lib/crc: powerpc: Migrate optimized CRC code into lib/crc/

Move the powerpc-optimized CRC code from arch/powerpc/lib/crc* into its
new location in lib/crc/powerpc/, and wire it up in the new way.  This
new way of organizing the CRC code eliminates the need to artificially
split the code for each CRC variant into separate arch and generic
modules, enabling better inlining and dead code elimination.  For more
details, see "lib/crc: Prepare for arch-optimized code in subdirs of
lib/crc/".

Reviewed-by: "Martin K. Petersen" <martin.petersen@oracle.com>
Acked-by: Ingo Molnar <mingo@kernel.org>
Acked-by: "Jason A. Donenfeld" <Jason@zx2c4.com>
Link: https://lore.kernel.org/r/20250607200454.73587-8-ebiggers@kernel.org
Signed-off-by: Eric Biggers <ebiggers@kernel.org>

9 files changed, 14 insertions, 56 deletions

diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index c3e0cc83f120..45b4fa7b9b02 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -127,8 +127,6 @@ 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_CRC_T10DIF		if PPC64 && ALTIVEC
 	select ARCH_HAS_CURRENT_STACK_POINTER
 	select ARCH_HAS_DEBUG_VIRTUAL
 	select ARCH_HAS_DEBUG_VM_PGTABLE
diff --git a/arch/powerpc/lib/Makefile b/arch/powerpc/lib/Makefile
index 481f968e42c7..59de2e2232df 100644
--- a/arch/powerpc/lib/Makefile
+++ b/arch/powerpc/lib/Makefile
@@ -80,10 +80,4 @@ 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-$(CONFIG_CRC32_ARCH) += crc32-powerpc.o
-crc32-powerpc-y := crc32.o crc32c-vpmsum_asm.o
-
-obj-$(CONFIG_CRC_T10DIF_ARCH) += crc-t10dif-powerpc.o
-crc-t10dif-powerpc-y := crc-t10dif.o crct10dif-vpmsum_asm.o
-
 obj-$(CONFIG_PPC64) += $(obj64-y)
diff --git a/lib/crc/Kconfig b/lib/crc/Kconfig
index a15aad24136a..bfcf43c2592a 100644
--- a/lib/crc/Kconfig
+++ b/lib/crc/Kconfig
@@ -52,6 +52,7 @@ config CRC_T10DIF_ARCH
 	depends on CRC_T10DIF && CRC_OPTIMIZATIONS
 	default y if ARM && KERNEL_MODE_NEON
 	default y if ARM64 && KERNEL_MODE_NEON
+	default y if PPC64 && ALTIVEC
 
 config CRC32
 	tristate
@@ -70,6 +71,7 @@ config CRC32_ARCH
 	default y if ARM64
 	default y if LOONGARCH
 	default y if MIPS && CPU_MIPSR6
+	default y if PPC64 && ALTIVEC
 
 config CRC64
 	tristate
diff --git a/lib/crc/Makefile b/lib/crc/Makefile
index 8adff4ae1ba6..555fd3fb6d19 100644
--- a/lib/crc/Makefile
+++ b/lib/crc/Makefile
@@ -15,6 +15,7 @@ ifeq ($(CONFIG_CRC_T10DIF_ARCH),y)
 CFLAGS_crc-t10dif-main.o += -I$(src)/$(SRCARCH)
 crc-t10dif-$(CONFIG_ARM) += arm/crc-t10dif-core.o
 crc-t10dif-$(CONFIG_ARM64) += arm64/crc-t10dif-core.o
+crc-t10dif-$(CONFIG_PPC) += powerpc/crct10dif-vpmsum_asm.o
 endif
 
 obj-$(CONFIG_CRC32) += crc32.o
@@ -23,6 +24,7 @@ ifeq ($(CONFIG_CRC32_ARCH),y)
 CFLAGS_crc32-main.o += -I$(src)/$(SRCARCH)
 crc32-$(CONFIG_ARM) += arm/crc32-core.o
 crc32-$(CONFIG_ARM64) += arm64/crc32-core.o
+crc32-$(CONFIG_PPC) += powerpc/crc32c-vpmsum_asm.o
 endif
 
 obj-$(CONFIG_CRC64) += crc64.o
diff --git a/arch/powerpc/lib/crc-t10dif.c b/lib/crc/powerpc/crc-t10dif.h
index be23ded3a9df..59e16804a6ea 100644
--- a/arch/powerpc/lib/crc-t10dif.c
+++ b/lib/crc/powerpc/crc-t10dif.h
@@ -9,10 +9,7 @@
 #include <asm/switch_to.h>
 #include <crypto/internal/simd.h>
 #include <linux/cpufeature.h>
-#include <linux/crc-t10dif.h>
 #include <linux/jump_label.h>
-#include <linux/kernel.h>
-#include <linux/module.h>
 #include <linux/preempt.h>
 #include <linux/uaccess.h>
 
@@ -25,7 +22,7 @@ static __ro_after_init DEFINE_STATIC_KEY_FALSE(have_vec_crypto);
 
 u32 __crct10dif_vpmsum(u32 crc, unsigned char const *p, size_t len);
 
-u16 crc_t10dif_arch(u16 crci, const u8 *p, size_t len)
+static inline u16 crc_t10dif_arch(u16 crci, const u8 *p, size_t len)
 {
 	unsigned int prealign;
 	unsigned int tail;
@@ -62,22 +59,11 @@ u16 crc_t10dif_arch(u16 crci, const u8 *p, size_t len)
 
 	return crc & 0xffff;
 }
-EXPORT_SYMBOL(crc_t10dif_arch);
 
-static int __init crc_t10dif_powerpc_init(void)
+#define crc_t10dif_mod_init_arch crc_t10dif_mod_init_arch
+static inline void crc_t10dif_mod_init_arch(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;
 }
-subsys_initcall(crc_t10dif_powerpc_init);
-
-static void __exit crc_t10dif_powerpc_exit(void)
-{
-}
-module_exit(crc_t10dif_powerpc_exit);
-
-MODULE_AUTHOR("Daniel Axtens <dja@axtens.net>");
-MODULE_DESCRIPTION("CRCT10DIF using vector polynomial multiply-sum instructions");
-MODULE_LICENSE("GPL");
diff --git a/arch/powerpc/lib/crc-vpmsum-template.S b/lib/crc/powerpc/crc-vpmsum-template.S
index b0f87f595b26..b0f87f595b26 100644
--- a/arch/powerpc/lib/crc-vpmsum-template.S
+++ b/lib/crc/powerpc/crc-vpmsum-template.S
diff --git a/arch/powerpc/lib/crc32.c b/lib/crc/powerpc/crc32.h
index 0d9befb6e7b8..811cc2e6ed24 100644
--- a/arch/powerpc/lib/crc32.c
+++ b/lib/crc/powerpc/crc32.h
@@ -2,10 +2,7 @@
 #include <asm/switch_to.h>
 #include <crypto/internal/simd.h>
 #include <linux/cpufeature.h>
-#include <linux/crc32.h>
 #include <linux/jump_label.h>
-#include <linux/kernel.h>
-#include <linux/module.h>
 #include <linux/preempt.h>
 #include <linux/uaccess.h>
 
@@ -16,15 +13,12 @@
 
 static __ro_after_init DEFINE_STATIC_KEY_FALSE(have_vec_crypto);
 
-u32 __crc32c_vpmsum(u32 crc, const u8 *p, size_t len);
+#define crc32_le_arch crc32_le_base /* not implemented on this arch */
+#define crc32_be_arch crc32_be_base /* not implemented on this arch */
 
-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_vpmsum(u32 crc, const u8 *p, size_t len);
 
-u32 crc32c_arch(u32 crc, const u8 *p, size_t len)
+static inline u32 crc32c_arch(u32 crc, const u8 *p, size_t len)
 {
 	unsigned int prealign;
 	unsigned int tail;
@@ -58,36 +52,18 @@ u32 crc32c_arch(u32 crc, const u8 *p, size_t len)
 
 	return crc;
 }
-EXPORT_SYMBOL(crc32c_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)
+#define crc32_mod_init_arch crc32_mod_init_arch
+static inline void crc32_mod_init_arch(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;
-}
-subsys_initcall(crc32_powerpc_init);
-
-static void __exit crc32_powerpc_exit(void)
-{
 }
-module_exit(crc32_powerpc_exit);
 
-u32 crc32_optimizations(void)
+static inline u32 crc32_optimizations_arch(void)
 {
 	if (static_key_enabled(&have_vec_crypto))
 		return CRC32C_OPTIMIZATION;
 	return 0;
 }
-EXPORT_SYMBOL(crc32_optimizations);
-
-MODULE_AUTHOR("Anton Blanchard <anton@samba.org>");
-MODULE_DESCRIPTION("CRC32C using vector polynomial multiply-sum instructions");
-MODULE_LICENSE("GPL");
diff --git a/arch/powerpc/lib/crc32c-vpmsum_asm.S b/lib/crc/powerpc/crc32c-vpmsum_asm.S
index 1b35c55cce0a..1b35c55cce0a 100644
--- a/arch/powerpc/lib/crc32c-vpmsum_asm.S
+++ b/lib/crc/powerpc/crc32c-vpmsum_asm.S
diff --git a/arch/powerpc/lib/crct10dif-vpmsum_asm.S b/lib/crc/powerpc/crct10dif-vpmsum_asm.S
index 47a6266d89a8..47a6266d89a8 100644
--- a/arch/powerpc/lib/crct10dif-vpmsum_asm.S
+++ b/lib/crc/powerpc/crct10dif-vpmsum_asm.S