powerpc/crc32: expose CRC32 functions through lib

Move the powerpc CRC32C assembly code into the lib directory and wire it
up to the library interface.  This allows it to be used without going
through the crypto API.  It remains usable via the crypto API too via
the shash algorithms that use the library interface.  Thus all the
arch-specific "shash" code becomes unnecessary and is removed.

Note: to see the diff from arch/powerpc/crypto/crc32c-vpmsum_glue.c to
arch/powerpc/lib/crc32-glue.c, view this commit with 'git show -M10'.

Reviewed-by: Ard Biesheuvel <[email protected]>
Acked-by: Michael Ellerman <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Eric Biggers <[email protected]>

Author: ebiggers

arch/powerpc/Kconfig

@@ -127,6 +127,7 @@ config PPC
 	select ARCH_ENABLE_MEMORY_HOTPLUG
 	select ARCH_ENABLE_MEMORY_HOTREMOVE
 	select ARCH_HAS_COPY_MC			if PPC64
+	select ARCH_HAS_CRC32			if PPC64 && ALTIVEC
 	select ARCH_HAS_CURRENT_STACK_POINTER
 	select ARCH_HAS_DEBUG_VIRTUAL
 	select ARCH_HAS_DEBUG_VM_PGTABLE

arch/powerpc/configs/powernv_defconfig

@@ -320,7 +320,6 @@ CONFIG_XMON=y
 CONFIG_CRYPTO_TEST=m
 CONFIG_CRYPTO_PCBC=m
 CONFIG_CRYPTO_HMAC=y
-CONFIG_CRYPTO_CRC32C_VPMSUM=m
 CONFIG_CRYPTO_CRCT10DIF_VPMSUM=m
 CONFIG_CRYPTO_MD5_PPC=m
 CONFIG_CRYPTO_MICHAEL_MIC=m

arch/powerpc/configs/ppc64_defconfig

@@ -389,7 +389,6 @@ CONFIG_CRYPTO_MICHAEL_MIC=m
 CONFIG_CRYPTO_SHA256=y
 CONFIG_CRYPTO_WP512=m
 CONFIG_CRYPTO_LZO=m
-CONFIG_CRYPTO_CRC32C_VPMSUM=m
 CONFIG_CRYPTO_CRCT10DIF_VPMSUM=m
 CONFIG_CRYPTO_VPMSUM_TESTER=m
 CONFIG_CRYPTO_MD5_PPC=m

arch/powerpc/crypto/Kconfig

@@ -13,19 +13,6 @@ config CRYPTO_CURVE25519_PPC64
 	  Architecture: PowerPC64
 	  - Little-endian
 
-config CRYPTO_CRC32C_VPMSUM
-	tristate "CRC32c"
-	depends on PPC64 && ALTIVEC
-	select CRYPTO_HASH
-	select CRC32
-	help
-	  CRC32c CRC algorithm with the iSCSI polynomial (RFC 3385 and RFC 3720)
-
-	  Architecture: powerpc64 using
-	  - AltiVec extensions
-
-	  Enable on POWER8 and newer processors for improved performance.
-
 config CRYPTO_CRCT10DIF_VPMSUM
 	tristate "CRC32T10DIF"
 	depends on PPC64 && ALTIVEC && CRC_T10DIF
@@ -40,7 +27,7 @@ config CRYPTO_CRCT10DIF_VPMSUM
 
 config CRYPTO_VPMSUM_TESTER
 	tristate "CRC32c and CRC32T10DIF hardware acceleration tester"
-	depends on CRYPTO_CRCT10DIF_VPMSUM && CRYPTO_CRC32C_VPMSUM
+	depends on CRYPTO_CRCT10DIF_VPMSUM && CRYPTO_CRC32C && CRC32_ARCH
 	help
 	  Stress test for CRC32c and CRCT10DIF algorithms implemented with
 	  powerpc64 AltiVec extensions (POWER8 vpmsum instructions).

arch/powerpc/crypto/Makefile

@@ -10,7 +10,6 @@ obj-$(CONFIG_CRYPTO_MD5_PPC) += md5-ppc.o
 obj-$(CONFIG_CRYPTO_SHA1_PPC) += sha1-powerpc.o
 obj-$(CONFIG_CRYPTO_SHA1_PPC_SPE) += sha1-ppc-spe.o
 obj-$(CONFIG_CRYPTO_SHA256_PPC_SPE) += sha256-ppc-spe.o
-obj-$(CONFIG_CRYPTO_CRC32C_VPMSUM) += crc32c-vpmsum.o
 obj-$(CONFIG_CRYPTO_CRCT10DIF_VPMSUM) += crct10dif-vpmsum.o
 obj-$(CONFIG_CRYPTO_VPMSUM_TESTER) += crc-vpmsum_test.o
 obj-$(CONFIG_CRYPTO_AES_GCM_P10) += aes-gcm-p10-crypto.o
@@ -24,7 +23,6 @@ md5-ppc-y := md5-asm.o md5-glue.o
 sha1-powerpc-y := sha1-powerpc-asm.o sha1.o
 sha1-ppc-spe-y := sha1-spe-asm.o sha1-spe-glue.o
 sha256-ppc-spe-y := sha256-spe-asm.o sha256-spe-glue.o
-crc32c-vpmsum-y := crc32c-vpmsum_asm.o crc32c-vpmsum_glue.o
 crct10dif-vpmsum-y := crct10dif-vpmsum_asm.o crct10dif-vpmsum_glue.o
 aes-gcm-p10-crypto-y := aes-gcm-p10-glue.o aes-gcm-p10.o ghashp10-ppc.o aesp10-ppc.o
 chacha-p10-crypto-y := chacha-p10-glue.o chacha-p10le-8x.o

arch/powerpc/crypto/crc32c-vpmsum_glue.c

@@ -842,4 +842,4 @@
 	.octa 0x0000000000000000000000018bb70000
 
 #define CRC_FUNCTION_NAME __crct10dif_vpmsum
-#include "crc32-vpmsum_core.S"
+#include "../lib/crc32-vpmsum_core.S"

arch/powerpc/crypto/crct10dif-vpmsum_asm.S

@@ -78,4 +78,7 @@ CFLAGS_xor_vmx.o += -mhard-float -maltivec $(call cc-option,-mabi=altivec)
 # Enable <altivec.h>
 CFLAGS_xor_vmx.o += -isystem $(shell $(CC) -print-file-name=include)
 
+obj-$(CONFIG_CRC32_ARCH) += crc32-powerpc.o
+crc32-powerpc-y := crc32-glue.o crc32c-vpmsum_asm.o
+
 obj-$(CONFIG_PPC64) += $(obj64-y)

arch/powerpc/lib/Makefile

@@ -0,0 +1,92 @@
+// SPDX-License-Identifier: GPL-2.0-only
+#include <linux/crc32.h>
+#include <crypto/internal/simd.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/cpufeature.h>
+#include <asm/simd.h>
+#include <asm/switch_to.h>
+
+#define VMX_ALIGN		16
+#define VMX_ALIGN_MASK		(VMX_ALIGN-1)
+
+#define VECTOR_BREAKPOINT	512
+
+static DEFINE_STATIC_KEY_FALSE(have_vec_crypto);
+
+u32 __crc32c_vpmsum(u32 crc, const u8 *p, size_t len);
+
+u32 crc32_le_arch(u32 crc, const u8 *p, size_t len)
+{
+	return crc32_le_base(crc, p, len);
+}
+EXPORT_SYMBOL(crc32_le_arch);
+
+u32 crc32c_le_arch(u32 crc, const u8 *p, size_t len)
+{
+	unsigned int prealign;
+	unsigned int tail;
+
+	if (len < (VECTOR_BREAKPOINT + VMX_ALIGN) ||
+	    !static_branch_likely(&have_vec_crypto) || !crypto_simd_usable())
+		return crc32c_le_base(crc, p, len);
+
+	if ((unsigned long)p & VMX_ALIGN_MASK) {
+		prealign = VMX_ALIGN - ((unsigned long)p & VMX_ALIGN_MASK);
+		crc = crc32c_le_base(crc, p, prealign);
+		len -= prealign;
+		p += prealign;
+	}
+
+	if (len & ~VMX_ALIGN_MASK) {
+		preempt_disable();
+		pagefault_disable();
+		enable_kernel_altivec();
+		crc = __crc32c_vpmsum(crc, p, len & ~VMX_ALIGN_MASK);
+		disable_kernel_altivec();
+		pagefault_enable();
+		preempt_enable();
+	}
+
+	tail = len & VMX_ALIGN_MASK;
+	if (tail) {
+		p += len & ~VMX_ALIGN_MASK;
+		crc = crc32c_le_base(crc, p, tail);
+	}
+
+	return crc;
+}
+EXPORT_SYMBOL(crc32c_le_arch);
+
+u32 crc32_be_arch(u32 crc, const u8 *p, size_t len)
+{
+	return crc32_be_base(crc, p, len);
+}
+EXPORT_SYMBOL(crc32_be_arch);
+
+static int __init crc32_powerpc_init(void)
+{
+	if (cpu_has_feature(CPU_FTR_ARCH_207S) &&
+	    (cur_cpu_spec->cpu_user_features2 & PPC_FEATURE2_VEC_CRYPTO))
+		static_branch_enable(&have_vec_crypto);
+	return 0;
+}
+arch_initcall(crc32_powerpc_init);
+
+static void __exit crc32_powerpc_exit(void)
+{
+}
+module_exit(crc32_powerpc_exit);
+
+u32 crc32_optimizations(void)
+{
+	if (static_key_enabled(&have_vec_crypto))
+		return CRC32C_OPTIMIZATION;
+	return 0;
+}
+EXPORT_SYMBOL(crc32_optimizations);
+
+MODULE_AUTHOR("Anton Blanchard <[email protected]>");
+MODULE_DESCRIPTION("CRC32C using vector polynomial multiply-sum instructions");
+MODULE_LICENSE("GPL");