Re: [PATCH] crypto: arm64/crc32 - merge CRC32 and PMULL instruction based drivers

2017-02-11 Thread Herbert Xu 
On Wed, Feb 01, 2017 at 03:35:40PM +, Ard Biesheuvel wrote:
> The PMULL based CRC32 implementation already contains code based on the
> separate, optional CRC32 instructions to fallback to when operating on
> small quantities of data. We can expose these routines directly on systems
> that lack the 64x64 PMULL instructions but do implement the CRC32 ones,
> which makes the driver that is based solely on those CRC32 instructions
> redundant. So remove it.
> 
> Note that this aligns arm64 with ARM, whose accelerated CRC32 driver
> also combines the CRC32 extension based and the PMULL based versions.
> 
> Signed-off-by: Ard Biesheuvel 

Patch applied.  Thanks.
-- 
Email: Herbert Xu 
Home Page: http://gondor.apana.org.au/~herbert/
PGP Key: http://gondor.apana.org.au/~herbert/pubkey.txt

Re: [PATCH] crypto: arm64/crc32 - merge CRC32 and PMULL instruction based drivers

2017-02-02 Thread Matthias Brugger 



On 02/01/2017 04:35 PM, Ard Biesheuvel wrote:

The PMULL based CRC32 implementation already contains code based on the
separate, optional CRC32 instructions to fallback to when operating on
small quantities of data. We can expose these routines directly on systems
that lack the 64x64 PMULL instructions but do implement the CRC32 ones,
which makes the driver that is based solely on those CRC32 instructions
redundant. So remove it.

Note that this aligns arm64 with ARM, whose accelerated CRC32 driver
also combines the CRC32 extension based and the PMULL based versions.

Signed-off-by: Ard Biesheuvel 
---

This is a meaningful patch by itself imho, but also fixes the issue reported
by Matthias where their v4.8 based GCC does not understand the -mcpu=generic+crc
command line option, resulting in failed builds.



This patch fixes the issue, thanks.
Tested-by: Matthias Brugger 


 arch/arm64/configs/defconfig  |   1 -
 arch/arm64/crypto/Kconfig |   9 +-
 arch/arm64/crypto/Makefile|   4 -
 arch/arm64/crypto/crc32-arm64.c   | 290 
 arch/arm64/crypto/crc32-ce-glue.c |  49 +++-
 5 files changed, 41 insertions(+), 312 deletions(-)

diff --git a/arch/arm64/configs/defconfig b/arch/arm64/configs/defconfig
index 33b744d54739..6fc6f5a2a6e5 100644
--- a/arch/arm64/configs/defconfig
+++ b/arch/arm64/configs/defconfig
@@ -516,4 +516,3 @@ CONFIG_CRYPTO_GHASH_ARM64_CE=y
 CONFIG_CRYPTO_AES_ARM64_CE_CCM=y
 CONFIG_CRYPTO_AES_ARM64_CE_BLK=y
 # CONFIG_CRYPTO_AES_ARM64_NEON_BLK is not set
-CONFIG_CRYPTO_CRC32_ARM64=y
diff --git a/arch/arm64/crypto/Kconfig b/arch/arm64/crypto/Kconfig
index bed7feddfeed..d92293747d63 100644
--- a/arch/arm64/crypto/Kconfig
+++ b/arch/arm64/crypto/Kconfig
@@ -37,8 +37,8 @@ config CRYPTO_CRCT10DIF_ARM64_CE
select CRYPTO_HASH

 config CRYPTO_CRC32_ARM64_CE
-   tristate "CRC32 and CRC32C digest algorithms using PMULL instructions"
-   depends on KERNEL_MODE_NEON && CRC32
+   tristate "CRC32 and CRC32C digest algorithms using ARMv8 extensions"
+   depends on CRC32
select CRYPTO_HASH

 config CRYPTO_AES_ARM64
@@ -71,11 +71,6 @@ config CRYPTO_AES_ARM64_NEON_BLK
select CRYPTO_AES
select CRYPTO_SIMD

-config CRYPTO_CRC32_ARM64
-   tristate "CRC32 and CRC32C using optional ARMv8 instructions"
-   depends on ARM64
-   select CRYPTO_HASH
-
 config CRYPTO_CHACHA20_NEON
tristate "NEON accelerated ChaCha20 symmetric cipher"
depends on KERNEL_MODE_NEON
diff --git a/arch/arm64/crypto/Makefile b/arch/arm64/crypto/Makefile
index d1ae1b9cbe70..b5edc5918c28 100644
--- a/arch/arm64/crypto/Makefile
+++ b/arch/arm64/crypto/Makefile
@@ -55,10 +55,6 @@ AFLAGS_aes-neon.o:= -DINTERLEAVE=4

 CFLAGS_aes-glue-ce.o   := -DUSE_V8_CRYPTO_EXTENSIONS

-obj-$(CONFIG_CRYPTO_CRC32_ARM64) += crc32-arm64.o
-
-CFLAGS_crc32-arm64.o   := -mcpu=generic+crc
-
 $(obj)/aes-glue-%.o: $(src)/aes-glue.c FORCE
$(call if_changed_rule,cc_o_c)

diff --git a/arch/arm64/crypto/crc32-arm64.c b/arch/arm64/crypto/crc32-arm64.c
deleted file mode 100644
index 6a37c3c6b11d..
--- a/arch/arm64/crypto/crc32-arm64.c
+++ /dev/null
@@ -1,290 +0,0 @@
-/*
- * crc32-arm64.c - CRC32 and CRC32C using optional ARMv8 instructions
- *
- * Module based on crypto/crc32c_generic.c
- *
- * CRC32 loop taken from Ed Nevill's Hadoop CRC patch
- * 
http://mail-archives.apache.org/mod_mbox/hadoop-common-dev/201406.mbox/%3C1403687030.3355.19.camel%40localhost.localdomain%3E
- *
- * Using inline assembly instead of intrinsics in order to be backwards
- * compatible with older compilers.
- *
- * Copyright (C) 2014 Linaro Ltd 
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#include 
-#include 
-#include 
-#include 
-#include 
-#include 
-
-#include 
-
-MODULE_AUTHOR("Yazen Ghannam ");
-MODULE_DESCRIPTION("CRC32 and CRC32C using optional ARMv8 instructions");
-MODULE_LICENSE("GPL v2");
-
-#define CRC32X(crc, value) __asm__("crc32x %w[c], %w[c], 
%x[v]":[c]"+r"(crc):[v]"r"(value))
-#define CRC32W(crc, value) __asm__("crc32w %w[c], %w[c], 
%w[v]":[c]"+r"(crc):[v]"r"(value))
-#define CRC32H(crc, value) __asm__("crc32h %w[c], %w[c], 
%w[v]":[c]"+r"(crc):[v]"r"(value))
-#define CRC32B(crc, value) __asm__("crc32b %w[c], %w[c], 
%w[v]":[c]"+r"(crc):[v]"r"(value))
-#define CRC32CX(crc, value) __asm__("crc32cx %w[c], %w[c], 
%x[v]":[c]"+r"(crc):[v]"r"(value))
-#define CRC32CW(crc, value) __asm__("crc32cw %w[c], %w[c], 
%w[v]":[c]"+r"(crc):[v]"r"(value))
-#define CRC32CH(crc, value) __asm__("crc32ch %w[c], %w[c], 
%w[v]":[c]"+r"(crc):[v]"r"(value))
-#define CRC32CB(crc, value) __asm__("crc32cb %w[c], %w[c], 
%w[v]":[c]"+r"(crc):[v]"r"(value))
-
-static u32 crc32_arm64_le_hw(u32 crc, const u8 *p, unsigned int

[PATCH] crypto: arm64/crc32 - merge CRC32 and PMULL instruction based drivers

2017-02-01 Thread Ard Biesheuvel 
The PMULL based CRC32 implementation already contains code based on the
separate, optional CRC32 instructions to fallback to when operating on
small quantities of data. We can expose these routines directly on systems
that lack the 64x64 PMULL instructions but do implement the CRC32 ones,
which makes the driver that is based solely on those CRC32 instructions
redundant. So remove it.

Note that this aligns arm64 with ARM, whose accelerated CRC32 driver
also combines the CRC32 extension based and the PMULL based versions.

Signed-off-by: Ard Biesheuvel 
---

This is a meaningful patch by itself imho, but also fixes the issue reported
by Matthias where their v4.8 based GCC does not understand the -mcpu=generic+crc
command line option, resulting in failed builds.

 arch/arm64/configs/defconfig  |   1 -
 arch/arm64/crypto/Kconfig |   9 +-
 arch/arm64/crypto/Makefile|   4 -
 arch/arm64/crypto/crc32-arm64.c   | 290 
 arch/arm64/crypto/crc32-ce-glue.c |  49 +++-
 5 files changed, 41 insertions(+), 312 deletions(-)

diff --git a/arch/arm64/configs/defconfig b/arch/arm64/configs/defconfig
index 33b744d54739..6fc6f5a2a6e5 100644
--- a/arch/arm64/configs/defconfig
+++ b/arch/arm64/configs/defconfig
@@ -516,4 +516,3 @@ CONFIG_CRYPTO_GHASH_ARM64_CE=y
 CONFIG_CRYPTO_AES_ARM64_CE_CCM=y
 CONFIG_CRYPTO_AES_ARM64_CE_BLK=y
 # CONFIG_CRYPTO_AES_ARM64_NEON_BLK is not set
-CONFIG_CRYPTO_CRC32_ARM64=y
diff --git a/arch/arm64/crypto/Kconfig b/arch/arm64/crypto/Kconfig
index bed7feddfeed..d92293747d63 100644
--- a/arch/arm64/crypto/Kconfig
+++ b/arch/arm64/crypto/Kconfig
@@ -37,8 +37,8 @@ config CRYPTO_CRCT10DIF_ARM64_CE
select CRYPTO_HASH
 
 config CRYPTO_CRC32_ARM64_CE
-   tristate "CRC32 and CRC32C digest algorithms using PMULL instructions"
-   depends on KERNEL_MODE_NEON && CRC32
+   tristate "CRC32 and CRC32C digest algorithms using ARMv8 extensions"
+   depends on CRC32
select CRYPTO_HASH
 
 config CRYPTO_AES_ARM64
@@ -71,11 +71,6 @@ config CRYPTO_AES_ARM64_NEON_BLK
select CRYPTO_AES
select CRYPTO_SIMD
 
-config CRYPTO_CRC32_ARM64
-   tristate "CRC32 and CRC32C using optional ARMv8 instructions"
-   depends on ARM64
-   select CRYPTO_HASH
-
 config CRYPTO_CHACHA20_NEON
tristate "NEON accelerated ChaCha20 symmetric cipher"
depends on KERNEL_MODE_NEON
diff --git a/arch/arm64/crypto/Makefile b/arch/arm64/crypto/Makefile
index d1ae1b9cbe70..b5edc5918c28 100644
--- a/arch/arm64/crypto/Makefile
+++ b/arch/arm64/crypto/Makefile
@@ -55,10 +55,6 @@ AFLAGS_aes-neon.o:= -DINTERLEAVE=4
 
 CFLAGS_aes-glue-ce.o   := -DUSE_V8_CRYPTO_EXTENSIONS
 
-obj-$(CONFIG_CRYPTO_CRC32_ARM64) += crc32-arm64.o
-
-CFLAGS_crc32-arm64.o   := -mcpu=generic+crc
-
 $(obj)/aes-glue-%.o: $(src)/aes-glue.c FORCE
$(call if_changed_rule,cc_o_c)
 
diff --git a/arch/arm64/crypto/crc32-arm64.c b/arch/arm64/crypto/crc32-arm64.c
deleted file mode 100644
index 6a37c3c6b11d..
--- a/arch/arm64/crypto/crc32-arm64.c
+++ /dev/null
@@ -1,290 +0,0 @@
-/*
- * crc32-arm64.c - CRC32 and CRC32C using optional ARMv8 instructions
- *
- * Module based on crypto/crc32c_generic.c
- *
- * CRC32 loop taken from Ed Nevill's Hadoop CRC patch
- * 
http://mail-archives.apache.org/mod_mbox/hadoop-common-dev/201406.mbox/%3C1403687030.3355.19.camel%40localhost.localdomain%3E
- *
- * Using inline assembly instead of intrinsics in order to be backwards
- * compatible with older compilers.
- *
- * Copyright (C) 2014 Linaro Ltd 
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#include 
-#include 
-#include 
-#include 
-#include 
-#include 
-
-#include 
-
-MODULE_AUTHOR("Yazen Ghannam ");
-MODULE_DESCRIPTION("CRC32 and CRC32C using optional ARMv8 instructions");
-MODULE_LICENSE("GPL v2");
-
-#define CRC32X(crc, value) __asm__("crc32x %w[c], %w[c], 
%x[v]":[c]"+r"(crc):[v]"r"(value))
-#define CRC32W(crc, value) __asm__("crc32w %w[c], %w[c], 
%w[v]":[c]"+r"(crc):[v]"r"(value))
-#define CRC32H(crc, value) __asm__("crc32h %w[c], %w[c], 
%w[v]":[c]"+r"(crc):[v]"r"(value))
-#define CRC32B(crc, value) __asm__("crc32b %w[c], %w[c], 
%w[v]":[c]"+r"(crc):[v]"r"(value))
-#define CRC32CX(crc, value) __asm__("crc32cx %w[c], %w[c], 
%x[v]":[c]"+r"(crc):[v]"r"(value))
-#define CRC32CW(crc, value) __asm__("crc32cw %w[c], %w[c], 
%w[v]":[c]"+r"(crc):[v]"r"(value))
-#define CRC32CH(crc, value) __asm__("crc32ch %w[c], %w[c], 
%w[v]":[c]"+r"(crc):[v]"r"(value))
-#define CRC32CB(crc, value) __asm__("crc32cb %w[c], %w[c], 
%w[v]":[c]"+r"(crc):[v]"r"(value))
-
-static u32 crc32_arm64_le_hw(u32 crc, const u8 *p, unsigned int len)
-{
-   s64 length = len;
-
-   while ((length -= sizeof(u64)) >= 0) {
-   CRC32X(crc,