Merge tag 'crc-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/ebiggers/linux

Pull CRC updates from Eric Biggers:

 - Reorganize the architecture-optimized CRC code

   It now lives in lib/crc/$(SRCARCH)/ rather than arch/$(SRCARCH)/lib/,
   and it is no longer artificially split into separate generic and arch
   modules. This allows better inlining and dead code elimination

   The generic CRC code is also no longer exported, simplifying the API.
   (This mirrors the similar changes to SHA-1 and SHA-2 in lib/crypto/,
   which can be found in the "Crypto library updates" pull request)

 - Improve crc32c() performance on newer x86_64 CPUs on long messages by
   enabling the VPCLMULQDQ optimized code

 - Simplify the crypto_shash wrappers for crc32_le() and crc32c()

   Register just one shash algorithm for each that uses the (fully
   optimized) library functions, instead of unnecessarily providing
   direct access to the generic CRC code

 - Remove unused and obsolete drivers for hardware CRC engines

 - Remove CRC-32 combination functions that are no longer used

 - Add kerneldoc for crc32_le(), crc32_be(), and crc32c()

 - Convert the crc32() macro to an inline function

* tag 'crc-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/ebiggers/linux: (26 commits)
  lib/crc: x86/crc32c: Enable VPCLMULQDQ optimization where beneficial
  lib/crc: x86: Reorganize crc-pclmul static_call initialization
  lib/crc: crc64: Add include/linux/crc64.h to kernel-api.rst
  lib/crc: crc32: Change crc32() from macro to inline function and remove cast
  nvmem: layouts: Switch from crc32() to crc32_le()
  lib/crc: crc32: Document crc32_le(), crc32_be(), and crc32c()
  lib/crc: Explicitly include <linux/export.h>
  lib/crc: Remove ARCH_HAS_* kconfig symbols
  lib/crc: x86: Migrate optimized CRC code into lib/crc/
  lib/crc: sparc: Migrate optimized CRC code into lib/crc/
  lib/crc: s390: Migrate optimized CRC code into lib/crc/
  lib/crc: riscv: Migrate optimized CRC code into lib/crc/
  lib/crc: powerpc: Migrate optimized CRC code into lib/crc/
  lib/crc: mips: Migrate optimized CRC code into lib/crc/
  lib/crc: loongarch: Migrate optimized CRC code into lib/crc/
  lib/crc: arm64: Migrate optimized CRC code into lib/crc/
  lib/crc: arm: Migrate optimized CRC code into lib/crc/
  lib/crc: Prepare for arch-optimized code in subdirs of lib/crc/
  lib/crc: Move files into lib/crc/
  lib/crc32: Remove unused combination support
  ...

4 files changed, 78 insertions, 89 deletions

diff --git a/include/linux/crc-t10dif.h b/include/linux/crc-t10dif.h
index a559fdff3f7e..ecc8bc2dd7f4 100644
--- a/include/linux/crc-t10dif.h
+++ b/include/linux/crc-t10dif.h
@@ -4,15 +4,7 @@
 
 #include <linux/types.h>
 
-u16 crc_t10dif_arch(u16 crc, const u8 *p, size_t len);
-u16 crc_t10dif_generic(u16 crc, const u8 *p, size_t len);
-
-static inline u16 crc_t10dif_update(u16 crc, const u8 *p, size_t len)
-{
-	if (IS_ENABLED(CONFIG_CRC_T10DIF_ARCH))
-		return crc_t10dif_arch(crc, p, len);
-	return crc_t10dif_generic(crc, p, len);
-}
+u16 crc_t10dif_update(u16 crc, const u8 *p, size_t len);
 
 static inline u16 crc_t10dif(const u8 *p, size_t len)
 {
diff --git a/include/linux/crc32.h b/include/linux/crc32.h
index 8c1883b81b42..da78b215ff2e 100644
--- a/include/linux/crc32.h
+++ b/include/linux/crc32.h
@@ -5,33 +5,81 @@
 #include <linux/types.h>
 #include <linux/bitrev.h>
 
-u32 crc32_le_arch(u32 crc, const u8 *p, size_t len);
-u32 crc32_le_base(u32 crc, const u8 *p, size_t len);
-u32 crc32_be_arch(u32 crc, const u8 *p, size_t len);
-u32 crc32_be_base(u32 crc, const u8 *p, size_t len);
-u32 crc32c_arch(u32 crc, const u8 *p, size_t len);
-u32 crc32c_base(u32 crc, const u8 *p, size_t len);
+/**
+ * crc32_le() - Compute least-significant-bit-first IEEE CRC-32
+ * @crc: Initial CRC value.  ~0 (recommended) or 0 for a new CRC computation, or
+ *	 the previous CRC value if computing incrementally.
+ * @p: Pointer to the data buffer
+ * @len: Length of data in bytes
+ *
+ * This implements the CRC variant that is often known as the IEEE CRC-32, or
+ * simply CRC-32, and is widely used in Ethernet and other applications:
+ *
+ * - Polynomial: 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
+ * - Bit order: Least-significant-bit-first
+ * - Polynomial in integer form: 0xedb88320
+ *
+ * This does *not* invert the CRC at the beginning or end.  The caller is
+ * expected to do that if it needs to.  Inverting at both ends is recommended.
+ *
+ * For new applications, prefer to use CRC-32C instead.  See crc32c().
+ *
+ * Context: Any context
+ * Return: The new CRC value
+ */
+u32 crc32_le(u32 crc, const void *p, size_t len);
 
-static inline u32 crc32_le(u32 crc, const void *p, size_t len)
+/* This is just an alias for crc32_le(). */
+static inline u32 crc32(u32 crc, const void *p, size_t len)
 {
-	if (IS_ENABLED(CONFIG_CRC32_ARCH))
-		return crc32_le_arch(crc, p, len);
-	return crc32_le_base(crc, p, len);
+	return crc32_le(crc, p, len);
 }
 
-static inline u32 crc32_be(u32 crc, const void *p, size_t len)
-{
-	if (IS_ENABLED(CONFIG_CRC32_ARCH))
-		return crc32_be_arch(crc, p, len);
-	return crc32_be_base(crc, p, len);
-}
+/**
+ * crc32_be() - Compute most-significant-bit-first IEEE CRC-32
+ * @crc: Initial CRC value.  ~0 (recommended) or 0 for a new CRC computation, or
+ *	 the previous CRC value if computing incrementally.
+ * @p: Pointer to the data buffer
+ * @len: Length of data in bytes
+ *
+ * crc32_be() is the same as crc32_le() except that crc32_be() computes the
+ * *most-significant-bit-first* variant of the CRC.  I.e., within each byte, the
+ * most significant bit is processed first (treated as highest order polynomial
+ * coefficient).  The same bit order is also used for the CRC value itself:
+ *
+ * - Polynomial: 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
+ * - Bit order: Most-significant-bit-first
+ * - Polynomial in integer form: 0x04c11db7
+ *
+ * Context: Any context
+ * Return: The new CRC value
+ */
+u32 crc32_be(u32 crc, const void *p, size_t len);
 
-static inline u32 crc32c(u32 crc, const void *p, size_t len)
-{
-	if (IS_ENABLED(CONFIG_CRC32_ARCH))
-		return crc32c_arch(crc, p, len);
-	return crc32c_base(crc, p, len);
-}
+/**
+ * crc32c() - Compute CRC-32C
+ * @crc: Initial CRC value.  ~0 (recommended) or 0 for a new CRC computation, or
+ *	 the previous CRC value if computing incrementally.
+ * @p: Pointer to the data buffer
+ * @len: Length of data in bytes
+ *
+ * This implements CRC-32C, i.e. the Castagnoli CRC.  This is the recommended
+ * CRC variant to use in new applications that want a 32-bit CRC.
+ *
+ * - Polynomial: 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
+ * - Bit order: Least-significant-bit-first
+ * - Polynomial in integer form: 0x82f63b78
+ *
+ * This does *not* invert the CRC at the beginning or end.  The caller is
+ * expected to do that if it needs to.  Inverting at both ends is recommended.
+ *
+ * Context: Any context
+ * Return: The new CRC value
+ */
+u32 crc32c(u32 crc, const void *p, size_t len);
 
 /*
  * crc32_optimizations() returns flags that indicate which CRC32 library
@@ -48,33 +96,6 @@ u32 crc32_optimizations(void);
 static inline u32 crc32_optimizations(void) { return 0; }
 #endif
 
-/**
- * crc32_le_combine - Combine two crc32 check values into one. For two
- * 		      sequences of bytes, seq1 and seq2 with lengths len1
- * 		      and len2, crc32_le() check values were calculated
- * 		      for each, crc1 and crc2.
- *
- * @crc1: crc32 of the first block
- * @crc2: crc32 of the second block
- * @len2: length of the second block
- *
- * Return: The crc32_le() check value of seq1 and seq2 concatenated,
- * 	   requiring only crc1, crc2, and len2. Note: If seq_full denotes
- * 	   the concatenated memory area of seq1 with seq2, and crc_full
- * 	   the crc32_le() value of seq_full, then crc_full ==
- * 	   crc32_le_combine(crc1, crc2, len2) when crc_full was seeded
- * 	   with the same initializer as crc1, and crc2 seed was 0. See
- * 	   also crc32_combine_test().
- */
-u32 crc32_le_shift(u32 crc, size_t len);
-
-static inline u32 crc32_le_combine(u32 crc1, u32 crc2, size_t len2)
-{
-	return crc32_le_shift(crc1, len2) ^ crc2;
-}
-
-#define crc32(seed, data, length)  crc32_le(seed, (unsigned char const *)(data), length)
-
 /*
  * Helpers for hash table generation of ethernet nics:
  *
diff --git a/include/linux/crc32poly.h b/include/linux/crc32poly.h
index 62c4b7790a28..ccab711295fa 100644
--- a/include/linux/crc32poly.h
+++ b/include/linux/crc32poly.h
@@ -2,19 +2,13 @@
 #ifndef _LINUX_CRC32_POLY_H
 #define _LINUX_CRC32_POLY_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
- */
+/* The polynomial used by crc32_le(), in integer form.  See crc32_le(). */
 #define CRC32_POLY_LE 0xedb88320
+
+/* The polynomial used by crc32_be(), in integer form.  See crc32_be(). */
 #define CRC32_POLY_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
+/* The polynomial used by crc32c(), in integer form.  See crc32c(). */
+#define CRC32C_POLY_LE 0x82f63b78
 
 #endif /* _LINUX_CRC32_POLY_H */
diff --git a/include/linux/crc64.h b/include/linux/crc64.h
index 41de30b907df..fc0c06ab1993 100644
--- a/include/linux/crc64.h
+++ b/include/linux/crc64.h
@@ -1,17 +1,9 @@
 /* SPDX-License-Identifier: GPL-2.0 */
-/*
- * See lib/crc64.c for the related specification and polynomial arithmetic.
- */
 #ifndef _LINUX_CRC64_H
 #define _LINUX_CRC64_H
 
 #include <linux/types.h>
 
-u64 crc64_be_arch(u64 crc, const u8 *p, size_t len);
-u64 crc64_be_generic(u64 crc, const u8 *p, size_t len);
-u64 crc64_nvme_arch(u64 crc, const u8 *p, size_t len);
-u64 crc64_nvme_generic(u64 crc, const u8 *p, size_t len);
-
 /**
  * crc64_be - Calculate bitwise big-endian ECMA-182 CRC64
  * @crc: seed value for computation. 0 or (u64)~0 for a new CRC calculation,
@@ -19,12 +11,7 @@ u64 crc64_nvme_generic(u64 crc, const u8 *p, size_t len);
  * @p: pointer to buffer over which CRC64 is run
  * @len: length of buffer @p
  */
-static inline u64 crc64_be(u64 crc, const void *p, size_t len)
-{
-	if (IS_ENABLED(CONFIG_CRC64_ARCH))
-		return crc64_be_arch(crc, p, len);
-	return crc64_be_generic(crc, p, len);
-}
+u64 crc64_be(u64 crc, const void *p, size_t len);
 
 /**
  * crc64_nvme - Calculate CRC64-NVME
@@ -36,11 +23,6 @@ static inline u64 crc64_be(u64 crc, const void *p, size_t len)
  * This computes the CRC64 defined in the NVME NVM Command Set Specification,
  * *including the bitwise inversion at the beginning and end*.
  */
-static inline u64 crc64_nvme(u64 crc, const void *p, size_t len)
-{
-	if (IS_ENABLED(CONFIG_CRC64_ARCH))
-		return ~crc64_nvme_arch(~crc, p, len);
-	return ~crc64_nvme_generic(~crc, p, len);
-}
+u64 crc64_nvme(u64 crc, const void *p, size_t len);
 
 #endif /* _LINUX_CRC64_H */