Merge git://git.kernel.org/pub/scm/linux/kernel/git/herbert/crypto-2.6

Pull crypto update from Herbert Xu:

 - XTS mode optimisation for twofish/cast6/camellia/aes on x86

 - AVX2/x86_64 implementation for blowfish/twofish/serpent/camellia

 - SSSE3/AVX/AVX2 optimisations for sha256/sha512

 - Added driver for SAHARA2 crypto accelerator

 - Fix for GMAC when used in non-IPsec secnarios

 - Added generic CMAC implementation (including IPsec glue)

 - IP update for crypto/atmel

 - Support for more than one device in hwrng/timeriomem

 - Added Broadcom BCM2835 RNG driver

 - Misc fixes

* git://git.kernel.org/pub/scm/linux/kernel/git/herbert/crypto-2.6: (59 commits)
  crypto: caam - fix job ring cleanup code
  crypto: camellia - add AVX2/AES-NI/x86_64 assembler implementation of camellia cipher
  crypto: serpent - add AVX2/x86_64 assembler implementation of serpent cipher
  crypto: twofish - add AVX2/x86_64 assembler implementation of twofish cipher
  crypto: blowfish - add AVX2/x86_64 implementation of blowfish cipher
  crypto: tcrypt - add async cipher speed tests for blowfish
  crypto: testmgr - extend camellia test-vectors for camellia-aesni/avx2
  crypto: aesni_intel - fix Kconfig problem with CRYPTO_GLUE_HELPER_X86
  crypto: aesni_intel - add more optimized XTS mode for x86-64
  crypto: x86/camellia-aesni-avx - add more optimized XTS code
  crypto: cast6-avx: use new optimized XTS code
  crypto: x86/twofish-avx - use optimized XTS code
  crypto: x86 - add more optimized XTS-mode for serpent-avx
  xfrm: add rfc4494 AES-CMAC-96 support
  crypto: add CMAC support to CryptoAPI
  crypto: testmgr - add empty test vectors for null ciphers
  crypto: testmgr - add AES GMAC test vectors
  crypto: gcm - fix rfc4543 to handle async crypto correctly
  crypto: gcm - make GMAC work when dst and src are different
  hwrng: timeriomem - added devicetree hooks
  ...

Documentation/devicetree/bindings/crypto/fsl-imx-sahara.txt

@@ -0,0 +1,15 @@
+Freescale SAHARA Cryptographic Accelerator included in some i.MX chips.
+Currently only i.MX27 is supported.
+
+Required properties:
+- compatible : Should be "fsl,<soc>-sahara"
+- reg : Should contain SAHARA registers location and length
+- interrupts : Should contain SAHARA interrupt number
+
+Example:
+
+sah@10025000 {
+	compatible = "fsl,imx27-sahara";
+	reg = <	0x10025000 0x800>;
+	interrupts = <75>;
+};

Documentation/devicetree/bindings/hwrng/timeriomem_rng.txt

@@ -0,0 +1,18 @@
+HWRNG support for the timeriomem_rng driver
+
+Required properties:
+- compatible : "timeriomem_rng"
+- reg : base address to sample from
+- period : wait time in microseconds to use between samples
+
+N.B. currently 'reg' must be four bytes wide and aligned
+
+Example:
+
+hwrng@44 {
+	#address-cells = <1>;
+	#size-cells = <1>;
+	compatible = "timeriomem_rng";
+	reg = <0x44 0x04>;
+	period = <1000000>;
+};

Documentation/devicetree/bindings/rng/brcm,bcm2835.txt

@@ -0,0 +1,13 @@
+BCM2835 Random number generator
+
+Required properties:
+
+- compatible : should be "brcm,bcm2835-rng"
+- reg : Specifies base physical address and size of the registers.
+
+Example:
+
+rng {
+        compatible = "brcm,bcm2835-rng";
+        reg = <0x7e104000 0x10>;
+};

Documentation/hw_random.txt

@@ -63,7 +63,7 @@ Intel RNG Driver notes:
 
 	* FIXME: support poll(2)
 
-	NOTE: request_mem_region was removed, for two reasons:
+	NOTE: request_mem_region was removed, for three reasons:
 	1) Only one RNG is supported by this driver, 2) The location
 	used by the RNG is a fixed location in MMIO-addressable memory,
 	3) users with properly working BIOS e820 handling will always

arch/arm/mach-at91/at91sam9g45_devices.c

@@ -18,7 +18,7 @@
 #include <linux/platform_device.h>
 #include <linux/i2c-gpio.h>
 #include <linux/atmel-mci.h>
-#include <linux/platform_data/atmel-aes.h>
+#include <linux/platform_data/crypto-atmel.h>
 
 #include <linux/platform_data/at91_adc.h>
 
@@ -1900,7 +1900,8 @@ static void __init at91_add_device_tdes(void) {}
  * -------------------------------------------------------------------- */
 
 #if defined(CONFIG_CRYPTO_DEV_ATMEL_AES) || defined(CONFIG_CRYPTO_DEV_ATMEL_AES_MODULE)
-static struct aes_platform_data aes_data;
+static struct crypto_platform_data aes_data;
+static struct crypto_dma_data alt_atslave;
 static u64 aes_dmamask = DMA_BIT_MASK(32);
 
 static struct resource aes_resources[] = {
@@ -1931,23 +1932,20 @@ static struct platform_device at91sam9g45_aes_device = {
 static void __init at91_add_device_aes(void)
 {
 	struct at_dma_slave	*atslave;
-	struct aes_dma_data	*alt_atslave;
-
-	alt_atslave = kzalloc(sizeof(struct aes_dma_data), GFP_KERNEL);
 
 	/* DMA TX slave channel configuration */
-	atslave = &alt_atslave->txdata;
+	atslave = &alt_atslave.txdata;
 	atslave->dma_dev = &at_hdmac_device.dev;
 	atslave->cfg = ATC_FIFOCFG_ENOUGHSPACE	| ATC_SRC_H2SEL_HW |
 						ATC_SRC_PER(AT_DMA_ID_AES_RX);
 
 	/* DMA RX slave channel configuration */
-	atslave = &alt_atslave->rxdata;
+	atslave = &alt_atslave.rxdata;
 	atslave->dma_dev = &at_hdmac_device.dev;
 	atslave->cfg = ATC_FIFOCFG_ENOUGHSPACE	| ATC_DST_H2SEL_HW |
 						ATC_DST_PER(AT_DMA_ID_AES_TX);
 
-	aes_data.dma_slave = alt_atslave;
+	aes_data.dma_slave = &alt_atslave;
 	platform_device_register(&at91sam9g45_aes_device);
 }
 #else

arch/x86/crypto/Makefile

@@ -2,6 +2,10 @@
 # Arch-specific CryptoAPI modules.
 #
 
+avx_supported := $(call as-instr,vpxor %xmm0$(comma)%xmm0$(comma)%xmm0,yes,no)
+avx2_supported := $(call as-instr,vpgatherdd %ymm0$(comma)(%eax$(comma)%ymm1\
+					$(comma)4)$(comma)%ymm2,yes,no)
+
 obj-$(CONFIG_CRYPTO_ABLK_HELPER_X86) += ablk_helper.o
 obj-$(CONFIG_CRYPTO_GLUE_HELPER_X86) += glue_helper.o
 
@@ -12,22 +16,37 @@ obj-$(CONFIG_CRYPTO_SERPENT_SSE2_586) += serpent-sse2-i586.o
 
 obj-$(CONFIG_CRYPTO_AES_X86_64) += aes-x86_64.o
 obj-$(CONFIG_CRYPTO_CAMELLIA_X86_64) += camellia-x86_64.o
-obj-$(CONFIG_CRYPTO_CAMELLIA_AESNI_AVX_X86_64) += camellia-aesni-avx-x86_64.o
-obj-$(CONFIG_CRYPTO_CAST5_AVX_X86_64) += cast5-avx-x86_64.o
-obj-$(CONFIG_CRYPTO_CAST6_AVX_X86_64) += cast6-avx-x86_64.o
 obj-$(CONFIG_CRYPTO_BLOWFISH_X86_64) += blowfish-x86_64.o
 obj-$(CONFIG_CRYPTO_TWOFISH_X86_64) += twofish-x86_64.o
 obj-$(CONFIG_CRYPTO_TWOFISH_X86_64_3WAY) += twofish-x86_64-3way.o
-obj-$(CONFIG_CRYPTO_TWOFISH_AVX_X86_64) += twofish-avx-x86_64.o
 obj-$(CONFIG_CRYPTO_SALSA20_X86_64) += salsa20-x86_64.o
 obj-$(CONFIG_CRYPTO_SERPENT_SSE2_X86_64) += serpent-sse2-x86_64.o
-obj-$(CONFIG_CRYPTO_SERPENT_AVX_X86_64) += serpent-avx-x86_64.o
 obj-$(CONFIG_CRYPTO_AES_NI_INTEL) += aesni-intel.o
 obj-$(CONFIG_CRYPTO_GHASH_CLMUL_NI_INTEL) += ghash-clmulni-intel.o
 
 obj-$(CONFIG_CRYPTO_CRC32C_INTEL) += crc32c-intel.o
 obj-$(CONFIG_CRYPTO_SHA1_SSSE3) += sha1-ssse3.o
 obj-$(CONFIG_CRYPTO_CRC32_PCLMUL) += crc32-pclmul.o
+obj-$(CONFIG_CRYPTO_SHA256_SSSE3) += sha256-ssse3.o
+obj-$(CONFIG_CRYPTO_SHA512_SSSE3) += sha512-ssse3.o
+
+# These modules require assembler to support AVX.
+ifeq ($(avx_supported),yes)
+	obj-$(CONFIG_CRYPTO_CAMELLIA_AESNI_AVX_X86_64) += \
+						camellia-aesni-avx-x86_64.o
+	obj-$(CONFIG_CRYPTO_CAST5_AVX_X86_64) += cast5-avx-x86_64.o
+	obj-$(CONFIG_CRYPTO_CAST6_AVX_X86_64) += cast6-avx-x86_64.o
+	obj-$(CONFIG_CRYPTO_TWOFISH_AVX_X86_64) += twofish-avx-x86_64.o
+	obj-$(CONFIG_CRYPTO_SERPENT_AVX_X86_64) += serpent-avx-x86_64.o
+endif
+
+# These modules require assembler to support AVX2.
+ifeq ($(avx2_supported),yes)
+	obj-$(CONFIG_CRYPTO_BLOWFISH_AVX2_X86_64) += blowfish-avx2.o
+	obj-$(CONFIG_CRYPTO_CAMELLIA_AESNI_AVX2_X86_64) += camellia-aesni-avx2.o
+	obj-$(CONFIG_CRYPTO_SERPENT_AVX2_X86_64) += serpent-avx2.o
+	obj-$(CONFIG_CRYPTO_TWOFISH_AVX2_X86_64) += twofish-avx2.o
+endif
 
 aes-i586-y := aes-i586-asm_32.o aes_glue.o
 twofish-i586-y := twofish-i586-asm_32.o twofish_glue.o
@@ -36,21 +55,35 @@ serpent-sse2-i586-y := serpent-sse2-i586-asm_32.o serpent_sse2_glue.o
 
 aes-x86_64-y := aes-x86_64-asm_64.o aes_glue.o
 camellia-x86_64-y := camellia-x86_64-asm_64.o camellia_glue.o
-camellia-aesni-avx-x86_64-y := camellia-aesni-avx-asm_64.o \
-			       camellia_aesni_avx_glue.o
-cast5-avx-x86_64-y := cast5-avx-x86_64-asm_64.o cast5_avx_glue.o
-cast6-avx-x86_64-y := cast6-avx-x86_64-asm_64.o cast6_avx_glue.o
 blowfish-x86_64-y := blowfish-x86_64-asm_64.o blowfish_glue.o
 twofish-x86_64-y := twofish-x86_64-asm_64.o twofish_glue.o
 twofish-x86_64-3way-y := twofish-x86_64-asm_64-3way.o twofish_glue_3way.o
-twofish-avx-x86_64-y := twofish-avx-x86_64-asm_64.o twofish_avx_glue.o
 salsa20-x86_64-y := salsa20-x86_64-asm_64.o salsa20_glue.o
 serpent-sse2-x86_64-y := serpent-sse2-x86_64-asm_64.o serpent_sse2_glue.o
-serpent-avx-x86_64-y := serpent-avx-x86_64-asm_64.o serpent_avx_glue.o
+
+ifeq ($(avx_supported),yes)
+	camellia-aesni-avx-x86_64-y := camellia-aesni-avx-asm_64.o \
+					camellia_aesni_avx_glue.o
+	cast5-avx-x86_64-y := cast5-avx-x86_64-asm_64.o cast5_avx_glue.o
+	cast6-avx-x86_64-y := cast6-avx-x86_64-asm_64.o cast6_avx_glue.o
+	twofish-avx-x86_64-y := twofish-avx-x86_64-asm_64.o \
+				twofish_avx_glue.o
+	serpent-avx-x86_64-y := serpent-avx-x86_64-asm_64.o \
+				serpent_avx_glue.o
+endif
+
+ifeq ($(avx2_supported),yes)
+	blowfish-avx2-y := blowfish-avx2-asm_64.o blowfish_avx2_glue.o
+	camellia-aesni-avx2-y := camellia-aesni-avx2-asm_64.o camellia_aesni_avx2_glue.o
+	serpent-avx2-y := serpent-avx2-asm_64.o serpent_avx2_glue.o
+	twofish-avx2-y := twofish-avx2-asm_64.o twofish_avx2_glue.o
+endif
 
 aesni-intel-y := aesni-intel_asm.o aesni-intel_glue.o fpu.o
 ghash-clmulni-intel-y := ghash-clmulni-intel_asm.o ghash-clmulni-intel_glue.o
 sha1-ssse3-y := sha1_ssse3_asm.o sha1_ssse3_glue.o
 crc32c-intel-y := crc32c-intel_glue.o
-crc32c-intel-$(CONFIG_CRYPTO_CRC32C_X86_64) += crc32c-pcl-intel-asm_64.o
+crc32c-intel-$(CONFIG_64BIT) += crc32c-pcl-intel-asm_64.o
 crc32-pclmul-y := crc32-pclmul_asm.o crc32-pclmul_glue.o
+sha256-ssse3-y := sha256-ssse3-asm.o sha256-avx-asm.o sha256-avx2-asm.o sha256_ssse3_glue.o
+sha512-ssse3-y := sha512-ssse3-asm.o sha512-avx-asm.o sha512-avx2-asm.o sha512_ssse3_glue.o

arch/x86/crypto/aesni-intel_asm.S

@@ -34,6 +34,10 @@
 
 #ifdef __x86_64__
 .data
+.align 16
+.Lgf128mul_x_ble_mask:
+	.octa 0x00000000000000010000000000000087
+
 POLY:   .octa 0xC2000000000000000000000000000001
 TWOONE: .octa 0x00000001000000000000000000000001
 
@@ -105,6 +109,8 @@ enc:        .octa 0x2
 #define CTR	%xmm11
 #define INC	%xmm12
 
+#define GF128MUL_MASK %xmm10
+
 #ifdef __x86_64__
 #define AREG	%rax
 #define KEYP	%rdi
@@ -2636,4 +2642,115 @@ ENTRY(aesni_ctr_enc)
 .Lctr_enc_just_ret:
 	ret
 ENDPROC(aesni_ctr_enc)
+
+/*
+ * _aesni_gf128mul_x_ble:		internal ABI
+ *	Multiply in GF(2^128) for XTS IVs
+ * input:
+ *	IV:	current IV
+ *	GF128MUL_MASK == mask with 0x87 and 0x01
+ * output:
+ *	IV:	next IV
+ * changed:
+ *	CTR:	== temporary value
+ */
+#define _aesni_gf128mul_x_ble() \
+	pshufd $0x13, IV, CTR; \
+	paddq IV, IV; \
+	psrad $31, CTR; \
+	pand GF128MUL_MASK, CTR; \
+	pxor CTR, IV;
+
+/*
+ * void aesni_xts_crypt8(struct crypto_aes_ctx *ctx, const u8 *dst, u8 *src,
+ *			 bool enc, u8 *iv)
+ */
+ENTRY(aesni_xts_crypt8)
+	cmpb $0, %cl
+	movl $0, %ecx
+	movl $240, %r10d
+	leaq _aesni_enc4, %r11
+	leaq _aesni_dec4, %rax
+	cmovel %r10d, %ecx
+	cmoveq %rax, %r11
+
+	movdqa .Lgf128mul_x_ble_mask, GF128MUL_MASK
+	movups (IVP), IV
+
+	mov 480(KEYP), KLEN
+	addq %rcx, KEYP
+
+	movdqa IV, STATE1
+	pxor 0x00(INP), STATE1
+	movdqu IV, 0x00(OUTP)
+
+	_aesni_gf128mul_x_ble()
+	movdqa IV, STATE2
+	pxor 0x10(INP), STATE2
+	movdqu IV, 0x10(OUTP)
+
+	_aesni_gf128mul_x_ble()
+	movdqa IV, STATE3
+	pxor 0x20(INP), STATE3
+	movdqu IV, 0x20(OUTP)
+
+	_aesni_gf128mul_x_ble()
+	movdqa IV, STATE4
+	pxor 0x30(INP), STATE4
+	movdqu IV, 0x30(OUTP)
+
+	call *%r11
+
+	pxor 0x00(OUTP), STATE1
+	movdqu STATE1, 0x00(OUTP)
+
+	_aesni_gf128mul_x_ble()
+	movdqa IV, STATE1
+	pxor 0x40(INP), STATE1
+	movdqu IV, 0x40(OUTP)
+
+	pxor 0x10(OUTP), STATE2
+	movdqu STATE2, 0x10(OUTP)
+
+	_aesni_gf128mul_x_ble()
+	movdqa IV, STATE2
+	pxor 0x50(INP), STATE2
+	movdqu IV, 0x50(OUTP)
+
+	pxor 0x20(OUTP), STATE3
+	movdqu STATE3, 0x20(OUTP)
+
+	_aesni_gf128mul_x_ble()
+	movdqa IV, STATE3
+	pxor 0x60(INP), STATE3
+	movdqu IV, 0x60(OUTP)
+
+	pxor 0x30(OUTP), STATE4
+	movdqu STATE4, 0x30(OUTP)
+
+	_aesni_gf128mul_x_ble()
+	movdqa IV, STATE4
+	pxor 0x70(INP), STATE4
+	movdqu IV, 0x70(OUTP)
+
+	_aesni_gf128mul_x_ble()
+	movups IV, (IVP)
+
+	call *%r11
+
+	pxor 0x40(OUTP), STATE1
+	movdqu STATE1, 0x40(OUTP)
+
+	pxor 0x50(OUTP), STATE2
+	movdqu STATE2, 0x50(OUTP)
+
+	pxor 0x60(OUTP), STATE3
+	movdqu STATE3, 0x60(OUTP)
+
+	pxor 0x70(OUTP), STATE4
+	movdqu STATE4, 0x70(OUTP)
+
+	ret
+ENDPROC(aesni_xts_crypt8)
+
 #endif