@@ -19,10 +19,11 @@ config ARM64
select ARCH_ENABLE_MEMORY_HOTREMOVE
select ARCH_ENABLE_SPLIT_PMD_PTLOCK if PGTABLE_LEVELS > 2
select ARCH_ENABLE_THP_MIGRATION if TRANSPARENT_HUGEPAGE
select ARCH_HAS_CACHE_LINE_SIZE
select ARCH_HAS_CC_PLATFORM
+ select ARCH_HAS_CRC32
select ARCH_HAS_CURRENT_STACK_POINTER
select ARCH_HAS_DEBUG_VIRTUAL
select ARCH_HAS_DEBUG_VM_PGTABLE
select ARCH_HAS_DMA_OPS if XEN
select ARCH_HAS_DMA_PREP_COHERENT
@@ -11,11 +11,12 @@ CFLAGS_xor-neon.o += $(CC_FLAGS_FPU)
CFLAGS_REMOVE_xor-neon.o += $(CC_FLAGS_NO_FPU)
endif
lib-$(CONFIG_ARCH_HAS_UACCESS_FLUSHCACHE) += uaccess_flushcache.o
-obj-$(CONFIG_CRC32) += crc32.o crc32-glue.o
+obj-$(CONFIG_CRC32_ARCH) += crc32-arm64.o
+crc32-arm64-y := crc32.o crc32-glue.o
obj-$(CONFIG_FUNCTION_ERROR_INJECTION) += error-inject.o
obj-$(CONFIG_ARM64_MTE) += mte.o
@@ -1,9 +1,10 @@
// SPDX-License-Identifier: GPL-2.0-only
#include <linux/crc32.h>
#include <linux/linkage.h>
+#include <linux/module.h>
#include <asm/alternative.h>
#include <asm/cpufeature.h>
#include <asm/neon.h>
#include <asm/simd.h>
@@ -19,11 +20,11 @@ asmlinkage u32 crc32_be_arm64(u32 crc, unsigned char const *p, size_t len);
asmlinkage u32 crc32_le_arm64_4way(u32 crc, unsigned char const *p, size_t len);
asmlinkage u32 crc32c_le_arm64_4way(u32 crc, unsigned char const *p, size_t len);
asmlinkage u32 crc32_be_arm64_4way(u32 crc, unsigned char const *p, size_t len);
-u32 __pure crc32_le(u32 crc, unsigned char const *p, size_t len)
+u32 __pure crc32_le_arch(u32 crc, const u8 *p, size_t len)
{
if (!alternative_has_cap_likely(ARM64_HAS_CRC32))
return crc32_le_base(crc, p, len);
if (len >= min_len && cpu_have_named_feature(PMULL) && crypto_simd_usable()) {
@@ -38,12 +39,13 @@ u32 __pure crc32_le(u32 crc, unsigned char const *p, size_t len)
return crc;
}
return crc32_le_arm64(crc, p, len);
}
+EXPORT_SYMBOL(crc32_le_arch);
-u32 __pure __crc32c_le(u32 crc, unsigned char const *p, size_t len)
+u32 __pure crc32c_le_arch(u32 crc, const u8 *p, size_t len)
{
if (!alternative_has_cap_likely(ARM64_HAS_CRC32))
return crc32c_le_base(crc, p, len);
if (len >= min_len && cpu_have_named_feature(PMULL) && crypto_simd_usable()) {
@@ -58,12 +60,13 @@ u32 __pure __crc32c_le(u32 crc, unsigned char const *p, size_t len)
return crc;
}
return crc32c_le_arm64(crc, p, len);
}
+EXPORT_SYMBOL(crc32c_le_arch);
-u32 __pure crc32_be(u32 crc, unsigned char const *p, size_t len)
+u32 __pure crc32_be_arch(u32 crc, const u8 *p, size_t len)
{
if (!alternative_has_cap_likely(ARM64_HAS_CRC32))
return crc32_be_base(crc, p, len);
if (len >= min_len && cpu_have_named_feature(PMULL) && crypto_simd_usable()) {
@@ -78,5 +81,9 @@ u32 __pure crc32_be(u32 crc, unsigned char const *p, size_t len)
return crc;
}
return crc32_be_arm64(crc, p, len);
}
+EXPORT_SYMBOL(crc32_be_arch);
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("arm64-optimized CRC32 functions");
@@ -22,10 +22,11 @@ config RISCV
select ARCH_ENABLE_MEMORY_HOTPLUG if SPARSEMEM_VMEMMAP
select ARCH_ENABLE_MEMORY_HOTREMOVE if MEMORY_HOTPLUG
select ARCH_ENABLE_SPLIT_PMD_PTLOCK if PGTABLE_LEVELS > 2
select ARCH_ENABLE_THP_MIGRATION if TRANSPARENT_HUGEPAGE
select ARCH_HAS_BINFMT_FLAT
+ select ARCH_HAS_CRC32 if RISCV_ISA_ZBC
select ARCH_HAS_CURRENT_STACK_POINTER
select ARCH_HAS_DEBUG_VIRTUAL if MMU
select ARCH_HAS_DEBUG_VM_PGTABLE
select ARCH_HAS_DEBUG_WX
select ARCH_HAS_FAST_MULTIPLIER
@@ -13,10 +13,9 @@ ifeq ($(CONFIG_MMU), y)
lib-$(CONFIG_RISCV_ISA_V) += uaccess_vector.o
endif
lib-$(CONFIG_MMU) += uaccess.o
lib-$(CONFIG_64BIT) += tishift.o
lib-$(CONFIG_RISCV_ISA_ZICBOZ) += clear_page.o
-lib-$(CONFIG_RISCV_ISA_ZBC) += crc32.o
-
+obj-$(CONFIG_CRC32_ARCH) += crc32-riscv.o
obj-$(CONFIG_FUNCTION_ERROR_INJECTION) += error-inject.o
lib-$(CONFIG_RISCV_ISA_V) += xor.o
lib-$(CONFIG_RISCV_ISA_V) += riscv_v_helpers.o
similarity index 94%
rename from arch/riscv/lib/crc32.c
rename to arch/riscv/lib/crc32-riscv.c
@@ -12,10 +12,11 @@
#include <linux/types.h>
#include <linux/minmax.h>
#include <linux/crc32poly.h>
#include <linux/crc32.h>
#include <linux/byteorder/generic.h>
+#include <linux/module.h>
/*
* Refer to https://www.corsix.org/content/barrett-reduction-polynomials for
* better understanding of how this math works.
*
@@ -215,21 +216,23 @@ static inline u32 __pure crc32_le_generic(u32 crc, unsigned char const *p,
legacy:
return crc_fb(crc, p, len);
}
-u32 __pure crc32_le(u32 crc, unsigned char const *p, size_t len)
+u32 __pure crc32_le_arch(u32 crc, const u8 *p, size_t len)
{
return crc32_le_generic(crc, p, len, CRC32_POLY_LE, CRC32_POLY_QT_LE,
crc32_le_base);
}
+EXPORT_SYMBOL(crc32_le_arch);
-u32 __pure __crc32c_le(u32 crc, unsigned char const *p, size_t len)
+u32 __pure crc32c_le_arch(u32 crc, const u8 *p, size_t len)
{
return crc32_le_generic(crc, p, len, CRC32C_POLY_LE,
CRC32C_POLY_QT_LE, crc32c_le_base);
}
+EXPORT_SYMBOL(crc32c_le_arch);
static inline u32 crc32_be_unaligned(u32 crc, unsigned char const *p,
size_t len)
{
size_t bits = len * 8;
@@ -251,11 +254,11 @@ static inline u32 crc32_be_unaligned(u32 crc, unsigned char const *p,
crc ^= crc_low;
return crc;
}
-u32 __pure crc32_be(u32 crc, unsigned char const *p, size_t len)
+u32 __pure crc32_be_arch(u32 crc, const u8 *p, size_t len)
{
size_t offset, head_len, tail_len;
unsigned long const *p_ul;
unsigned long s;
@@ -290,5 +293,9 @@ u32 __pure crc32_be(u32 crc, unsigned char const *p, size_t len)
return crc;
legacy:
return crc32_be_base(crc, p, len);
}
+EXPORT_SYMBOL(crc32_be_arch);
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("Accelerated CRC32 implementation with Zbc extension");
@@ -158,16 +158,16 @@ static struct shash_alg algs[] = {{
}};
static int __init crc32_mod_init(void)
{
/* register the arch flavor only if it differs from the generic one */
- return crypto_register_shashes(algs, 1 + (&crc32_le != &crc32_le_base));
+ return crypto_register_shashes(algs, 1 + IS_ENABLED(CONFIG_CRC32_ARCH));
}
static void __exit crc32_mod_fini(void)
{
- crypto_unregister_shashes(algs, 1 + (&crc32_le != &crc32_le_base));
+ crypto_unregister_shashes(algs, 1 + IS_ENABLED(CONFIG_CRC32_ARCH));
}
subsys_initcall(crc32_mod_init);
module_exit(crc32_mod_fini);
@@ -198,16 +198,16 @@ static struct shash_alg algs[] = {{
}};
static int __init crc32c_mod_init(void)
{
/* register the arch flavor only if it differs from the generic one */
- return crypto_register_shashes(algs, 1 + (&__crc32c_le != &crc32c_le_base));
+ return crypto_register_shashes(algs, 1 + IS_ENABLED(CONFIG_CRC32_ARCH));
}
static void __exit crc32c_mod_fini(void)
{
- crypto_unregister_shashes(algs, 1 + (&__crc32c_le != &crc32c_le_base));
+ crypto_unregister_shashes(algs, 1 + IS_ENABLED(CONFIG_CRC32_ARCH));
}
subsys_initcall(crc32c_mod_init);
module_exit(crc32c_mod_fini);
@@ -6,14 +6,38 @@
#define _LINUX_CRC32_H
#include <linux/types.h>
#include <linux/bitrev.h>
-u32 __pure crc32_le(u32 crc, unsigned char const *p, size_t len);
-u32 __pure crc32_le_base(u32 crc, unsigned char const *p, size_t len);
-u32 __pure crc32_be(u32 crc, unsigned char const *p, size_t len);
-u32 __pure crc32_be_base(u32 crc, unsigned char const *p, size_t len);
+u32 __pure crc32_le_arch(u32 crc, const u8 *p, size_t len);
+u32 __pure crc32_le_base(u32 crc, const u8 *p, size_t len);
+u32 __pure crc32_be_arch(u32 crc, const u8 *p, size_t len);
+u32 __pure crc32_be_base(u32 crc, const u8 *p, size_t len);
+u32 __pure crc32c_le_arch(u32 crc, const u8 *p, size_t len);
+u32 __pure crc32c_le_base(u32 crc, const u8 *p, size_t len);
+
+static inline u32 __pure crc32_le(u32 crc, const u8 *p, size_t len)
+{
+ if (IS_ENABLED(CONFIG_CRC32_ARCH))
+ return crc32_le_arch(crc, p, len);
+ return crc32_le_base(crc, p, len);
+}
+
+static inline u32 __pure crc32_be(u32 crc, const u8 *p, size_t len)
+{
+ if (IS_ENABLED(CONFIG_CRC32_ARCH))
+ return crc32_be_arch(crc, p, len);
+ return crc32_be_base(crc, p, len);
+}
+
+/* TODO: leading underscores should be dropped once callers have been updated */
+static inline u32 __pure __crc32c_le(u32 crc, const u8 *p, size_t len)
+{
+ if (IS_ENABLED(CONFIG_CRC32_ARCH))
+ return crc32c_le_arch(crc, p, len);
+ return crc32c_le_base(crc, p, len);
+}
/**
* 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
@@ -36,13 +60,10 @@ u32 __attribute_const__ 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;
}
-u32 __pure __crc32c_le(u32 crc, unsigned char const *p, size_t len);
-u32 __pure crc32c_le_base(u32 crc, unsigned char const *p, size_t len);
-
/**
* __crc32c_le_combine - Combine two crc32c check values into one. For two
* sequences of bytes, seq1 and seq2 with lengths len1
* and len2, __crc32c_le() check values were calculated
* for each, crc1 and crc2.
@@ -188,10 +188,13 @@ config CRC32
This option is provided for the case where no in-kernel-tree
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 ARCH_HAS_CRC32
+ bool
+
config CRC32_SELFTEST
tristate "CRC32 perform self test on init"
depends on CRC32
help
This option enables the CRC32 library functions to perform a
@@ -200,54 +203,89 @@ config CRC32_SELFTEST
and computes the total elapsed time and number of bytes processed.
choice
prompt "CRC32 implementation"
depends on CRC32
- default CRC32_SLICEBY8
+ default CRC32_IMPL_ARCH_PLUS_SLICEBY8 if ARCH_HAS_CRC32
+ default CRC32_IMPL_SLICEBY8 if !ARCH_HAS_CRC32
help
- This option allows a kernel builder to override the default choice
- of CRC32 algorithm. Choose the default ("slice by 8") unless you
- know that you need one of the others.
+ This option allows you to override the default choice of CRC32
+ implementation. Choose the default unless you know that you need one
+ of the others.
-config CRC32_SLICEBY8
+config CRC32_IMPL_ARCH_PLUS_SLICEBY8
+ bool "Arch-optimized, with fallback to slice-by-8" if ARCH_HAS_CRC32
+ help
+ Use architecture-optimized implementation of CRC32. Fall back to
+ slice-by-8 in cases where the arch-optimized implementation cannot be
+ used, e.g. if the CPU lacks support for the needed instructions.
+
+ This is the default when an arch-optimized implementation exists.
+
+config CRC32_IMPL_ARCH_PLUS_SLICEBY1
+ bool "Arch-optimized, with fallback to slice-by-1" if ARCH_HAS_CRC32
+ help
+ Use architecture-optimized implementation of CRC32, but fall back to
+ slice-by-1 instead of slice-by-8 in order to reduce the binary size.
+
+config CRC32_IMPL_SLICEBY8
bool "Slice by 8 bytes"
help
Calculate checksum 8 bytes at a time with a clever slicing algorithm.
- This is the fastest algorithm, but comes with a 8KiB lookup table.
- Most modern processors have enough cache to hold this table without
- thrashing the cache.
-
- This is the default implementation choice. Choose this one unless
- you have a good reason not to.
+ This is much slower than the architecture-optimized implementation of
+ CRC32 (if the selected arch has one), but it is portable and is the
+ fastest implementation when no arch-optimized implementation is
+ available. It uses an 8KiB lookup table. Most modern processors have
+ enough cache to hold this table without thrashing the cache.
-config CRC32_SLICEBY4
+config CRC32_IMPL_SLICEBY4
bool "Slice by 4 bytes"
help
Calculate checksum 4 bytes at a time with a clever slicing algorithm.
This is a bit slower than slice by 8, but has a smaller 4KiB lookup
table.
Only choose this option if you know what you are doing.
-config CRC32_SARWATE
- bool "Sarwate's Algorithm (one byte at a time)"
+config CRC32_IMPL_SLICEBY1
+ bool "Slice by 1 byte (Sarwate's algorithm)"
help
Calculate checksum a byte at a time using Sarwate's algorithm. This
- is not particularly fast, but has a small 256 byte lookup table.
+ is not particularly fast, but has a small 1KiB lookup table.
Only choose this option if you know what you are doing.
-config CRC32_BIT
+config CRC32_IMPL_BIT
bool "Classic Algorithm (one bit at a time)"
help
Calculate checksum one bit at a time. This is VERY slow, but has
no lookup table. This is provided as a debugging option.
Only choose this option if you are debugging crc32.
endchoice
+config CRC32_ARCH
+ tristate
+ default CRC32 if CRC32_IMPL_ARCH_PLUS_SLICEBY8 || CRC32_IMPL_ARCH_PLUS_SLICEBY1
+
+config CRC32_SLICEBY8
+ bool
+ default y if CRC32_IMPL_SLICEBY8 || CRC32_IMPL_ARCH_PLUS_SLICEBY8
+
+config CRC32_SLICEBY4
+ bool
+ default y if CRC32_IMPL_SLICEBY4
+
+config CRC32_SARWATE
+ bool
+ default y if CRC32_IMPL_SLICEBY1 || CRC32_IMPL_ARCH_PLUS_SLICEBY1
+
+config CRC32_BIT
+ bool
+ default y if CRC32_IMPL_BIT
+
config CRC64
tristate "CRC64 functions"
help
This option is provided for the case where no in-kernel-tree
modules require CRC64 functions, but a module built outside
@@ -181,39 +181,31 @@ static inline u32 __pure crc32_le_generic(u32 crc, unsigned char const *p,
#endif
return crc;
}
#if CRC_LE_BITS == 1
-u32 __pure __weak crc32_le(u32 crc, unsigned char const *p, size_t len)
+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 __weak __crc32c_le(u32 crc, unsigned char const *p, size_t len)
+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 __weak crc32_le(u32 crc, unsigned char const *p, size_t len)
+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 __weak __crc32c_le(u32 crc, unsigned char const *p, size_t len)
+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);
}
#endif
-EXPORT_SYMBOL(crc32_le);
-EXPORT_SYMBOL(__crc32c_le);
-
-u32 __pure crc32_le_base(u32, unsigned char const *, size_t) __alias(crc32_le);
EXPORT_SYMBOL(crc32_le_base);
-
-u32 __pure crc32c_le_base(u32, unsigned char const *, size_t) __alias(__crc32c_le);
EXPORT_SYMBOL(crc32c_le_base);
-u32 __pure crc32_be_base(u32, unsigned char const *, size_t) __alias(crc32_be);
-
/*
* This multiplies the polynomials x and y modulo the given modulus.
* This follows the "little-endian" CRC convention that the lsbit
* represents the highest power of x, and the msbit represents x^0.
*/
@@ -333,16 +325,16 @@ static inline u32 __pure crc32_be_generic(u32 crc, unsigned char const *p,
# endif
return crc;
}
#if CRC_BE_BITS == 1
-u32 __pure __weak crc32_be(u32 crc, unsigned char const *p, size_t len)
+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 __weak crc32_be(u32 crc, unsigned char const *p, size_t len)
+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);
}
#endif
-EXPORT_SYMBOL(crc32_be);
+EXPORT_SYMBOL(crc32_be_base);