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 CRC32 and CRC-T10DIF code to be
   directly accessible via the library API, instead of requiring the
   crypto API. This is much simpler and more efficient.

 - Convert some users such as ext4 to use the CRC32 library API instead
   of the crypto API. More conversions like this will come later.

 - Add a KUnit test that tests and benchmarks multiple CRC variants.
   Remove older, less-comprehensive tests that are made redundant by
   this.

 - Add an entry to MAINTAINERS for the kernel's CRC library code. I'm
   volunteering to maintain it. I have additional cleanups and
   optimizations planned for future cycles.

* tag 'crc-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/ebiggers/linux: (31 commits)
  MAINTAINERS: add entry for CRC library
  powerpc/crc: delete obsolete crc-vpmsum_test.c
  lib/crc32test: delete obsolete crc32test.c
  lib/crc16_kunit: delete obsolete crc16_kunit.c
  lib/crc_kunit.c: add KUnit test suite for CRC library functions
  powerpc/crc-t10dif: expose CRC-T10DIF function through lib
  arm64/crc-t10dif: expose CRC-T10DIF function through lib
  arm/crc-t10dif: expose CRC-T10DIF function through lib
  x86/crc-t10dif: expose CRC-T10DIF function through lib
  crypto: crct10dif - expose arch-optimized lib function
  lib/crc-t10dif: add support for arch overrides
  lib/crc-t10dif: stop wrapping the crypto API
  scsi: target: iscsi: switch to using the crc32c library
  f2fs: switch to using the crc32 library
  jbd2: switch to using the crc32c library
  ext4: switch to using the crc32c library
  lib/crc32: make crc32c() go directly to lib
  bcachefs: Explicitly select CRYPTO from BCACHEFS_FS
  x86/crc32: expose CRC32 functions through lib
  x86/crc32: update prototype for crc32_pclmul_le_16()
  ...

9 files changed, 109 insertions, 151 deletions

diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 83017757be8e..fcdd0ed3eca8 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -21,6 +21,8 @@ config ARM64
 	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_CRC_T10DIF if KERNEL_MODE_NEON
 	select ARCH_HAS_CURRENT_STACK_POINTER
 	select ARCH_HAS_DEBUG_VIRTUAL
 	select ARCH_HAS_DEBUG_VM_PGTABLE
diff --git a/arch/arm64/configs/defconfig b/arch/arm64/configs/defconfig
index c62831e61586..9c0d6b93a3c2 100644
--- a/arch/arm64/configs/defconfig
+++ b/arch/arm64/configs/defconfig
@@ -1698,7 +1698,6 @@ CONFIG_CRYPTO_SM3_ARM64_CE=m
 CONFIG_CRYPTO_AES_ARM64_CE_BLK=y
 CONFIG_CRYPTO_AES_ARM64_BS=m
 CONFIG_CRYPTO_AES_ARM64_CE_CCM=y
-CONFIG_CRYPTO_CRCT10DIF_ARM64_CE=m
 CONFIG_CRYPTO_DEV_SUN8I_CE=m
 CONFIG_CRYPTO_DEV_FSL_CAAM=m
 CONFIG_CRYPTO_DEV_FSL_DPAA2_CAAM=m
diff --git a/arch/arm64/crypto/Kconfig b/arch/arm64/crypto/Kconfig
index e7d9bd8e4709..5636ab83f22a 100644
--- a/arch/arm64/crypto/Kconfig
+++ b/arch/arm64/crypto/Kconfig
@@ -312,15 +312,5 @@ config CRYPTO_SM4_ARM64_CE_GCM
 	  - PMULL (Polynomial Multiply Long) instructions
 	  - NEON (Advanced SIMD) extensions
 
-config CRYPTO_CRCT10DIF_ARM64_CE
-	tristate "CRCT10DIF (PMULL)"
-	depends on KERNEL_MODE_NEON && CRC_T10DIF
-	select CRYPTO_HASH
-	help
-	  CRC16 CRC algorithm used for the T10 (SCSI) Data Integrity Field (DIF)
-
-	  Architecture: arm64 using
-	  - PMULL (Polynomial Multiply Long) instructions
-
 endmenu
 
diff --git a/arch/arm64/crypto/Makefile b/arch/arm64/crypto/Makefile
index fbe64dce66e0..e7139c4768ce 100644
--- a/arch/arm64/crypto/Makefile
+++ b/arch/arm64/crypto/Makefile
@@ -44,9 +44,6 @@ ghash-ce-y := ghash-ce-glue.o ghash-ce-core.o
 obj-$(CONFIG_CRYPTO_POLYVAL_ARM64_CE) += polyval-ce.o
 polyval-ce-y := polyval-ce-glue.o polyval-ce-core.o
 
-obj-$(CONFIG_CRYPTO_CRCT10DIF_ARM64_CE) += crct10dif-ce.o
-crct10dif-ce-y := crct10dif-ce-core.o crct10dif-ce-glue.o
-
 obj-$(CONFIG_CRYPTO_AES_ARM64_CE) += aes-ce-cipher.o
 aes-ce-cipher-y := aes-ce-core.o aes-ce-glue.o
 
diff --git a/arch/arm64/crypto/crct10dif-ce-glue.c b/arch/arm64/crypto/crct10dif-ce-glue.c
deleted file mode 100644
index 08bcbd884395..000000000000
--- a/arch/arm64/crypto/crct10dif-ce-glue.c
+++ /dev/null
@@ -1,132 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Accelerated CRC-T10DIF using arm64 NEON and Crypto Extensions instructions
- *
- * Copyright (C) 2016 - 2017 Linaro Ltd <ard.biesheuvel@linaro.org>
- */
-
-#include <linux/cpufeature.h>
-#include <linux/crc-t10dif.h>
-#include <linux/init.h>
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/string.h>
-
-#include <crypto/internal/hash.h>
-#include <crypto/internal/simd.h>
-
-#include <asm/neon.h>
-#include <asm/simd.h>
-
-#define CRC_T10DIF_PMULL_CHUNK_SIZE	16U
-
-asmlinkage void crc_t10dif_pmull_p8(u16 init_crc, const u8 *buf, size_t len,
-				    u8 out[16]);
-asmlinkage u16 crc_t10dif_pmull_p64(u16 init_crc, const u8 *buf, size_t len);
-
-static int crct10dif_init(struct shash_desc *desc)
-{
-	u16 *crc = shash_desc_ctx(desc);
-
-	*crc = 0;
-	return 0;
-}
-
-static int crct10dif_update_pmull_p8(struct shash_desc *desc, const u8 *data,
-			    unsigned int length)
-{
-	u16 *crcp = shash_desc_ctx(desc);
-	u16 crc = *crcp;
-	u8 buf[16];
-
-	if (length > CRC_T10DIF_PMULL_CHUNK_SIZE && crypto_simd_usable()) {
-		kernel_neon_begin();
-		crc_t10dif_pmull_p8(crc, data, length, buf);
-		kernel_neon_end();
-
-		crc = 0;
-		data = buf;
-		length = sizeof(buf);
-	}
-
-	*crcp = crc_t10dif_generic(crc, data, length);
-	return 0;
-}
-
-static int crct10dif_update_pmull_p64(struct shash_desc *desc, const u8 *data,
-			    unsigned int length)
-{
-	u16 *crc = shash_desc_ctx(desc);
-
-	if (length >= CRC_T10DIF_PMULL_CHUNK_SIZE && crypto_simd_usable()) {
-		kernel_neon_begin();
-		*crc = crc_t10dif_pmull_p64(*crc, data, length);
-		kernel_neon_end();
-	} else {
-		*crc = crc_t10dif_generic(*crc, data, length);
-	}
-
-	return 0;
-}
-
-static int crct10dif_final(struct shash_desc *desc, u8 *out)
-{
-	u16 *crc = shash_desc_ctx(desc);
-
-	*(u16 *)out = *crc;
-	return 0;
-}
-
-static struct shash_alg crc_t10dif_alg[] = {{
-	.digestsize		= CRC_T10DIF_DIGEST_SIZE,
-	.init			= crct10dif_init,
-	.update			= crct10dif_update_pmull_p8,
-	.final			= crct10dif_final,
-	.descsize		= CRC_T10DIF_DIGEST_SIZE,
-
-	.base.cra_name		= "crct10dif",
-	.base.cra_driver_name	= "crct10dif-arm64-neon",
-	.base.cra_priority	= 150,
-	.base.cra_blocksize	= CRC_T10DIF_BLOCK_SIZE,
-	.base.cra_module	= THIS_MODULE,
-}, {
-	.digestsize		= CRC_T10DIF_DIGEST_SIZE,
-	.init			= crct10dif_init,
-	.update			= crct10dif_update_pmull_p64,
-	.final			= crct10dif_final,
-	.descsize		= CRC_T10DIF_DIGEST_SIZE,
-
-	.base.cra_name		= "crct10dif",
-	.base.cra_driver_name	= "crct10dif-arm64-ce",
-	.base.cra_priority	= 200,
-	.base.cra_blocksize	= CRC_T10DIF_BLOCK_SIZE,
-	.base.cra_module	= THIS_MODULE,
-}};
-
-static int __init crc_t10dif_mod_init(void)
-{
-	if (cpu_have_named_feature(PMULL))
-		return crypto_register_shashes(crc_t10dif_alg,
-					       ARRAY_SIZE(crc_t10dif_alg));
-	else
-		/* only register the first array element */
-		return crypto_register_shash(crc_t10dif_alg);
-}
-
-static void __exit crc_t10dif_mod_exit(void)
-{
-	if (cpu_have_named_feature(PMULL))
-		crypto_unregister_shashes(crc_t10dif_alg,
-					  ARRAY_SIZE(crc_t10dif_alg));
-	else
-		crypto_unregister_shash(crc_t10dif_alg);
-}
-
-module_cpu_feature_match(ASIMD, crc_t10dif_mod_init);
-module_exit(crc_t10dif_mod_exit);
-
-MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>");
-MODULE_DESCRIPTION("CRC-T10DIF using arm64 NEON and Crypto Extensions");
-MODULE_LICENSE("GPL v2");
-MODULE_ALIAS_CRYPTO("crct10dif");
-MODULE_ALIAS_CRYPTO("crct10dif-arm64-ce");
diff --git a/arch/arm64/lib/Makefile b/arch/arm64/lib/Makefile
index 8e882f479d98..4d49dff721a8 100644
--- a/arch/arm64/lib/Makefile
+++ b/arch/arm64/lib/Makefile
@@ -13,7 +13,11 @@ 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_CRC_T10DIF_ARCH) += crc-t10dif-arm64.o
+crc-t10dif-arm64-y := crc-t10dif-glue.o crc-t10dif-core.o
 
 obj-$(CONFIG_FUNCTION_ERROR_INJECTION) += error-inject.o
 
diff --git a/arch/arm64/crypto/crct10dif-ce-core.S b/arch/arm64/lib/crc-t10dif-core.S
index 87dd6d46224d..87dd6d46224d 100644
--- a/arch/arm64/crypto/crct10dif-ce-core.S
+++ b/arch/arm64/lib/crc-t10dif-core.S
diff --git a/arch/arm64/lib/crc-t10dif-glue.c b/arch/arm64/lib/crc-t10dif-glue.c
new file mode 100644
index 000000000000..dab7e3796232
--- /dev/null
+++ b/arch/arm64/lib/crc-t10dif-glue.c
@@ -0,0 +1,81 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Accelerated CRC-T10DIF using arm64 NEON and Crypto Extensions instructions
+ *
+ * Copyright (C) 2016 - 2017 Linaro Ltd <ard.biesheuvel@linaro.org>
+ */
+
+#include <linux/cpufeature.h>
+#include <linux/crc-t10dif.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/string.h>
+
+#include <crypto/internal/simd.h>
+
+#include <asm/neon.h>
+#include <asm/simd.h>
+
+static DEFINE_STATIC_KEY_FALSE(have_asimd);
+static DEFINE_STATIC_KEY_FALSE(have_pmull);
+
+#define CRC_T10DIF_PMULL_CHUNK_SIZE	16U
+
+asmlinkage void crc_t10dif_pmull_p8(u16 init_crc, const u8 *buf, size_t len,
+				    u8 out[16]);
+asmlinkage u16 crc_t10dif_pmull_p64(u16 init_crc, const u8 *buf, size_t len);
+
+u16 crc_t10dif_arch(u16 crc, const u8 *data, size_t length)
+{
+	if (length >= CRC_T10DIF_PMULL_CHUNK_SIZE) {
+		if (static_branch_likely(&have_pmull)) {
+			if (crypto_simd_usable()) {
+				kernel_neon_begin();
+				crc = crc_t10dif_pmull_p64(crc, data, length);
+				kernel_neon_end();
+				return crc;
+			}
+		} else if (length > CRC_T10DIF_PMULL_CHUNK_SIZE &&
+			   static_branch_likely(&have_asimd) &&
+			   crypto_simd_usable()) {
+			u8 buf[16];
+
+			kernel_neon_begin();
+			crc_t10dif_pmull_p8(crc, data, length, buf);
+			kernel_neon_end();
+
+			crc = 0;
+			data = buf;
+			length = sizeof(buf);
+		}
+	}
+	return crc_t10dif_generic(crc, data, length);
+}
+EXPORT_SYMBOL(crc_t10dif_arch);
+
+static int __init crc_t10dif_arm64_init(void)
+{
+	if (cpu_have_named_feature(ASIMD)) {
+		static_branch_enable(&have_asimd);
+		if (cpu_have_named_feature(PMULL))
+			static_branch_enable(&have_pmull);
+	}
+	return 0;
+}
+arch_initcall(crc_t10dif_arm64_init);
+
+static void __exit crc_t10dif_arm64_exit(void)
+{
+}
+module_exit(crc_t10dif_arm64_exit);
+
+bool crc_t10dif_is_optimized(void)
+{
+	return static_key_enabled(&have_asimd);
+}
+EXPORT_SYMBOL(crc_t10dif_is_optimized);
+
+MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>");
+MODULE_DESCRIPTION("CRC-T10DIF using arm64 NEON and Crypto Extensions");
+MODULE_LICENSE("GPL v2");
diff --git a/arch/arm64/lib/crc32-glue.c b/arch/arm64/lib/crc32-glue.c
index 295ae3e6b997..15c4c9db573e 100644
--- a/arch/arm64/lib/crc32-glue.c
+++ b/arch/arm64/lib/crc32-glue.c
@@ -2,6 +2,7 @@
 
 #include <linux/crc32.h>
 #include <linux/linkage.h>
+#include <linux/module.h>
 
 #include <asm/alternative.h>
 #include <asm/cpufeature.h>
@@ -21,7 +22,7 @@ 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);
@@ -40,11 +41,12 @@ u32 __pure crc32_le(u32 crc, unsigned char const *p, size_t len)
 
 	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);
+		return crc32c_le_base(crc, p, len);
 
 	if (len >= min_len && cpu_have_named_feature(PMULL) && crypto_simd_usable()) {
 		kernel_neon_begin();
@@ -60,8 +62,9 @@ u32 __pure __crc32c_le(u32 crc, unsigned char const *p, size_t len)
 
 	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);
@@ -80,3 +83,17 @@ u32 __pure crc32_be(u32 crc, unsigned char const *p, size_t len)
 
 	return crc32_be_arm64(crc, p, len);
 }
+EXPORT_SYMBOL(crc32_be_arch);
+
+u32 crc32_optimizations(void)
+{
+	if (alternative_has_cap_likely(ARM64_HAS_CRC32))
+		return CRC32_LE_OPTIMIZATION |
+		       CRC32_BE_OPTIMIZATION |
+		       CRC32C_OPTIMIZATION;
+	return 0;
+}
+EXPORT_SYMBOL(crc32_optimizations);
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("arm64-optimized CRC32 functions");