x86/crc-t10dif: expose CRC-T10DIF function through lib

Move the x86 CRC-T10DIF 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.

Reviewed-by: Ard Biesheuvel <ardb@kernel.org>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Link: https://lore.kernel.org/r/20241202012056.209768-5-ebiggers@kernel.org
Signed-off-by: Eric Biggers <ebiggers@google.com>

arch/x86/Kconfig

@@ -77,6 +77,7 @@ config X86
 	select ARCH_HAS_CPU_FINALIZE_INIT
 	select ARCH_HAS_CPU_PASID		if IOMMU_SVA
 	select ARCH_HAS_CRC32
+	select ARCH_HAS_CRC_T10DIF		if X86_64
 	select ARCH_HAS_CURRENT_STACK_POINTER
 	select ARCH_HAS_DEBUG_VIRTUAL
 	select ARCH_HAS_DEBUG_VM_PGTABLE	if !X86_PAE

arch/x86/crypto/Kconfig

@@ -492,14 +492,4 @@ config CRYPTO_GHASH_CLMUL_NI_INTEL
 	  Architecture: x86_64 using:
 	  - CLMUL-NI (carry-less multiplication new instructions)
 
-config CRYPTO_CRCT10DIF_PCLMUL
-	tristate "CRCT10DIF (PCLMULQDQ)"
-	depends on X86 && 64BIT && CRC_T10DIF
-	select CRYPTO_HASH
-	help
-	  CRC16 CRC algorithm used for the T10 (SCSI) Data Integrity Field (DIF)
-
-	  Architecture: x86_64 using:
-	  - PCLMULQDQ (carry-less multiplication)
-
 endmenu

arch/x86/crypto/Makefile

@@ -75,9 +75,6 @@ ghash-clmulni-intel-y := ghash-clmulni-intel_asm.o ghash-clmulni-intel_glue.o
 obj-$(CONFIG_CRYPTO_POLYVAL_CLMUL_NI) += polyval-clmulni.o
 polyval-clmulni-y := polyval-clmulni_asm.o polyval-clmulni_glue.o
 
-obj-$(CONFIG_CRYPTO_CRCT10DIF_PCLMUL) += crct10dif-pclmul.o
-crct10dif-pclmul-y := crct10dif-pcl-asm_64.o crct10dif-pclmul_glue.o
-
 obj-$(CONFIG_CRYPTO_POLY1305_X86_64) += poly1305-x86_64.o
 poly1305-x86_64-y := poly1305-x86_64-cryptogams.o poly1305_glue.o
 targets += poly1305-x86_64-cryptogams.S

arch/x86/lib/Makefile

@@ -42,6 +42,9 @@ obj-$(CONFIG_CRC32_ARCH) += crc32-x86.o
 crc32-x86-y := crc32-glue.o crc32-pclmul.o
 crc32-x86-$(CONFIG_64BIT) += crc32c-3way.o
 
+obj-$(CONFIG_CRC_T10DIF_ARCH) += crc-t10dif-x86.o
+crc-t10dif-x86-y := crc-t10dif-glue.o crct10dif-pcl-asm_64.o
+
 obj-y += msr.o msr-reg.o msr-reg-export.o hweight.o
 obj-y += iomem.o
 

arch/x86/lib/crc-t10dif-glue.c

@@ -0,0 +1,51 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * CRC-T10DIF using PCLMULQDQ instructions
+ *
+ * Copyright 2024 Google LLC
+ */
+
+#include <asm/cpufeatures.h>
+#include <asm/simd.h>
+#include <crypto/internal/simd.h>
+#include <linux/crc-t10dif.h>
+#include <linux/module.h>
+
+static DEFINE_STATIC_KEY_FALSE(have_pclmulqdq);
+
+asmlinkage u16 crc_t10dif_pcl(u16 init_crc, const u8 *buf, size_t len);
+
+u16 crc_t10dif_arch(u16 crc, const u8 *p, size_t len)
+{
+	if (len >= 16 &&
+	    static_key_enabled(&have_pclmulqdq) && crypto_simd_usable()) {
+		kernel_fpu_begin();
+		crc = crc_t10dif_pcl(crc, p, len);
+		kernel_fpu_end();
+		return crc;
+	}
+	return crc_t10dif_generic(crc, p, len);
+}
+EXPORT_SYMBOL(crc_t10dif_arch);
+
+static int __init crc_t10dif_x86_init(void)
+{
+	if (boot_cpu_has(X86_FEATURE_PCLMULQDQ))
+		static_branch_enable(&have_pclmulqdq);
+	return 0;
+}
+arch_initcall(crc_t10dif_x86_init);
+
+static void __exit crc_t10dif_x86_exit(void)
+{
+}
+module_exit(crc_t10dif_x86_exit);
+
+bool crc_t10dif_is_optimized(void)
+{
+	return static_key_enabled(&have_pclmulqdq);
+}
+EXPORT_SYMBOL(crc_t10dif_is_optimized);
+
+MODULE_DESCRIPTION("CRC-T10DIF using PCLMULQDQ instructions");
+MODULE_LICENSE("GPL");