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

Pull crypto updates from Herbert Xu:
 "Here is the crypto update for 3.15:
   - Added 3DES driver for OMAP4/AM43xx
   - Added AVX2 acceleration for SHA
   - Added hash-only AEAD algorithms in caam
   - Removed tegra driver as it is not functioning and the hardware is
     too slow
   - Allow blkcipher walks over AEAD (needed for ARM)
   - Fixed unprotected FPU/SSE access in ghash-clmulni-intel
   - Fixed highmem crash in omap-sham
   - Add (zero entropy) randomness when initialising hardware RNGs
   - Fixed unaligned ahash comletion functions
   - Added soft module depedency for crc32c for initrds that use crc32c"

* git://git.kernel.org/pub/scm/linux/kernel/git/herbert/crypto-2.6: (60 commits)
  crypto: ghash-clmulni-intel - use C implementation for setkey()
  crypto: x86/sha1 - reduce size of the AVX2 asm implementation
  crypto: x86/sha1 - fix stack alignment of AVX2 variant
  crypto: x86/sha1 - re-enable the AVX variant
  crypto: sha - SHA1 transform x86_64 AVX2
  crypto: crypto_wq - Fix late crypto work queue initialization
  crypto: caam - add missing key_dma unmap
  crypto: caam - add support for aead null encryption
  crypto: testmgr - add aead null encryption test vectors
  crypto: export NULL algorithms defines
  crypto: caam - remove error propagation handling
  crypto: hash - Simplify the ahash_finup implementation
  crypto: hash - Pull out the functions to save/restore request
  crypto: hash - Fix the pointer voodoo in unaligned ahash
  crypto: caam - Fix first parameter to caam_init_rng
  crypto: omap-sham - Map SG pages if they are HIGHMEM before accessing
  crypto: caam - Dynamic memory allocation for caam_rng_ctx object
  crypto: allow blkcipher walks over AEAD data
  crypto: remove direct blkcipher_walk dependency on transform
  hwrng: add randomness to system from rng sources
  ...

arch/x86/crypto/Makefile

@@ -79,6 +79,9 @@ aesni-intel-y := aesni-intel_asm.o aesni-intel_glue.o fpu.o
 aesni-intel-$(CONFIG_64BIT) += aesni-intel_avx-x86_64.o
 ghash-clmulni-intel-y := ghash-clmulni-intel_asm.o ghash-clmulni-intel_glue.o
 sha1-ssse3-y := sha1_ssse3_asm.o sha1_ssse3_glue.o
+ifeq ($(avx2_supported),yes)
+sha1-ssse3-y += sha1_avx2_x86_64_asm.o
+endif
 crc32c-intel-y := crc32c-intel_glue.o
 crc32c-intel-$(CONFIG_64BIT) += crc32c-pcl-intel-asm_64.o
 crc32-pclmul-y := crc32-pclmul_asm.o crc32-pclmul_glue.o

arch/x86/crypto/blowfish_glue.c

@@ -223,9 +223,6 @@ static unsigned int __cbc_decrypt(struct blkcipher_desc *desc,
 			src -= 1;
 			dst -= 1;
 		} while (nbytes >= bsize * 4);
-
-		if (nbytes < bsize)
-			goto done;
 	}
 
 	/* Handle leftovers */

arch/x86/crypto/cast5_avx_glue.c

@@ -203,9 +203,6 @@ static unsigned int __cbc_decrypt(struct blkcipher_desc *desc,
 			src -= 1;
 			dst -= 1;
 		} while (nbytes >= bsize * CAST5_PARALLEL_BLOCKS);
-
-		if (nbytes < bsize)
-			goto done;
 	}
 
 	/* Handle leftovers */

arch/x86/crypto/ghash-clmulni-intel_asm.S

@@ -24,10 +24,6 @@
 .align 16
 .Lbswap_mask:
 	.octa 0x000102030405060708090a0b0c0d0e0f
-.Lpoly:
-	.octa 0xc2000000000000000000000000000001
-.Ltwo_one:
-	.octa 0x00000001000000000000000000000001
 
 #define DATA	%xmm0
 #define SHASH	%xmm1
@@ -134,28 +130,3 @@ ENTRY(clmul_ghash_update)
 .Lupdate_just_ret:
 	ret
 ENDPROC(clmul_ghash_update)
-
-/*
- * void clmul_ghash_setkey(be128 *shash, const u8 *key);
- *
- * Calculate hash_key << 1 mod poly
- */
-ENTRY(clmul_ghash_setkey)
-	movaps .Lbswap_mask, BSWAP
-	movups (%rsi), %xmm0
-	PSHUFB_XMM BSWAP %xmm0
-	movaps %xmm0, %xmm1
-	psllq $1, %xmm0
-	psrlq $63, %xmm1
-	movaps %xmm1, %xmm2
-	pslldq $8, %xmm1
-	psrldq $8, %xmm2
-	por %xmm1, %xmm0
-	# reduction
-	pshufd $0b00100100, %xmm2, %xmm1
-	pcmpeqd .Ltwo_one, %xmm1
-	pand .Lpoly, %xmm1
-	pxor %xmm1, %xmm0
-	movups %xmm0, (%rdi)
-	ret
-ENDPROC(clmul_ghash_setkey)

arch/x86/crypto/ghash-clmulni-intel_glue.c

@@ -30,8 +30,6 @@ void clmul_ghash_mul(char *dst, const be128 *shash);
 void clmul_ghash_update(char *dst, const char *src, unsigned int srclen,
 			const be128 *shash);
 
-void clmul_ghash_setkey(be128 *shash, const u8 *key);
-
 struct ghash_async_ctx {
 	struct cryptd_ahash *cryptd_tfm;
 };
@@ -58,13 +56,23 @@ static int ghash_setkey(struct crypto_shash *tfm,
 			const u8 *key, unsigned int keylen)
 {
 	struct ghash_ctx *ctx = crypto_shash_ctx(tfm);
+	be128 *x = (be128 *)key;
+	u64 a, b;
 
 	if (keylen != GHASH_BLOCK_SIZE) {
 		crypto_shash_set_flags(tfm, CRYPTO_TFM_RES_BAD_KEY_LEN);
 		return -EINVAL;
 	}
 
-	clmul_ghash_setkey(&ctx->shash, key);
+	/* perform multiplication by 'x' in GF(2^128) */
+	a = be64_to_cpu(x->a);
+	b = be64_to_cpu(x->b);
+
+	ctx->shash.a = (__be64)((b << 1) | (a >> 63));
+	ctx->shash.b = (__be64)((a << 1) | (b >> 63));
+
+	if (a >> 63)
+		ctx->shash.b ^= cpu_to_be64(0xc2);
 
 	return 0;
 }

arch/x86/crypto/sha1_avx2_x86_64_asm.S

+/*
+ *	Implement fast SHA-1 with AVX2 instructions. (x86_64)
+ *
+ * This file is provided under a dual BSD/GPLv2 license.  When using or
+ * redistributing this file, you may do so under either license.
+ *
+ * GPL LICENSE SUMMARY
+ *
+ * Copyright(c) 2014 Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of version 2 of the GNU General Public License as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * Contact Information:
+ * Ilya Albrekht <ilya.albrekht@intel.com>
+ * Maxim Locktyukhin <maxim.locktyukhin@intel.com>
+ * Ronen Zohar <ronen.zohar@intel.com>
+ * Chandramouli Narayanan <mouli@linux.intel.com>
+ *
+ * BSD LICENSE
+ *
+ * Copyright(c) 2014 Intel Corporation.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ *
+ * Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ * Redistributions in binary form must reproduce the above copyright
+ * notice, this list of conditions and the following disclaimer in
+ * the documentation and/or other materials provided with the
+ * distribution.
+ * Neither the name of Intel Corporation nor the names of its
+ * contributors may be used to endorse or promote products derived
+ * from this software without specific prior written permission.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ *
+ */
+
+/*
+ * SHA-1 implementation with Intel(R) AVX2 instruction set extensions.
+ *
+ *This implementation is based on the previous SSSE3 release:
+ *Visit http://software.intel.com/en-us/articles/
+ *and refer to improving-the-performance-of-the-secure-hash-algorithm-1/
+ *
+ *Updates 20-byte SHA-1 record in 'hash' for even number of
+ *'num_blocks' consecutive 64-byte blocks
+ *
+ *extern "C" void sha1_transform_avx2(
+ *	int *hash, const char* input, size_t num_blocks );
+ */
+
+#include <linux/linkage.h>
+
+#define	CTX	%rdi	/* arg1 */
+#define BUF	%rsi	/* arg2 */
+#define CNT	%rdx	/* arg3 */
+
+#define	REG_A	%ecx
+#define	REG_B	%esi
+#define	REG_C	%edi
+#define	REG_D	%eax
+#define	REG_E	%edx
+#define	REG_TB	%ebx
+#define	REG_TA	%r12d
+#define	REG_RA	%rcx
+#define	REG_RB	%rsi
+#define	REG_RC	%rdi
+#define	REG_RD	%rax
+#define	REG_RE	%rdx
+#define	REG_RTA	%r12
+#define	REG_RTB	%rbx
+#define	REG_T1	%ebp
+#define	xmm_mov	vmovups
+#define	avx2_zeroupper	vzeroupper
+#define	RND_F1	1
+#define	RND_F2	2
+#define	RND_F3	3
+
+.macro REGALLOC
+	.set A, REG_A
+	.set B, REG_B
+	.set C, REG_C
+	.set D, REG_D
+	.set E, REG_E
+	.set TB, REG_TB
+	.set TA, REG_TA
+
+	.set RA, REG_RA
+	.set RB, REG_RB
+	.set RC, REG_RC
+	.set RD, REG_RD
+	.set RE, REG_RE
+
+	.set RTA, REG_RTA
+	.set RTB, REG_RTB
+
+	.set T1, REG_T1
+.endm
+
+#define K_BASE		%r8
+#define HASH_PTR	%r9
+#define BUFFER_PTR	%r10
+#define BUFFER_PTR2	%r13
+#define BUFFER_END	%r11
+
+#define PRECALC_BUF	%r14
+#define WK_BUF		%r15
+
+#define W_TMP		%xmm0
+#define WY_TMP		%ymm0
+#define WY_TMP2		%ymm9
+
+# AVX2 variables
+#define WY0		%ymm3
+#define WY4		%ymm5
+#define WY08		%ymm7
+#define WY12		%ymm8
+#define WY16		%ymm12
+#define WY20		%ymm13
+#define WY24		%ymm14
+#define WY28		%ymm15
+
+#define YMM_SHUFB_BSWAP	%ymm10
+
+/*
+ * Keep 2 iterations precalculated at a time:
+ *    - 80 DWORDs per iteration * 2
+ */
+#define W_SIZE		(80*2*2 +16)
+
+#define WK(t)	((((t) % 80) / 4)*32 + ( (t) % 4)*4 + ((t)/80)*16 )(WK_BUF)
+#define PRECALC_WK(t)	((t)*2*2)(PRECALC_BUF)
+
+
+.macro UPDATE_HASH  hash, val
+	add	\hash, \val
+	mov	\val, \hash
+.endm
+
+.macro PRECALC_RESET_WY
+	.set WY_00, WY0
+	.set WY_04, WY4
+	.set WY_08, WY08
+	.set WY_12, WY12
+	.set WY_16, WY16
+	.set WY_20, WY20
+	.set WY_24, WY24
+	.set WY_28, WY28
+	.set WY_32, WY_00
+.endm
+
+.macro PRECALC_ROTATE_WY
+	/* Rotate macros */
+	.set WY_32, WY_28
+	.set WY_28, WY_24
+	.set WY_24, WY_20
+	.set WY_20, WY_16
+	.set WY_16, WY_12
+	.set WY_12, WY_08
+	.set WY_08, WY_04
+	.set WY_04, WY_00
+	.set WY_00, WY_32
+
+	/* Define register aliases */
+	.set WY, WY_00
+	.set WY_minus_04, WY_04
+	.set WY_minus_08, WY_08
+	.set WY_minus_12, WY_12
+	.set WY_minus_16, WY_16
+	.set WY_minus_20, WY_20
+	.set WY_minus_24, WY_24
+	.set WY_minus_28, WY_28
+	.set WY_minus_32, WY
+.endm
+
+.macro PRECALC_00_15
+	.if (i == 0) # Initialize and rotate registers
+		PRECALC_RESET_WY
+		PRECALC_ROTATE_WY
+	.endif
+
+	/* message scheduling pre-compute for rounds 0-15 */
+	.if   ((i & 7) == 0)
+		/*
+		 * blended AVX2 and ALU instruction scheduling
+		 * 1 vector iteration per 8 rounds
+		 */
+		vmovdqu ((i * 2) + PRECALC_OFFSET)(BUFFER_PTR), W_TMP
+	.elseif ((i & 7) == 1)
+		vinsertf128 $1, (((i-1) * 2)+PRECALC_OFFSET)(BUFFER_PTR2),\
+			 WY_TMP, WY_TMP
+	.elseif ((i & 7) == 2)
+		vpshufb YMM_SHUFB_BSWAP, WY_TMP, WY
+	.elseif ((i & 7) == 4)
+		vpaddd  K_XMM(K_BASE), WY, WY_TMP
+	.elseif ((i & 7) == 7)
+		vmovdqu  WY_TMP, PRECALC_WK(i&~7)
+
+		PRECALC_ROTATE_WY
+	.endif
+.endm
+
+.macro PRECALC_16_31
+	/*
+	 * message scheduling pre-compute for rounds 16-31
+	 * calculating last 32 w[i] values in 8 XMM registers
+	 * pre-calculate K+w[i] values and store to mem
+	 * for later load by ALU add instruction
+	 *
+	 * "brute force" vectorization for rounds 16-31 only
+	 * due to w[i]->w[i-3] dependency
+	 */
+	.if   ((i & 7) == 0)
+		/*
+		 * blended AVX2 and ALU instruction scheduling
+		 * 1 vector iteration per 8 rounds
+		 */
+		/* w[i-14] */
+		vpalignr	$8, WY_minus_16, WY_minus_12, WY
+		vpsrldq	$4, WY_minus_04, WY_TMP               /* w[i-3] */
+	.elseif ((i & 7) == 1)
+		vpxor	WY_minus_08, WY, WY
+		vpxor	WY_minus_16, WY_TMP, WY_TMP
+	.elseif ((i & 7) == 2)
+		vpxor	WY_TMP, WY, WY
+		vpslldq	$12, WY, WY_TMP2
+	.elseif ((i & 7) == 3)
+		vpslld	$1, WY, WY_TMP
+		vpsrld	$31, WY, WY
+	.elseif ((i & 7) == 4)
+		vpor	WY, WY_TMP, WY_TMP
+		vpslld	$2, WY_TMP2, WY
+	.elseif ((i & 7) == 5)
+		vpsrld	$30, WY_TMP2, WY_TMP2
+		vpxor	WY, WY_TMP, WY_TMP
+	.elseif ((i & 7) == 7)
+		vpxor	WY_TMP2, WY_TMP, WY
+		vpaddd	K_XMM(K_BASE), WY, WY_TMP
+		vmovdqu	WY_TMP, PRECALC_WK(i&~7)
+
+		PRECALC_ROTATE_WY
+	.endif
+.endm
+
+.macro PRECALC_32_79
+	/*
+	 * in SHA-1 specification:
+	 * w[i] = (w[i-3] ^ w[i-8]  ^ w[i-14] ^ w[i-16]) rol 1
+	 * instead we do equal:
+	 * w[i] = (w[i-6] ^ w[i-16] ^ w[i-28] ^ w[i-32]) rol 2
+	 * allows more efficient vectorization
+	 * since w[i]=>w[i-3] dependency is broken
+	 */
+
+	.if   ((i & 7) == 0)
+	/*
+	 * blended AVX2 and ALU instruction scheduling
+	 * 1 vector iteration per 8 rounds
+	 */
+		vpalignr	$8, WY_minus_08, WY_minus_04, WY_TMP
+	.elseif ((i & 7) == 1)
+		/* W is W_minus_32 before xor */
+		vpxor	WY_minus_28, WY, WY
+	.elseif ((i & 7) == 2)
+		vpxor	WY_minus_16, WY_TMP, WY_TMP
+	.elseif ((i & 7) == 3)
+		vpxor	WY_TMP, WY, WY
+	.elseif ((i & 7) == 4)
+		vpslld	$2, WY, WY_TMP
+	.elseif ((i & 7) == 5)
+		vpsrld	$30, WY, WY
+		vpor	WY, WY_TMP, WY
+	.elseif ((i & 7) == 7)
+		vpaddd	K_XMM(K_BASE), WY, WY_TMP
+		vmovdqu	WY_TMP, PRECALC_WK(i&~7)
+
+		PRECALC_ROTATE_WY
+	.endif
+.endm
+
+.macro PRECALC r, s
+	.set i, \r
+
+	.if (i < 40)
+		.set K_XMM, 32*0
+	.elseif (i < 80)
+		.set K_XMM, 32*1
+	.elseif (i < 120)
+		.set K_XMM, 32*2
+	.else
+		.set K_XMM, 32*3
+	.endif
+
+	.if (i<32)
+		PRECALC_00_15	\s
+	.elseif (i<64)
+		PRECALC_16_31	\s
+	.elseif (i < 160)
+		PRECALC_32_79	\s
+	.endif
+.endm
+
+.macro ROTATE_STATE
+	.set T_REG, E
+	.set E, D
+	.set D, C
+	.set C, B
+	.set B, TB
+	.set TB, A
+	.set A, T_REG
+
+	.set T_REG, RE
+	.set RE, RD
+	.set RD, RC
+	.set RC, RB
+	.set RB, RTB
+	.set RTB, RA
+	.set RA, T_REG
+.endm
+
+/* Macro relies on saved ROUND_Fx */
+
+.macro RND_FUN f, r
+	.if (\f == RND_F1)
+		ROUND_F1	\r
+	.elseif (\f == RND_F2)
+		ROUND_F2	\r
+	.elseif (\f == RND_F3)
+		ROUND_F3	\r
+	.endif
+.endm
+
+.macro RR r
+	.set round_id, (\r % 80)
+
+	.if (round_id == 0)        /* Precalculate F for first round */
+		.set ROUND_FUNC, RND_F1
+		mov	B, TB
+
+		rorx	$(32-30), B, B    /* b>>>2 */
+		andn	D, TB, T1
+		and	C, TB
+		xor	T1, TB
+	.endif
+
+	RND_FUN ROUND_FUNC, \r
+	ROTATE_STATE
+
+	.if   (round_id == 18)
+		.set ROUND_FUNC, RND_F2
+	.elseif (round_id == 38)
+		.set ROUND_FUNC, RND_F3
+	.elseif (round_id == 58)
+		.set ROUND_FUNC, RND_F2
+	.endif
+
+	.set round_id, ( (\r+1) % 80)
+
+	RND_FUN ROUND_FUNC, (\r+1)
+	ROTATE_STATE
+.endm
+
+.macro ROUND_F1 r
+	add	WK(\r), E
+
+	andn	C, A, T1			/* ~b&d */
+	lea	(RE,RTB), E		/* Add F from the previous round */
+
+	rorx	$(32-5), A, TA		/* T2 = A >>> 5 */
+	rorx	$(32-30),A, TB		/* b>>>2 for next round */
+
+	PRECALC	(\r)			/* msg scheduling for next 2 blocks */
+
+	/*
+	 * Calculate F for the next round
+	 * (b & c) ^ andn[b, d]
+	 */
+	and	B, A			/* b&c */
+	xor	T1, A			/* F1 = (b&c) ^ (~b&d) */
+
+	lea	(RE,RTA), E		/* E += A >>> 5 */
+.endm
+
+.macro ROUND_F2 r
+	add	WK(\r), E
+	lea	(RE,RTB), E		/* Add F from the previous round */
+
+	/* Calculate F for the next round */
+	rorx	$(32-5), A, TA		/* T2 = A >>> 5 */
+	.if ((round_id) < 79)
+		rorx	$(32-30), A, TB	/* b>>>2 for next round */
+	.endif
+	PRECALC	(\r)			/* msg scheduling for next 2 blocks */
+
+	.if ((round_id) < 79)
+		xor	B, A
+	.endif
+
+	add	TA, E			/* E += A >>> 5 */
+
+	.if ((round_id) < 79)
+		xor	C, A
+	.endif
+.endm
+
+.macro ROUND_F3 r
+	add	WK(\r), E
+	PRECALC	(\r)			/* msg scheduling for next 2 blocks */
+
+	lea	(RE,RTB), E		/* Add F from the previous round */
+
+	mov	B, T1
+	or	A, T1
+
+	rorx	$(32-5), A, TA		/* T2 = A >>> 5 */
+	rorx	$(32-30), A, TB		/* b>>>2 for next round */
+
+	/* Calculate F for the next round
+	 * (b and c) or (d and (b or c))
+	 */
+	and	C, T1
+	and	B, A
+	or	T1, A
+
+	add	TA, E			/* E += A >>> 5 */
+
+.endm
+
+/*
+ * macro implements 80 rounds of SHA-1, for multiple blocks with s/w pipelining
+ */
+.macro SHA1_PIPELINED_MAIN_BODY
+
+	REGALLOC
+
+	mov	(HASH_PTR), A
+	mov	4(HASH_PTR), B
+	mov	8(HASH_PTR), C
+	mov	12(HASH_PTR), D
+	mov	16(HASH_PTR), E
+
+	mov	%rsp, PRECALC_BUF
+	lea	(2*4*80+32)(%rsp), WK_BUF
+
+	# Precalc WK for first 2 blocks
+	PRECALC_OFFSET = 0
+	.set i, 0
+	.rept    160
+		PRECALC i
+		.set i, i + 1
+	.endr
+	PRECALC_OFFSET = 128
+	xchg	WK_BUF, PRECALC_BUF
+
+	.align 32
+_loop:
+	/*
+	 * code loops through more than one block
+	 * we use K_BASE value as a signal of a last block,
+	 * it is set below by: cmovae BUFFER_PTR, K_BASE
+	 */
+	cmp	K_BASE, BUFFER_PTR
+	jne	_begin
+	.align 32
+	jmp	_end
+	.align 32
+_begin:
+
+	/*
+	 * Do first block
+	 * rounds: 0,2,4,6,8
+	 */
+	.set j, 0
+	.rept 5
+		RR	j
+		.set j, j+2
+	.endr
+
+	jmp _loop0
+_loop0:
+
+	/*
+	 * rounds:
+	 * 10,12,14,16,18
+	 * 20,22,24,26,28
+	 * 30,32,34,36,38
+	 * 40,42,44,46,48
+	 * 50,52,54,56,58
+	 */
+	.rept 25
+		RR	j
+		.set j, j+2
+	.endr
+
+	add	$(2*64), BUFFER_PTR       /* move to next odd-64-byte block */
+	cmp	BUFFER_END, BUFFER_PTR    /* is current block the last one? */
+	cmovae	K_BASE, BUFFER_PTR	/* signal the last iteration smartly */
+
+	/*
+	 * rounds
+	 * 60,62,64,66,68
+	 * 70,72,74,76,78
+	 */
+	.rept 10
+		RR	j
+		.set j, j+2
+	.endr
+
+	UPDATE_HASH	(HASH_PTR), A
+	UPDATE_HASH	4(HASH_PTR), TB
+	UPDATE_HASH	8(HASH_PTR), C
+	UPDATE_HASH	12(HASH_PTR), D
+	UPDATE_HASH	16(HASH_PTR), E
+
+	cmp	K_BASE, BUFFER_PTR	/* is current block the last one? */
+	je	_loop
+
+	mov	TB, B
+
+	/* Process second block */
+	/*
+	 * rounds
+	 *  0+80, 2+80, 4+80, 6+80, 8+80
+	 * 10+80,12+80,14+80,16+80,18+80
+	 */
+
+	.set j, 0
+	.rept 10
+		RR	j+80
+		.set j, j+2
+	.endr
+
+	jmp	_loop1
+_loop1:
+	/*
+	 * rounds
+	 * 20+80,22+80,24+80,26+80,28+80
+	 * 30+80,32+80,34+80,36+80,38+80
+	 */
+	.rept 10
+		RR	j+80
+		.set j, j+2
+	.endr
+
+	jmp	_loop2
+_loop2:
+
+	/*
+	 * rounds
+	 * 40+80,42+80,44+80,46+80,48+80
+	 * 50+80,52+80,54+80,56+80,58+80
+	 */
+	.rept 10
+		RR	j+80
+		.set j, j+2
+	.endr
+
+	add	$(2*64), BUFFER_PTR2      /* move to next even-64-byte block */
+
+	cmp	BUFFER_END, BUFFER_PTR2   /* is current block the last one */
+	cmovae	K_BASE, BUFFER_PTR       /* signal the last iteration smartly */
+
+	jmp	_loop3
+_loop3:
+
+	/*
+	 * rounds
+	 * 60+80,62+80,64+80,66+80,68+80
+	 * 70+80,72+80,74+80,76+80,78+80
+	 */
+	.rept 10
+		RR	j+80
+		.set j, j+2
+	.endr
+
+	UPDATE_HASH	(HASH_PTR), A
+	UPDATE_HASH	4(HASH_PTR), TB
+	UPDATE_HASH	8(HASH_PTR), C
+	UPDATE_HASH	12(HASH_PTR), D
+	UPDATE_HASH	16(HASH_PTR), E
+
+	/* Reset state for AVX2 reg permutation */
+	mov	A, TA
+	mov	TB, A
+	mov	C, TB
+	mov	E, C
+	mov	D, B
+	mov	TA, D
+
+	REGALLOC
+
+	xchg	WK_BUF, PRECALC_BUF
+
+	jmp	_loop
+
+	.align 32
+	_end:
+
+.endm
+/*
+ * macro implements SHA-1 function's body for several 64-byte blocks
+ * param: function's name
+ */
+.macro SHA1_VECTOR_ASM  name
+	ENTRY(\name)
+
+	push	%rbx
+	push	%rbp
+	push	%r12
+	push	%r13
+	push	%r14
+	push	%r15
+
+	RESERVE_STACK  = (W_SIZE*4 + 8+24)
+
+	/* Align stack */
+	mov	%rsp, %rbx
+	and	$~(0x20-1), %rsp
+	push	%rbx
+	sub	$RESERVE_STACK, %rsp
+
+	avx2_zeroupper
+
+	lea	K_XMM_AR(%rip), K_BASE
+
+	mov	CTX, HASH_PTR
+	mov	BUF, BUFFER_PTR
+	lea	64(BUF), BUFFER_PTR2
+
+	shl	$6, CNT			/* mul by 64 */
+	add	BUF, CNT
+	add	$64, CNT
+	mov	CNT, BUFFER_END
+
+	cmp	BUFFER_END, BUFFER_PTR2
+	cmovae	K_BASE, BUFFER_PTR2
+
+	xmm_mov	BSWAP_SHUFB_CTL(%rip), YMM_SHUFB_BSWAP
+
+	SHA1_PIPELINED_MAIN_BODY
+
+	avx2_zeroupper
+
+	add	$RESERVE_STACK, %rsp
+	pop	%rsp
+
+	pop	%r15
+	pop	%r14
+	pop	%r13
+	pop	%r12
+	pop	%rbp
+	pop	%rbx
+
+	ret
+
+	ENDPROC(\name)
+.endm
+
+.section .rodata
+
+#define K1 0x5a827999
+#define K2 0x6ed9eba1
+#define K3 0x8f1bbcdc
+#define K4 0xca62c1d6
+
+.align 128
+K_XMM_AR:
+	.long K1, K1, K1, K1
+	.long K1, K1, K1, K1
+	.long K2, K2, K2, K2
+	.long K2, K2, K2, K2
+	.long K3, K3, K3, K3
+	.long K3, K3, K3, K3
+	.long K4, K4, K4, K4
+	.long K4, K4, K4, K4
+
+BSWAP_SHUFB_CTL:
+	.long 0x00010203
+	.long 0x04050607
+	.long 0x08090a0b
+	.long 0x0c0d0e0f
+	.long 0x00010203
+	.long 0x04050607
+	.long 0x08090a0b
+	.long 0x0c0d0e0f
+.text
+
+SHA1_VECTOR_ASM     sha1_transform_avx2

arch/x86/crypto/sha1_ssse3_glue.c

@@ -10,6 +10,7 @@
  * Copyright (c) Andrew McDonald <andrew@mcdonald.org.uk>
  * Copyright (c) Jean-Francois Dive <jef@linuxbe.org>
  * Copyright (c) Mathias Krause <minipli@googlemail.com>
+ * Copyright (c) Chandramouli Narayanan <mouli@linux.intel.com>
  *
  * This program is free software; you can redistribute it and/or modify it
  * under the terms of the GNU General Public License as published by the Free
@@ -39,6 +40,12 @@ asmlinkage void sha1_transform_ssse3(u32 *digest, const char *data,
 asmlinkage void sha1_transform_avx(u32 *digest, const char *data,
 				   unsigned int rounds);
 #endif
+#ifdef CONFIG_AS_AVX2
+#define SHA1_AVX2_BLOCK_OPTSIZE	4	/* optimal 4*64 bytes of SHA1 blocks */
+
+asmlinkage void sha1_transform_avx2(u32 *digest, const char *data,
+				unsigned int rounds);
+#endif
 
 static asmlinkage void (*sha1_transform_asm)(u32 *, const char *, unsigned int);
 
@@ -165,6 +172,18 @@ static int sha1_ssse3_import(struct shash_desc *desc, const void *in)
 	return 0;
 }
 
+#ifdef CONFIG_AS_AVX2
+static void sha1_apply_transform_avx2(u32 *digest, const char *data,
+				unsigned int rounds)
+{
+	/* Select the optimal transform based on data block size */
+	if (rounds >= SHA1_AVX2_BLOCK_OPTSIZE)
+		sha1_transform_avx2(digest, data, rounds);
+	else
+		sha1_transform_avx(digest, data, rounds);
+}
+#endif
+
 static struct shash_alg alg = {
 	.digestsize	=	SHA1_DIGEST_SIZE,
 	.init		=	sha1_ssse3_init,
@@ -201,27 +220,49 @@ static bool __init avx_usable(void)
 
 	return true;
 }
+
+#ifdef CONFIG_AS_AVX2
+static bool __init avx2_usable(void)
+{
+	if (avx_usable() && cpu_has_avx2 && boot_cpu_has(X86_FEATURE_BMI1) &&
+	    boot_cpu_has(X86_FEATURE_BMI2))
+		return true;
+
+	return false;
+}
+#endif
 #endif
 
 static int __init sha1_ssse3_mod_init(void)
 {
+	char *algo_name;
+
 	/* test for SSSE3 first */
-	if (cpu_has_ssse3)
+	if (cpu_has_ssse3) {
 		sha1_transform_asm = sha1_transform_ssse3;
+		algo_name = "SSSE3";
+	}
 
 #ifdef CONFIG_AS_AVX
 	/* allow AVX to override SSSE3, it's a little faster */
-	if (avx_usable())
+	if (avx_usable()) {
 		sha1_transform_asm = sha1_transform_avx;
+		algo_name = "AVX";
+#ifdef CONFIG_AS_AVX2
+		/* allow AVX2 to override AVX, it's a little faster */
+		if (avx2_usable()) {
+			sha1_transform_asm = sha1_apply_transform_avx2;
+			algo_name = "AVX2";
+		}
+#endif
+	}
 #endif
 
 	if (sha1_transform_asm) {
-		pr_info("Using %s optimized SHA-1 implementation\n",
-		        sha1_transform_asm == sha1_transform_ssse3 ? "SSSE3"
-		                                                   : "AVX");
+		pr_info("Using %s optimized SHA-1 implementation\n", algo_name);
 		return crypto_register_shash(&alg);
 	}
-	pr_info("Neither AVX nor SSSE3 is available/usable.\n");
+	pr_info("Neither AVX nor AVX2 nor SSSE3 is available/usable.\n");
 
 	return -ENODEV;
 }

crypto/Kconfig

@@ -491,14 +491,14 @@ config CRYPTO_SHA1
 	  SHA-1 secure hash standard (FIPS 180-1/DFIPS 180-2).
 
 config CRYPTO_SHA1_SSSE3
-	tristate "SHA1 digest algorithm (SSSE3/AVX)"
+	tristate "SHA1 digest algorithm (SSSE3/AVX/AVX2)"
 	depends on X86 && 64BIT
 	select CRYPTO_SHA1
 	select CRYPTO_HASH
 	help
 	  SHA-1 secure hash standard (FIPS 180-1/DFIPS 180-2) implemented
 	  using Supplemental SSE3 (SSSE3) instructions or Advanced Vector
-	  Extensions (AVX), when available.
+	  Extensions (AVX/AVX2), when available.
 
 config CRYPTO_SHA256_SSSE3
 	tristate "SHA256 digest algorithm (SSSE3/AVX/AVX2)"

crypto/Makefile

@@ -81,7 +81,7 @@ obj-$(CONFIG_CRYPTO_SALSA20) += salsa20_generic.o
 obj-$(CONFIG_CRYPTO_DEFLATE) += deflate.o
 obj-$(CONFIG_CRYPTO_ZLIB) += zlib.o
 obj-$(CONFIG_CRYPTO_MICHAEL_MIC) += michael_mic.o
-obj-$(CONFIG_CRYPTO_CRC32C) += crc32c.o
+obj-$(CONFIG_CRYPTO_CRC32C) += crc32c_generic.o
 obj-$(CONFIG_CRYPTO_CRC32) += crc32.o
 obj-$(CONFIG_CRYPTO_CRCT10DIF) += crct10dif_common.o crct10dif_generic.o
 obj-$(CONFIG_CRYPTO_AUTHENC) += authenc.o authencesn.o

crypto/ahash.c

@@ -190,6 +190,75 @@ static inline unsigned int ahash_align_buffer_size(unsigned len,
 	return len + (mask & ~(crypto_tfm_ctx_alignment() - 1));
 }
 
+static int ahash_save_req(struct ahash_request *req, crypto_completion_t cplt)
+{
+	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
+	unsigned long alignmask = crypto_ahash_alignmask(tfm);
+	unsigned int ds = crypto_ahash_digestsize(tfm);
+	struct ahash_request_priv *priv;
+
+	priv = kmalloc(sizeof(*priv) + ahash_align_buffer_size(ds, alignmask),
+		       (req->base.flags & CRYPTO_TFM_REQ_MAY_SLEEP) ?
+		       GFP_KERNEL : GFP_ATOMIC);
+	if (!priv)
+		return -ENOMEM;
+
+	/*
+	 * WARNING: Voodoo programming below!
+	 *
+	 * The code below is obscure and hard to understand, thus explanation
+	 * is necessary. See include/crypto/hash.h and include/linux/crypto.h
+	 * to understand the layout of structures used here!
+	 *
+	 * The code here will replace portions of the ORIGINAL request with
+	 * pointers to new code and buffers so the hashing operation can store
+	 * the result in aligned buffer. We will call the modified request
+	 * an ADJUSTED request.
+	 *
+	 * The newly mangled request will look as such:
+	 *
+	 * req {
+	 *   .result        = ADJUSTED[new aligned buffer]
+	 *   .base.complete = ADJUSTED[pointer to completion function]
+	 *   .base.data     = ADJUSTED[*req (pointer to self)]
+	 *   .priv          = ADJUSTED[new priv] {
+	 *           .result   = ORIGINAL(result)
+	 *           .complete = ORIGINAL(base.complete)
+	 *           .data     = ORIGINAL(base.data)
+	 *   }
+	 */
+
+	priv->result = req->result;
+	priv->complete = req->base.complete;
+	priv->data = req->base.data;
+	/*
+	 * WARNING: We do not backup req->priv here! The req->priv
+	 *          is for internal use of the Crypto API and the
+	 *          user must _NOT_ _EVER_ depend on it's content!
+	 */
+
+	req->result = PTR_ALIGN((u8 *)priv->ubuf, alignmask + 1);
+	req->base.complete = cplt;
+	req->base.data = req;
+	req->priv = priv;
+
+	return 0;
+}
+
+static void ahash_restore_req(struct ahash_request *req)
+{
+	struct ahash_request_priv *priv = req->priv;
+
+	/* Restore the original crypto request. */
+	req->result = priv->result;
+	req->base.complete = priv->complete;
+	req->base.data = priv->data;
+	req->priv = NULL;
+
+	/* Free the req->priv.priv from the ADJUSTED request. */
+	kzfree(priv);
+}
+
 static void ahash_op_unaligned_finish(struct ahash_request *req, int err)
 {
 	struct ahash_request_priv *priv = req->priv;
@@ -201,47 +270,37 @@ static void ahash_op_unaligned_finish(struct ahash_request *req, int err)
 		memcpy(priv->result, req->result,
 		       crypto_ahash_digestsize(crypto_ahash_reqtfm(req)));
 
-	kzfree(priv);
+	ahash_restore_req(req);
 }
 
 static void ahash_op_unaligned_done(struct crypto_async_request *req, int err)
 {
 	struct ahash_request *areq = req->data;
-	struct ahash_request_priv *priv = areq->priv;
-	crypto_completion_t complete = priv->complete;
-	void *data = priv->data;
 
-	ahash_op_unaligned_finish(areq, err);
+	/*
+	 * Restore the original request, see ahash_op_unaligned() for what
+	 * goes where.
+	 *
+	 * The "struct ahash_request *req" here is in fact the "req.base"
+	 * from the ADJUSTED request from ahash_op_unaligned(), thus as it
+	 * is a pointer to self, it is also the ADJUSTED "req" .
+	 */
 
-	areq->base.complete = complete;
-	areq->base.data = data;
+	/* First copy req->result into req->priv.result */
+	ahash_op_unaligned_finish(areq, err);
 
-	complete(&areq->base, err);
+	/* Complete the ORIGINAL request. */
+	areq->base.complete(&areq->base, err);
 }
 
 static int ahash_op_unaligned(struct ahash_request *req,
 			      int (*op)(struct ahash_request *))
 {
-	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
-	unsigned long alignmask = crypto_ahash_alignmask(tfm);
-	unsigned int ds = crypto_ahash_digestsize(tfm);
-	struct ahash_request_priv *priv;
 	int err;
 
-	priv = kmalloc(sizeof(*priv) + ahash_align_buffer_size(ds, alignmask),
-		       (req->base.flags & CRYPTO_TFM_REQ_MAY_SLEEP) ?
-		       GFP_KERNEL : GFP_ATOMIC);
-	if (!priv)
-		return -ENOMEM;
-
-	priv->result = req->result;
-	priv->complete = req->base.complete;
-	priv->data = req->base.data;
-
-	req->result = PTR_ALIGN((u8 *)priv->ubuf, alignmask + 1);
-	req->base.complete = ahash_op_unaligned_done;
-	req->base.data = req;
-	req->priv = priv;
+	err = ahash_save_req(req, ahash_op_unaligned_done);
+	if (err)
+		return err;
 
 	err = op(req);
 	ahash_op_unaligned_finish(req, err);
@@ -290,19 +349,16 @@ static void ahash_def_finup_finish2(struct ahash_request *req, int err)
 		memcpy(priv->result, req->result,
 		       crypto_ahash_digestsize(crypto_ahash_reqtfm(req)));
 
-	kzfree(priv);
+	ahash_restore_req(req);
 }
 
 static void ahash_def_finup_done2(struct crypto_async_request *req, int err)
 {
 	struct ahash_request *areq = req->data;
-	struct ahash_request_priv *priv = areq->priv;
-	crypto_completion_t complete = priv->complete;
-	void *data = priv->data;
 
 	ahash_def_finup_finish2(areq, err);
 
-	complete(data, err);
+	areq->base.complete(&areq->base, err);
 }
 
 static int ahash_def_finup_finish1(struct ahash_request *req, int err)
@@ -322,38 +378,23 @@ static int ahash_def_finup_finish1(struct ahash_request *req, int err)
 static void ahash_def_finup_done1(struct crypto_async_request *req, int err)
 {
 	struct ahash_request *areq = req->data;
-	struct ahash_request_priv *priv = areq->priv;
-	crypto_completion_t complete = priv->complete;
-	void *data = priv->data;
 
 	err = ahash_def_finup_finish1(areq, err);
 
-	complete(data, err);
+	areq->base.complete(&areq->base, err);
 }
 
 static int ahash_def_finup(struct ahash_request *req)
 {
 	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
-	unsigned long alignmask = crypto_ahash_alignmask(tfm);
-	unsigned int ds = crypto_ahash_digestsize(tfm);
-	struct ahash_request_priv *priv;
-
-	priv = kmalloc(sizeof(*priv) + ahash_align_buffer_size(ds, alignmask),
-		       (req->base.flags & CRYPTO_TFM_REQ_MAY_SLEEP) ?
-		       GFP_KERNEL : GFP_ATOMIC);
-	if (!priv)
-		return -ENOMEM;
-
-	priv->result = req->result;
-	priv->complete = req->base.complete;
-	priv->data = req->base.data;
+	int err;
 
-	req->result = PTR_ALIGN((u8 *)priv->ubuf, alignmask + 1);
-	req->base.complete = ahash_def_finup_done1;
-	req->base.data = req;
-	req->priv = priv;
+	err = ahash_save_req(req, ahash_def_finup_done1);
+	if (err)
+		return err;
 
-	return ahash_def_finup_finish1(req, tfm->update(req));
+	err = tfm->update(req);
+	return ahash_def_finup_finish1(req, err);
 }
 
 static int ahash_no_export(struct ahash_request *req, void *out)

crypto/blkcipher.c

@@ -70,14 +70,12 @@ static inline u8 *blkcipher_get_spot(u8 *start, unsigned int len)
 	return max(start, end_page);
 }
 
-static inline unsigned int blkcipher_done_slow(struct crypto_blkcipher *tfm,
-					       struct blkcipher_walk *walk,
+static inline unsigned int blkcipher_done_slow(struct blkcipher_walk *walk,
 					       unsigned int bsize)
 {
 	u8 *addr;
-	unsigned int alignmask = crypto_blkcipher_alignmask(tfm);
 
-	addr = (u8 *)ALIGN((unsigned long)walk->buffer, alignmask + 1);
+	addr = (u8 *)ALIGN((unsigned long)walk->buffer, walk->alignmask + 1);
 	addr = blkcipher_get_spot(addr, bsize);
 	scatterwalk_copychunks(addr, &walk->out, bsize, 1);
 	return bsize;
@@ -105,7 +103,6 @@ static inline unsigned int blkcipher_done_fast(struct blkcipher_walk *walk,
 int blkcipher_walk_done(struct blkcipher_desc *desc,
 			struct blkcipher_walk *walk, int err)
 {
-	struct crypto_blkcipher *tfm = desc->tfm;
 	unsigned int nbytes = 0;
 
 	if (likely(err >= 0)) {
@@ -117,7 +114,7 @@ int blkcipher_walk_done(struct blkcipher_desc *desc,
 			err = -EINVAL;
 			goto err;
 		} else
-			n = blkcipher_done_slow(tfm, walk, n);
+			n = blkcipher_done_slow(walk, n);
 
 		nbytes = walk->total - n;
 		err = 0;
@@ -136,7 +133,7 @@ int blkcipher_walk_done(struct blkcipher_desc *desc,
 	}
 
 	if (walk->iv != desc->info)
-		memcpy(desc->info, walk->iv, crypto_blkcipher_ivsize(tfm));
+		memcpy(desc->info, walk->iv, walk->ivsize);
 	if (walk->buffer != walk->page)
 		kfree(walk->buffer);
 	if (walk->page)
@@ -226,22 +223,20 @@ static inline int blkcipher_next_fast(struct blkcipher_desc *desc,
 static int blkcipher_walk_next(struct blkcipher_desc *desc,
 			       struct blkcipher_walk *walk)
 {
-	struct crypto_blkcipher *tfm = desc->tfm;
-	unsigned int alignmask = crypto_blkcipher_alignmask(tfm);
 	unsigned int bsize;
 	unsigned int n;
 	int err;
 
 	n = walk->total;
-	if (unlikely(n < crypto_blkcipher_blocksize(tfm))) {
+	if (unlikely(n < walk->cipher_blocksize)) {
 		desc->flags |= CRYPTO_TFM_RES_BAD_BLOCK_LEN;
 		return blkcipher_walk_done(desc, walk, -EINVAL);
 	}
 
 	walk->flags &= ~(BLKCIPHER_WALK_SLOW | BLKCIPHER_WALK_COPY |
 			 BLKCIPHER_WALK_DIFF);
-	if (!scatterwalk_aligned(&walk->in, alignmask) ||
-	    !scatterwalk_aligned(&walk->out, alignmask)) {
+	if (!scatterwalk_aligned(&walk->in, walk->alignmask) ||
+	    !scatterwalk_aligned(&walk->out, walk->alignmask)) {
 		walk->flags |= BLKCIPHER_WALK_COPY;
 		if (!walk->page) {
 			walk->page = (void *)__get_free_page(GFP_ATOMIC);
@@ -250,12 +245,12 @@ static int blkcipher_walk_next(struct blkcipher_desc *desc,
 		}
 	}
 
-	bsize = min(walk->blocksize, n);
+	bsize = min(walk->walk_blocksize, n);
 	n = scatterwalk_clamp(&walk->in, n);
 	n = scatterwalk_clamp(&walk->out, n);
 
 	if (unlikely(n < bsize)) {
-		err = blkcipher_next_slow(desc, walk, bsize, alignmask);
+		err = blkcipher_next_slow(desc, walk, bsize, walk->alignmask);
 		goto set_phys_lowmem;
 	}
 
@@ -277,28 +272,26 @@ static int blkcipher_walk_next(struct blkcipher_desc *desc,
 	return err;
 }
 
-static inline int blkcipher_copy_iv(struct blkcipher_walk *walk,
-				    struct crypto_blkcipher *tfm,
-				    unsigned int alignmask)
+static inline int blkcipher_copy_iv(struct blkcipher_walk *walk)
 {
-	unsigned bs = walk->blocksize;
-	unsigned int ivsize = crypto_blkcipher_ivsize(tfm);
-	unsigned aligned_bs = ALIGN(bs, alignmask + 1);
-	unsigned int size = aligned_bs * 2 + ivsize + max(aligned_bs, ivsize) -
-			    (alignmask + 1);
+	unsigned bs = walk->walk_blocksize;
+	unsigned aligned_bs = ALIGN(bs, walk->alignmask + 1);
+	unsigned int size = aligned_bs * 2 +
+			    walk->ivsize + max(aligned_bs, walk->ivsize) -
+			    (walk->alignmask + 1);
 	u8 *iv;
 
-	size += alignmask & ~(crypto_tfm_ctx_alignment() - 1);
+	size += walk->alignmask & ~(crypto_tfm_ctx_alignment() - 1);
 	walk->buffer = kmalloc(size, GFP_ATOMIC);
 	if (!walk->buffer)
 		return -ENOMEM;
 
-	iv = (u8 *)ALIGN((unsigned long)walk->buffer, alignmask + 1);
+	iv = (u8 *)ALIGN((unsigned long)walk->buffer, walk->alignmask + 1);
 	iv = blkcipher_get_spot(iv, bs) + aligned_bs;
 	iv = blkcipher_get_spot(iv, bs) + aligned_bs;
-	iv = blkcipher_get_spot(iv, ivsize);
+	iv = blkcipher_get_spot(iv, walk->ivsize);
 
-	walk->iv = memcpy(iv, walk->iv, ivsize);
+	walk->iv = memcpy(iv, walk->iv, walk->ivsize);
 	return 0;
 }
 
@@ -306,7 +299,10 @@ int blkcipher_walk_virt(struct blkcipher_desc *desc,
 			struct blkcipher_walk *walk)
 {
 	walk->flags &= ~BLKCIPHER_WALK_PHYS;
-	walk->blocksize = crypto_blkcipher_blocksize(desc->tfm);
+	walk->walk_blocksize = crypto_blkcipher_blocksize(desc->tfm);
+	walk->cipher_blocksize = walk->walk_blocksize;
+	walk->ivsize = crypto_blkcipher_ivsize(desc->tfm);
+	walk->alignmask = crypto_blkcipher_alignmask(desc->tfm);
 	return blkcipher_walk_first(desc, walk);
 }
 EXPORT_SYMBOL_GPL(blkcipher_walk_virt);
@@ -315,7 +311,10 @@ int blkcipher_walk_phys(struct blkcipher_desc *desc,
 			struct blkcipher_walk *walk)
 {
 	walk->flags |= BLKCIPHER_WALK_PHYS;
-	walk->blocksize = crypto_blkcipher_blocksize(desc->tfm);
+	walk->walk_blocksize = crypto_blkcipher_blocksize(desc->tfm);
+	walk->cipher_blocksize = walk->walk_blocksize;
+	walk->ivsize = crypto_blkcipher_ivsize(desc->tfm);
+	walk->alignmask = crypto_blkcipher_alignmask(desc->tfm);
 	return blkcipher_walk_first(desc, walk);
 }
 EXPORT_SYMBOL_GPL(blkcipher_walk_phys);
@@ -323,9 +322,6 @@ EXPORT_SYMBOL_GPL(blkcipher_walk_phys);
 static int blkcipher_walk_first(struct blkcipher_desc *desc,
 				struct blkcipher_walk *walk)
 {
-	struct crypto_blkcipher *tfm = desc->tfm;
-	unsigned int alignmask = crypto_blkcipher_alignmask(tfm);
-
 	if (WARN_ON_ONCE(in_irq()))
 		return -EDEADLK;
 
@@ -335,8 +331,8 @@ static int blkcipher_walk_first(struct blkcipher_desc *desc,
 
 	walk->buffer = NULL;
 	walk->iv = desc->info;
-	if (unlikely(((unsigned long)walk->iv & alignmask))) {
-		int err = blkcipher_copy_iv(walk, tfm, alignmask);
+	if (unlikely(((unsigned long)walk->iv & walk->alignmask))) {
+		int err = blkcipher_copy_iv(walk);
 		if (err)
 			return err;
 	}
@@ -353,11 +349,28 @@ int blkcipher_walk_virt_block(struct blkcipher_desc *desc,
 			      unsigned int blocksize)
 {
 	walk->flags &= ~BLKCIPHER_WALK_PHYS;
-	walk->blocksize = blocksize;
+	walk->walk_blocksize = blocksize;
+	walk->cipher_blocksize = crypto_blkcipher_blocksize(desc->tfm);
+	walk->ivsize = crypto_blkcipher_ivsize(desc->tfm);
+	walk->alignmask = crypto_blkcipher_alignmask(desc->tfm);
 	return blkcipher_walk_first(desc, walk);
 }
 EXPORT_SYMBOL_GPL(blkcipher_walk_virt_block);
 
+int blkcipher_aead_walk_virt_block(struct blkcipher_desc *desc,
+				   struct blkcipher_walk *walk,
+				   struct crypto_aead *tfm,
+				   unsigned int blocksize)
+{
+	walk->flags &= ~BLKCIPHER_WALK_PHYS;
+	walk->walk_blocksize = blocksize;
+	walk->cipher_blocksize = crypto_aead_blocksize(tfm);
+	walk->ivsize = crypto_aead_ivsize(tfm);
+	walk->alignmask = crypto_aead_alignmask(tfm);
+	return blkcipher_walk_first(desc, walk);
+}
+EXPORT_SYMBOL_GPL(blkcipher_aead_walk_virt_block);
+
 static int setkey_unaligned(struct crypto_tfm *tfm, const u8 *key,
 			    unsigned int keylen)
 {

crypto/crc32c.c → crypto/crc32c_generic.c

@@ -170,3 +170,5 @@ module_exit(crc32c_mod_fini);
 MODULE_AUTHOR("Clay Haapala <chaapala@cisco.com>");
 MODULE_DESCRIPTION("CRC32c (Castagnoli) calculations wrapper for lib/crc32c");
 MODULE_LICENSE("GPL");
+MODULE_ALIAS("crc32c");
+MODULE_SOFTDEP("pre: crc32c");

crypto/crypto_null.c

@@ -17,6 +17,7 @@
  *
  */
 
+#include <crypto/null.h>
 #include <crypto/internal/hash.h>
 #include <crypto/internal/skcipher.h>
 #include <linux/init.h>
@@ -24,11 +25,6 @@
 #include <linux/mm.h>
 #include <linux/string.h>
 
-#define NULL_KEY_SIZE		0
-#define NULL_BLOCK_SIZE		1
-#define NULL_DIGEST_SIZE	0
-#define NULL_IV_SIZE		0
-
 static int null_compress(struct crypto_tfm *tfm, const u8 *src,
 			 unsigned int slen, u8 *dst, unsigned int *dlen)
 {

crypto/crypto_wq.c

@@ -33,7 +33,7 @@ static void __exit crypto_wq_exit(void)
 	destroy_workqueue(kcrypto_wq);
 }
 
-module_init(crypto_wq_init);
+subsys_initcall(crypto_wq_init);
 module_exit(crypto_wq_exit);
 
 MODULE_LICENSE("GPL");

crypto/tcrypt.c

@@ -1511,6 +1511,14 @@ static int do_test(int m)
 		ret += tcrypt_test("authenc(hmac(sha1),cbc(aes))");
 		break;
 
+	case 156:
+		ret += tcrypt_test("authenc(hmac(md5),ecb(cipher_null))");
+		break;
+
+	case 157:
+		ret += tcrypt_test("authenc(hmac(sha1),ecb(cipher_null))");
+		break;
+
 	case 200:
 		test_cipher_speed("ecb(aes)", ENCRYPT, sec, NULL, 0,
 				speed_template_16_24_32);

crypto/testmgr.c

@@ -1808,6 +1808,22 @@ static const struct alg_test_desc alg_test_descs[] = {
 				.count = ANSI_CPRNG_AES_TEST_VECTORS
 			}
 		}
+	}, {
+		.alg = "authenc(hmac(md5),ecb(cipher_null))",
+		.test = alg_test_aead,
+		.fips_allowed = 1,
+		.suite = {
+			.aead = {
+				.enc = {
+					.vecs = hmac_md5_ecb_cipher_null_enc_tv_template,
+					.count = HMAC_MD5_ECB_CIPHER_NULL_ENC_TEST_VECTORS
+				},
+				.dec = {
+					.vecs = hmac_md5_ecb_cipher_null_dec_tv_template,
+					.count = HMAC_MD5_ECB_CIPHER_NULL_DEC_TEST_VECTORS
+				}
+			}
+		}
 	}, {
 		.alg = "authenc(hmac(sha1),cbc(aes))",
 		.test = alg_test_aead,
@@ -1820,6 +1836,22 @@ static const struct alg_test_desc alg_test_descs[] = {
 				}
 			}
 		}
+	}, {
+		.alg = "authenc(hmac(sha1),ecb(cipher_null))",
+		.test = alg_test_aead,
+		.fips_allowed = 1,
+		.suite = {
+			.aead = {
+				.enc = {
+					.vecs = hmac_sha1_ecb_cipher_null_enc_tv_template,
+					.count = HMAC_SHA1_ECB_CIPHER_NULL_ENC_TEST_VECTORS
+				},
+				.dec = {
+					.vecs = hmac_sha1_ecb_cipher_null_dec_tv_template,
+					.count = HMAC_SHA1_ECB_CIPHER_NULL_DEC_TEST_VECTORS
+				}
+			}
+		}
 	}, {
 		.alg = "authenc(hmac(sha256),cbc(aes))",
 		.test = alg_test_aead,

crypto/testmgr.h

@@ -12821,6 +12821,10 @@ static struct cipher_testvec cast6_xts_dec_tv_template[] = {
 #define AES_DEC_TEST_VECTORS 4
 #define AES_CBC_ENC_TEST_VECTORS 5
 #define AES_CBC_DEC_TEST_VECTORS 5
+#define HMAC_MD5_ECB_CIPHER_NULL_ENC_TEST_VECTORS 2
+#define HMAC_MD5_ECB_CIPHER_NULL_DEC_TEST_VECTORS 2
+#define HMAC_SHA1_ECB_CIPHER_NULL_ENC_TEST_VECTORS 2
+#define HMAC_SHA1_ECB_CIPHER_NULL_DEC_TEST_VECTORS 2
 #define HMAC_SHA1_AES_CBC_ENC_TEST_VECTORS 7
 #define HMAC_SHA256_AES_CBC_ENC_TEST_VECTORS 7
 #define HMAC_SHA512_AES_CBC_ENC_TEST_VECTORS 7
@@ -13627,6 +13631,90 @@ static struct cipher_testvec aes_cbc_dec_tv_template[] = {
 	},
 };
+static struct aead_testvec hmac_md5_ecb_cipher_null_enc_tv_template[] = {
+	{ /* Input data from RFC 2410 Case 1 */
+#ifdef __LITTLE_ENDIAN
+		.key    = "\x08\x00"		/* rta length */
+			  "\x01\x00"		/* rta type */
+#else
+		.key    = "\x00\x08"		/* rta length */
+			  "\x00\x01"		/* rta type */
+#endif
+			  "\x00\x00\x00\x00"	/* enc key length */
+			  "\x00\x00\x00\x00\x00\x00\x00\x00"
+			  "\x00\x00\x00\x00\x00\x00\x00\x00",
+		.klen   = 8 + 16 + 0,
+		.iv     = "",
+		.input  = "\x01\x23\x45\x67\x89\xab\xcd\xef",
+		.ilen   = 8,
+		.result = "\x01\x23\x45\x67\x89\xab\xcd\xef"
+			  "\xaa\x42\xfe\x43\x8d\xea\xa3\x5a"
+			  "\xb9\x3d\x9f\xb1\xa3\x8e\x9b\xae",
+		.rlen   = 8 + 16,
+	}, { /* Input data from RFC 2410 Case 2 */
+#ifdef __LITTLE_ENDIAN
+		.key    = "\x08\x00"		/* rta length */
+			  "\x01\x00"		/* rta type */
+#else
+		.key    = "\x00\x08"		/* rta length */
+			  "\x00\x01"		/* rta type */
+#endif
+			  "\x00\x00\x00\x00"	/* enc key length */
+			  "\x00\x00\x00\x00\x00\x00\x00\x00"
+			  "\x00\x00\x00\x00\x00\x00\x00\x00",
+		.klen   = 8 + 16 + 0,
+		.iv     = "",
+		.input  = "Network Security People Have A Strange Sense Of Humor",
+		.ilen   = 53,
+		.result = "Network Security People Have A Strange Sense Of Humor"
+			  "\x73\xa5\x3e\x1c\x08\x0e\x8a\x8a"
+			  "\x8e\xb5\x5f\x90\x8e\xfe\x13\x23",
+		.rlen   = 53 + 16,
+	},
+};
+
+static struct aead_testvec hmac_md5_ecb_cipher_null_dec_tv_template[] = {
+	{
+#ifdef __LITTLE_ENDIAN
+		.key    = "\x08\x00"		/* rta length */
+			  "\x01\x00"		/* rta type */
+#else
+		.key    = "\x00\x08"		/* rta length */
+			  "\x00\x01"		/* rta type */
+#endif
+			  "\x00\x00\x00\x00"	/* enc key length */
+			  "\x00\x00\x00\x00\x00\x00\x00\x00"
+			  "\x00\x00\x00\x00\x00\x00\x00\x00",
+		.klen   = 8 + 16 + 0,
+		.iv     = "",
+		.input  = "\x01\x23\x45\x67\x89\xab\xcd\xef"
+			  "\xaa\x42\xfe\x43\x8d\xea\xa3\x5a"
+			  "\xb9\x3d\x9f\xb1\xa3\x8e\x9b\xae",
+		.ilen   = 8 + 16,
+		.result = "\x01\x23\x45\x67\x89\xab\xcd\xef",
+		.rlen   = 8,
+	}, {
+#ifdef __LITTLE_ENDIAN
+		.key    = "\x08\x00"		/* rta length */
+			  "\x01\x00"		/* rta type */
+#else
+		.key    = "\x00\x08"		/* rta length */
+			  "\x00\x01"		/* rta type */
+#endif
+			  "\x00\x00\x00\x00"	/* enc key length */
+			  "\x00\x00\x00\x00\x00\x00\x00\x00"
+			  "\x00\x00\x00\x00\x00\x00\x00\x00",
+		.klen   = 8 + 16 + 0,
+		.iv     = "",
+		.input  = "Network Security People Have A Strange Sense Of Humor"
+			  "\x73\xa5\x3e\x1c\x08\x0e\x8a\x8a"
+			  "\x8e\xb5\x5f\x90\x8e\xfe\x13\x23",
+		.ilen   = 53 + 16,
+		.result = "Network Security People Have A Strange Sense Of Humor",
+		.rlen   = 53,
+	},
+};
+
 static struct aead_testvec hmac_sha1_aes_cbc_enc_tv_template[] = {
 	{ /* RFC 3602 Case 1 */
 #ifdef __LITTLE_ENDIAN
@@ -13876,6 +13964,98 @@ static struct aead_testvec hmac_sha1_aes_cbc_enc_tv_template[] = {
 	},
 };
+static struct aead_testvec hmac_sha1_ecb_cipher_null_enc_tv_template[] = {
+	{ /* Input data from RFC 2410 Case 1 */
+#ifdef __LITTLE_ENDIAN
+		.key    = "\x08\x00"		/* rta length */
+			  "\x01\x00"		/* rta type */
+#else
+		.key    = "\x00\x08"		/* rta length */
+			  "\x00\x01"		/* rta type */
+#endif
+			  "\x00\x00\x00\x00"	/* enc key length */
+			  "\x00\x00\x00\x00\x00\x00\x00\x00"
+			  "\x00\x00\x00\x00\x00\x00\x00\x00"
+			  "\x00\x00\x00\x00",
+		.klen   = 8 + 20 + 0,
+		.iv     = "",
+		.input  = "\x01\x23\x45\x67\x89\xab\xcd\xef",
+		.ilen   = 8,
+		.result = "\x01\x23\x45\x67\x89\xab\xcd\xef"
+			  "\x40\xc3\x0a\xa1\xc9\xa0\x28\xab"
+			  "\x99\x5e\x19\x04\xd1\x72\xef\xb8"
+			  "\x8c\x5e\xe4\x08",
+		.rlen   = 8 + 20,
+	}, { /* Input data from RFC 2410 Case 2 */
+#ifdef __LITTLE_ENDIAN
+		.key    = "\x08\x00"		/* rta length */
+			  "\x01\x00"		/* rta type */
+#else
+		.key    = "\x00\x08"		/* rta length */
+			  "\x00\x01"		/* rta type */
+#endif
+			  "\x00\x00\x00\x00"	/* enc key length */
+			  "\x00\x00\x00\x00\x00\x00\x00\x00"
+			  "\x00\x00\x00\x00\x00\x00\x00\x00"
+			  "\x00\x00\x00\x00",
+		.klen   = 8 + 20 + 0,
+		.iv     = "",
+		.input  = "Network Security People Have A Strange Sense Of Humor",
+		.ilen   = 53,
+		.result = "Network Security People Have A Strange Sense Of Humor"
+			  "\x75\x6f\x42\x1e\xf8\x50\x21\xd2"
+			  "\x65\x47\xee\x8e\x1a\xef\x16\xf6"
+			  "\x91\x56\xe4\xd6",
+		.rlen   = 53 + 20,
+	},
+};
+
+static struct aead_testvec hmac_sha1_ecb_cipher_null_dec_tv_template[] = {
+	{
+#ifdef __LITTLE_ENDIAN
+		.key    = "\x08\x00"		/* rta length */
+			  "\x01\x00"		/* rta type */
+#else
+		.key    = "\x00\x08"		/* rta length */
+			  "\x00\x01"		/* rta type */
+#endif
+			  "\x00\x00\x00\x00"	/* enc key length */
+			  "\x00\x00\x00\x00\x00\x00\x00\x00"
+			  "\x00\x00\x00\x00\x00\x00\x00\x00"
+			  "\x00\x00\x00\x00",
+		.klen   = 8 + 20 + 0,
+		.iv     = "",
+		.input  = "\x01\x23\x45\x67\x89\xab\xcd\xef"
+			  "\x40\xc3\x0a\xa1\xc9\xa0\x28\xab"
+			  "\x99\x5e\x19\x04\xd1\x72\xef\xb8"
+			  "\x8c\x5e\xe4\x08",
+		.ilen   = 8 + 20,
+		.result = "\x01\x23\x45\x67\x89\xab\xcd\xef",
+		.rlen   = 8,
+	}, {
+#ifdef __LITTLE_ENDIAN
+		.key    = "\x08\x00"		/* rta length */
+			  "\x01\x00"		/* rta type */
+#else
+		.key    = "\x00\x08"		/* rta length */
+			  "\x00\x01"		/* rta type */
+#endif
+			  "\x00\x00\x00\x00"	/* enc key length */
+			  "\x00\x00\x00\x00\x00\x00\x00\x00"
+			  "\x00\x00\x00\x00\x00\x00\x00\x00"
+			  "\x00\x00\x00\x00",
+		.klen   = 8 + 20 + 0,
+		.iv     = "",
+		.input  = "Network Security People Have A Strange Sense Of Humor"
+			  "\x75\x6f\x42\x1e\xf8\x50\x21\xd2"
+			  "\x65\x47\xee\x8e\x1a\xef\x16\xf6"
+			  "\x91\x56\xe4\xd6",
+		.ilen   = 53 + 20,
+		.result = "Network Security People Have A Strange Sense Of Humor",
+		.rlen   = 53,
+	},
+};
+
 static struct aead_testvec hmac_sha256_aes_cbc_enc_tv_template[] = {
 	{ /* RFC 3602 Case 1 */
 #ifdef __LITTLE_ENDIAN

drivers/char/hw_random/atmel-rng.c

@@ -54,29 +54,22 @@ static int atmel_trng_probe(struct platform_device *pdev)
 	struct resource *res;
 	int ret;
 
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	if (!res)
-		return -EINVAL;
-
 	trng = devm_kzalloc(&pdev->dev, sizeof(*trng), GFP_KERNEL);
 	if (!trng)
 		return -ENOMEM;
 
-	if (!devm_request_mem_region(&pdev->dev, res->start,
-				     resource_size(res), pdev->name))
-		return -EBUSY;
-
-	trng->base = devm_ioremap(&pdev->dev, res->start, resource_size(res));
-	if (!trng->base)
-		return -EBUSY;
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	trng->base = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(trng->base))
+		return PTR_ERR(trng->base);
 
-	trng->clk = clk_get(&pdev->dev, NULL);
+	trng->clk = devm_clk_get(&pdev->dev, NULL);
 	if (IS_ERR(trng->clk))
 		return PTR_ERR(trng->clk);
 
 	ret = clk_enable(trng->clk);
 	if (ret)
-		goto err_enable;
+		return ret;
 
 	writel(TRNG_KEY | 1, trng->base + TRNG_CR);
 	trng->rng.name = pdev->name;
@@ -92,9 +85,6 @@ static int atmel_trng_probe(struct platform_device *pdev)
 
 err_register:
 	clk_disable(trng->clk);
-err_enable:
-	clk_put(trng->clk);
-
 	return ret;
 }
 
@@ -106,7 +96,6 @@ static int atmel_trng_remove(struct platform_device *pdev)
 
 	writel(TRNG_KEY, trng->base + TRNG_CR);
 	clk_disable(trng->clk);
-	clk_put(trng->clk);
 
 	return 0;
 }

drivers/char/hw_random/core.c

@@ -40,6 +40,7 @@
 #include <linux/miscdevice.h>
 #include <linux/delay.h>
 #include <linux/slab.h>
+#include <linux/random.h>
 #include <asm/uaccess.h>
 
 
@@ -301,9 +302,10 @@ static int register_miscdev(void)
 
 int hwrng_register(struct hwrng *rng)
 {
-	int must_register_misc;
 	int err = -EINVAL;
 	struct hwrng *old_rng, *tmp;
+	unsigned char bytes[16];
+	int bytes_read;
 
 	if (rng->name == NULL ||
 	    (rng->data_read == NULL && rng->read == NULL))
@@ -326,7 +328,6 @@ int hwrng_register(struct hwrng *rng)
 			goto out_unlock;
 	}
 
-	must_register_misc = (current_rng == NULL);
 	old_rng = current_rng;
 	if (!old_rng) {
 		err = hwrng_init(rng);
@@ -335,18 +336,20 @@ int hwrng_register(struct hwrng *rng)
 		current_rng = rng;
 	}
 	err = 0;
-	if (must_register_misc) {
+	if (!old_rng) {
 		err = register_miscdev();
 		if (err) {
-			if (!old_rng) {
-				hwrng_cleanup(rng);
-				current_rng = NULL;
-			}
+			hwrng_cleanup(rng);
+			current_rng = NULL;
 			goto out_unlock;
 		}
 	}
 	INIT_LIST_HEAD(&rng->list);
 	list_add_tail(&rng->list, &rng_list);
+
+	bytes_read = rng_get_data(rng, bytes, sizeof(bytes), 1);
+	if (bytes_read > 0)
+		add_device_randomness(bytes, bytes_read);
 out_unlock:
 	mutex_unlock(&rng_mutex);
 out:

drivers/char/hw_random/nomadik-rng.c

@@ -43,7 +43,7 @@ static int nmk_rng_probe(struct amba_device *dev, const struct amba_id *id)
 	void __iomem *base;
 	int ret;
 
-	rng_clk = clk_get(&dev->dev, NULL);
+	rng_clk = devm_clk_get(&dev->dev, NULL);
 	if (IS_ERR(rng_clk)) {
 		dev_err(&dev->dev, "could not get rng clock\n");
 		ret = PTR_ERR(rng_clk);
@@ -56,33 +56,28 @@ static int nmk_rng_probe(struct amba_device *dev, const struct amba_id *id)
 	if (ret)
 		goto out_clk;
 	ret = -ENOMEM;
-	base = ioremap(dev->res.start, resource_size(&dev->res));
+	base = devm_ioremap(&dev->dev, dev->res.start,
+			    resource_size(&dev->res));
 	if (!base)
 		goto out_release;
 	nmk_rng.priv = (unsigned long)base;
 	ret = hwrng_register(&nmk_rng);
 	if (ret)
-		goto out_unmap;
+		goto out_release;
 	return 0;
 
-out_unmap:
-	iounmap(base);
 out_release:
 	amba_release_regions(dev);
 out_clk:
 	clk_disable(rng_clk);
-	clk_put(rng_clk);
 	return ret;
 }
 
 static int nmk_rng_remove(struct amba_device *dev)
 {
-	void __iomem *base = (void __iomem *)nmk_rng.priv;
 	hwrng_unregister(&nmk_rng);
-	iounmap(base);
 	amba_release_regions(dev);
 	clk_disable(rng_clk);
-	clk_put(rng_clk);
 	return 0;
 }