Merge branch 'for-linus' of git://ftp.arm.linux.org.uk/~rmk/linux-arm

Pull ARM updates from Russell King:
 "Included in this update:

   - perf updates from Will Deacon:

     The main changes are callchain stability fixes from Jean Pihet and
     event mapping and PMU name rework from Mark Rutland

     The latter is preparatory work for enabling some code re-use with
     arm64 in the future.

   - updates for nommu from Uwe Kleine-König:

     Two different fixes for the same problem making some ARM nommu
     configurations not boot since 3.6-rc1.  The problem is that
     user_addr_max returned the biggest available RAM address which
     makes some copy_from_user variants fail to read from XIP memory.

   - deprecate legacy OMAP DMA API, in preparation for it's removal.

     The popular drivers have been converted over, leaving a very small
     number of rarely used drivers, which hopefully can be converted
     during the next cycle with a bit more visibility (and hopefully
     people popping out of the woodwork to help test)

   - more tweaks for BE systems, particularly with the kernel image
     format.  In connection with this, I've cleaned up the way we
     generate the linker script for the decompressor.

   - removal of hard-coded assumptions of the kernel stack size, making
     everywhere depend on the value of THREAD_SIZE_ORDER.

   - MCPM updates from Nicolas Pitre.

   - Make it easier for proper CPU part number checks (which should
     always include the vendor field).

   - Assembly code optimisation - use the "bx" instruction when
     returning from a function on ARMv6+ rather than "mov pc, reg".

   - Save the last kernel misaligned fault location and report it via
     the procfs alignment file.

   - Clean up the way we create the initial stack frame, which is a
     repeated pattern in several different locations.

   - Support for 8-byte get_user(), needed for some DRM implementations.

   - mcs locking from Will Deacon.

   - Save and restore a few more Cortex-A9 registers (for errata
     workarounds)

   - Fix various aspects of the SWP emulation, and the ELF hwcap for the
     SWP instruction.

   - Update LPAE logic for pte_write and pmd_write to make it more
     correct.

   - Support for Broadcom Brahma15 CPU cores.

   - ARM assembly crypto updates from Ard Biesheuvel"

* 'for-linus' of git://ftp.arm.linux.org.uk/~rmk/linux-arm: (53 commits)
  ARM: add comments to the early page table remap code
  ARM: 8122/1: smp_scu: enable SCU standby support
  ARM: 8121/1: smp_scu: use macro for SCU enable bit
  ARM: 8120/1: crypto: sha512: add ARM NEON implementation
  ARM: 8119/1: crypto: sha1: add ARM NEON implementation
  ARM: 8118/1: crypto: sha1/make use of common SHA-1 structures
  ARM: 8113/1: remove remaining definitions of PLAT_PHYS_OFFSET from <mach/memory.h>
  ARM: 8111/1: Enable erratum 798181 for Broadcom Brahma-B15
  ARM: 8110/1: do CPU-specific init for Broadcom Brahma15 cores
  ARM: 8109/1: mm: Modify pte_write and pmd_write logic for LPAE
  ARM: 8108/1: mm: Introduce {pte,pmd}_isset and {pte,pmd}_isclear
  ARM: hwcap: disable HWCAP_SWP if the CPU advertises it has exclusives
  ARM: SWP emulation: only initialise on ARMv7 CPUs
  ARM: SWP emulation: always enable when SMP is enabled
  ARM: 8103/1: save/restore Cortex-A9 CP15 registers on suspend/resume
  ARM: 8098/1: mcs lock: implement wfe-based polling for MCS locking
  ARM: 8091/2: add get_user() support for 8 byte types
  ARM: 8097/1: unistd.h: relocate comments back to place
  ARM: 8096/1: Describe required sort order for textofs-y (TEXT_OFFSET)
  ARM: 8090/1: add revision info for PL310 errata 588369 and 727915
  ...

7 files changed, 1624 insertions, 32 deletions

diff --git a/arch/arm/crypto/Makefile b/arch/arm/crypto/Makefile
index 81cda39860c5..b48fa341648d 100644
--- a/arch/arm/crypto/Makefile
+++ b/arch/arm/crypto/Makefile
@@ -5,10 +5,14 @@
 obj-$(CONFIG_CRYPTO_AES_ARM) += aes-arm.o
 obj-$(CONFIG_CRYPTO_AES_ARM_BS) += aes-arm-bs.o
 obj-$(CONFIG_CRYPTO_SHA1_ARM) += sha1-arm.o
+obj-$(CONFIG_CRYPTO_SHA1_ARM_NEON) += sha1-arm-neon.o
+obj-$(CONFIG_CRYPTO_SHA512_ARM_NEON) += sha512-arm-neon.o
 
 aes-arm-y	:= aes-armv4.o aes_glue.o
 aes-arm-bs-y	:= aesbs-core.o aesbs-glue.o
 sha1-arm-y	:= sha1-armv4-large.o sha1_glue.o
+sha1-arm-neon-y	:= sha1-armv7-neon.o sha1_neon_glue.o
+sha512-arm-neon-y := sha512-armv7-neon.o sha512_neon_glue.o
 
 quiet_cmd_perl = PERL    $@
       cmd_perl = $(PERL) $(<) > $(@)
diff --git a/arch/arm/crypto/aes-armv4.S b/arch/arm/crypto/aes-armv4.S
index 3a14ea8fe97e..ebb9761fb572 100644
--- a/arch/arm/crypto/aes-armv4.S
+++ b/arch/arm/crypto/aes-armv4.S
@@ -35,6 +35,7 @@
 @ that is being targetted.
 
 #include <linux/linkage.h>
+#include <asm/assembler.h>
 
 .text
 
@@ -648,7 +649,7 @@ _armv4_AES_set_encrypt_key:
 
 .Ldone:	mov	r0,#0
 	ldmia   sp!,{r4-r12,lr}
-.Labrt:	mov	pc,lr
+.Labrt:	ret	lr
 ENDPROC(private_AES_set_encrypt_key)
 
 .align	5
diff --git a/arch/arm/crypto/sha1-armv7-neon.S b/arch/arm/crypto/sha1-armv7-neon.S
new file mode 100644
index 000000000000..50013c0e2864
--- /dev/null
+++ b/arch/arm/crypto/sha1-armv7-neon.S
@@ -0,0 +1,634 @@
+/* sha1-armv7-neon.S - ARM/NEON accelerated SHA-1 transform function
+ *
+ * Copyright © 2013-2014 Jussi Kivilinna <jussi.kivilinna@iki.fi>
+ *
+ * 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
+ * Software Foundation; either version 2 of the License, or (at your option)
+ * any later version.
+ */
+
+#include <linux/linkage.h>
+
+
+.syntax unified
+.code   32
+.fpu neon
+
+.text
+
+
+/* Context structure */
+
+#define state_h0 0
+#define state_h1 4
+#define state_h2 8
+#define state_h3 12
+#define state_h4 16
+
+
+/* Constants */
+
+#define K1  0x5A827999
+#define K2  0x6ED9EBA1
+#define K3  0x8F1BBCDC
+#define K4  0xCA62C1D6
+.align 4
+.LK_VEC:
+.LK1:	.long K1, K1, K1, K1
+.LK2:	.long K2, K2, K2, K2
+.LK3:	.long K3, K3, K3, K3
+.LK4:	.long K4, K4, K4, K4
+
+
+/* Register macros */
+
+#define RSTATE r0
+#define RDATA r1
+#define RNBLKS r2
+#define ROLDSTACK r3
+#define RWK lr
+
+#define _a r4
+#define _b r5
+#define _c r6
+#define _d r7
+#define _e r8
+
+#define RT0 r9
+#define RT1 r10
+#define RT2 r11
+#define RT3 r12
+
+#define W0 q0
+#define W1 q1
+#define W2 q2
+#define W3 q3
+#define W4 q4
+#define W5 q5
+#define W6 q6
+#define W7 q7
+
+#define tmp0 q8
+#define tmp1 q9
+#define tmp2 q10
+#define tmp3 q11
+
+#define qK1 q12
+#define qK2 q13
+#define qK3 q14
+#define qK4 q15
+
+
+/* Round function macros. */
+
+#define WK_offs(i) (((i) & 15) * 4)
+
+#define _R_F1(a,b,c,d,e,i,pre1,pre2,pre3,i16,\
+	      W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
+	ldr RT3, [sp, WK_offs(i)]; \
+		pre1(i16,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28); \
+	bic RT0, d, b; \
+	add e, e, a, ror #(32 - 5); \
+	and RT1, c, b; \
+		pre2(i16,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28); \
+	add RT0, RT0, RT3; \
+	add e, e, RT1; \
+	ror b, #(32 - 30); \
+		pre3(i16,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28); \
+	add e, e, RT0;
+
+#define _R_F2(a,b,c,d,e,i,pre1,pre2,pre3,i16,\
+	      W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
+	ldr RT3, [sp, WK_offs(i)]; \
+		pre1(i16,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28); \
+	eor RT0, d, b; \
+	add e, e, a, ror #(32 - 5); \
+	eor RT0, RT0, c; \
+		pre2(i16,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28); \
+	add e, e, RT3; \
+	ror b, #(32 - 30); \
+		pre3(i16,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28); \
+	add e, e, RT0; \
+
+#define _R_F3(a,b,c,d,e,i,pre1,pre2,pre3,i16,\
+	      W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
+	ldr RT3, [sp, WK_offs(i)]; \
+		pre1(i16,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28); \
+	eor RT0, b, c; \
+	and RT1, b, c; \
+	add e, e, a, ror #(32 - 5); \
+		pre2(i16,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28); \
+	and RT0, RT0, d; \
+	add RT1, RT1, RT3; \
+	add e, e, RT0; \
+	ror b, #(32 - 30); \
+		pre3(i16,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28); \
+	add e, e, RT1;
+
+#define _R_F4(a,b,c,d,e,i,pre1,pre2,pre3,i16,\
+	      W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
+	_R_F2(a,b,c,d,e,i,pre1,pre2,pre3,i16,\
+	      W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28)
+
+#define _R(a,b,c,d,e,f,i,pre1,pre2,pre3,i16,\
+           W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
+	_R_##f(a,b,c,d,e,i,pre1,pre2,pre3,i16,\
+	       W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28)
+
+#define R(a,b,c,d,e,f,i) \
+	_R_##f(a,b,c,d,e,i,dummy,dummy,dummy,i16,\
+	       W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28)
+
+#define dummy(...)
+
+
+/* Input expansion macros. */
+
+/********* Precalc macros for rounds 0-15 *************************************/
+
+#define W_PRECALC_00_15() \
+	add       RWK, sp, #(WK_offs(0));			\
+	\
+	vld1.32   {tmp0, tmp1}, [RDATA]!;			\
+	vrev32.8  W0, tmp0;		/* big => little */	\
+	vld1.32   {tmp2, tmp3}, [RDATA]!;			\
+	vadd.u32  tmp0, W0, curK;				\
+	vrev32.8  W7, tmp1;		/* big => little */	\
+	vrev32.8  W6, tmp2;		/* big => little */	\
+	vadd.u32  tmp1, W7, curK;				\
+	vrev32.8  W5, tmp3;		/* big => little */	\
+	vadd.u32  tmp2, W6, curK;				\
+	vst1.32   {tmp0, tmp1}, [RWK]!;				\
+	vadd.u32  tmp3, W5, curK;				\
+	vst1.32   {tmp2, tmp3}, [RWK];				\
+
+#define WPRECALC_00_15_0(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
+	vld1.32   {tmp0, tmp1}, [RDATA]!;			\
+
+#define WPRECALC_00_15_1(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
+	add       RWK, sp, #(WK_offs(0));			\
+
+#define WPRECALC_00_15_2(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
+	vrev32.8  W0, tmp0;		/* big => little */	\
+
+#define WPRECALC_00_15_3(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
+	vld1.32   {tmp2, tmp3}, [RDATA]!;			\
+
+#define WPRECALC_00_15_4(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
+	vadd.u32  tmp0, W0, curK;				\
+
+#define WPRECALC_00_15_5(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
+	vrev32.8  W7, tmp1;		/* big => little */	\
+
+#define WPRECALC_00_15_6(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
+	vrev32.8  W6, tmp2;		/* big => little */	\
+
+#define WPRECALC_00_15_7(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
+	vadd.u32  tmp1, W7, curK;				\
+
+#define WPRECALC_00_15_8(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
+	vrev32.8  W5, tmp3;		/* big => little */	\
+
+#define WPRECALC_00_15_9(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
+	vadd.u32  tmp2, W6, curK;				\
+
+#define WPRECALC_00_15_10(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
+	vst1.32   {tmp0, tmp1}, [RWK]!;				\
+
+#define WPRECALC_00_15_11(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
+	vadd.u32  tmp3, W5, curK;				\
+
+#define WPRECALC_00_15_12(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
+	vst1.32   {tmp2, tmp3}, [RWK];				\
+
+
+/********* Precalc macros for rounds 16-31 ************************************/
+
+#define WPRECALC_16_31_0(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
+	veor      tmp0, tmp0;			\
+	vext.8    W, W_m16, W_m12, #8;		\
+
+#define WPRECALC_16_31_1(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
+	add       RWK, sp, #(WK_offs(i));	\
+	vext.8    tmp0, W_m04, tmp0, #4;	\
+
+#define WPRECALC_16_31_2(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
+	veor      tmp0, tmp0, W_m16;		\
+	veor.32   W, W, W_m08;			\
+
+#define WPRECALC_16_31_3(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
+	veor      tmp1, tmp1;			\
+	veor      W, W, tmp0;			\
+
+#define WPRECALC_16_31_4(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
+	vshl.u32  tmp0, W, #1;			\
+
+#define WPRECALC_16_31_5(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
+	vext.8    tmp1, tmp1, W, #(16-12);	\
+	vshr.u32  W, W, #31;			\
+
+#define WPRECALC_16_31_6(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
+	vorr      tmp0, tmp0, W;		\
+	vshr.u32  W, tmp1, #30;			\
+
+#define WPRECALC_16_31_7(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
+	vshl.u32  tmp1, tmp1, #2;		\
+
+#define WPRECALC_16_31_8(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
+	veor      tmp0, tmp0, W;		\
+
+#define WPRECALC_16_31_9(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
+	veor      W, tmp0, tmp1;		\
+
+#define WPRECALC_16_31_10(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
+	vadd.u32  tmp0, W, curK;		\
+
+#define WPRECALC_16_31_11(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
+	vst1.32   {tmp0}, [RWK];
+
+
+/********* Precalc macros for rounds 32-79 ************************************/
+
+#define WPRECALC_32_79_0(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
+	veor W, W_m28; \
+
+#define WPRECALC_32_79_1(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
+	vext.8 tmp0, W_m08, W_m04, #8; \
+
+#define WPRECALC_32_79_2(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
+	veor W, W_m16; \
+
+#define WPRECALC_32_79_3(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
+	veor W, tmp0; \
+
+#define WPRECALC_32_79_4(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
+	add RWK, sp, #(WK_offs(i&~3)); \
+
+#define WPRECALC_32_79_5(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
+	vshl.u32 tmp1, W, #2; \
+
+#define WPRECALC_32_79_6(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
+	vshr.u32 tmp0, W, #30; \
+
+#define WPRECALC_32_79_7(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
+	vorr W, tmp0, tmp1; \
+
+#define WPRECALC_32_79_8(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
+	vadd.u32 tmp0, W, curK; \
+
+#define WPRECALC_32_79_9(i,W,W_m04,W_m08,W_m12,W_m16,W_m20,W_m24,W_m28) \
+	vst1.32 {tmp0}, [RWK];
+
+
+/*
+ * Transform nblks*64 bytes (nblks*16 32-bit words) at DATA.
+ *
+ * unsigned int
+ * sha1_transform_neon (void *ctx, const unsigned char *data,
+ *                      unsigned int nblks)
+ */
+.align 3
+ENTRY(sha1_transform_neon)
+  /* input:
+   *	r0: ctx, CTX
+   *	r1: data (64*nblks bytes)
+   *	r2: nblks
+   */
+
+  cmp RNBLKS, #0;
+  beq .Ldo_nothing;
+
+  push {r4-r12, lr};
+  /*vpush {q4-q7};*/
+
+  adr RT3, .LK_VEC;
+
+  mov ROLDSTACK, sp;
+
+  /* Align stack. */
+  sub RT0, sp, #(16*4);
+  and RT0, #(~(16-1));
+  mov sp, RT0;
+
+  vld1.32 {qK1-qK2}, [RT3]!; /* Load K1,K2 */
+
+  /* Get the values of the chaining variables. */
+  ldm RSTATE, {_a-_e};
+
+  vld1.32 {qK3-qK4}, [RT3]; /* Load K3,K4 */
+
+#undef curK
+#define curK qK1
+  /* Precalc 0-15. */
+  W_PRECALC_00_15();
+
+.Loop:
+  /* Transform 0-15 + Precalc 16-31. */
+  _R( _a, _b, _c, _d, _e, F1,  0,
+      WPRECALC_16_31_0, WPRECALC_16_31_1, WPRECALC_16_31_2, 16,
+      W4, W5, W6, W7, W0, _, _, _ );
+  _R( _e, _a, _b, _c, _d, F1,  1,
+      WPRECALC_16_31_3, WPRECALC_16_31_4, WPRECALC_16_31_5, 16,
+      W4, W5, W6, W7, W0, _, _, _ );
+  _R( _d, _e, _a, _b, _c, F1,  2,
+      WPRECALC_16_31_6, WPRECALC_16_31_7, WPRECALC_16_31_8, 16,
+      W4, W5, W6, W7, W0, _, _, _ );
+  _R( _c, _d, _e, _a, _b, F1,  3,
+      WPRECALC_16_31_9, WPRECALC_16_31_10,WPRECALC_16_31_11,16,
+      W4, W5, W6, W7, W0, _, _, _ );
+
+#undef curK
+#define curK qK2
+  _R( _b, _c, _d, _e, _a, F1,  4,
+      WPRECALC_16_31_0, WPRECALC_16_31_1, WPRECALC_16_31_2, 20,
+      W3, W4, W5, W6, W7, _, _, _ );
+  _R( _a, _b, _c, _d, _e, F1,  5,
+      WPRECALC_16_31_3, WPRECALC_16_31_4, WPRECALC_16_31_5, 20,
+      W3, W4, W5, W6, W7, _, _, _ );
+  _R( _e, _a, _b, _c, _d, F1,  6,
+      WPRECALC_16_31_6, WPRECALC_16_31_7, WPRECALC_16_31_8, 20,
+      W3, W4, W5, W6, W7, _, _, _ );
+  _R( _d, _e, _a, _b, _c, F1,  7,
+      WPRECALC_16_31_9, WPRECALC_16_31_10,WPRECALC_16_31_11,20,
+      W3, W4, W5, W6, W7, _, _, _ );
+
+  _R( _c, _d, _e, _a, _b, F1,  8,
+      WPRECALC_16_31_0, WPRECALC_16_31_1, WPRECALC_16_31_2, 24,
+      W2, W3, W4, W5, W6, _, _, _ );
+  _R( _b, _c, _d, _e, _a, F1,  9,
+      WPRECALC_16_31_3, WPRECALC_16_31_4, WPRECALC_16_31_5, 24,
+      W2, W3, W4, W5, W6, _, _, _ );
+  _R( _a, _b, _c, _d, _e, F1, 10,
+      WPRECALC_16_31_6, WPRECALC_16_31_7, WPRECALC_16_31_8, 24,
+      W2, W3, W4, W5, W6, _, _, _ );
+  _R( _e, _a, _b, _c, _d, F1, 11,
+      WPRECALC_16_31_9, WPRECALC_16_31_10,WPRECALC_16_31_11,24,
+      W2, W3, W4, W5, W6, _, _, _ );
+
+  _R( _d, _e, _a, _b, _c, F1, 12,
+      WPRECALC_16_31_0, WPRECALC_16_31_1, WPRECALC_16_31_2, 28,
+      W1, W2, W3, W4, W5, _, _, _ );
+  _R( _c, _d, _e, _a, _b, F1, 13,
+      WPRECALC_16_31_3, WPRECALC_16_31_4, WPRECALC_16_31_5, 28,
+      W1, W2, W3, W4, W5, _, _, _ );
+  _R( _b, _c, _d, _e, _a, F1, 14,
+      WPRECALC_16_31_6, WPRECALC_16_31_7, WPRECALC_16_31_8, 28,
+      W1, W2, W3, W4, W5, _, _, _ );
+  _R( _a, _b, _c, _d, _e, F1, 15,
+      WPRECALC_16_31_9, WPRECALC_16_31_10,WPRECALC_16_31_11,28,
+      W1, W2, W3, W4, W5, _, _, _ );
+
+  /* Transform 16-63 + Precalc 32-79. */
+  _R( _e, _a, _b, _c, _d, F1, 16,
+      WPRECALC_32_79_0, WPRECALC_32_79_1, WPRECALC_32_79_2, 32,
+      W0, W1, W2, W3, W4, W5, W6, W7);
+  _R( _d, _e, _a, _b, _c, F1, 17,
+      WPRECALC_32_79_3, WPRECALC_32_79_4, WPRECALC_32_79_5, 32,
+      W0, W1, W2, W3, W4, W5, W6, W7);
+  _R( _c, _d, _e, _a, _b, F1, 18,
+      WPRECALC_32_79_6, dummy,            WPRECALC_32_79_7, 32,
+      W0, W1, W2, W3, W4, W5, W6, W7);
+  _R( _b, _c, _d, _e, _a, F1, 19,
+      WPRECALC_32_79_8, dummy,            WPRECALC_32_79_9, 32,
+      W0, W1, W2, W3, W4, W5, W6, W7);
+
+  _R( _a, _b, _c, _d, _e, F2, 20,
+      WPRECALC_32_79_0, WPRECALC_32_79_1, WPRECALC_32_79_2, 36,
+      W7, W0, W1, W2, W3, W4, W5, W6);
+  _R( _e, _a, _b, _c, _d, F2, 21,
+      WPRECALC_32_79_3, WPRECALC_32_79_4, WPRECALC_32_79_5, 36,
+      W7, W0, W1, W2, W3, W4, W5, W6);
+  _R( _d, _e, _a, _b, _c, F2, 22,
+      WPRECALC_32_79_6, dummy,            WPRECALC_32_79_7, 36,
+      W7, W0, W1, W2, W3, W4, W5, W6);
+  _R( _c, _d, _e, _a, _b, F2, 23,
+      WPRECALC_32_79_8, dummy,            WPRECALC_32_79_9, 36,
+      W7, W0, W1, W2, W3, W4, W5, W6);
+
+#undef curK
+#define curK qK3
+  _R( _b, _c, _d, _e, _a, F2, 24,
+      WPRECALC_32_79_0, WPRECALC_32_79_1, WPRECALC_32_79_2, 40,
+      W6, W7, W0, W1, W2, W3, W4, W5);
+  _R( _a, _b, _c, _d, _e, F2, 25,
+      WPRECALC_32_79_3, WPRECALC_32_79_4, WPRECALC_32_79_5, 40,
+      W6, W7, W0, W1, W2, W3, W4, W5);
+  _R( _e, _a, _b, _c, _d, F2, 26,
+      WPRECALC_32_79_6, dummy,            WPRECALC_32_79_7, 40,
+      W6, W7, W0, W1, W2, W3, W4, W5);
+  _R( _d, _e, _a, _b, _c, F2, 27,
+      WPRECALC_32_79_8, dummy,            WPRECALC_32_79_9, 40,
+      W6, W7, W0, W1, W2, W3, W4, W5);
+
+  _R( _c, _d, _e, _a, _b, F2, 28,
+      WPRECALC_32_79_0, WPRECALC_32_79_1, WPRECALC_32_79_2, 44,
+      W5, W6, W7, W0, W1, W2, W3, W4);
+  _R( _b, _c, _d, _e, _a, F2, 29,
+      WPRECALC_32_79_3, WPRECALC_32_79_4, WPRECALC_32_79_5, 44,
+      W5, W6, W7, W0, W1, W2, W3, W4);
+  _R( _a, _b, _c, _d, _e, F2, 30,
+      WPRECALC_32_79_6, dummy,            WPRECALC_32_79_7, 44,
+      W5, W6, W7, W0, W1, W2, W3, W4);
+  _R( _e, _a, _b, _c, _d, F2, 31,
+      WPRECALC_32_79_8, dummy,            WPRECALC_32_79_9, 44,
+      W5, W6, W7, W0, W1, W2, W3, W4);
+
+  _R( _d, _e, _a, _b, _c, F2, 32,
+      WPRECALC_32_79_0, WPRECALC_32_79_1, WPRECALC_32_79_2, 48,
+      W4, W5, W6, W7, W0, W1, W2, W3);
+  _R( _c, _d, _e, _a, _b, F2, 33,
+      WPRECALC_32_79_3, WPRECALC_32_79_4, WPRECALC_32_79_5, 48,
+      W4, W5, W6, W7, W0, W1, W2, W3);
+  _R( _b, _c, _d, _e, _a, F2, 34,
+      WPRECALC_32_79_6, dummy,            WPRECALC_32_79_7, 48,
+      W4, W5, W6, W7, W0, W1, W2, W3);
+  _R( _a, _b, _c, _d, _e, F2, 35,
+      WPRECALC_32_79_8, dummy,            WPRECALC_32_79_9, 48,
+      W4, W5, W6, W7, W0, W1, W2, W3);
+
+  _R( _e, _a, _b, _c, _d, F2, 36,
+      WPRECALC_32_79_0, WPRECALC_32_79_1, WPRECALC_32_79_2, 52,
+      W3, W4, W5, W6, W7, W0, W1, W2);
+  _R( _d, _e, _a, _b, _c, F2, 37,
+      WPRECALC_32_79_3, WPRECALC_32_79_4, WPRECALC_32_79_5, 52,
+      W3, W4, W5, W6, W7, W0, W1, W2);
+  _R( _c, _d, _e, _a, _b, F2, 38,
+      WPRECALC_32_79_6, dummy,            WPRECALC_32_79_7, 52,
+      W3, W4, W5, W6, W7, W0, W1, W2);
+  _R( _b, _c, _d, _e, _a, F2, 39,
+      WPRECALC_32_79_8, dummy,            WPRECALC_32_79_9, 52,
+      W3, W4, W5, W6, W7, W0, W1, W2);
+
+  _R( _a, _b, _c, _d, _e, F3, 40,
+      WPRECALC_32_79_0, WPRECALC_32_79_1, WPRECALC_32_79_2, 56,
+      W2, W3, W4, W5, W6, W7, W0, W1);
+  _R( _e, _a, _b, _c, _d, F3, 41,
+      WPRECALC_32_79_3, WPRECALC_32_79_4, WPRECALC_32_79_5, 56,
+      W2, W3, W4, W5, W6, W7, W0, W1);
+  _R( _d, _e, _a, _b, _c, F3, 42,
+      WPRECALC_32_79_6, dummy,            WPRECALC_32_79_7, 56,
+      W2, W3, W4, W5, W6, W7, W0, W1);
+  _R( _c, _d, _e, _a, _b, F3, 43,
+      WPRECALC_32_79_8, dummy,            WPRECALC_32_79_9, 56,
+      W2, W3, W4, W5, W6, W7, W0, W1);
+
+#undef curK
+#define curK qK4
+  _R( _b, _c, _d, _e, _a, F3, 44,
+      WPRECALC_32_79_0, WPRECALC_32_79_1, WPRECALC_32_79_2, 60,
+      W1, W2, W3, W4, W5, W6, W7, W0);
+  _R( _a, _b, _c, _d, _e, F3, 45,
+      WPRECALC_32_79_3, WPRECALC_32_79_4, WPRECALC_32_79_5, 60,
+      W1, W2, W3, W4, W5, W6, W7, W0);
+  _R( _e, _a, _b, _c, _d, F3, 46,
+      WPRECALC_32_79_6, dummy,            WPRECALC_32_79_7, 60,
+      W1, W2, W3, W4, W5, W6, W7, W0);
+  _R( _d, _e, _a, _b, _c, F3, 47,
+      WPRECALC_32_79_8, dummy,            WPRECALC_32_79_9, 60,
+      W1, W2, W3, W4, W5, W6, W7, W0);
+
+  _R( _c, _d, _e, _a, _b, F3, 48,
+      WPRECALC_32_79_0, WPRECALC_32_79_1, WPRECALC_32_79_2, 64,
+      W0, W1, W2, W3, W4, W5, W6, W7);
+  _R( _b, _c, _d, _e, _a, F3, 49,
+      WPRECALC_32_79_3, WPRECALC_32_79_4, WPRECALC_32_79_5, 64,
+      W0, W1, W2, W3, W4, W5, W6, W7);
+  _R( _a, _b, _c, _d, _e, F3, 50,
+      WPRECALC_32_79_6, dummy,            WPRECALC_32_79_7, 64,
+      W0, W1, W2, W3, W4, W5, W6, W7);
+  _R( _e, _a, _b, _c, _d, F3, 51,
+      WPRECALC_32_79_8, dummy,            WPRECALC_32_79_9, 64,
+      W0, W1, W2, W3, W4, W5, W6, W7);
+
+  _R( _d, _e, _a, _b, _c, F3, 52,
+      WPRECALC_32_79_0, WPRECALC_32_79_1, WPRECALC_32_79_2, 68,
+      W7, W0, W1, W2, W3, W4, W5, W6);
+  _R( _c, _d, _e, _a, _b, F3, 53,
+      WPRECALC_32_79_3, WPRECALC_32_79_4, WPRECALC_32_79_5, 68,
+      W7, W0, W1, W2, W3, W4, W5, W6);
+  _R( _b, _c, _d, _e, _a, F3, 54,
+      WPRECALC_32_79_6, dummy,            WPRECALC_32_79_7, 68,
+      W7, W0, W1, W2, W3, W4, W5, W6);
+  _R( _a, _b, _c, _d, _e, F3, 55,
+      WPRECALC_32_79_8, dummy,            WPRECALC_32_79_9, 68,
+      W7, W0, W1, W2, W3, W4, W5, W6);
+
+  _R( _e, _a, _b, _c, _d, F3, 56,
+      WPRECALC_32_79_0, WPRECALC_32_79_1, WPRECALC_32_79_2, 72,
+      W6, W7, W0, W1, W2, W3, W4, W5);
+  _R( _d, _e, _a, _b, _c, F3, 57,
+      WPRECALC_32_79_3, WPRECALC_32_79_4, WPRECALC_32_79_5, 72,
+      W6, W7, W0, W1, W2, W3, W4, W5);
+  _R( _c, _d, _e, _a, _b, F3, 58,
+      WPRECALC_32_79_6, dummy,            WPRECALC_32_79_7, 72,
+      W6, W7, W0, W1, W2, W3, W4, W5);
+  _R( _b, _c, _d, _e, _a, F3, 59,
+      WPRECALC_32_79_8, dummy,            WPRECALC_32_79_9, 72,
+      W6, W7, W0, W1, W2, W3, W4, W5);
+
+  subs RNBLKS, #1;
+
+  _R( _a, _b, _c, _d, _e, F4, 60,
+      WPRECALC_32_79_0, WPRECALC_32_79_1, WPRECALC_32_79_2, 76,
+      W5, W6, W7, W0, W1, W2, W3, W4);
+  _R( _e, _a, _b, _c, _d, F4, 61,
+      WPRECALC_32_79_3, WPRECALC_32_79_4, WPRECALC_32_79_5, 76,
+      W5, W6, W7, W0, W1, W2, W3, W4);
+  _R( _d, _e, _a, _b, _c, F4, 62,
+      WPRECALC_32_79_6, dummy,            WPRECALC_32_79_7, 76,
+      W5, W6, W7, W0, W1, W2, W3, W4);
+  _R( _c, _d, _e, _a, _b, F4, 63,
+      WPRECALC_32_79_8, dummy,            WPRECALC_32_79_9, 76,
+      W5, W6, W7, W0, W1, W2, W3, W4);
+
+  beq .Lend;
+
+  /* Transform 64-79 + Precalc 0-15 of next block. */
+#undef curK
+#define curK qK1
+  _R( _b, _c, _d, _e, _a, F4, 64,
+      WPRECALC_00_15_0, dummy, dummy, _, _, _, _, _, _, _, _, _ );
+  _R( _a, _b, _c, _d, _e, F4, 65,
+      WPRECALC_00_15_1, dummy, dummy, _, _, _, _, _, _, _, _, _ );
+  _R( _e, _a, _b, _c, _d, F4, 66,
+      WPRECALC_00_15_2, dummy, dummy, _, _, _, _, _, _, _, _, _ );
+  _R( _d, _e, _a, _b, _c, F4, 67,
+      WPRECALC_00_15_3, dummy, dummy, _, _, _, _, _, _, _, _, _ );
+
+  _R( _c, _d, _e, _a, _b, F4, 68,
+      dummy,            dummy, dummy, _, _, _, _, _, _, _, _, _ );
+  _R( _b, _c, _d, _e, _a, F4, 69,
+      dummy,            dummy, dummy, _, _, _, _, _, _, _, _, _ );
+  _R( _a, _b, _c, _d, _e, F4, 70,
+      WPRECALC_00_15_4, dummy, dummy, _, _, _, _, _, _, _, _, _ );
+  _R( _e, _a, _b, _c, _d, F4, 71,
+      WPRECALC_00_15_5, dummy, dummy, _, _, _, _, _, _, _, _, _ );
+
+  _R( _d, _e, _a, _b, _c, F4, 72,
+      dummy,            dummy, dummy, _, _, _, _, _, _, _, _, _ );
+  _R( _c, _d, _e, _a, _b, F4, 73,
+      dummy,            dummy, dummy, _, _, _, _, _, _, _, _, _ );
+  _R( _b, _c, _d, _e, _a, F4, 74,
+      WPRECALC_00_15_6, dummy, dummy, _, _, _, _, _, _, _, _, _ );
+  _R( _a, _b, _c, _d, _e, F4, 75,
+      WPRECALC_00_15_7, dummy, dummy, _, _, _, _, _, _, _, _, _ );
+
+  _R( _e, _a, _b, _c, _d, F4, 76,
+      WPRECALC_00_15_8, dummy, dummy, _, _, _, _, _, _, _, _, _ );
+  _R( _d, _e, _a, _b, _c, F4, 77,
+      WPRECALC_00_15_9, dummy, dummy, _, _, _, _, _, _, _, _, _ );
+  _R( _c, _d, _e, _a, _b, F4, 78,
+      WPRECALC_00_15_10, dummy, dummy, _, _, _, _, _, _, _, _, _ );
+  _R( _b, _c, _d, _e, _a, F4, 79,
+      WPRECALC_00_15_11, dummy, WPRECALC_00_15_12, _, _, _, _, _, _, _, _, _ );
+
+  /* Update the chaining variables. */
+  ldm RSTATE, {RT0-RT3};
+  add _a, RT0;
+  ldr RT0, [RSTATE, #state_h4];
+  add _b, RT1;
+  add _c, RT2;
+  add _d, RT3;
+  add _e, RT0;
+  stm RSTATE, {_a-_e};
+
+  b .Loop;
+
+.Lend:
+  /* Transform 64-79 */
+  R( _b, _c, _d, _e, _a, F4, 64 );
+  R( _a, _b, _c, _d, _e, F4, 65 );
+  R( _e, _a, _b, _c, _d, F4, 66 );
+  R( _d, _e, _a, _b, _c, F4, 67 );
+  R( _c, _d, _e, _a, _b, F4, 68 );
+  R( _b, _c, _d, _e, _a, F4, 69 );
+  R( _a, _b, _c, _d, _e, F4, 70 );
+  R( _e, _a, _b, _c, _d, F4, 71 );
+  R( _d, _e, _a, _b, _c, F4, 72 );
+  R( _c, _d, _e, _a, _b, F4, 73 );
+  R( _b, _c, _d, _e, _a, F4, 74 );
+  R( _a, _b, _c, _d, _e, F4, 75 );
+  R( _e, _a, _b, _c, _d, F4, 76 );
+  R( _d, _e, _a, _b, _c, F4, 77 );
+  R( _c, _d, _e, _a, _b, F4, 78 );
+  R( _b, _c, _d, _e, _a, F4, 79 );
+
+  mov sp, ROLDSTACK;
+
+  /* Update the chaining variables. */
+  ldm RSTATE, {RT0-RT3};
+  add _a, RT0;
+  ldr RT0, [RSTATE, #state_h4];
+  add _b, RT1;
+  add _c, RT2;
+  add _d, RT3;
+  /*vpop {q4-q7};*/
+  add _e, RT0;
+  stm RSTATE, {_a-_e};
+
+  pop {r4-r12, pc};
+
+.Ldo_nothing:
+  bx lr
+ENDPROC(sha1_transform_neon)
diff --git a/arch/arm/crypto/sha1_glue.c b/arch/arm/crypto/sha1_glue.c
index 76cd976230bc..84f2a756588b 100644
--- a/arch/arm/crypto/sha1_glue.c
+++ b/arch/arm/crypto/sha1_glue.c
@@ -23,32 +23,27 @@
 #include <linux/types.h>
 #include <crypto/sha.h>
 #include <asm/byteorder.h>
+#include <asm/crypto/sha1.h>
 
-struct SHA1_CTX {
-	uint32_t h0,h1,h2,h3,h4;
-	u64 count;
-	u8 data[SHA1_BLOCK_SIZE];
-};
 
-asmlinkage void sha1_block_data_order(struct SHA1_CTX *digest,
+asmlinkage void sha1_block_data_order(u32 *digest,
 		const unsigned char *data, unsigned int rounds);
 
 
 static int sha1_init(struct shash_desc *desc)
 {
-	struct SHA1_CTX *sctx = shash_desc_ctx(desc);
-	memset(sctx, 0, sizeof(*sctx));
-	sctx->h0 = SHA1_H0;
-	sctx->h1 = SHA1_H1;
-	sctx->h2 = SHA1_H2;
-	sctx->h3 = SHA1_H3;
-	sctx->h4 = SHA1_H4;
+	struct sha1_state *sctx = shash_desc_ctx(desc);
+
+	*sctx = (struct sha1_state){
+		.state = { SHA1_H0, SHA1_H1, SHA1_H2, SHA1_H3, SHA1_H4 },
+	};
+
 	return 0;
 }
 
 
-static int __sha1_update(struct SHA1_CTX *sctx, const u8 *data,
-			       unsigned int len, unsigned int partial)
+static int __sha1_update(struct sha1_state *sctx, const u8 *data,
+			 unsigned int len, unsigned int partial)
 {
 	unsigned int done = 0;
 
@@ -56,43 +51,44 @@ static int __sha1_update(struct SHA1_CTX *sctx, const u8 *data,
 
 	if (partial) {
 		done = SHA1_BLOCK_SIZE - partial;
-		memcpy(sctx->data + partial, data, done);
-		sha1_block_data_order(sctx, sctx->data, 1);
+		memcpy(sctx->buffer + partial, data, done);
+		sha1_block_data_order(sctx->state, sctx->buffer, 1);
 	}
 
 	if (len - done >= SHA1_BLOCK_SIZE) {
 		const unsigned int rounds = (len - done) / SHA1_BLOCK_SIZE;
-		sha1_block_data_order(sctx, data + done, rounds);
+		sha1_block_data_order(sctx->state, data + done, rounds);
 		done += rounds * SHA1_BLOCK_SIZE;
 	}
 
-	memcpy(sctx->data, data + done, len - done);
+	memcpy(sctx->buffer, data + done, len - done);
 	return 0;
 }
 
 
-static int sha1_update(struct shash_desc *desc, const u8 *data,
-			     unsigned int len)
+int sha1_update_arm(struct shash_desc *desc, const u8 *data,
+		    unsigned int len)
 {
-	struct SHA1_CTX *sctx = shash_desc_ctx(desc);
+	struct sha1_state *sctx = shash_desc_ctx(desc);
 	unsigned int partial = sctx->count % SHA1_BLOCK_SIZE;
 	int res;
 
 	/* Handle the fast case right here */
 	if (partial + len < SHA1_BLOCK_SIZE) {
 		sctx->count += len;
-		memcpy(sctx->data + partial, data, len);
+		memcpy(sctx->buffer + partial, data, len);
 		return 0;
 	}
 	res = __sha1_update(sctx, data, len, partial);
 	return res;
 }
+EXPORT_SYMBOL_GPL(sha1_update_arm);
 
 
 /* Add padding and return the message digest. */
 static int sha1_final(struct shash_desc *desc, u8 *out)
 {
-	struct SHA1_CTX *sctx = shash_desc_ctx(desc);
+	struct sha1_state *sctx = shash_desc_ctx(desc);
 	unsigned int i, index, padlen;
 	__be32 *dst = (__be32 *)out;
 	__be64 bits;
@@ -106,7 +102,7 @@ static int sha1_final(struct shash_desc *desc, u8 *out)
 	/* We need to fill a whole block for __sha1_update() */
 	if (padlen <= 56) {
 		sctx->count += padlen;
-		memcpy(sctx->data + index, padding, padlen);
+		memcpy(sctx->buffer + index, padding, padlen);
 	} else {
 		__sha1_update(sctx, padding, padlen, index);
 	}
@@ -114,7 +110,7 @@ static int sha1_final(struct shash_desc *desc, u8 *out)
 
 	/* Store state in digest */
 	for (i = 0; i < 5; i++)
-		dst[i] = cpu_to_be32(((u32 *)sctx)[i]);
+		dst[i] = cpu_to_be32(sctx->state[i]);
 
 	/* Wipe context */
 	memset(sctx, 0, sizeof(*sctx));
@@ -124,7 +120,7 @@ static int sha1_final(struct shash_desc *desc, u8 *out)
 
 static int sha1_export(struct shash_desc *desc, void *out)
 {
-	struct SHA1_CTX *sctx = shash_desc_ctx(desc);
+	struct sha1_state *sctx = shash_desc_ctx(desc);
 	memcpy(out, sctx, sizeof(*sctx));
 	return 0;
 }
@@ -132,7 +128,7 @@ static int sha1_export(struct shash_desc *desc, void *out)
 
 static int sha1_import(struct shash_desc *desc, const void *in)
 {
-	struct SHA1_CTX *sctx = shash_desc_ctx(desc);
+	struct sha1_state *sctx = shash_desc_ctx(desc);
 	memcpy(sctx, in, sizeof(*sctx));
 	return 0;
 }
@@ -141,12 +137,12 @@ static int sha1_import(struct shash_desc *desc, const void *in)
 static struct shash_alg alg = {
 	.digestsize	=	SHA1_DIGEST_SIZE,
 	.init		=	sha1_init,
-	.update		=	sha1_update,
+	.update		=	sha1_update_arm,
 	.final		=	sha1_final,
 	.export		=	sha1_export,
 	.import		=	sha1_import,
-	.descsize	=	sizeof(struct SHA1_CTX),
-	.statesize	=	sizeof(struct SHA1_CTX),
+	.descsize	=	sizeof(struct sha1_state),
+	.statesize	=	sizeof(struct sha1_state),
 	.base		=	{
 		.cra_name	=	"sha1",
 		.cra_driver_name=	"sha1-asm",
diff --git a/arch/arm/crypto/sha1_neon_glue.c b/arch/arm/crypto/sha1_neon_glue.c
new file mode 100644
index 000000000000..6f1b411b1d55
--- /dev/null
+++ b/arch/arm/crypto/sha1_neon_glue.c
@@ -0,0 +1,197 @@
+/*
+ * Glue code for the SHA1 Secure Hash Algorithm assembler implementation using
+ * ARM NEON instructions.
+ *
+ * Copyright © 2014 Jussi Kivilinna <jussi.kivilinna@iki.fi>
+ *
+ * This file is based on sha1_generic.c and sha1_ssse3_glue.c:
+ *  Copyright (c) Alan Smithee.
+ *  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
+ * Software Foundation; either version 2 of the License, or (at your option)
+ * any later version.
+ *
+ */
+
+#include <crypto/internal/hash.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/mm.h>
+#include <linux/cryptohash.h>
+#include <linux/types.h>
+#include <crypto/sha.h>
+#include <asm/byteorder.h>
+#include <asm/neon.h>
+#include <asm/simd.h>
+#include <asm/crypto/sha1.h>
+
+
+asmlinkage void sha1_transform_neon(void *state_h, const char *data,
+				    unsigned int rounds);
+
+
+static int sha1_neon_init(struct shash_desc *desc)
+{
+	struct sha1_state *sctx = shash_desc_ctx(desc);
+
+	*sctx = (struct sha1_state){
+		.state = { SHA1_H0, SHA1_H1, SHA1_H2, SHA1_H3, SHA1_H4 },
+	};
+
+	return 0;
+}
+
+static int __sha1_neon_update(struct shash_desc *desc, const u8 *data,
+			       unsigned int len, unsigned int partial)
+{
+	struct sha1_state *sctx = shash_desc_ctx(desc);
+	unsigned int done = 0;
+
+	sctx->count += len;
+
+	if (partial) {
+		done = SHA1_BLOCK_SIZE - partial;
+		memcpy(sctx->buffer + partial, data, done);
+		sha1_transform_neon(sctx->state, sctx->buffer, 1);
+	}
+
+	if (len - done >= SHA1_BLOCK_SIZE) {
+		const unsigned int rounds = (len - done) / SHA1_BLOCK_SIZE;
+
+		sha1_transform_neon(sctx->state, data + done, rounds);
+		done += rounds * SHA1_BLOCK_SIZE;
+	}
+
+	memcpy(sctx->buffer, data + done, len - done);
+
+	return 0;
+}
+
+static int sha1_neon_update(struct shash_desc *desc, const u8 *data,
+			     unsigned int len)
+{
+	struct sha1_state *sctx = shash_desc_ctx(desc);
+	unsigned int partial = sctx->count % SHA1_BLOCK_SIZE;
+	int res;
+
+	/* Handle the fast case right here */
+	if (partial + len < SHA1_BLOCK_SIZE) {
+		sctx->count += len;
+		memcpy(sctx->buffer + partial, data, len);
+
+		return 0;
+	}
+
+	if (!may_use_simd()) {
+		res = sha1_update_arm(desc, data, len);
+	} else {
+		kernel_neon_begin();
+		res = __sha1_neon_update(desc, data, len, partial);
+		kernel_neon_end();
+	}
+
+	return res;
+}
+
+
+/* Add padding and return the message digest. */
+static int sha1_neon_final(struct shash_desc *desc, u8 *out)
+{
+	struct sha1_state *sctx = shash_desc_ctx(desc);
+	unsigned int i, index, padlen;
+	__be32 *dst = (__be32 *)out;
+	__be64 bits;
+	static const u8 padding[SHA1_BLOCK_SIZE] = { 0x80, };
+
+	bits = cpu_to_be64(sctx->count << 3);
+
+	/* Pad out to 56 mod 64 and append length */
+	index = sctx->count % SHA1_BLOCK_SIZE;
+	padlen = (index < 56) ? (56 - index) : ((SHA1_BLOCK_SIZE+56) - index);
+	if (!may_use_simd()) {
+		sha1_update_arm(desc, padding, padlen);
+		sha1_update_arm(desc, (const u8 *)&bits, sizeof(bits));
+	} else {
+		kernel_neon_begin();
+		/* We need to fill a whole block for __sha1_neon_update() */
+		if (padlen <= 56) {
+			sctx->count += padlen;
+			memcpy(sctx->buffer + index, padding, padlen);
+		} else {
+			__sha1_neon_update(desc, padding, padlen, index);
+		}
+		__sha1_neon_update(desc, (const u8 *)&bits, sizeof(bits), 56);
+		kernel_neon_end();
+	}
+
+	/* Store state in digest */
+	for (i = 0; i < 5; i++)
+		dst[i] = cpu_to_be32(sctx->state[i]);
+
+	/* Wipe context */
+	memset(sctx, 0, sizeof(*sctx));
+
+	return 0;
+}
+
+static int sha1_neon_export(struct shash_desc *desc, void *out)
+{
+	struct sha1_state *sctx = shash_desc_ctx(desc);
+
+	memcpy(out, sctx, sizeof(*sctx));
+
+	return 0;
+}
+
+static int sha1_neon_import(struct shash_desc *desc, const void *in)
+{
+	struct sha1_state *sctx = shash_desc_ctx(desc);
+
+	memcpy(sctx, in, sizeof(*sctx));
+
+	return 0;
+}
+
+static struct shash_alg alg = {
+	.digestsize	=	SHA1_DIGEST_SIZE,
+	.init		=	sha1_neon_init,
+	.update		=	sha1_neon_update,
+	.final		=	sha1_neon_final,
+	.export		=	sha1_neon_export,
+	.import		=	sha1_neon_import,
+	.descsize	=	sizeof(struct sha1_state),
+	.statesize	=	sizeof(struct sha1_state),
+	.base		=	{
+		.cra_name		= "sha1",
+		.cra_driver_name	= "sha1-neon",
+		.cra_priority		= 250,
+		.cra_flags		= CRYPTO_ALG_TYPE_SHASH,
+		.cra_blocksize		= SHA1_BLOCK_SIZE,
+		.cra_module		= THIS_MODULE,
+	}
+};
+
+static int __init sha1_neon_mod_init(void)
+{
+	if (!cpu_has_neon())
+		return -ENODEV;
+
+	return crypto_register_shash(&alg);
+}
+
+static void __exit sha1_neon_mod_fini(void)
+{
+	crypto_unregister_shash(&alg);
+}
+
+module_init(sha1_neon_mod_init);
+module_exit(sha1_neon_mod_fini);
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("SHA1 Secure Hash Algorithm, NEON accelerated");
+MODULE_ALIAS("sha1");
diff --git a/arch/arm/crypto/sha512-armv7-neon.S b/arch/arm/crypto/sha512-armv7-neon.S
new file mode 100644
index 000000000000..fe99472e507c
--- /dev/null
+++ b/arch/arm/crypto/sha512-armv7-neon.S
@@ -0,0 +1,455 @@
+/* sha512-armv7-neon.S  -  ARM/NEON assembly implementation of SHA-512 transform
+ *
+ * Copyright © 2013-2014 Jussi Kivilinna <jussi.kivilinna@iki.fi>
+ *
+ * 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
+ * Software Foundation; either version 2 of the License, or (at your option)
+ * any later version.
+ */
+
+#include <linux/linkage.h>
+
+
+.syntax unified
+.code   32
+.fpu neon
+
+.text
+
+/* structure of SHA512_CONTEXT */
+#define hd_a 0
+#define hd_b ((hd_a) + 8)
+#define hd_c ((hd_b) + 8)
+#define hd_d ((hd_c) + 8)
+#define hd_e ((hd_d) + 8)
+#define hd_f ((hd_e) + 8)
+#define hd_g ((hd_f) + 8)
+
+/* register macros */
+#define RK %r2
+
+#define RA d0
+#define RB d1
+#define RC d2
+#define RD d3
+#define RE d4
+#define RF d5
+#define RG d6
+#define RH d7
+
+#define RT0 d8
+#define RT1 d9
+#define RT2 d10
+#define RT3 d11
+#define RT4 d12
+#define RT5 d13
+#define RT6 d14
+#define RT7 d15
+
+#define RT01q q4
+#define RT23q q5
+#define RT45q q6
+#define RT67q q7
+
+#define RW0 d16
+#define RW1 d17
+#define RW2 d18
+#define RW3 d19
+#define RW4 d20
+#define RW5 d21
+#define RW6 d22
+#define RW7 d23
+#define RW8 d24
+#define RW9 d25
+#define RW10 d26
+#define RW11 d27
+#define RW12 d28
+#define RW13 d29
+#define RW14 d30
+#define RW15 d31
+
+#define RW01q q8
+#define RW23q q9
+#define RW45q q10
+#define RW67q q11
+#define RW89q q12
+#define RW1011q q13
+#define RW1213q q14
+#define RW1415q q15
+
+/***********************************************************************
+ * ARM assembly implementation of sha512 transform
+ ***********************************************************************/
+#define rounds2_0_63(ra, rb, rc, rd, re, rf, rg, rh, rw0, rw1, rw01q, rw2, \
+                     rw23q, rw1415q, rw9, rw10, interleave_op, arg1) \
+	/* t1 = h + Sum1 (e) + Ch (e, f, g) + k[t] + w[t]; */ \
+	vshr.u64 RT2, re, #14; \
+	vshl.u64 RT3, re, #64 - 14; \
+	interleave_op(arg1); \
+	vshr.u64 RT4, re, #18; \
+	vshl.u64 RT5, re, #64 - 18; \
+	vld1.64 {RT0}, [RK]!; \
+	veor.64 RT23q, RT23q, RT45q; \
+	vshr.u64 RT4, re, #41; \
+	vshl.u64 RT5, re, #64 - 41; \
+	vadd.u64 RT0, RT0, rw0; \
+	veor.64 RT23q, RT23q, RT45q; \
+	vmov.64 RT7, re; \
+	veor.64 RT1, RT2, RT3; \
+	vbsl.64 RT7, rf, rg; \
+	\
+	vadd.u64 RT1, RT1, rh; \
+	vshr.u64 RT2, ra, #28; \
+	vshl.u64 RT3, ra, #64 - 28; \
+	vadd.u64 RT1, RT1, RT0; \
+	vshr.u64 RT4, ra, #34; \
+	vshl.u64 RT5, ra, #64 - 34; \
+	vadd.u64 RT1, RT1, RT7; \
+	\
+	/* h = Sum0 (a) + Maj (a, b, c); */ \
+	veor.64 RT23q, RT23q, RT45q; \
+	vshr.u64 RT4, ra, #39; \
+	vshl.u64 RT5, ra, #64 - 39; \
+	veor.64 RT0, ra, rb; \
+	veor.64 RT23q, RT23q, RT45q; \
+	vbsl.64 RT0, rc, rb; \
+	vadd.u64 rd, rd, RT1; /* d+=t1; */ \
+	veor.64 rh, RT2, RT3; \
+	\
+	/* t1 = g + Sum1 (d) + Ch (d, e, f) + k[t] + w[t]; */ \
+	vshr.u64 RT2, rd, #14; \
+	vshl.u64 RT3, rd, #64 - 14; \
+	vadd.u64 rh, rh, RT0; \
+	vshr.u64 RT4, rd, #18; \
+	vshl.u64 RT5, rd, #64 - 18; \
+	vadd.u64 rh, rh, RT1; /* h+=t1; */ \
+	vld1.64 {RT0}, [RK]!; \
+	veor.64 RT23q, RT23q, RT45q; \
+	vshr.u64 RT4, rd, #41; \
+	vshl.u64 RT5, rd, #64 - 41; \
+	vadd.u64 RT0, RT0, rw1; \
+	veor.64 RT23q, RT23q, RT45q; \
+	vmov.64 RT7, rd; \
+	veor.64 RT1, RT2, RT3; \
+	vbsl.64 RT7, re, rf; \
+	\
+	vadd.u64 RT1, RT1, rg; \
+	vshr.u64 RT2, rh, #28; \
+	vshl.u64 RT3, rh, #64 - 28; \
+	vadd.u64 RT1, RT1, RT0; \
+	vshr.u64 RT4, rh, #34; \
+	vshl.u64 RT5, rh, #64 - 34; \
+	vadd.u64 RT1, RT1, RT7; \
+	\
+	/* g = Sum0 (h) + Maj (h, a, b); */ \
+	veor.64 RT23q, RT23q, RT45q; \
+	vshr.u64 RT4, rh, #39; \
+	vshl.u64 RT5, rh, #64 - 39; \
+	veor.64 RT0, rh, ra; \
+	veor.64 RT23q, RT23q, RT45q; \
+	vbsl.64 RT0, rb, ra; \
+	vadd.u64 rc, rc, RT1; /* c+=t1; */ \
+	veor.64 rg, RT2, RT3; \
+	\
+	/* w[0] += S1 (w[14]) + w[9] + S0 (w[1]); */ \
+	/* w[1] += S1 (w[15]) + w[10] + S0 (w[2]); */ \
+	\
+	/**** S0(w[1:2]) */ \
+	\
+	/* w[0:1] += w[9:10] */ \
+	/* RT23q = rw1:rw2 */ \
+	vext.u64 RT23q, rw01q, rw23q, #1; \
+	vadd.u64 rw0, rw9; \
+	vadd.u64 rg, rg, RT0; \
+	vadd.u64 rw1, rw10;\
+	vadd.u64 rg, rg, RT1; /* g+=t1; */ \
+	\
+	vshr.u64 RT45q, RT23q, #1; \
+	vshl.u64 RT67q, RT23q, #64 - 1; \
+	vshr.u64 RT01q, RT23q, #8; \
+	veor.u64 RT45q, RT45q, RT67q; \
+	vshl.u64 RT67q, RT23q, #64 - 8; \
+	veor.u64 RT45q, RT45q, RT01q; \
+	vshr.u64 RT01q, RT23q, #7; \
+	veor.u64 RT45q, RT45q, RT67q; \
+	\
+	/**** S1(w[14:15]) */ \
+	vshr.u64 RT23q, rw1415q, #6; \
+	veor.u64 RT01q, RT01q, RT45q; \
+	vshr.u64 RT45q, rw1415q, #19; \
+	vshl.u64 RT67q, rw1415q, #64 - 19; \
+	veor.u64 RT23q, RT23q, RT45q; \
+	vshr.u64 RT45q, rw1415q, #61; \
+	veor.u64 RT23q, RT23q, RT67q; \
+	vshl.u64 RT67q, rw1415q, #64 - 61; \
+	veor.u64 RT23q, RT23q, RT45q; \
+	vadd.u64 rw01q, RT01q; /* w[0:1] += S(w[1:2]) */ \
+	veor.u64 RT01q, RT23q, RT67q;
+#define vadd_RT01q(rw01q) \
+	/* w[0:1] += S(w[14:15]) */ \
+	vadd.u64 rw01q, RT01q;
+
+#define dummy(_) /*_*/
+
+#define rounds2_64_79(ra, rb, rc, rd, re, rf, rg, rh, rw0, rw1, \
+	              interleave_op1, arg1, interleave_op2, arg2) \
+	/* t1 = h + Sum1 (e) + Ch (e, f, g) + k[t] + w[t]; */ \
+	vshr.u64 RT2, re, #14; \
+	vshl.u64 RT3, re, #64 - 14; \
+	interleave_op1(arg1); \
+	vshr.u64 RT4, re, #18; \
+	vshl.u64 RT5, re, #64 - 18; \
+	interleave_op2(arg2); \
+	vld1.64 {RT0}, [RK]!; \
+	veor.64 RT23q, RT23q, RT45q; \
+	vshr.u64 RT4, re, #41; \
+	vshl.u64 RT5, re, #64 - 41; \
+	vadd.u64 RT0, RT0, rw0; \
+	veor.64 RT23q, RT23q, RT45q; \
+	vmov.64 RT7, re; \
+	veor.64 RT1, RT2, RT3; \
+	vbsl.64 RT7, rf, rg; \
+	\
+	vadd.u64 RT1, RT1, rh; \
+	vshr.u64 RT2, ra, #28; \
+	vshl.u64 RT3, ra, #64 - 28; \
+	vadd.u64 RT1, RT1, RT0; \
+	vshr.u64 RT4, ra, #34; \
+	vshl.u64 RT5, ra, #64 - 34; \
+	vadd.u64 RT1, RT1, RT7; \
+	\
+	/* h = Sum0 (a) + Maj (a, b, c); */ \
+	veor.64 RT23q, RT23q, RT45q; \
+	vshr.u64 RT4, ra, #39; \
+	vshl.u64 RT5, ra, #64 - 39; \
+	veor.64 RT0, ra, rb; \
+	veor.64 RT23q, RT23q, RT45q; \
+	vbsl.64 RT0, rc, rb; \
+	vadd.u64 rd, rd, RT1; /* d+=t1; */ \
+	veor.64 rh, RT2, RT3; \
+	\
+	/* t1 = g + Sum1 (d) + Ch (d, e, f) + k[t] + w[t]; */ \
+	vshr.u64 RT2, rd, #14; \
+	vshl.u64 RT3, rd, #64 - 14; \
+	vadd.u64 rh, rh, RT0; \
+	vshr.u64 RT4, rd, #18; \
+	vshl.u64 RT5, rd, #64 - 18; \
+	vadd.u64 rh, rh, RT1; /* h+=t1; */ \
+	vld1.64 {RT0}, [RK]!; \
+	veor.64 RT23q, RT23q, RT45q; \
+	vshr.u64 RT4, rd, #41; \
+	vshl.u64 RT5, rd, #64 - 41; \
+	vadd.u64 RT0, RT0, rw1; \
+	veor.64 RT23q, RT23q, RT45q; \
+	vmov.64 RT7, rd; \
+	veor.64 RT1, RT2, RT3; \
+	vbsl.64 RT7, re, rf; \
+	\
+	vadd.u64 RT1, RT1, rg; \
+	vshr.u64 RT2, rh, #28; \
+	vshl.u64 RT3, rh, #64 - 28; \
+	vadd.u64 RT1, RT1, RT0; \
+	vshr.u64 RT4, rh, #34; \
+	vshl.u64 RT5, rh, #64 - 34; \
+	vadd.u64 RT1, RT1, RT7; \
+	\
+	/* g = Sum0 (h) + Maj (h, a, b); */ \
+	veor.64 RT23q, RT23q, RT45q; \
+	vshr.u64 RT4, rh, #39; \
+	vshl.u64 RT5, rh, #64 - 39; \
+	veor.64 RT0, rh, ra; \
+	veor.64 RT23q, RT23q, RT45q; \
+	vbsl.64 RT0, rb, ra; \
+	vadd.u64 rc, rc, RT1; /* c+=t1; */ \
+	veor.64 rg, RT2, RT3;
+#define vadd_rg_RT0(rg) \
+	vadd.u64 rg, rg, RT0;
+#define vadd_rg_RT1(rg) \
+	vadd.u64 rg, rg, RT1; /* g+=t1; */
+
+.align 3
+ENTRY(sha512_transform_neon)
+	/* Input:
+	 *	%r0: SHA512_CONTEXT
+	 *	%r1: data
+	 *	%r2: u64 k[] constants
+	 *	%r3: nblks
+	 */
+	push {%lr};
+
+	mov %lr, #0;
+
+	/* Load context to d0-d7 */
+	vld1.64 {RA-RD}, [%r0]!;
+	vld1.64 {RE-RH}, [%r0];
+	sub %r0, #(4*8);
+
+	/* Load input to w[16], d16-d31 */
+	/* NOTE: Assumes that on ARMv7 unaligned accesses are always allowed. */
+	vld1.64 {RW0-RW3}, [%r1]!;
+	vld1.64 {RW4-RW7}, [%r1]!;
+	vld1.64 {RW8-RW11}, [%r1]!;
+	vld1.64 {RW12-RW15}, [%r1]!;
+#ifdef __ARMEL__
+	/* byteswap */
+	vrev64.8 RW01q, RW01q;
+	vrev64.8 RW23q, RW23q;
+	vrev64.8 RW45q, RW45q;
+	vrev64.8 RW67q, RW67q;
+	vrev64.8 RW89q, RW89q;
+	vrev64.8 RW1011q, RW1011q;
+	vrev64.8 RW1213q, RW1213q;
+	vrev64.8 RW1415q, RW1415q;
+#endif
+
+	/* EABI says that d8-d15 must be preserved by callee. */
+	/*vpush {RT0-RT7};*/
+
+.Loop:
+	rounds2_0_63(RA, RB, RC, RD, RE, RF, RG, RH, RW0, RW1, RW01q, RW2,
+		     RW23q, RW1415q, RW9, RW10, dummy, _);
+	b .Lenter_rounds;
+
+.Loop_rounds:
+	rounds2_0_63(RA, RB, RC, RD, RE, RF, RG, RH, RW0, RW1, RW01q, RW2,
+		     RW23q, RW1415q, RW9, RW10, vadd_RT01q, RW1415q);
+.Lenter_rounds:
+	rounds2_0_63(RG, RH, RA, RB, RC, RD, RE, RF, RW2, RW3, RW23q, RW4,
+		     RW45q, RW01q, RW11, RW12, vadd_RT01q, RW01q);
+	rounds2_0_63(RE, RF, RG, RH, RA, RB, RC, RD, RW4, RW5, RW45q, RW6,
+		     RW67q, RW23q, RW13, RW14, vadd_RT01q, RW23q);
+	rounds2_0_63(RC, RD, RE, RF, RG, RH, RA, RB, RW6, RW7, RW67q, RW8,
+		     RW89q, RW45q, RW15, RW0, vadd_RT01q, RW45q);
+	rounds2_0_63(RA, RB, RC, RD, RE, RF, RG, RH, RW8, RW9, RW89q, RW10,
+		     RW1011q, RW67q, RW1, RW2, vadd_RT01q, RW67q);
+	rounds2_0_63(RG, RH, RA, RB, RC, RD, RE, RF, RW10, RW11, RW1011q, RW12,
+		     RW1213q, RW89q, RW3, RW4, vadd_RT01q, RW89q);
+	add %lr, #16;
+	rounds2_0_63(RE, RF, RG, RH, RA, RB, RC, RD, RW12, RW13, RW1213q, RW14,
+		     RW1415q, RW1011q, RW5, RW6, vadd_RT01q, RW1011q);
+	cmp %lr, #64;
+	rounds2_0_63(RC, RD, RE, RF, RG, RH, RA, RB, RW14, RW15, RW1415q, RW0,
+		     RW01q, RW1213q, RW7, RW8, vadd_RT01q, RW1213q);
+	bne .Loop_rounds;
+
+	subs %r3, #1;
+
+	rounds2_64_79(RA, RB, RC, RD, RE, RF, RG, RH, RW0, RW1,
+		      vadd_RT01q, RW1415q, dummy, _);
+	rounds2_64_79(RG, RH, RA, RB, RC, RD, RE, RF, RW2, RW3,
+		      vadd_rg_RT0, RG, vadd_rg_RT1, RG);
+	beq .Lhandle_tail;
+	vld1.64 {RW0-RW3}, [%r1]!;
+	rounds2_64_79(RE, RF, RG, RH, RA, RB, RC, RD, RW4, RW5,
+		      vadd_rg_RT0, RE, vadd_rg_RT1, RE);
+	rounds2_64_79(RC, RD, RE, RF, RG, RH, RA, RB, RW6, RW7,
+		      vadd_rg_RT0, RC, vadd_rg_RT1, RC);
+#ifdef __ARMEL__
+	vrev64.8 RW01q, RW01q;
+	vrev64.8 RW23q, RW23q;
+#endif
+	vld1.64 {RW4-RW7}, [%r1]!;
+	rounds2_64_79(RA, RB, RC, RD, RE, RF, RG, RH, RW8, RW9,
+		      vadd_rg_RT0, RA, vadd_rg_RT1, RA);
+	rounds2_64_79(RG, RH, RA, RB, RC, RD, RE, RF, RW10, RW11,
+		      vadd_rg_RT0, RG, vadd_rg_RT1, RG);
+#ifdef __ARMEL__
+	vrev64.8 RW45q, RW45q;
+	vrev64.8 RW67q, RW67q;
+#endif
+	vld1.64 {RW8-RW11}, [%r1]!;
+	rounds2_64_79(RE, RF, RG, RH, RA, RB, RC, RD, RW12, RW13,
+		      vadd_rg_RT0, RE, vadd_rg_RT1, RE);
+	rounds2_64_79(RC, RD, RE, RF, RG, RH, RA, RB, RW14, RW15,
+		      vadd_rg_RT0, RC, vadd_rg_RT1, RC);
+#ifdef __ARMEL__
+	vrev64.8 RW89q, RW89q;
+	vrev64.8 RW1011q, RW1011q;
+#endif
+	vld1.64 {RW12-RW15}, [%r1]!;
+	vadd_rg_RT0(RA);
+	vadd_rg_RT1(RA);
+
+	/* Load context */
+	vld1.64 {RT0-RT3}, [%r0]!;
+	vld1.64 {RT4-RT7}, [%r0];
+	sub %r0, #(4*8);
+
+#ifdef __ARMEL__
+	vrev64.8 RW1213q, RW1213q;
+	vrev64.8 RW1415q, RW1415q;
+#endif
+
+	vadd.u64 RA, RT0;
+	vadd.u64 RB, RT1;
+	vadd.u64 RC, RT2;
+	vadd.u64 RD, RT3;
+	vadd.u64 RE, RT4;
+	vadd.u64 RF, RT5;
+	vadd.u64 RG, RT6;
+	vadd.u64 RH, RT7;
+
+	/* Store the first half of context */
+	vst1.64 {RA-RD}, [%r0]!;
+	sub RK, $(8*80);
+	vst1.64 {RE-RH}, [%r0]; /* Store the last half of context */
+	mov %lr, #0;
+	sub %r0, #(4*8);
+
+	b .Loop;
+
+.Lhandle_tail:
+	rounds2_64_79(RE, RF, RG, RH, RA, RB, RC, RD, RW4, RW5,
+		      vadd_rg_RT0, RE, vadd_rg_RT1, RE);
+	rounds2_64_79(RC, RD, RE, RF, RG, RH, RA, RB, RW6, RW7,
+		      vadd_rg_RT0, RC, vadd_rg_RT1, RC);
+	rounds2_64_79(RA, RB, RC, RD, RE, RF, RG, RH, RW8, RW9,
+		      vadd_rg_RT0, RA, vadd_rg_RT1, RA);
+	rounds2_64_79(RG, RH, RA, RB, RC, RD, RE, RF, RW10, RW11,
+		      vadd_rg_RT0, RG, vadd_rg_RT1, RG);
+	rounds2_64_79(RE, RF, RG, RH, RA, RB, RC, RD, RW12, RW13,
+		      vadd_rg_RT0, RE, vadd_rg_RT1, RE);
+	rounds2_64_79(RC, RD, RE, RF, RG, RH, RA, RB, RW14, RW15,
+		      vadd_rg_RT0, RC, vadd_rg_RT1, RC);
+
+	/* Load context to d16-d23 */
+	vld1.64 {RW0-RW3}, [%r0]!;
+	vadd_rg_RT0(RA);
+	vld1.64 {RW4-RW7}, [%r0];
+	vadd_rg_RT1(RA);
+	sub %r0, #(4*8);
+
+	vadd.u64 RA, RW0;
+	vadd.u64 RB, RW1;
+	vadd.u64 RC, RW2;
+	vadd.u64 RD, RW3;
+	vadd.u64 RE, RW4;
+	vadd.u64 RF, RW5;
+	vadd.u64 RG, RW6;
+	vadd.u64 RH, RW7;
+
+	/* Store the first half of context */
+	vst1.64 {RA-RD}, [%r0]!;
+
+	/* Clear used registers */
+	/* d16-d31 */
+	veor.u64 RW01q, RW01q;
+	veor.u64 RW23q, RW23q;
+	veor.u64 RW45q, RW45q;
+	veor.u64 RW67q, RW67q;
+	vst1.64 {RE-RH}, [%r0]; /* Store the last half of context */
+	veor.u64 RW89q, RW89q;
+	veor.u64 RW1011q, RW1011q;
+	veor.u64 RW1213q, RW1213q;
+	veor.u64 RW1415q, RW1415q;
+	/* d8-d15 */
+	/*vpop {RT0-RT7};*/
+	/* d0-d7 (q0-q3) */
+	veor.u64 %q0, %q0;
+	veor.u64 %q1, %q1;
+	veor.u64 %q2, %q2;
+	veor.u64 %q3, %q3;
+
+	pop {%pc};
+ENDPROC(sha512_transform_neon)
diff --git a/arch/arm/crypto/sha512_neon_glue.c b/arch/arm/crypto/sha512_neon_glue.c
new file mode 100644
index 000000000000..0d2758ff5e12
--- /dev/null
+++ b/arch/arm/crypto/sha512_neon_glue.c
@@ -0,0 +1,305 @@
+/*
+ * Glue code for the SHA512 Secure Hash Algorithm assembly implementation
+ * using NEON instructions.
+ *
+ * Copyright © 2014 Jussi Kivilinna <jussi.kivilinna@iki.fi>
+ *
+ * This file is based on sha512_ssse3_glue.c:
+ *   Copyright (C) 2013 Intel Corporation
+ *   Author: Tim Chen <tim.c.chen@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
+ * Software Foundation; either version 2 of the License, or (at your option)
+ * any later version.
+ *
+ */
+
+#include <crypto/internal/hash.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/mm.h>
+#include <linux/cryptohash.h>
+#include <linux/types.h>
+#include <linux/string.h>
+#include <crypto/sha.h>
+#include <asm/byteorder.h>
+#include <asm/simd.h>
+#include <asm/neon.h>
+
+
+static const u64 sha512_k[] = {
+	0x428a2f98d728ae22ULL, 0x7137449123ef65cdULL,
+	0xb5c0fbcfec4d3b2fULL, 0xe9b5dba58189dbbcULL,
+	0x3956c25bf348b538ULL, 0x59f111f1b605d019ULL,
+	0x923f82a4af194f9bULL, 0xab1c5ed5da6d8118ULL,
+	0xd807aa98a3030242ULL, 0x12835b0145706fbeULL,
+	0x243185be4ee4b28cULL, 0x550c7dc3d5ffb4e2ULL,
+	0x72be5d74f27b896fULL, 0x80deb1fe3b1696b1ULL,
+	0x9bdc06a725c71235ULL, 0xc19bf174cf692694ULL,
+	0xe49b69c19ef14ad2ULL, 0xefbe4786384f25e3ULL,
+	0x0fc19dc68b8cd5b5ULL, 0x240ca1cc77ac9c65ULL,
+	0x2de92c6f592b0275ULL, 0x4a7484aa6ea6e483ULL,
+	0x5cb0a9dcbd41fbd4ULL, 0x76f988da831153b5ULL,
+	0x983e5152ee66dfabULL, 0xa831c66d2db43210ULL,
+	0xb00327c898fb213fULL, 0xbf597fc7beef0ee4ULL,
+	0xc6e00bf33da88fc2ULL, 0xd5a79147930aa725ULL,
+	0x06ca6351e003826fULL, 0x142929670a0e6e70ULL,
+	0x27b70a8546d22ffcULL, 0x2e1b21385c26c926ULL,
+	0x4d2c6dfc5ac42aedULL, 0x53380d139d95b3dfULL,
+	0x650a73548baf63deULL, 0x766a0abb3c77b2a8ULL,
+	0x81c2c92e47edaee6ULL, 0x92722c851482353bULL,
+	0xa2bfe8a14cf10364ULL, 0xa81a664bbc423001ULL,
+	0xc24b8b70d0f89791ULL, 0xc76c51a30654be30ULL,
+	0xd192e819d6ef5218ULL, 0xd69906245565a910ULL,
+	0xf40e35855771202aULL, 0x106aa07032bbd1b8ULL,
+	0x19a4c116b8d2d0c8ULL, 0x1e376c085141ab53ULL,
+	0x2748774cdf8eeb99ULL, 0x34b0bcb5e19b48a8ULL,
+	0x391c0cb3c5c95a63ULL, 0x4ed8aa4ae3418acbULL,
+	0x5b9cca4f7763e373ULL, 0x682e6ff3d6b2b8a3ULL,
+	0x748f82ee5defb2fcULL, 0x78a5636f43172f60ULL,
+	0x84c87814a1f0ab72ULL, 0x8cc702081a6439ecULL,
+	0x90befffa23631e28ULL, 0xa4506cebde82bde9ULL,
+	0xbef9a3f7b2c67915ULL, 0xc67178f2e372532bULL,
+	0xca273eceea26619cULL, 0xd186b8c721c0c207ULL,
+	0xeada7dd6cde0eb1eULL, 0xf57d4f7fee6ed178ULL,
+	0x06f067aa72176fbaULL, 0x0a637dc5a2c898a6ULL,
+	0x113f9804bef90daeULL, 0x1b710b35131c471bULL,
+	0x28db77f523047d84ULL, 0x32caab7b40c72493ULL,
+	0x3c9ebe0a15c9bebcULL, 0x431d67c49c100d4cULL,
+	0x4cc5d4becb3e42b6ULL, 0x597f299cfc657e2aULL,
+	0x5fcb6fab3ad6faecULL, 0x6c44198c4a475817ULL
+};
+
+
+asmlinkage void sha512_transform_neon(u64 *digest, const void *data,
+				      const u64 k[], unsigned int num_blks);
+
+
+static int sha512_neon_init(struct shash_desc *desc)
+{
+	struct sha512_state *sctx = shash_desc_ctx(desc);
+
+	sctx->state[0] = SHA512_H0;
+	sctx->state[1] = SHA512_H1;
+	sctx->state[2] = SHA512_H2;
+	sctx->state[3] = SHA512_H3;
+	sctx->state[4] = SHA512_H4;
+	sctx->state[5] = SHA512_H5;
+	sctx->state[6] = SHA512_H6;
+	sctx->state[7] = SHA512_H7;
+	sctx->count[0] = sctx->count[1] = 0;
+
+	return 0;
+}
+
+static int __sha512_neon_update(struct shash_desc *desc, const u8 *data,
+				unsigned int len, unsigned int partial)
+{
+	struct sha512_state *sctx = shash_desc_ctx(desc);
+	unsigned int done = 0;
+
+	sctx->count[0] += len;
+	if (sctx->count[0] < len)
+		sctx->count[1]++;
+
+	if (partial) {
+		done = SHA512_BLOCK_SIZE - partial;
+		memcpy(sctx->buf + partial, data, done);
+		sha512_transform_neon(sctx->state, sctx->buf, sha512_k, 1);
+	}
+
+	if (len - done >= SHA512_BLOCK_SIZE) {
+		const unsigned int rounds = (len - done) / SHA512_BLOCK_SIZE;
+
+		sha512_transform_neon(sctx->state, data + done, sha512_k,
+				      rounds);
+
+		done += rounds * SHA512_BLOCK_SIZE;
+	}
+
+	memcpy(sctx->buf, data + done, len - done);
+
+	return 0;
+}
+
+static int sha512_neon_update(struct shash_desc *desc, const u8 *data,
+			     unsigned int len)
+{
+	struct sha512_state *sctx = shash_desc_ctx(desc);
+	unsigned int partial = sctx->count[0] % SHA512_BLOCK_SIZE;
+	int res;
+
+	/* Handle the fast case right here */
+	if (partial + len < SHA512_BLOCK_SIZE) {
+		sctx->count[0] += len;
+		if (sctx->count[0] < len)
+			sctx->count[1]++;
+		memcpy(sctx->buf + partial, data, len);
+
+		return 0;
+	}
+
+	if (!may_use_simd()) {
+		res = crypto_sha512_update(desc, data, len);
+	} else {
+		kernel_neon_begin();
+		res = __sha512_neon_update(desc, data, len, partial);
+		kernel_neon_end();
+	}
+
+	return res;
+}
+
+
+/* Add padding and return the message digest. */
+static int sha512_neon_final(struct shash_desc *desc, u8 *out)
+{
+	struct sha512_state *sctx = shash_desc_ctx(desc);
+	unsigned int i, index, padlen;
+	__be64 *dst = (__be64 *)out;
+	__be64 bits[2];
+	static const u8 padding[SHA512_BLOCK_SIZE] = { 0x80, };
+
+	/* save number of bits */
+	bits[1] = cpu_to_be64(sctx->count[0] << 3);
+	bits[0] = cpu_to_be64(sctx->count[1] << 3 | sctx->count[0] >> 61);
+
+	/* Pad out to 112 mod 128 and append length */
+	index = sctx->count[0] & 0x7f;
+	padlen = (index < 112) ? (112 - index) : ((128+112) - index);
+
+	if (!may_use_simd()) {
+		crypto_sha512_update(desc, padding, padlen);
+		crypto_sha512_update(desc, (const u8 *)&bits, sizeof(bits));
+	} else {
+		kernel_neon_begin();
+		/* We need to fill a whole block for __sha512_neon_update() */
+		if (padlen <= 112) {
+			sctx->count[0] += padlen;
+			if (sctx->count[0] < padlen)
+				sctx->count[1]++;
+			memcpy(sctx->buf + index, padding, padlen);
+		} else {
+			__sha512_neon_update(desc, padding, padlen, index);
+		}
+		__sha512_neon_update(desc, (const u8 *)&bits,
+					sizeof(bits), 112);
+		kernel_neon_end();
+	}
+
+	/* Store state in digest */
+	for (i = 0; i < 8; i++)
+		dst[i] = cpu_to_be64(sctx->state[i]);
+
+	/* Wipe context */
+	memset(sctx, 0, sizeof(*sctx));
+
+	return 0;
+}
+
+static int sha512_neon_export(struct shash_desc *desc, void *out)
+{
+	struct sha512_state *sctx = shash_desc_ctx(desc);
+
+	memcpy(out, sctx, sizeof(*sctx));
+
+	return 0;
+}
+
+static int sha512_neon_import(struct shash_desc *desc, const void *in)
+{
+	struct sha512_state *sctx = shash_desc_ctx(desc);
+
+	memcpy(sctx, in, sizeof(*sctx));
+
+	return 0;
+}
+
+static int sha384_neon_init(struct shash_desc *desc)
+{
+	struct sha512_state *sctx = shash_desc_ctx(desc);
+
+	sctx->state[0] = SHA384_H0;
+	sctx->state[1] = SHA384_H1;
+	sctx->state[2] = SHA384_H2;
+	sctx->state[3] = SHA384_H3;
+	sctx->state[4] = SHA384_H4;
+	sctx->state[5] = SHA384_H5;
+	sctx->state[6] = SHA384_H6;
+	sctx->state[7] = SHA384_H7;
+
+	sctx->count[0] = sctx->count[1] = 0;
+
+	return 0;
+}
+
+static int sha384_neon_final(struct shash_desc *desc, u8 *hash)
+{
+	u8 D[SHA512_DIGEST_SIZE];
+
+	sha512_neon_final(desc, D);
+
+	memcpy(hash, D, SHA384_DIGEST_SIZE);
+	memset(D, 0, SHA512_DIGEST_SIZE);
+
+	return 0;
+}
+
+static struct shash_alg algs[] = { {
+	.digestsize	=	SHA512_DIGEST_SIZE,
+	.init		=	sha512_neon_init,
+	.update		=	sha512_neon_update,
+	.final		=	sha512_neon_final,
+	.export		=	sha512_neon_export,
+	.import		=	sha512_neon_import,
+	.descsize	=	sizeof(struct sha512_state),
+	.statesize	=	sizeof(struct sha512_state),
+	.base		=	{
+		.cra_name	=	"sha512",
+		.cra_driver_name =	"sha512-neon",
+		.cra_priority	=	250,
+		.cra_flags	=	CRYPTO_ALG_TYPE_SHASH,
+		.cra_blocksize	=	SHA512_BLOCK_SIZE,
+		.cra_module	=	THIS_MODULE,
+	}
+},  {
+	.digestsize	=	SHA384_DIGEST_SIZE,
+	.init		=	sha384_neon_init,
+	.update		=	sha512_neon_update,
+	.final		=	sha384_neon_final,
+	.export		=	sha512_neon_export,
+	.import		=	sha512_neon_import,
+	.descsize	=	sizeof(struct sha512_state),
+	.statesize	=	sizeof(struct sha512_state),
+	.base		=	{
+		.cra_name	=	"sha384",
+		.cra_driver_name =	"sha384-neon",
+		.cra_priority	=	250,
+		.cra_flags	=	CRYPTO_ALG_TYPE_SHASH,
+		.cra_blocksize	=	SHA384_BLOCK_SIZE,
+		.cra_module	=	THIS_MODULE,
+	}
+} };
+
+static int __init sha512_neon_mod_init(void)
+{
+	if (!cpu_has_neon())
+		return -ENODEV;
+
+	return crypto_register_shashes(algs, ARRAY_SIZE(algs));
+}
+
+static void __exit sha512_neon_mod_fini(void)
+{
+	crypto_unregister_shashes(algs, ARRAY_SIZE(algs));
+}
+
+module_init(sha512_neon_mod_init);
+module_exit(sha512_neon_mod_fini);
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("SHA512 Secure Hash Algorithm, NEON accelerated");
+
+MODULE_ALIAS("sha512");
+MODULE_ALIAS("sha384");