointer to buffer over which CRC32/CRC32C is run
- * @len: length of buffer @p
- * @tab: little-endian Ethernet table
- * @polynomial: CRC32/CRC32c LE polynomial
- */
-static inline u32 __pure crc32_le_generic(u32 crc, unsigned char const *p,
-					  size_t len, const u32 (*tab)[256],
-					  u32 polynomial)
+u32 __pure crc32_le_base(u32 crc, const u8 *p, size_t len)
 {
-#if CRC_LE_BITS == 1
-	int i;
-	while (len--) {
-		crc ^= *p++;
-		for (i = 0; i < 8; i++)
-			crc = (crc >> 1) ^ ((crc & 1) ? polynomial : 0);
-	}
-# elif CRC_LE_BITS == 2
-	while (len--) {
-		crc ^= *p++;
-		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) ^ 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) ^ tab[0][crc & 255];
-	}
-# else
-	crc = (__force u32) __cpu_to_le32(crc);
-	crc = crc32_body(crc, p, len, tab);
-	crc = __le32_to_cpu((__force __le32)crc);
-#endif
+	while (len--)
+		crc = (crc >> 8) ^ crc32table_le[(crc & 255) ^ *p++];
 	return crc;
 }
+EXPORT_SYMBOL(crc32_le_base);
 
-#if CRC_LE_BITS == 1
-u32 __pure crc32_le_base(u32 crc, const u8 *p, size_t len)
-{
-	return crc32_le_generic(crc, p, len, NULL, CRC32_POLY_LE);
-}
-u32 __pure crc32c_le_base(u32 crc, const u8 *p, size_t len)
-{
-	return crc32_le_generic(crc, p, len, NULL, CRC32C_POLY_LE);
-}
-#else
-u32 __pure crc32_le_base(u32 crc, const u8 *p, size_t len)
-{
-	return crc32_le_generic(crc, p, len, crc32table_le, CRC32_POLY_LE);
-}
 u32 __pure crc32c_le_base(u32 crc, const u8 *p, size_t len)
 {
-	return crc32_le_generic(crc, p, len, crc32ctable_le, CRC32C_POLY_LE);
+	while (len--)
+		crc = (crc >> 8) ^ crc32ctable_le[(crc & 255) ^ *p++];
+	return crc;
 }
-#endif
-EXPORT_SYMBOL(crc32_le_base);
 EXPORT_SYMBOL(crc32c_le_base);
 
 /*
@@ -277,64 +126,10 @@ u32 __attribute_const__ __crc32c_le_shift(u32 crc, size_t len)
 EXPORT_SYMBOL(crc32_le_shift);
 EXPORT_SYMBOL(__crc32c_le_shift);
 
-/**
- * crc32_be_generic() - Calculate bitwise big-endian Ethernet AUTODIN II CRC32
- * @crc: seed value for computation.  ~0 for Ethernet, sometimes 0 for
- *	other uses, or the previous crc32 value if computing incrementally.
- * @p: pointer to buffer over which CRC32 is run
- * @len: length of buffer @p
- * @tab: big-endian Ethernet table
- * @polynomial: CRC32 BE polynomial
- */
-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;
-	while (len--) {
-		crc ^= *p++ << 24;
-		for (i = 0; i < 8; i++)
-			crc =
-			    (crc << 1) ^ ((crc & 0x80000000) ? polynomial :
-					  0);
-	}
-# elif CRC_BE_BITS == 2
-	while (len--) {
-		crc ^= *p++ << 24;
-		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) ^ tab[0][crc >> 28];
-		crc = (crc << 4) ^ tab[0][crc >> 28];
-	}
-# elif CRC_BE_BITS == 8
-	while (len--) {
-		crc ^= *p++ << 24;
-		crc = (crc << 8) ^ tab[0][crc >> 24];
-	}
-# else
-	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_BE_BITS == 1
-u32 __pure crc32_be_base(u32 crc, const u8 *p, size_t len)
-{
-	return crc32_be_generic(crc, p, len, NULL, CRC32_POLY_BE);
-}
-#else
 u32 __pure crc32_be_base(u32 crc, const u8 *p, size_t len)
 {
-	return crc32_be_generic(crc, p, len, crc32table_be, CRC32_POLY_BE);
+	while (len--)
+		crc = (crc << 8) ^ crc32table_be[(crc >> 24) ^ *p++];
+	return crc;
 }
-#endif
 EXPORT_SYMBOL(crc32_be_base);