Merge branch 'linaro-android-3.10-lsk' of git://android.git.linaro.org/kernel/linaro-android into linux-linaro-lsk-android

 Remove conflictsed drivers/staging/android/logger.c

41 files changed, 5280 insertions, 1660 deletions

diff --git a/Documentation/ABI/testing/sysfs-kernel-wakeup_reasons b/Documentation/ABI/testing/sysfs-kernel-wakeup_reasons
new file mode 100644
index 000000000000..acb19b91c192
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-kernel-wakeup_reasons
@@ -0,0 +1,16 @@
+What:		/sys/kernel/wakeup_reasons/last_resume_reason
+Date:		February 2014
+Contact:	Ruchi Kandoi <kandoiruchi@google.com>
+Description:
+		The /sys/kernel/wakeup_reasons/last_resume_reason is
+		used to report wakeup reasons after system exited suspend.
+
+What:		/sys/kernel/wakeup_reasons/last_suspend_time
+Date:		March 2015
+Contact:	jinqian <jinqian@google.com>
+Description:
+		The /sys/kernel/wakeup_reasons/last_suspend_time is
+		used to report time spent in last suspend cycle. It contains
+		two numbers (in seconds) separated by space. First number is
+		the time spent in suspend and resume processes. Second number
+		is the time spent in sleep state.
\ No newline at end of file
diff --git a/android/configs/android-base.cfg b/android/configs/android-base.cfg
index 6c08830ae6ed..3ddcecd716be 100644
--- a/android/configs/android-base.cfg
+++ b/android/configs/android-base.cfg
@@ -6,7 +6,6 @@
 # CONFIG_OABI_COMPAT is not set
 CONFIG_ANDROID=y
 CONFIG_ANDROID_BINDER_IPC=y
-CONFIG_ANDROID_INTF_ALARM_DEV=y
 CONFIG_ANDROID_LOW_MEMORY_KILLER=y
 CONFIG_ARMV7_COMPAT=y
 CONFIG_ASHMEM=y
diff --git a/arch/arm/crypto/Makefile b/arch/arm/crypto/Makefile
index b48fa341648d..2cee53b27238 100644
--- a/arch/arm/crypto/Makefile
+++ b/arch/arm/crypto/Makefile
@@ -6,12 +6,15 @@ 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-$(CONFIG_CRYPTO_SHA256_ARM) += sha256-arm.o
 obj-$(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
+sha256-arm-neon-$(CONFIG_KERNEL_MODE_NEON) := sha256_neon_glue.o
+sha256-arm-y	:= sha256-core.o sha256_glue.o $(sha256-arm-neon-y)
 sha512-arm-neon-y := sha512-armv7-neon.o sha512_neon_glue.o
 
 quiet_cmd_perl = PERL    $@
@@ -20,4 +23,7 @@ quiet_cmd_perl = PERL    $@
 $(src)/aesbs-core.S_shipped: $(src)/bsaes-armv7.pl
 	$(call cmd,perl)
 
-.PRECIOUS: $(obj)/aesbs-core.S
+$(src)/sha256-core.S_shipped: $(src)/sha256-armv4.pl
+	$(call cmd,perl)
+
+.PRECIOUS: $(obj)/aesbs-core.S $(obj)/sha256-core.S
diff --git a/arch/arm/crypto/sha256-armv4.pl b/arch/arm/crypto/sha256-armv4.pl
new file mode 100644
index 000000000000..fac0533ea633
--- /dev/null
+++ b/arch/arm/crypto/sha256-armv4.pl
@@ -0,0 +1,716 @@
+#!/usr/bin/env perl
+
+# ====================================================================
+# Written by Andy Polyakov <appro@openssl.org> for the OpenSSL
+# project. The module is, however, dual licensed under OpenSSL and
+# CRYPTOGAMS licenses depending on where you obtain it. For further
+# details see http://www.openssl.org/~appro/cryptogams/.
+#
+# Permission to use under GPL terms is granted.
+# ====================================================================
+
+# SHA256 block procedure for ARMv4. May 2007.
+
+# Performance is ~2x better than gcc 3.4 generated code and in "abso-
+# lute" terms is ~2250 cycles per 64-byte block or ~35 cycles per
+# byte [on single-issue Xscale PXA250 core].
+
+# July 2010.
+#
+# Rescheduling for dual-issue pipeline resulted in 22% improvement on
+# Cortex A8 core and ~20 cycles per processed byte.
+
+# February 2011.
+#
+# Profiler-assisted and platform-specific optimization resulted in 16%
+# improvement on Cortex A8 core and ~15.4 cycles per processed byte.
+
+# September 2013.
+#
+# Add NEON implementation. On Cortex A8 it was measured to process one
+# byte in 12.5 cycles or 23% faster than integer-only code. Snapdragon
+# S4 does it in 12.5 cycles too, but it's 50% faster than integer-only
+# code (meaning that latter performs sub-optimally, nothing was done
+# about it).
+
+# May 2014.
+#
+# Add ARMv8 code path performing at 2.0 cpb on Apple A7.
+
+while (($output=shift) && ($output!~/^\w[\w\-]*\.\w+$/)) {}
+open STDOUT,">$output";
+
+$ctx="r0";	$t0="r0";
+$inp="r1";	$t4="r1";
+$len="r2";	$t1="r2";
+$T1="r3";	$t3="r3";
+$A="r4";
+$B="r5";
+$C="r6";
+$D="r7";
+$E="r8";
+$F="r9";
+$G="r10";
+$H="r11";
+@V=($A,$B,$C,$D,$E,$F,$G,$H);
+$t2="r12";
+$Ktbl="r14";
+
+@Sigma0=( 2,13,22);
+@Sigma1=( 6,11,25);
+@sigma0=( 7,18, 3);
+@sigma1=(17,19,10);
+
+sub BODY_00_15 {
+my ($i,$a,$b,$c,$d,$e,$f,$g,$h) = @_;
+
+$code.=<<___ if ($i<16);
+#if __ARM_ARCH__>=7
+	@ ldr	$t1,[$inp],#4			@ $i
+# if $i==15
+	str	$inp,[sp,#17*4]			@ make room for $t4
+# endif
+	eor	$t0,$e,$e,ror#`$Sigma1[1]-$Sigma1[0]`
+	add	$a,$a,$t2			@ h+=Maj(a,b,c) from the past
+	eor	$t0,$t0,$e,ror#`$Sigma1[2]-$Sigma1[0]`	@ Sigma1(e)
+# ifndef __ARMEB__
+	rev	$t1,$t1
+# endif
+#else
+	@ ldrb	$t1,[$inp,#3]			@ $i
+	add	$a,$a,$t2			@ h+=Maj(a,b,c) from the past
+	ldrb	$t2,[$inp,#2]
+	ldrb	$t0,[$inp,#1]
+	orr	$t1,$t1,$t2,lsl#8
+	ldrb	$t2,[$inp],#4
+	orr	$t1,$t1,$t0,lsl#16
+# if $i==15
+	str	$inp,[sp,#17*4]			@ make room for $t4
+# endif
+	eor	$t0,$e,$e,ror#`$Sigma1[1]-$Sigma1[0]`
+	orr	$t1,$t1,$t2,lsl#24
+	eor	$t0,$t0,$e,ror#`$Sigma1[2]-$Sigma1[0]`	@ Sigma1(e)
+#endif
+___
+$code.=<<___;
+	ldr	$t2,[$Ktbl],#4			@ *K256++
+	add	$h,$h,$t1			@ h+=X[i]
+	str	$t1,[sp,#`$i%16`*4]
+	eor	$t1,$f,$g
+	add	$h,$h,$t0,ror#$Sigma1[0]	@ h+=Sigma1(e)
+	and	$t1,$t1,$e
+	add	$h,$h,$t2			@ h+=K256[i]
+	eor	$t1,$t1,$g			@ Ch(e,f,g)
+	eor	$t0,$a,$a,ror#`$Sigma0[1]-$Sigma0[0]`
+	add	$h,$h,$t1			@ h+=Ch(e,f,g)
+#if $i==31
+	and	$t2,$t2,#0xff
+	cmp	$t2,#0xf2			@ done?
+#endif
+#if $i<15
+# if __ARM_ARCH__>=7
+	ldr	$t1,[$inp],#4			@ prefetch
+# else
+	ldrb	$t1,[$inp,#3]
+# endif
+	eor	$t2,$a,$b			@ a^b, b^c in next round
+#else
+	ldr	$t1,[sp,#`($i+2)%16`*4]		@ from future BODY_16_xx
+	eor	$t2,$a,$b			@ a^b, b^c in next round
+	ldr	$t4,[sp,#`($i+15)%16`*4]	@ from future BODY_16_xx
+#endif
+	eor	$t0,$t0,$a,ror#`$Sigma0[2]-$Sigma0[0]`	@ Sigma0(a)
+	and	$t3,$t3,$t2			@ (b^c)&=(a^b)
+	add	$d,$d,$h			@ d+=h
+	eor	$t3,$t3,$b			@ Maj(a,b,c)
+	add	$h,$h,$t0,ror#$Sigma0[0]	@ h+=Sigma0(a)
+	@ add	$h,$h,$t3			@ h+=Maj(a,b,c)
+___
+	($t2,$t3)=($t3,$t2);
+}
+
+sub BODY_16_XX {
+my ($i,$a,$b,$c,$d,$e,$f,$g,$h) = @_;
+
+$code.=<<___;
+	@ ldr	$t1,[sp,#`($i+1)%16`*4]		@ $i
+	@ ldr	$t4,[sp,#`($i+14)%16`*4]
+	mov	$t0,$t1,ror#$sigma0[0]
+	add	$a,$a,$t2			@ h+=Maj(a,b,c) from the past
+	mov	$t2,$t4,ror#$sigma1[0]
+	eor	$t0,$t0,$t1,ror#$sigma0[1]
+	eor	$t2,$t2,$t4,ror#$sigma1[1]
+	eor	$t0,$t0,$t1,lsr#$sigma0[2]	@ sigma0(X[i+1])
+	ldr	$t1,[sp,#`($i+0)%16`*4]
+	eor	$t2,$t2,$t4,lsr#$sigma1[2]	@ sigma1(X[i+14])
+	ldr	$t4,[sp,#`($i+9)%16`*4]
+
+	add	$t2,$t2,$t0
+	eor	$t0,$e,$e,ror#`$Sigma1[1]-$Sigma1[0]`	@ from BODY_00_15
+	add	$t1,$t1,$t2
+	eor	$t0,$t0,$e,ror#`$Sigma1[2]-$Sigma1[0]`	@ Sigma1(e)
+	add	$t1,$t1,$t4			@ X[i]
+___
+	&BODY_00_15(@_);
+}
+
+$code=<<___;
+#ifndef __KERNEL__
+# include "arm_arch.h"
+#else
+# define __ARM_ARCH__ __LINUX_ARM_ARCH__
+# define __ARM_MAX_ARCH__ 7
+#endif
+
+.text
+#if __ARM_ARCH__<7
+.code	32
+#else
+.syntax unified
+# ifdef __thumb2__
+#  define adrl adr
+.thumb
+# else
+.code   32
+# endif
+#endif
+
+.type	K256,%object
+.align	5
+K256:
+.word	0x428a2f98,0x71374491,0xb5c0fbcf,0xe9b5dba5
+.word	0x3956c25b,0x59f111f1,0x923f82a4,0xab1c5ed5
+.word	0xd807aa98,0x12835b01,0x243185be,0x550c7dc3
+.word	0x72be5d74,0x80deb1fe,0x9bdc06a7,0xc19bf174
+.word	0xe49b69c1,0xefbe4786,0x0fc19dc6,0x240ca1cc
+.word	0x2de92c6f,0x4a7484aa,0x5cb0a9dc,0x76f988da
+.word	0x983e5152,0xa831c66d,0xb00327c8,0xbf597fc7
+.word	0xc6e00bf3,0xd5a79147,0x06ca6351,0x14292967
+.word	0x27b70a85,0x2e1b2138,0x4d2c6dfc,0x53380d13
+.word	0x650a7354,0x766a0abb,0x81c2c92e,0x92722c85
+.word	0xa2bfe8a1,0xa81a664b,0xc24b8b70,0xc76c51a3
+.word	0xd192e819,0xd6990624,0xf40e3585,0x106aa070
+.word	0x19a4c116,0x1e376c08,0x2748774c,0x34b0bcb5
+.word	0x391c0cb3,0x4ed8aa4a,0x5b9cca4f,0x682e6ff3
+.word	0x748f82ee,0x78a5636f,0x84c87814,0x8cc70208
+.word	0x90befffa,0xa4506ceb,0xbef9a3f7,0xc67178f2
+.size	K256,.-K256
+.word	0				@ terminator
+#if __ARM_MAX_ARCH__>=7 && !defined(__KERNEL__)
+.LOPENSSL_armcap:
+.word	OPENSSL_armcap_P-sha256_block_data_order
+#endif
+.align	5
+
+.global	sha256_block_data_order
+.type	sha256_block_data_order,%function
+sha256_block_data_order:
+#if __ARM_ARCH__<7
+	sub	r3,pc,#8		@ sha256_block_data_order
+#else
+	adr	r3,sha256_block_data_order
+#endif
+#if __ARM_MAX_ARCH__>=7 && !defined(__KERNEL__)
+	ldr	r12,.LOPENSSL_armcap
+	ldr	r12,[r3,r12]		@ OPENSSL_armcap_P
+	tst	r12,#ARMV8_SHA256
+	bne	.LARMv8
+	tst	r12,#ARMV7_NEON
+	bne	.LNEON
+#endif
+	add	$len,$inp,$len,lsl#6	@ len to point at the end of inp
+	stmdb	sp!,{$ctx,$inp,$len,r4-r11,lr}
+	ldmia	$ctx,{$A,$B,$C,$D,$E,$F,$G,$H}
+	sub	$Ktbl,r3,#256+32	@ K256
+	sub	sp,sp,#16*4		@ alloca(X[16])
+.Loop:
+# if __ARM_ARCH__>=7
+	ldr	$t1,[$inp],#4
+# else
+	ldrb	$t1,[$inp,#3]
+# endif
+	eor	$t3,$B,$C		@ magic
+	eor	$t2,$t2,$t2
+___
+for($i=0;$i<16;$i++)	{ &BODY_00_15($i,@V); unshift(@V,pop(@V)); }
+$code.=".Lrounds_16_xx:\n";
+for (;$i<32;$i++)	{ &BODY_16_XX($i,@V); unshift(@V,pop(@V)); }
+$code.=<<___;
+#if __ARM_ARCH__>=7
+	ite	eq			@ Thumb2 thing, sanity check in ARM
+#endif
+	ldreq	$t3,[sp,#16*4]		@ pull ctx
+	bne	.Lrounds_16_xx
+
+	add	$A,$A,$t2		@ h+=Maj(a,b,c) from the past
+	ldr	$t0,[$t3,#0]
+	ldr	$t1,[$t3,#4]
+	ldr	$t2,[$t3,#8]
+	add	$A,$A,$t0
+	ldr	$t0,[$t3,#12]
+	add	$B,$B,$t1
+	ldr	$t1,[$t3,#16]
+	add	$C,$C,$t2
+	ldr	$t2,[$t3,#20]
+	add	$D,$D,$t0
+	ldr	$t0,[$t3,#24]
+	add	$E,$E,$t1
+	ldr	$t1,[$t3,#28]
+	add	$F,$F,$t2
+	ldr	$inp,[sp,#17*4]		@ pull inp
+	ldr	$t2,[sp,#18*4]		@ pull inp+len
+	add	$G,$G,$t0
+	add	$H,$H,$t1
+	stmia	$t3,{$A,$B,$C,$D,$E,$F,$G,$H}
+	cmp	$inp,$t2
+	sub	$Ktbl,$Ktbl,#256	@ rewind Ktbl
+	bne	.Loop
+
+	add	sp,sp,#`16+3`*4	@ destroy frame
+#if __ARM_ARCH__>=5
+	ldmia	sp!,{r4-r11,pc}
+#else
+	ldmia	sp!,{r4-r11,lr}
+	tst	lr,#1
+	moveq	pc,lr			@ be binary compatible with V4, yet
+	bx	lr			@ interoperable with Thumb ISA:-)
+#endif
+.size	sha256_block_data_order,.-sha256_block_data_order
+___
+######################################################################
+# NEON stuff
+#
+{{{
+my @X=map("q$_",(0..3));
+my ($T0,$T1,$T2,$T3,$T4,$T5)=("q8","q9","q10","q11","d24","d25");
+my $Xfer=$t4;
+my $j=0;
+
+sub Dlo()   { shift=~m|q([1]?[0-9])|?"d".($1*2):"";     }
+sub Dhi()   { shift=~m|q([1]?[0-9])|?"d".($1*2+1):"";   }
+
+sub AUTOLOAD()          # thunk [simplified] x86-style perlasm
+{ my $opcode = $AUTOLOAD; $opcode =~ s/.*:://; $opcode =~ s/_/\./;
+  my $arg = pop;
+    $arg = "#$arg" if ($arg*1 eq $arg);
+    $code .= "\t$opcode\t".join(',',@_,$arg)."\n";
+}
+
+sub Xupdate()
+{ use integer;
+  my $body = shift;
+  my @insns = (&$body,&$body,&$body,&$body);
+  my ($a,$b,$c,$d,$e,$f,$g,$h);
+
+	&vext_8		($T0,@X[0],@X[1],4);	# X[1..4]
+	 eval(shift(@insns));
+	 eval(shift(@insns));
+	 eval(shift(@insns));
+	&vext_8		($T1,@X[2],@X[3],4);	# X[9..12]
+	 eval(shift(@insns));
+	 eval(shift(@insns));
+	 eval(shift(@insns));
+	&vshr_u32	($T2,$T0,$sigma0[0]);
+	 eval(shift(@insns));
+	 eval(shift(@insns));
+	&vadd_i32	(@X[0],@X[0],$T1);	# X[0..3] += X[9..12]
+	 eval(shift(@insns));
+	 eval(shift(@insns));
+	&vshr_u32	($T1,$T0,$sigma0[2]);
+	 eval(shift(@insns));
+	 eval(shift(@insns));
+	&vsli_32	($T2,$T0,32-$sigma0[0]);
+	 eval(shift(@insns));
+	 eval(shift(@insns));
+	&vshr_u32	($T3,$T0,$sigma0[1]);
+	 eval(shift(@insns));
+	 eval(shift(@insns));
+	&veor		($T1,$T1,$T2);
+	 eval(shift(@insns));
+	 eval(shift(@insns));
+	&vsli_32	($T3,$T0,32-$sigma0[1]);
+	 eval(shift(@insns));
+	 eval(shift(@insns));
+	  &vshr_u32	($T4,&Dhi(@X[3]),$sigma1[0]);
+	 eval(shift(@insns));
+	 eval(shift(@insns));
+	&veor		($T1,$T1,$T3);		# sigma0(X[1..4])
+	 eval(shift(@insns));
+	 eval(shift(@insns));
+	  &vsli_32	($T4,&Dhi(@X[3]),32-$sigma1[0]);
+	 eval(shift(@insns));
+	 eval(shift(@insns));
+	  &vshr_u32	($T5,&Dhi(@X[3]),$sigma1[2]);
+	 eval(shift(@insns));
+	 eval(shift(@insns));
+	&vadd_i32	(@X[0],@X[0],$T1);	# X[0..3] += sigma0(X[1..4])
+	 eval(shift(@insns));
+	 eval(shift(@insns));
+	  &veor		($T5,$T5,$T4);
+	 eval(shift(@insns));
+	 eval(shift(@insns));
+	  &vshr_u32	($T4,&Dhi(@X[3]),$sigma1[1]);
+	 eval(shift(@insns));
+	 eval(shift(@insns));
+	  &vsli_32	($T4,&Dhi(@X[3]),32-$sigma1[1]);
+	 eval(shift(@insns));
+	 eval(shift(@insns));
+	  &veor		($T5,$T5,$T4);		# sigma1(X[14..15])
+	 eval(shift(@insns));
+	 eval(shift(@insns));
+	&vadd_i32	(&Dlo(@X[0]),&Dlo(@X[0]),$T5);# X[0..1] += sigma1(X[14..15])
+	 eval(shift(@insns));
+	 eval(shift(@insns));
+	  &vshr_u32	($T4,&Dlo(@X[0]),$sigma1[0]);
+	 eval(shift(@insns));
+	 eval(shift(@insns));
+	  &vsli_32	($T4,&Dlo(@X[0]),32-$sigma1[0]);
+	 eval(shift(@insns));
+	 eval(shift(@insns));
+	  &vshr_u32	($T5,&Dlo(@X[0]),$sigma1[2]);
+	 eval(shift(@insns));
+	 eval(shift(@insns));
+	  &veor		($T5,$T5,$T4);
+	 eval(shift(@insns));
+	 eval(shift(@insns));
+	  &vshr_u32	($T4,&Dlo(@X[0]),$sigma1[1]);
+	 eval(shift(@insns));
+	 eval(shift(@insns));
+	&vld1_32	("{$T0}","[$Ktbl,:128]!");
+	 eval(shift(@insns));
+	 eval(shift(@insns));
+	  &vsli_32	($T4,&Dlo(@X[0]),32-$sigma1[1]);
+	 eval(shift(@insns));
+	 eval(shift(@insns));
+	  &veor		($T5,$T5,$T4);		# sigma1(X[16..17])
+	 eval(shift(@insns));
+	 eval(shift(@insns));
+	&vadd_i32	(&Dhi(@X[0]),&Dhi(@X[0]),$T5);# X[2..3] += sigma1(X[16..17])
+	 eval(shift(@insns));
+	 eval(shift(@insns));
+	&vadd_i32	($T0,$T0,@X[0]);
+	 while($#insns>=2) { eval(shift(@insns)); }
+	&vst1_32	("{$T0}","[$Xfer,:128]!");
+	 eval(shift(@insns));
+	 eval(shift(@insns));
+
+	push(@X,shift(@X));		# "rotate" X[]
+}
+
+sub Xpreload()
+{ use integer;
+  my $body = shift;
+  my @insns = (&$body,&$body,&$body,&$body);
+  my ($a,$b,$c,$d,$e,$f,$g,$h);
+
+	 eval(shift(@insns));
+	 eval(shift(@insns));
+	 eval(shift(@insns));
+	 eval(shift(@insns));
+	&vld1_32	("{$T0}","[$Ktbl,:128]!");
+	 eval(shift(@insns));
+	 eval(shift(@insns));
+	 eval(shift(@insns));
+	 eval(shift(@insns));
+	&vrev32_8	(@X[0],@X[0]);
+	 eval(shift(@insns));
+	 eval(shift(@insns));
+	 eval(shift(@insns));
+	 eval(shift(@insns));
+	&vadd_i32	($T0,$T0,@X[0]);
+	 foreach (@insns) { eval; }	# remaining instructions
+	&vst1_32	("{$T0}","[$Xfer,:128]!");
+
+	push(@X,shift(@X));		# "rotate" X[]
+}
+
+sub body_00_15 () {
+	(
+	'($a,$b,$c,$d,$e,$f,$g,$h)=@V;'.
+	'&add	($h,$h,$t1)',			# h+=X[i]+K[i]
+	'&eor	($t1,$f,$g)',
+	'&eor	($t0,$e,$e,"ror#".($Sigma1[1]-$Sigma1[0]))',
+	'&add	($a,$a,$t2)',			# h+=Maj(a,b,c) from the past
+	'&and	($t1,$t1,$e)',
+	'&eor	($t2,$t0,$e,"ror#".($Sigma1[2]-$Sigma1[0]))',	# Sigma1(e)
+	'&eor	($t0,$a,$a,"ror#".($Sigma0[1]-$Sigma0[0]))',
+	'&eor	($t1,$t1,$g)',			# Ch(e,f,g)
+	'&add	($h,$h,$t2,"ror#$Sigma1[0]")',	# h+=Sigma1(e)
+	'&eor	($t2,$a,$b)',			# a^b, b^c in next round
+	'&eor	($t0,$t0,$a,"ror#".($Sigma0[2]-$Sigma0[0]))',	# Sigma0(a)
+	'&add	($h,$h,$t1)',			# h+=Ch(e,f,g)
+	'&ldr	($t1,sprintf "[sp,#%d]",4*(($j+1)&15))	if (($j&15)!=15);'.
+	'&ldr	($t1,"[$Ktbl]")				if ($j==15);'.
+	'&ldr	($t1,"[sp,#64]")			if ($j==31)',
+	'&and	($t3,$t3,$t2)',			# (b^c)&=(a^b)
+	'&add	($d,$d,$h)',			# d+=h
+	'&add	($h,$h,$t0,"ror#$Sigma0[0]");'.	# h+=Sigma0(a)
+	'&eor	($t3,$t3,$b)',			# Maj(a,b,c)
+	'$j++;	unshift(@V,pop(@V)); ($t2,$t3)=($t3,$t2);'
+	)
+}
+
+$code.=<<___;
+#if __ARM_MAX_ARCH__>=7
+.arch	armv7-a
+.fpu	neon
+
+.global	sha256_block_data_order_neon
+.type	sha256_block_data_order_neon,%function
+.align	4
+sha256_block_data_order_neon:
+.LNEON:
+	stmdb	sp!,{r4-r12,lr}
+
+	sub	$H,sp,#16*4+16
+	adrl	$Ktbl,K256
+	bic	$H,$H,#15		@ align for 128-bit stores
+	mov	$t2,sp
+	mov	sp,$H			@ alloca
+	add	$len,$inp,$len,lsl#6	@ len to point at the end of inp
+
+	vld1.8		{@X[0]},[$inp]!
+	vld1.8		{@X[1]},[$inp]!
+	vld1.8		{@X[2]},[$inp]!
+	vld1.8		{@X[3]},[$inp]!
+	vld1.32		{$T0},[$Ktbl,:128]!
+	vld1.32		{$T1},[$Ktbl,:128]!
+	vld1.32		{$T2},[$Ktbl,:128]!
+	vld1.32		{$T3},[$Ktbl,:128]!
+	vrev32.8	@X[0],@X[0]		@ yes, even on
+	str		$ctx,[sp,#64]
+	vrev32.8	@X[1],@X[1]		@ big-endian
+	str		$inp,[sp,#68]
+	mov		$Xfer,sp
+	vrev32.8	@X[2],@X[2]
+	str		$len,[sp,#72]
+	vrev32.8	@X[3],@X[3]
+	str		$t2,[sp,#76]		@ save original sp
+	vadd.i32	$T0,$T0,@X[0]
+	vadd.i32	$T1,$T1,@X[1]
+	vst1.32		{$T0},[$Xfer,:128]!
+	vadd.i32	$T2,$T2,@X[2]
+	vst1.32		{$T1},[$Xfer,:128]!
+	vadd.i32	$T3,$T3,@X[3]
+	vst1.32		{$T2},[$Xfer,:128]!
+	vst1.32		{$T3},[$Xfer,:128]!
+
+	ldmia		$ctx,{$A-$H}
+	sub		$Xfer,$Xfer,#64
+	ldr		$t1,[sp,#0]
+	eor		$t2,$t2,$t2
+	eor		$t3,$B,$C
+	b		.L_00_48
+
+.align	4
+.L_00_48:
+___
+	&Xupdate(\&body_00_15);
+	&Xupdate(\&body_00_15);
+	&Xupdate(\&body_00_15);
+	&Xupdate(\&body_00_15);
+$code.=<<___;
+	teq	$t1,#0				@ check for K256 terminator
+	ldr	$t1,[sp,#0]
+	sub	$Xfer,$Xfer,#64
+	bne	.L_00_48
+
+	ldr		$inp,[sp,#68]
+	ldr		$t0,[sp,#72]
+	sub		$Ktbl,$Ktbl,#256	@ rewind $Ktbl
+	teq		$inp,$t0
+	it		eq
+	subeq		$inp,$inp,#64		@ avoid SEGV
+	vld1.8		{@X[0]},[$inp]!		@ load next input block
+	vld1.8		{@X[1]},[$inp]!
+	vld1.8		{@X[2]},[$inp]!
+	vld1.8		{@X[3]},[$inp]!
+	it		ne
+	strne		$inp,[sp,#68]
+	mov		$Xfer,sp
+___
+	&Xpreload(\&body_00_15);
+	&Xpreload(\&body_00_15);
+	&Xpreload(\&body_00_15);
+	&Xpreload(\&body_00_15);
+$code.=<<___;
+	ldr	$t0,[$t1,#0]
+	add	$A,$A,$t2			@ h+=Maj(a,b,c) from the past
+	ldr	$t2,[$t1,#4]
+	ldr	$t3,[$t1,#8]
+	ldr	$t4,[$t1,#12]
+	add	$A,$A,$t0			@ accumulate
+	ldr	$t0,[$t1,#16]
+	add	$B,$B,$t2
+	ldr	$t2,[$t1,#20]
+	add	$C,$C,$t3
+	ldr	$t3,[$t1,#24]
+	add	$D,$D,$t4
+	ldr	$t4,[$t1,#28]
+	add	$E,$E,$t0
+	str	$A,[$t1],#4
+	add	$F,$F,$t2
+	str	$B,[$t1],#4
+	add	$G,$G,$t3
+	str	$C,[$t1],#4
+	add	$H,$H,$t4
+	str	$D,[$t1],#4
+	stmia	$t1,{$E-$H}
+
+	ittte	ne
+	movne	$Xfer,sp
+	ldrne	$t1,[sp,#0]
+	eorne	$t2,$t2,$t2
+	ldreq	sp,[sp,#76]			@ restore original sp
+	itt	ne
+	eorne	$t3,$B,$C
+	bne	.L_00_48
+
+	ldmia	sp!,{r4-r12,pc}
+.size	sha256_block_data_order_neon,.-sha256_block_data_order_neon
+#endif
+___
+}}}
+######################################################################
+# ARMv8 stuff
+#
+{{{
+my ($ABCD,$EFGH,$abcd)=map("q$_",(0..2));
+my @MSG=map("q$_",(8..11));
+my ($W0,$W1,$ABCD_SAVE,$EFGH_SAVE)=map("q$_",(12..15));
+my $Ktbl="r3";
+
+$code.=<<___;
+#if __ARM_MAX_ARCH__>=7 && !defined(__KERNEL__)
+
+# ifdef __thumb2__
+#  define INST(a,b,c,d)	.byte	c,d|0xc,a,b
+# else
+#  define INST(a,b,c,d)	.byte	a,b,c,d
+# endif
+
+.type	sha256_block_data_order_armv8,%function
+.align	5
+sha256_block_data_order_armv8:
+.LARMv8:
+	vld1.32	{$ABCD,$EFGH},[$ctx]
+# ifdef __thumb2__
+	adr	$Ktbl,.LARMv8
+	sub	$Ktbl,$Ktbl,#.LARMv8-K256
+# else
+	adrl	$Ktbl,K256
+# endif
+	add	$len,$inp,$len,lsl#6	@ len to point at the end of inp
+
+.Loop_v8:
+	vld1.8		{@MSG[0]-@MSG[1]},[$inp]!
+	vld1.8		{@MSG[2]-@MSG[3]},[$inp]!
+	vld1.32		{$W0},[$Ktbl]!
+	vrev32.8	@MSG[0],@MSG[0]
+	vrev32.8	@MSG[1],@MSG[1]
+	vrev32.8	@MSG[2],@MSG[2]
+	vrev32.8	@MSG[3],@MSG[3]
+	vmov		$ABCD_SAVE,$ABCD	@ offload
+	vmov		$EFGH_SAVE,$EFGH
+	teq		$inp,$len
+___
+for($i=0;$i<12;$i++) {
+$code.=<<___;
+	vld1.32		{$W1},[$Ktbl]!
+	vadd.i32	$W0,$W0,@MSG[0]
+	sha256su0	@MSG[0],@MSG[1]
+	vmov		$abcd,$ABCD
+	sha256h		$ABCD,$EFGH,$W0
+	sha256h2	$EFGH,$abcd,$W0
+	sha256su1	@MSG[0],@MSG[2],@MSG[3]
+___
+	($W0,$W1)=($W1,$W0);	push(@MSG,shift(@MSG));
+}
+$code.=<<___;
+	vld1.32		{$W1},[$Ktbl]!
+	vadd.i32	$W0,$W0,@MSG[0]
+	vmov		$abcd,$ABCD
+	sha256h		$ABCD,$EFGH,$W0
+	sha256h2	$EFGH,$abcd,$W0
+
+	vld1.32		{$W0},[$Ktbl]!
+	vadd.i32	$W1,$W1,@MSG[1]
+	vmov		$abcd,$ABCD
+	sha256h		$ABCD,$EFGH,$W1
+	sha256h2	$EFGH,$abcd,$W1
+
+	vld1.32		{$W1},[$Ktbl]
+	vadd.i32	$W0,$W0,@MSG[2]
+	sub		$Ktbl,$Ktbl,#256-16	@ rewind
+	vmov		$abcd,$ABCD
+	sha256h		$ABCD,$EFGH,$W0
+	sha256h2	$EFGH,$abcd,$W0
+
+	vadd.i32	$W1,$W1,@MSG[3]
+	vmov		$abcd,$ABCD
+	sha256h		$ABCD,$EFGH,$W1
+	sha256h2	$EFGH,$abcd,$W1
+
+	vadd.i32	$ABCD,$ABCD,$ABCD_SAVE
+	vadd.i32	$EFGH,$EFGH,$EFGH_SAVE
+	it		ne
+	bne		.Loop_v8
+
+	vst1.32		{$ABCD,$EFGH},[$ctx]
+
+	ret		@ bx lr
+.size	sha256_block_data_order_armv8,.-sha256_block_data_order_armv8
+#endif
+___
+}}}
+$code.=<<___;
+.asciz  "SHA256 block transform for ARMv4/NEON/ARMv8, CRYPTOGAMS by <appro\@openssl.org>"
+.align	2
+#if __ARM_MAX_ARCH__>=7 && !defined(__KERNEL__)
+.comm   OPENSSL_armcap_P,4,4
+#endif
+___
+
+open SELF,$0;
+while(<SELF>) {
+	next if (/^#!/);
+	last if (!s/^#/@/ and !/^$/);
+	print;
+}
+close SELF;
+
+{   my  %opcode = (
+	"sha256h"	=> 0xf3000c40,	"sha256h2"	=> 0xf3100c40,
+	"sha256su0"	=> 0xf3ba03c0,	"sha256su1"	=> 0xf3200c40	);
+
+    sub unsha256 {
+	my ($mnemonic,$arg)=@_;
+
+	if ($arg =~ m/q([0-9]+)(?:,\s*q([0-9]+))?,\s*q([0-9]+)/o) {
+	    my $word = $opcode{$mnemonic}|(($1&7)<<13)|(($1&8)<<19)
+					 |(($2&7)<<17)|(($2&8)<<4)
+					 |(($3&7)<<1) |(($3&8)<<2);
+	    # since ARMv7 instructions are always encoded little-endian.
+	    # correct solution is to use .inst directive, but older
+	    # assemblers don't implement it:-(
+	    sprintf "INST(0x%02x,0x%02x,0x%02x,0x%02x)\t@ %s %s",
+			$word&0xff,($word>>8)&0xff,
+			($word>>16)&0xff,($word>>24)&0xff,
+			$mnemonic,$arg;
+	}
+    }
+}
+
+foreach (split($/,$code)) {
+
+	s/\`([^\`]*)\`/eval $1/geo;
+
+	s/\b(sha256\w+)\s+(q.*)/unsha256($1,$2)/geo;
+
+	s/\bret\b/bx	lr/go		or
+	s/\bbx\s+lr\b/.word\t0xe12fff1e/go;	# make it possible to compile with -march=armv4
+
+	print $_,"\n";
+}
+
+close STDOUT; # enforce flush
diff --git a/arch/arm/crypto/sha256-core.S_shipped b/arch/arm/crypto/sha256-core.S_shipped
new file mode 100644
index 000000000000..555a1a8eec90
--- /dev/null
+++ b/arch/arm/crypto/sha256-core.S_shipped
@@ -0,0 +1,2808 @@
+
+@ ====================================================================
+@ Written by Andy Polyakov <appro@openssl.org> for the OpenSSL
+@ project. The module is, however, dual licensed under OpenSSL and
+@ CRYPTOGAMS licenses depending on where you obtain it. For further
+@ details see http://www.openssl.org/~appro/cryptogams/.
+@
+@ Permission to use under GPL terms is granted.
+@ ====================================================================
+
+@ SHA256 block procedure for ARMv4. May 2007.
+
+@ Performance is ~2x better than gcc 3.4 generated code and in "abso-
+@ lute" terms is ~2250 cycles per 64-byte block or ~35 cycles per
+@ byte [on single-issue Xscale PXA250 core].
+
+@ July 2010.
+@
+@ Rescheduling for dual-issue pipeline resulted in 22% improvement on
+@ Cortex A8 core and ~20 cycles per processed byte.
+
+@ February 2011.
+@
+@ Profiler-assisted and platform-specific optimization resulted in 16%
+@ improvement on Cortex A8 core and ~15.4 cycles per processed byte.
+
+@ September 2013.
+@
+@ Add NEON implementation. On Cortex A8 it was measured to process one
+@ byte in 12.5 cycles or 23% faster than integer-only code. Snapdragon
+@ S4 does it in 12.5 cycles too, but it's 50% faster than integer-only
+@ code (meaning that latter performs sub-optimally, nothing was done
+@ about it).
+
+@ May 2014.
+@
+@ Add ARMv8 code path performing at 2.0 cpb on Apple A7.
+
+#ifndef __KERNEL__
+# include "arm_arch.h"
+#else
+# define __ARM_ARCH__ __LINUX_ARM_ARCH__
+# define __ARM_MAX_ARCH__ 7
+#endif
+
+.text
+#if __ARM_ARCH__<7
+.code	32
+#else
+.syntax unified
+# ifdef __thumb2__
+#  define adrl adr
+.thumb
+# else
+.code   32
+# endif
+#endif
+
+.type	K256,%object
+.align	5
+K256:
+.word	0x428a2f98,0x71374491,0xb5c0fbcf,0xe9b5dba5
+.word	0x3956c25b,0x59f111f1,0x923f82a4,0xab1c5ed5
+.word	0xd807aa98,0x12835b01,0x243185be,0x550c7dc3
+.word	0x72be5d74,0x80deb1fe,0x9bdc06a7,0xc19bf174
+.word	0xe49b69c1,0xefbe4786,0x0fc19dc6,0x240ca1cc
+.word	0x2de92c6f,0x4a7484aa,0x5cb0a9dc,0x76f988da
+.word	0x983e5152,0xa831c66d,0xb00327c8,0xbf597fc7
+.word	0xc6e00bf3,0xd5a79147,0x06ca6351,0x14292967
+.word	0x27b70a85,0x2e1b2138,0x4d2c6dfc,0x53380d13
+.word	0x650a7354,0x766a0abb,0x81c2c92e,0x92722c85
+.word	0xa2bfe8a1,0xa81a664b,0xc24b8b70,0xc76c51a3
+.word	0xd192e819,0xd6990624,0xf40e3585,0x106aa070
+.word	0x19a4c116,0x1e376c08,0x2748774c,0x34b0bcb5
+.word	0x391c0cb3,0x4ed8aa4a,0x5b9cca4f,0x682e6ff3
+.word	0x748f82ee,0x78a5636f,0x84c87814,0x8cc70208
+.word	0x90befffa,0xa4506ceb,0xbef9a3f7,0xc67178f2
+.size	K256,.-K256
+.word	0				@ terminator
+#if __ARM_MAX_ARCH__>=7 && !defined(__KERNEL__)
+.LOPENSSL_armcap:
+.word	OPENSSL_armcap_P-sha256_block_data_order
+#endif
+.align	5
+
+.global	sha256_block_data_order
+.type	sha256_block_data_order,%function
+sha256_block_data_order:
+#if __ARM_ARCH__<7
+	sub	r3,pc,#8		@ sha256_block_data_order
+#else
+	adr	r3,sha256_block_data_order
+#endif
+#if __ARM_MAX_ARCH__>=7 && !defined(__KERNEL__)
+	ldr	r12,.LOPENSSL_armcap
+	ldr	r12,[r3,r12]		@ OPENSSL_armcap_P
+	tst	r12,#ARMV8_SHA256
+	bne	.LARMv8
+	tst	r12,#ARMV7_NEON
+	bne	.LNEON
+#endif
+	add	r2,r1,r2,lsl#6	@ len to point at the end of inp
+	stmdb	sp!,{r0,r1,r2,r4-r11,lr}
+	ldmia	r0,{r4,r5,r6,r7,r8,r9,r10,r11}
+	sub	r14,r3,#256+32	@ K256
+	sub	sp,sp,#16*4		@ alloca(X[16])
+.Loop:
+# if __ARM_ARCH__>=7
+	ldr	r2,[r1],#4
+# else
+	ldrb	r2,[r1,#3]
+# endif
+	eor	r3,r5,r6		@ magic
+	eor	r12,r12,r12
+#if __ARM_ARCH__>=7
+	@ ldr	r2,[r1],#4			@ 0
+# if 0==15
+	str	r1,[sp,#17*4]			@ make room for r1
+# endif
+	eor	r0,r8,r8,ror#5
+	add	r4,r4,r12			@ h+=Maj(a,b,c) from the past
+	eor	r0,r0,r8,ror#19	@ Sigma1(e)
+# ifndef __ARMEB__
+	rev	r2,r2
+# endif
+#else
+	@ ldrb	r2,[r1,#3]			@ 0
+	add	r4,r4,r12			@ h+=Maj(a,b,c) from the past
+	ldrb	r12,[r1,#2]
+	ldrb	r0,[r1,#1]
+	orr	r2,r2,r12,lsl#8
+	ldrb	r12,[r1],#4
+	orr	r2,r2,r0,lsl#16
+# if 0==15
+	str	r1,[sp,#17*4]			@ make room for r1
+# endif
+	eor	r0,r8,r8,ror#5
+	orr	r2,r2,r12,lsl#24
+	eor	r0,r0,r8,ror#19	@ Sigma1(e)
+#endif
+	ldr	r12,[r14],#4			@ *K256++
+	add	r11,r11,r2			@ h+=X[i]
+	str	r2,[sp,#0*4]
+	eor	r2,r9,r10
+	add	r11,r11,r0,ror#6	@ h+=Sigma1(e)
+	and	r2,r2,r8
+	add	r11,r11,r12			@ h+=K256[i]
+	eor	r2,r2,r10			@ Ch(e,f,g)
+	eor	r0,r4,r4,ror#11
+	add	r11,r11,r2			@ h+=Ch(e,f,g)
+#if 0==31
+	and	r12,r12,#0xff
+	cmp	r12,#0xf2			@ done?
+#endif
+#if 0<15
+# if __ARM_ARCH__>=7
+	ldr	r2,[r1],#4			@ prefetch
+# else
+	ldrb	r2,[r1,#3]
+# endif
+	eor	r12,r4,r5			@ a^b, b^c in next round
+#else
+	ldr	r2,[sp,#2*4]		@ from future BODY_16_xx
+	eor	r12,r4,r5			@ a^b, b^c in next round
+	ldr	r1,[sp,#15*4]	@ from future BODY_16_xx
+#endif
+	eor	r0,r0,r4,ror#20	@ Sigma0(a)
+	and	r3,r3,r12			@ (b^c)&=(a^b)
+	add	r7,r7,r11			@ d+=h
+	eor	r3,r3,r5			@ Maj(a,b,c)
+	add	r11,r11,r0,ror#2	@ h+=Sigma0(a)
+	@ add	r11,r11,r3			@ h+=Maj(a,b,c)
+#if __ARM_ARCH__>=7
+	@ ldr	r2,[r1],#4			@ 1
+# if 1==15
+	str	r1,[sp,#17*4]			@ make room for r1
+# endif
+	eor	r0,r7,r7,ror#5
+	add	r11,r11,r3			@ h+=Maj(a,b,c) from the past
+	eor	r0,r0,r7,ror#19	@ Sigma1(e)
+# ifndef __ARMEB__
+	rev	r2,r2
+# endif
+#else
+	@ ldrb	r2,[r1,#3]			@ 1
+	add	r11,r11,r3			@ h+=Maj(a,b,c) from the past
+	ldrb	r3,[r1,#2]
+	ldrb	r0,[r1,#1]
+	orr	r2,r2,r3,lsl#8
+	ldrb	r3,[r1],#4
+	orr	r2,r2,r0,lsl#16
+# if 1==15
+	str	r1,[sp,#17*4]			@ make room for r1
+# endif
+	eor	r0,r7,r7,ror#5
+	orr	r2,r2,r3,lsl#24
+	eor	r0,r0,r7,ror#19	@ Sigma1(e)
+#endif
+	ldr	r3,[r14],#4			@ *K256++
+	add	r10,r10,r2			@ h+=X[i]
+	str	r2,[sp,#1*4]
+	eor	r2,r8,r9
+	add	r10,r10,r0,ror#6	@ h+=Sigma1(e)
+	and	r2,r2,r7
+	add	r10,r10,r3			@ h+=K256[i]
+	eor	r2,r2,r9			@ Ch(e,f,g)
+	eor	r0,r11,r11,ror#11
+	add	r10,r10,r2			@ h+=Ch(e,f,g)
+#if 1==31
+	and	r3,r3,#0xff
+	cmp	r3,#0xf2			@ done?
+#endif
+#if 1<15
+# if __ARM_ARCH__>=7
+	ldr	r2,[r1],#4			@ prefetch
+# else
+	ldrb	r2,[r1,#3]
+# endif
+	eor	r3,r11,r4			@ a^b, b^c in next round
+#else
+	ldr	r2,[sp,#3*4]		@ from future BODY_16_xx
+	eor	r3,r11,r4			@ a^b, b^c in next round
+	ldr	r1,[sp,#0*4]	@ from future BODY_16_xx
+#endif
+	eor	r0,r0,r11,ror#20	@ Sigma0(a)
+	and	r12,r12,r3			@ (b^c)&=(a^b)
+	add	r6,r6,r10			@ d+=h
+	eor	r12,r12,r4			@ Maj(a,b,c)
+	add	r10,r10,r0,ror#2	@ h+=Sigma0(a)
+	@ add	r10,r10,r12			@ h+=Maj(a,b,c)
+#if __ARM_ARCH__>=7
+	@ ldr	r2,[r1],#4			@ 2
+# if 2==15
+	str	r1,[sp,#17*4]			@ make room for r1
+# endif
+	eor	r0,r6,r6,ror#5
+	add	r10,r10,r12			@ h+=Maj(a,b,c) from the past
+	eor	r0,r0,r6,ror#19	@ Sigma1(e)
+# ifndef __ARMEB__
+	rev	r2,r2
+# endif
+#else
+	@ ldrb	r2,[r1,#3]			@ 2
+	add	r10,r10,r12			@ h+=Maj(a,b,c) from the past
+	ldrb	r12,[r1,#2]
+	ldrb	r0,[r1,#1]
+	orr	r2,r2,r12,lsl#8
+	ldrb	r12,[r1],#4
+	orr	r2,r2,r0,lsl#16
+# if 2==15
+	str	r1,[sp,#17*4]			@ make room for r1
+# endif
+	eor	r0,r6,r6,ror#5
+	orr	r2,r2,r12,lsl#24
+	eor	r0,r0,r6,ror#19	@ Sigma1(e)
+#endif
+	ldr	r12,[r14],#4			@ *K256++
+	add	r9,r9,r2			@ h+=X[i]
+	str	r2,[sp,#2*4]
+	eor	r2,r7,r8
+	add	r9,r9,r0,ror#6	@ h+=Sigma1(e)
+	and	r2,r2,r6
+	add	r9,r9,r12			@ h+=K256[i]
+	eor	r2,r2,r8			@ Ch(e,f,g)
+	eor	r0,r10,r10,ror#11
+	add	r9,r9,r2			@ h+=Ch(e,f,g)
+#if 2==31
+	and	r12,r12,#0xff
+	cmp	r12,#0xf2			@ done?
+#endif
+#if 2<15
+# if __ARM_ARCH__>=7
+	ldr	r2,[r1],#4			@ prefetch
+# else
+	ldrb	r2,[r1,#3]
+# endif
+	eor	r12,r10,r11			@ a^b, b^c in next round
+#else
+	ldr	r2,[sp,#4*4]		@ from future BODY_16_xx
+	eor	r12,r10,r11			@ a^b, b^c in next round
+	ldr	r1,[sp,#1*4]	@ from future BODY_16_xx
+#endif
+	eor	r0,r0,r10,ror#20	@ Sigma0(a)
+	and	r3,r3,r12			@ (b^c)&=(a^b)
+	add	r5,r5,r9			@ d+=h
+	eor	r3,r3,r11			@ Maj(a,b,c)
+	add	r9,r9,r0,ror#2	@ h+=Sigma0(a)
+	@ add	r9,r9,r3			@ h+=Maj(a,b,c)
+#if __ARM_ARCH__>=7
+	@ ldr	r2,[r1],#4			@ 3
+# if 3==15
+	str	r1,[sp,#17*4]			@ make room for r1
+# endif
+	eor	r0,r5,r5,ror#5
+	add	r9,r9,r3			@ h+=Maj(a,b,c) from the past
+	eor	r0,r0,r5,ror#19	@ Sigma1(e)
+# ifndef __ARMEB__
+	rev	r2,r2
+# endif
+#else
+	@ ldrb	r2,[r1,#3]			@ 3
+	add	r9,r9,r3			@ h+=Maj(a,b,c) from the past
+	ldrb	r3,[r1,#2]
+	ldrb	r0,[r1,#1]
+	orr	r2,r2,r3,lsl#8
+	ldrb	r3,[r1],#4
+	orr	r2,r2,r0,lsl#16
+# if 3==15
+	str	r1,[sp,#17*4]			@ make room for r1
+# endif
+	eor	r0,r5,r5,ror#5
+	orr	r2,r2,r3,lsl#24
+	eor	r0,r0,r5,ror#19	@ Sigma1(e)
+#endif
+	ldr	r3,[r14],#4			@ *K256++
+	add	r8,r8,r2			@ h+=X[i]
+	str	r2,[sp,#3*4]
+	eor	r2,r6,r7
+	add	r8,r8,r0,ror#6	@ h+=Sigma1(e)
+	and	r2,r2,r5
+	add	r8,r8,r3			@ h+=K256[i]
+	eor	r2,r2,r7			@ Ch(e,f,g)
+	eor	r0,r9,r9,ror#11
+	add	r8,r8,r2			@ h+=Ch(e,f,g)
+#if 3==31
+	and	r3,r3,#0xff
+	cmp	r3,#0xf2			@ done?
+#endif
+#if 3<15
+# if __ARM_ARCH__>=7
+	ldr	r2,[r1],#4			@ prefetch
+# else
+	ldrb	r2,[r1,#3]
+# endif
+	eor	r3,r9,r10			@ a^b, b^c in next round
+#else
+	ldr	r2,[sp,#5*4]		@ from future BODY_16_xx
+	eor	r3,r9,r10			@ a^b, b^c in next round
+	ldr	r1,[sp,#2*4]	@ from future BODY_16_xx
+#endif
+	eor	r0,r0,r9,ror#20	@ Sigma0(a)
+	and	r12,r12,r3			@ (b^c)&=(a^b)
+	add	r4,r4,r8			@ d+=h
+	eor	r12,r12,r10			@ Maj(a,b,c)
+	add	r8,r8,r0,ror#2	@ h+=Sigma0(a)
+	@ add	r8,r8,r12			@ h+=Maj(a,b,c)
+#if __ARM_ARCH__>=7
+	@ ldr	r2,[r1],#4			@ 4
+# if 4==15
+	str	r1,[sp,#17*4]			@ make room for r1
+# endif
+	eor	r0,r4,r4,ror#5
+	add	r8,r8,r12			@ h+=Maj(a,b,c) from the past
+	eor	r0,r0,r4,ror#19	@ Sigma1(e)
+# ifndef __ARMEB__
+	rev	r2,r2
+# endif
+#else
+	@ ldrb	r2,[r1,#3]			@ 4
+	add	r8,r8,r12			@ h+=Maj(a,b,c) from the past
+	ldrb	r12,[r1,#2]
+	ldrb	r0,[r1,#1]
+	orr	r2,r2,r12,lsl#8
+	ldrb	r12,[r1],#4
+	orr	r2,r2,r0,lsl#16
+# if 4==15
+	str	r1,[sp,#17*4]			@ make room for r1
+# endif
+	eor	r0,r4,r4,ror#5
+	orr	r2,r2,r12,lsl#24
+	eor	r0,r0,r4,ror#19	@ Sigma1(e)
+#endif
+	ldr	r12,[r14],#4			@ *K256++
+	add	r7,r7,r2			@ h+=X[i]
+	str	r2,[sp,#4*4]
+	eor	r2,r5,r6
+	add	r7,r7,r0,ror#6	@ h+=Sigma1(e)
+	and	r2,r2,r4
+	add	r7,r7,r12			@ h+=K256[i]
+	eor	r2,r2,r6			@ Ch(e,f,g)
+	eor	r0,r8,r8,ror#11
+	add	r7,r7,r2			@ h+=Ch(e,f,g)
+#if 4==31
+	and	r12,r12,#0xff
+	cmp	r12,#0xf2			@ done?
+#endif
+#if 4<15
+# if __ARM_ARCH__>=7
+	ldr	r2,[r1],#4			@ prefetch
+# else
+	ldrb	r2,[r1,#3]
+# endif
+	eor	r12,r8,r9			@ a^b, b^c in next round
+#else
+	ldr	r2,[sp,#6*4]		@ from future BODY_16_xx
+	eor	r12,r8,r9			@ a^b, b^c in next round
+	ldr	r1,[sp,#3*4]	@ from future BODY_16_xx
+#endif
+	eor	r0,r0,r8,ror#20	@ Sigma0(a)
+	and	r3,r3,r12			@ (b^c)&=(a^b)
+	add	r11,r11,r7			@ d+=h
+	eor	r3,r3,r9			@ Maj(a,b,c)
+	add	r7,r7,r0,ror#2	@ h+=Sigma0(a)
+	@ add	r7,r7,r3			@ h+=Maj(a,b,c)
+#if __ARM_ARCH__>=7
+	@ ldr	r2,[r1],#4			@ 5
+# if 5==15
+	str	r1,[sp,#17*4]			@ make room for r1
+# endif
+	eor	r0,r11,r11,ror#5
+	add	r7,r7,r3			@ h+=Maj(a,b,c) from the past
+	eor	r0,r0,r11,ror#19	@ Sigma1(e)
+# ifndef __ARMEB__
+	rev	r2,r2
+# endif
+#else
+	@ ldrb	r2,[r1,#3]			@ 5
+	add	r7,r7,r3			@ h+=Maj(a,b,c) from the past
+	ldrb	r3,[r1,#2]
+	ldrb	r0,[r1,#1]
+	orr	r2,r2,r3,lsl#8
+	ldrb	r3,[r1],#4
+	orr	r2,r2,r0,lsl#16
+# if 5==15
+	str	r1,[sp,#17*4]			@ make room for r1
+# endif
+	eor	r0,r11,r11,ror#5
+	orr	r2,r2,r3,lsl#24
+	eor	r0,r0,r11,ror#19	@ Sigma1(e)
+#endif
+	ldr	r3,[r14],#4			@ *K256++
+	add	r6,r6,r2			@ h+=X[i]
+	str	r2,[sp,#5*4]
+	eor	r2,r4,r5
+	add	r6,r6,r0,ror#6	@ h+=Sigma1(e)
+	and	r2,r2,r11
+	add	r6,r6,r3			@ h+=K256[i]
+	eor	r2,r2,r5			@ Ch(e,f,g)
+	eor	r0,r7,r7,ror#11
+	add	r6,r6,r2			@ h+=Ch(e,f,g)
+#if 5==31
+	and	r3,r3,#0xff
+	cmp	r3,#0xf2			@ done?
+#endif
+#if 5<15
+# if __ARM_ARCH__>=7
+	ldr	r2,[r1],#4			@ prefetch
+# else
+	ldrb	r2,[r1,#3]
+# endif
+	eor	r3,r7,r8			@ a^b, b^c in next round
+#else
+	ldr	r2,[sp,#7*4]		@ from future BODY_16_xx
+	eor	r3,r7,r8			@ a^b, b^c in next round
+	ldr	r1,[sp,#4*4]	@ from future BODY_16_xx
+#endif
+	eor	r0,r0,r7,ror#20	@ Sigma0(a)
+	and	r12,r12,r3			@ (b^c)&=(a^b)
+	add	r10,r10,r6			@ d+=h
+	eor	r12,r12,r8			@ Maj(a,b,c)
+	add	r6,r6,r0,ror#2	@ h+=Sigma0(a)
+	@ add	r6,r6,r12			@ h+=Maj(a,b,c)
+#if __ARM_ARCH__>=7
+	@ ldr	r2,[r1],#4			@ 6
+# if 6==15
+	str	r1,[sp,#17*4]			@ make room for r1
+# endif
+	eor	r0,r10,r10,ror#5
+	add	r6,r6,r12			@ h+=Maj(a,b,c) from the past
+	eor	r0,r0,r10,ror#19	@ Sigma1(e)
+# ifndef __ARMEB__
+	rev	r2,r2
+# endif
+#else
+	@ ldrb	r2,[r1,#3]			@ 6
+	add	r6,r6,r12			@ h+=Maj(a,b,c) from the past
+	ldrb	r12,[r1,#2]
+	ldrb	r0,[r1,#1]
+	orr	r2,r2,r12,lsl#8
+	ldrb	r12,[r1],#4
+	orr	r2,r2,r0,lsl#16
+# if 6==15
+	str	r1,[sp,#17*4]			@ make room for r1
+# endif
+	eor	r0,r10,r10,ror#5
+	orr	r2,r2,r12,lsl#24
+	eor	r0,r0,r10,ror#19	@ Sigma1(e)
+#endif
+	ldr	r12,[r14],#4			@ *K256++
+	add	r5,r5,r2			@ h+=X[i]
+	str	r2,[sp,#6*4]
+	eor	r2,r11,r4
+	add	r5,r5,r0,ror#6	@ h+=Sigma1(e)
+	and	r2,r2,r10
+	add	r5,r5,r12			@ h+=K256[i]
+	eor	r2,r2,r4			@ Ch(e,f,g)
+	eor	r0,r6,r6,ror#11
+	add	r5,r5,r2			@ h+=Ch(e,f,g)
+#if 6==31
+	and	r12,r12,#0xff
+	cmp	r12,#0xf2			@ done?
+#endif
+#if 6<15
+# if __ARM_ARCH__>=7
+	ldr	r2,[r1],#4			@ prefetch
+# else
+	ldrb	r2,[r1,#3]
+# endif
+	eor	r12,r6,r7			@ a^b, b^c in next round
+#else
+	ldr	r2,[sp,#8*4]		@ from future BODY_16_xx
+	eor	r12,r6,r7			@ a^b, b^c in next round
+	ldr	r1,[sp,#5*4]	@ from future BODY_16_xx
+#endif
+	eor	r0,r0,r6,ror#20	@ Sigma0(a)
+	and	r3,r3,r12			@ (b^c)&=(a^b)
+	add	r9,r9,r5			@ d+=h
+	eor	r3,r3,r7			@ Maj(a,b,c)
+	add	r5,r5,r0,ror#2	@ h+=Sigma0(a)
+	@ add	r5,r5,r3			@ h+=Maj(a,b,c)
+#if __ARM_ARCH__>=7
+	@ ldr	r2,[r1],#4			@ 7
+# if 7==15
+	str	r1,[sp,#17*4]			@ make room for r1
+# endif
+	eor	r0,r9,r9,ror#5
+	add	r5,r5,r3			@ h+=Maj(a,b,c) from the past
+	eor	r0,r0,r9,ror#19	@ Sigma1(e)
+# ifndef __ARMEB__
+	rev	r2,r2
+# endif
+#else
+	@ ldrb	r2,[r1,#3]			@ 7
+	add	r5,r5,r3			@ h+=Maj(a,b,c) from the past
+	ldrb	r3,[r1,#2]
+	ldrb	r0,[r1,#1]
+	orr	r2,r2,r3,lsl#8
+	ldrb	r3,[r1],#4
+	orr	r2,r2,r0,lsl#16
+# if 7==15
+	str	r1,[sp,#17*4]			@ make room for r1
+# endif
+	eor	r0,r9,r9,ror#5
+	orr	r2,r2,r3,lsl#24
+	eor	r0,r0,r9,ror#19	@ Sigma1(e)
+#endif
+	ldr	r3,[r14],#4			@ *K256++
+	add	r4,r4,r2			@ h+=X[i]
+	str	r2,[sp,#7*4]
+	eor	r2,r10,r11
+	add	r4,r4,r0,ror#6	@ h+=Sigma1(e)
+	and	r2,r2,r9
+	add	r4,r4,r3			@ h+=K256[i]
+	eor	r2,r2,r11			@ Ch(e,f,g)
+	eor	r0,r5,r5,ror#11
+	add	r4,r4,r2			@ h+=Ch(e,f,g)
+#if 7==31
+	and	r3,r3,#0xff
+	cmp	r3,#0xf2			@ done?
+#endif
+#if 7<15
+# if __ARM_ARCH__>=7
+	ldr	r2,[r1],#4			@ prefetch
+# else
+	ldrb	r2,[r1,#3]
+# endif
+	eor	r3,r5,r6			@ a^b, b^c in next round
+#else
+	ldr	r2,[sp,#9*4]		@ from future BODY_16_xx
+	eor	r3,r5,r6			@ a^b, b^c in next round
+	ldr	r1,[sp,#6*4]	@ from future BODY_16_xx
+#endif
+	eor	r0,r0,r5,ror#20	@ Sigma0(a)
+	and	r12,r12,r3			@ (b^c)&=(a^b)
+	add	r8,r8,r4			@ d+=h
+	eor	r12,r12,r6			@ Maj(a,b,c)
+	add	r4,r4,r0,ror#2	@ h+=Sigma0(a)
+	@ add	r4,r4,r12			@ h+=Maj(a,b,c)
+#if __ARM_ARCH__>=7
+	@ ldr	r2,[r1],#4			@ 8
+# if 8==15
+	str	r1,[sp,#17*4]			@ make room for r1
+# endif
+	eor	r0,r8,r8,ror#5
+	add	r4,r4,r12			@ h+=Maj(a,b,c) from the past
+	eor	r0,r0,r8,ror#19	@ Sigma1(e)
+# ifndef __ARMEB__
+	rev	r2,r2
+# endif
+#else
+	@ ldrb	r2,[r1,#3]			@ 8
+	add	r4,r4,r12			@ h+=Maj(a,b,c) from the past
+	ldrb	r12,[r1,#2]
+	ldrb	r0,[r1,#1]
+	orr	r2,r2,r12,lsl#8
+	ldrb	r12,[r1],#4
+	orr	r2,r2,r0,lsl#16
+# if 8==15
+	str	r1,[sp,#17*4]			@ make room for r1
+# endif
+	eor	r0,r8,r8,ror#5
+	orr	r2,r2,r12,lsl#24
+	eor	r0,r0,r8,ror#19	@ Sigma1(e)
+#endif
+	ldr	r12,[r14],#4			@ *K256++
+	add	r11,r11,r2			@ h+=X[i]
+	str	r2,[sp,#8*4]
+	eor	r2,r9,r10
+	add	r11,r11,r0,ror#6	@ h+=Sigma1(e)
+	and	r2,r2,r8
+	add	r11,r11,r12			@ h+=K256[i]
+	eor	r2,r2,r10			@ Ch(e,f,g)
+	eor	r0,r4,r4,ror#11
+	add	r11,r11,r2			@ h+=Ch(e,f,g)
+#if 8==31
+	and	r12,r12,#0xff
+	cmp	r12,#0xf2			@ done?
+#endif
+#if 8<15
+# if __ARM_ARCH__>=7
+	ldr	r2,[r1],#4			@ prefetch
+# else
+	ldrb	r2,[r1,#3]
+# endif
+	eor	r12,r4,r5			@ a^b, b^c in next round
+#else
+	ldr	r2,[sp,#10*4]		@ from future BODY_16_xx
+	eor	r12,r4,r5			@ a^b, b^c in next round
+	ldr	r1,[sp,#7*4]	@ from future BODY_16_xx
+#endif
+	eor	r0,r0,r4,ror#20	@ Sigma0(a)
+	and	r3,r3,r12			@ (b^c)&=(a^b)
+	add	r7,r7,r11			@ d+=h
+	eor	r3,r3,r5			@ Maj(a,b,c)
+	add	r11,r11,r0,ror#2	@ h+=Sigma0(a)
+	@ add	r11,r11,r3			@ h+=Maj(a,b,c)
+#if __ARM_ARCH__>=7
+	@ ldr	r2,[r1],#4			@ 9
+# if 9==15
+	str	r1,[sp,#17*4]			@ make room for r1
+# endif
+	eor	r0,r7,r7,ror#5
+	add	r11,r11,r3			@ h+=Maj(a,b,c) from the past
+	eor	r0,r0,r7,ror#19	@ Sigma1(e)
+# ifndef __ARMEB__
+	rev	r2,r2
+# endif
+#else
+	@ ldrb	r2,[r1,#3]			@ 9
+	add	r11,r11,r3			@ h+=Maj(a,b,c) from the past
+	ldrb	r3,[r1,#2]
+	ldrb	r0,[r1,#1]
+	orr	r2,r2,r3,lsl#8
+	ldrb	r3,[r1],#4
+	orr	r2,r2,r0,lsl#16
+# if 9==15
+	str	r1,[sp,#17*4]			@ make room for r1
+# endif
+	eor	r0,r7,r7,ror#5
+	orr	r2,r2,r3,lsl#24
+	eor	r0,r0,r7,ror#19	@ Sigma1(e)
+#endif
+	ldr	r3,[r14],#4			@ *K256++
+	add	r10,r10,r2			@ h+=X[i]
+	str	r2,[sp,#9*4]
+	eor	r2,r8,r9
+	add	r10,r10,r0,ror#6	@ h+=Sigma1(e)
+	and	r2,r2,r7
+	add	r10,r10,r3			@ h+=K256[i]
+	eor	r2,r2,r9			@ Ch(e,f,g)
+	eor	r0,r11,r11,ror#11
+	add	r10,r10,r2			@ h+=Ch(e,f,g)
+#if 9==31
+	and	r3,r3,#0xff
+	cmp	r3,#0xf2			@ done?
+#endif
+#if 9<15
+# if __ARM_ARCH__>=7
+	ldr	r2,[r1],#4			@ prefetch
+# else
+	ldrb	r2,[r1,#3]
+# endif
+	eor	r3,r11,r4			@ a^b, b^c in next round
+#else
+	ldr	r2,[sp,#11*4]		@ from future BODY_16_xx
+	eor	r3,r11,r4			@ a^b, b^c in next round
+	ldr	r1,[sp,#8*4]	@ from future BODY_16_xx
+#endif
+	eor	r0,r0,r11,ror#20	@ Sigma0(a)
+	and	r12,r12,r3			@ (b^c)&=(a^b)
+	add	r6,r6,r10			@ d+=h
+	eor	r12,r12,r4			@ Maj(a,b,c)
+	add	r10,r10,r0,ror#2	@ h+=Sigma0(a)
+	@ add	r10,r10,r12			@ h+=Maj(a,b,c)
+#if __ARM_ARCH__>=7
+	@ ldr	r2,[r1],#4			@ 10
+# if 10==15
+	str	r1,[sp,#17*4]			@ make room for r1
+# endif
+	eor	r0,r6,r6,ror#5
+	add	r10,r10,r12			@ h+=Maj(a,b,c) from the past
+	eor	r0,r0,r6,ror#19	@ Sigma1(e)
+# ifndef __ARMEB__
+	rev	r2,r2
+# endif
+#else
+	@ ldrb	r2,[r1,#3]			@ 10
+	add	r10,r10,r12			@ h+=Maj(a,b,c) from the past
+	ldrb	r12,[r1,#2]
+	ldrb	r0,[r1,#1]
+	orr	r2,r2,r12,lsl#8
+	ldrb	r12,[r1],#4
+	orr	r2,r2,r0,lsl#16
+# if 10==15
+	str	r1,[sp,#17*4]			@ make room for r1
+# endif
+	eor	r0,r6,r6,ror#5
+	orr	r2,r2,r12,lsl#24
+	eor	r0,r0,r6,ror#19	@ Sigma1(e)
+#endif
+	ldr	r12,[r14],#4			@ *K256++
+	add	r9,r9,r2			@ h+=X[i]
+	str	r2,[sp,#10*4]
+	eor	r2,r7,r8
+	add	r9,r9,r0,ror#6	@ h+=Sigma1(e)
+	and	r2,r2,r6
+	add	r9,r9,r12			@ h+=K256[i]
+	eor	r2,r2,r8			@ Ch(e,f,g)
+	eor	r0,r10,r10,ror#11
+	add	r9,r9,r2			@ h+=Ch(e,f,g)
+#if 10==31
+	and	r12,r12,#0xff
+	cmp	r12,#0xf2			@ done?
+#endif
+#if 10<15
+# if __ARM_ARCH__>=7
+	ldr	r2,[r1],#4			@ prefetch
+# else
+	ldrb	r2,[r1,#3]
+# endif
+	eor	r12,r10,r11			@ a^b, b^c in next round
+#else
+	ldr	r2,[sp,#12*4]		@ from future BODY_16_xx
+	eor	r12,r10,r11			@ a^b, b^c in next round
+	ldr	r1,[sp,#9*4]	@ from future BODY_16_xx
+#endif
+	eor	r0,r0,r10,ror#20	@ Sigma0(a)
+	and	r3,r3,r12			@ (b^c)&=(a^b)
+	add	r5,r5,r9			@ d+=h
+	eor	r3,r3,r11			@ Maj(a,b,c)
+	add	r9,r9,r0,ror#2	@ h+=Sigma0(a)
+	@ add	r9,r9,r3			@ h+=Maj(a,b,c)
+#if __ARM_ARCH__>=7
+	@ ldr	r2,[r1],#4			@ 11
+# if 11==15
+	str	r1,[sp,#17*4]			@ make room for r1
+# endif
+	eor	r0,r5,r5,ror#5
+	add	r9,r9,r3			@ h+=Maj(a,b,c) from the past
+	eor	r0,r0,r5,ror#19	@ Sigma1(e)
+# ifndef __ARMEB__
+	rev	r2,r2
+# endif
+#else
+	@ ldrb	r2,[r1,#3]			@ 11
+	add	r9,r9,r3			@ h+=Maj(a,b,c) from the past
+	ldrb	r3,[r1,#2]
+	ldrb	r0,[r1,#1]
+	orr	r2,r2,r3,lsl#8
+	ldrb	r3,[r1],#4
+	orr	r2,r2,r0,lsl#16
+# if 11==15
+	str	r1,[sp,#17*4]			@ make room for r1
+# endif
+	eor	r0,r5,r5,ror#5
+	orr	r2,r2,r3,lsl#24
+	eor	r0,r0,r5,ror#19	@ Sigma1(e)
+#endif
+	ldr	r3,[r14],#4			@ *K256++
+	add	r8,r8,r2			@ h+=X[i]
+	str	r2,[sp,#11*4]
+	eor	r2,r6,r7
+	add	r8,r8,r0,ror#6	@ h+=Sigma1(e)
+	and	r2,r2,r5
+	add	r8,r8,r3			@ h+=K256[i]
+	eor	r2,r2,r7			@ Ch(e,f,g)
+	eor	r0,r9,r9,ror#11
+	add	r8,r8,r2			@ h+=Ch(e,f,g)
+#if 11==31
+	and	r3,r3,#0xff
+	cmp	r3,#0xf2			@ done?
+#endif
+#if 11<15
+# if __ARM_ARCH__>=7
+	ldr	r2,[r1],#4			@ prefetch
+# else
+	ldrb	r2,[r1,#3]
+# endif
+	eor	r3,r9,r10			@ a^b, b^c in next round
+#else
+	ldr	r2,[sp,#13*4]		@ from future BODY_16_xx
+	eor	r3,r9,r10			@ a^b, b^c in next round
+	ldr	r1,[sp,#10*4]	@ from future BODY_16_xx
+#endif
+	eor	r0,r0,r9,ror#20	@ Sigma0(a)
+	and	r12,r12,r3			@ (b^c)&=(a^b)
+	add	r4,r4,r8			@ d+=h
+	eor	r12,r12,r10			@ Maj(a,b,c)
+	add	r8,r8,r0,ror#2	@ h+=Sigma0(a)
+	@ add	r8,r8,r12			@ h+=Maj(a,b,c)
+#if __ARM_ARCH__>=7
+	@ ldr	r2,[r1],#4			@ 12
+# if 12==15
+	str	r1,[sp,#17*4]			@ make room for r1
+# endif
+	eor	r0,r4,r4,ror#5
+	add	r8,r8,r12			@ h+=Maj(a,b,c) from the past
+	eor	r0,r0,r4,ror#19	@ Sigma1(e)
+# ifndef __ARMEB__
+	rev	r2,r2
+# endif
+#else
+	@ ldrb	r2,[r1,#3]			@ 12
+	add	r8,r8,r12			@ h+=Maj(a,b,c) from the past
+	ldrb	r12,[r1,#2]
+	ldrb	r0,[r1,#1]
+	orr	r2,r2,r12,lsl#8
+	ldrb	r12,[r1],#4
+	orr	r2,r2,r0,lsl#16
+# if 12==15
+	str	r1,[sp,#17*4]			@ make room for r1
+# endif
+	eor	r0,r4,r4,ror#5
+	orr	r2,r2,r12,lsl#24
+	eor	r0,r0,r4,ror#19	@ Sigma1(e)
+#endif
+	ldr	r12,[r14],#4			@ *K256++
+	add	r7,r7,r2			@ h+=X[i]
+	str	r2,[sp,#12*4]
+	eor	r2,r5,r6
+	add	r7,r7,r0,ror#6	@ h+=Sigma1(e)
+	and	r2,r2,r4
+	add	r7,r7,r12			@ h+=K256[i]
+	eor	r2,r2,r6			@ Ch(e,f,g)
+	eor	r0,r8,r8,ror#11
+	add	r7,r7,r2			@ h+=Ch(e,f,g)
+#if 12==31
+	and	r12,r12,#0xff
+	cmp	r12,#0xf2			@ done?
+#endif
+#if 12<15
+# if __ARM_ARCH__>=7
+	ldr	r2,[r1],#4			@ prefetch
+# else
+	ldrb	r2,[r1,#3]
+# endif
+	eor	r12,r8,r9			@ a^b, b^c in next round
+#else
+	ldr	r2,[sp,#14*4]		@ from future BODY_16_xx
+	eor	r12,r8,r9			@ a^b, b^c in next round
+	ldr	r1,[sp,#11*4]	@ from future BODY_16_xx
+#endif
+	eor	r0,r0,r8,ror#20	@ Sigma0(a)
+	and	r3,r3,r12			@ (b^c)&=(a^b)
+	add	r11,r11,r7			@ d+=h
+	eor	r3,r3,r9			@ Maj(a,b,c)
+	add	r7,r7,r0,ror#2	@ h+=Sigma0(a)
+	@ add	r7,r7,r3			@ h+=Maj(a,b,c)
+#if __ARM_ARCH__>=7
+	@ ldr	r2,[r1],#4			@ 13
+# if 13==15
+	str	r1,[sp,#17*4]			@ make room for r1
+# endif
+	eor	r0,r11,r11,ror#5
+	add	r7,r7,r3			@ h+=Maj(a,b,c) from the past
+	eor	r0,r0,r11,ror#19	@ Sigma1(e)
+# ifndef __ARMEB__
+	rev	r2,r2
+# endif
+#else
+	@ ldrb	r2,[r1,#3]			@ 13
+	add	r7,r7,r3			@ h+=Maj(a,b,c) from the past
+	ldrb	r3,[r1,#2]
+	ldrb	r0,[r1,#1]
+	orr	r2,r2,r3,lsl#8
+	ldrb	r3,[r1],#4
+	orr	r2,r2,r0,lsl#16
+# if 13==15
+	str	r1,[sp,#17*4]			@ make room for r1
+# endif
+	eor	r0,r11,r11,ror#5
+	orr	r2,r2,r3,lsl#24
+	eor	r0,r0,r11,ror#19	@ Sigma1(e)
+#endif
+	ldr	r3,[r14],#4			@ *K256++
+	add	r6,r6,r2			@ h+=X[i]
+	str	r2,[sp,#13*4]
+	eor	r2,r4,r5
+	add	r6,r6,r0,ror#6	@ h+=Sigma1(e)
+	and	r2,r2,r11
+	add	r6,r6,r3			@ h+=K256[i]
+	eor	r2,r2,r5			@ Ch(e,f,g)
+	eor	r0,r7,r7,ror#11
+	add	r6,r6,r2			@ h+=Ch(e,f,g)
+#if 13==31
+	and	r3,r3,#0xff
+	cmp	r3,#0xf2			@ done?
+#endif
+#if 13<15
+# if __ARM_ARCH__>=7
+	ldr	r2,[r1],#4			@ prefetch
+# else
+	ldrb	r2,[r1,#3]
+# endif
+	eor	r3,r7,r8			@ a^b, b^c in next round
+#else
+	ldr	r2,[sp,#15*4]		@ from future BODY_16_xx
+	eor	r3,r7,r8			@ a^b, b^c in next round
+	ldr	r1,[sp,#12*4]	@ from future BODY_16_xx
+#endif
+	eor	r0,r0,r7,ror#20	@ Sigma0(a)
+	and	r12,r12,r3			@ (b^c)&=(a^b)
+	add	r10,r10,r6			@ d+=h
+	eor	r12,r12,r8			@ Maj(a,b,c)
+	add	r6,r6,r0,ror#2	@ h+=Sigma0(a)
+	@ add	r6,r6,r12			@ h+=Maj(a,b,c)
+#if __ARM_ARCH__>=7
+	@ ldr	r2,[r1],#4			@ 14
+# if 14==15
+	str	r1,[sp,#17*4]			@ make room for r1
+# endif
+	eor	r0,r10,r10,ror#5
+	add	r6,r6,r12			@ h+=Maj(a,b,c) from the past
+	eor	r0,r0,r10,ror#19	@ Sigma1(e)
+# ifndef __ARMEB__
+	rev	r2,r2
+# endif
+#else
+	@ ldrb	r2,[r1,#3]			@ 14
+	add	r6,r6,r12			@ h+=Maj(a,b,c) from the past
+	ldrb	r12,[r1,#2]
+	ldrb	r0,[r1,#1]
+	orr	r2,r2,r12,lsl#8
+	ldrb	r12,[r1],#4
+	orr	r2,r2,r0,lsl#16
+# if 14==15
+	str	r1,[sp,#17*4]			@ make room for r1
+# endif
+	eor	r0,r10,r10,ror#5
+	orr	r2,r2,r12,lsl#24
+	eor	r0,r0,r10,ror#19	@ Sigma1(e)
+#endif
+	ldr	r12,[r14],#4			@ *K256++
+	add	r5,r5,r2			@ h+=X[i]
+	str	r2,[sp,#14*4]
+	eor	r2,r11,r4
+	add	r5,r5,r0,ror#6	@ h+=Sigma1(e)
+	and	r2,r2,r10
+	add	r5,r5,r12			@ h+=K256[i]
+	eor	r2,r2,r4			@ Ch(e,f,g)
+	eor	r0,r6,r6,ror#11
+	add	r5,r5,r2			@ h+=Ch(e,f,g)
+#if 14==31
+	and	r12,r12,#0xff
+	cmp	r12,#0xf2			@ done?
+#endif
+#if 14<15
+# if __ARM_ARCH__>=7
+	ldr	r2,[r1],#4			@ prefetch
+# else
+	ldrb	r2,[r1,#3]
+# endif
+	eor	r12,r6,r7			@ a^b, b^c in next round
+#else
+	ldr	r2,[sp,#0*4]		@ from future BODY_16_xx
+	eor	r12,r6,r7			@ a^b, b^c in next round
+	ldr	r1,[sp,#13*4]	@ from future BODY_16_xx
+#endif
+	eor	r0,r0,r6,ror#20	@ Sigma0(a)
+	and	r3,r3,r12			@ (b^c)&=(a^b)
+	add	r9,r9,r5			@ d+=h
+	eor	r3,r3,r7			@ Maj(a,b,c)
+	add	r5,r5,r0,ror#2	@ h+=Sigma0(a)
+	@ add	r5,r5,r3			@ h+=Maj(a,b,c)
+#if __ARM_ARCH__>=7
+	@ ldr	r2,[r1],#4			@ 15
+# if 15==15
+	str	r1,[sp,#17*4]			@ make room for r1
+# endif
+	eor	r0,r9,r9,ror#5
+	add	r5,r5,r3			@ h+=Maj(a,b,c) from the past
+	eor	r0,r0,r9,ror#19	@ Sigma1(e)
+# ifndef __ARMEB__
+	rev	r2,r2
+# endif
+#else
+	@ ldrb	r2,[r1,#3]			@ 15
+	add	r5,r5,r3			@ h+=Maj(a,b,c) from the past
+	ldrb	r3,[r1,#2]
+	ldrb	r0,[r1,#1]
+	orr	r2,r2,r3,lsl#8
+	ldrb	r3,[r1],#4
+	orr	r2,r2,r0,lsl#16
+# if 15==15
+	str	r1,[sp,#17*4]			@ make room for r1
+# endif
+	eor	r0,r9,r9,ror#5
+	orr	r2,r2,r3,lsl#24
+	eor	r0,r0,r9,ror#19	@ Sigma1(e)
+#endif
+	ldr	r3,[r14],#4			@ *K256++
+	add	r4,r4,r2			@ h+=X[i]
+	str	r2,[sp,#15*4]
+	eor	r2,r10,r11
+	add	r4,r4,r0,ror#6	@ h+=Sigma1(e)
+	and	r2,r2,r9
+	add	r4,r4,r3			@ h+=K256[i]
+	eor	r2,r2,r11			@ Ch(e,f,g)
+	eor	r0,r5,r5,ror#11
+	add	r4,r4,r2			@ h+=Ch(e,f,g)
+#if 15==31
+	and	r3,r3,#0xff
+	cmp	r3,#0xf2			@ done?
+#endif
+#if 15<15
+# if __ARM_ARCH__>=7
+	ldr	r2,[r1],#4			@ prefetch
+# else
+	ldrb	r2,[r1,#3]
+# endif
+	eor	r3,r5,r6			@ a^b, b^c in next round
+#else
+	ldr	r2,[sp,#1*4]		@ from future BODY_16_xx
+	eor	r3,r5,r6			@ a^b, b^c in next round
+	ldr	r1,[sp,#14*4]	@ from future BODY_16_xx
+#endif
+	eor	r0,r0,r5,ror#20	@ Sigma0(a)
+	and	r12,r12,r3			@ (b^c)&=(a^b)
+	add	r8,r8,r4			@ d+=h
+	eor	r12,r12,r6			@ Maj(a,b,c)
+	add	r4,r4,r0,ror#2	@ h+=Sigma0(a)
+	@ add	r4,r4,r12			@ h+=Maj(a,b,c)
+.Lrounds_16_xx:
+	@ ldr	r2,[sp,#1*4]		@ 16
+	@ ldr	r1,[sp,#14*4]
+	mov	r0,r2,ror#7
+	add	r4,r4,r12			@ h+=Maj(a,b,c) from the past
+	mov	r12,r1,ror#17
+	eor	r0,r0,r2,ror#18
+	eor	r12,r12,r1,ror#19
+	eor	r0,r0,r2,lsr#3	@ sigma0(X[i+1])
+	ldr	r2,[sp,#0*4]
+	eor	r12,r12,r1,lsr#10	@ sigma1(X[i+14])
+	ldr	r1,[sp,#9*4]
+
+	add	r12,r12,r0
+	eor	r0,r8,r8,ror#5	@ from BODY_00_15
+	add	r2,r2,r12
+	eor	r0,r0,r8,ror#19	@ Sigma1(e)
+	add	r2,r2,r1			@ X[i]
+	ldr	r12,[r14],#4			@ *K256++
+	add	r11,r11,r2			@ h+=X[i]
+	str	r2,[sp,#0*4]
+	eor	r2,r9,r10
+	add	r11,r11,r0,ror#6	@ h+=Sigma1(e)
+	and	r2,r2,r8
+	add	r11,r11,r12			@ h+=K256[i]
+	eor	r2,r2,r10			@ Ch(e,f,g)
+	eor	r0,r4,r4,ror#11
+	add	r11,r11,r2			@ h+=Ch(e,f,g)
+#if 16==31
+	and	r12,r12,#0xff
+	cmp	r12,#0xf2			@ done?
+#endif
+#if 16<15
+# if __ARM_ARCH__>=7
+	ldr	r2,[r1],#4			@ prefetch
+# else
+	ldrb	r2,[r1,#3]
+# endif
+	eor	r12,r4,r5			@ a^b, b^c in next round
+#else
+	ldr	r2,[sp,#2*4]		@ from future BODY_16_xx
+	eor	r12,r4,r5			@ a^b, b^c in next round
+	ldr	r1,[sp,#15*4]	@ from future BODY_16_xx
+#endif
+	eor	r0,r0,r4,ror#20	@ Sigma0(a)
+	and	r3,r3,r12			@ (b^c)&=(a^b)
+	add	r7,r7,r11			@ d+=h
+	eor	r3,r3,r5			@ Maj(a,b,c)
+	add	r11,r11,r0,ror#2	@ h+=Sigma0(a)
+	@ add	r11,r11,r3			@ h+=Maj(a,b,c)
+	@ ldr	r2,[sp,#2*4]		@ 17
+	@ ldr	r1,[sp,#15*4]
+	mov	r0,r2,ror#7
+	add	r11,r11,r3			@ h+=Maj(a,b,c) from the past
+	mov	r3,r1,ror#17
+	eor	r0,r0,r2,ror#18
+	eor	r3,r3,r1,ror#19
+	eor	r0,r0,r2,lsr#3	@ sigma0(X[i+1])
+	ldr	r2,[sp,#1*4]
+	eor	r3,r3,r1,lsr#10	@ sigma1(X[i+14])
+	ldr	r1,[sp,#10*4]
+
+	add	r3,r3,r0
+	eor	r0,r7,r7,ror#5	@ from BODY_00_15
+	add	r2,r2,r3
+	eor	r0,r0,r7,ror#19	@ Sigma1(e)
+	add	r2,r2,r1			@ X[i]
+	ldr	r3,[r14],#4			@ *K256++
+	add	r10,r10,r2			@ h+=X[i]
+	str	r2,[sp,#1*4]
+	eor	r2,r8,r9
+	add	r10,r10,r0,ror#6	@ h+=Sigma1(e)
+	and	r2,r2,r7
+	add	r10,r10,r3			@ h+=K256[i]
+	eor	r2,r2,r9			@ Ch(e,f,g)
+	eor	r0,r11,r11,ror#11
+	add	r10,r10,r2			@ h+=Ch(e,f,g)
+#if 17==31
+	and	r3,r3,#0xff
+	cmp	r3,#0xf2			@ done?
+#endif
+#if 17<15
+# if __ARM_ARCH__>=7
+	ldr	r2,[r1],#4			@ prefetch
+# else
+	ldrb	r2,[r1,#3]
+# endif
+	eor	r3,r11,r4			@ a^b, b^c in next round
+#else
+	ldr	r2,[sp,#3*4]		@ from future BODY_16_xx
+	eor	r3,r11,r4			@ a^b, b^c in next round
+	ldr	r1,[sp,#0*4]	@ from future BODY_16_xx
+#endif
+	eor	r0,r0,r11,ror#20	@ Sigma0(a)
+	and	r12,r12,r3			@ (b^c)&=(a^b)
+	add	r6,r6,r10			@ d+=h
+	eor	r12,r12,r4			@ Maj(a,b,c)
+	add	r10,r10,r0,ror#2	@ h+=Sigma0(a)
+	@ add	r10,r10,r12			@ h+=Maj(a,b,c)
+	@ ldr	r2,[sp,#3*4]		@ 18
+	@ ldr	r1,[sp,#0*4]
+	mov	r0,r2,ror#7
+	add	r10,r10,r12			@ h+=Maj(a,b,c) from the past
+	mov	r12,r1,ror#17
+	eor	r0,r0,r2,ror#18
+	eor	r12,r12,r1,ror#19
+	eor	r0,r0,r2,lsr#3	@ sigma0(X[i+1])
+	ldr	r2,[sp,#2*4]
+	eor	r12,r12,r1,lsr#10	@ sigma1(X[i+14])
+	ldr	r1,[sp,#11*4]
+
+	add	r12,r12,r0
+	eor	r0,r6,r6,ror#5	@ from BODY_00_15
+	add	r2,r2,r12
+	eor	r0,r0,r6,ror#19	@ Sigma1(e)
+	add	r2,r2,r1			@ X[i]
+	ldr	r12,[r14],#4			@ *K256++
+	add	r9,r9,r2			@ h+=X[i]
+	str	r2,[sp,#2*4]
+	eor	r2,r7,r8
+	add	r9,r9,r0,ror#6	@ h+=Sigma1(e)
+	and	r2,r2,r6
+	add	r9,r9,r12			@ h+=K256[i]
+	eor	r2,r2,r8			@ Ch(e,f,g)
+	eor	r0,r10,r10,ror#11
+	add	r9,r9,r2			@ h+=Ch(e,f,g)
+#if 18==31
+	and	r12,r12,#0xff
+	cmp	r12,#0xf2			@ done?
+#endif
+#if 18<15
+# if __ARM_ARCH__>=7
+	ldr	r2,[r1],#4			@ prefetch
+# else
+	ldrb	r2,[r1,#3]
+# endif
+	eor	r12,r10,r11			@ a^b, b^c in next round
+#else
+	ldr	r2,[sp,#4*4]		@ from future BODY_16_xx
+	eor	r12,r10,r11			@ a^b, b^c in next round
+	ldr	r1,[sp,#1*4]	@ from future BODY_16_xx
+#endif
+	eor	r0,r0,r10,ror#20	@ Sigma0(a)
+	and	r3,r3,r12			@ (b^c)&=(a^b)
+	add	r5,r5,r9			@ d+=h
+	eor	r3,r3,r11			@ Maj(a,b,c)
+	add	r9,r9,r0,ror#2	@ h+=Sigma0(a)
+	@ add	r9,r9,r3			@ h+=Maj(a,b,c)
+	@ ldr	r2,[sp,#4*4]		@ 19
+	@ ldr	r1,[sp,#1*4]
+	mov	r0,r2,ror#7
+	add	r9,r9,r3			@ h+=Maj(a,b,c) from the past
+	mov	r3,r1,ror#17
+	eor	r0,r0,r2,ror#18
+	eor	r3,r3,r1,ror#19
+	eor	r0,r0,r2,lsr#3	@ sigma0(X[i+1])
+	ldr	r2,[sp,#3*4]
+	eor	r3,r3,r1,lsr#10	@ sigma1(X[i+14])
+	ldr	r1,[sp,#12*4]
+
+	add	r3,r3,r0
+	eor	r0,r5,r5,ror#5	@ from BODY_00_15
+	add	r2,r2,r3
+	eor	r0,r0,r5,ror#19	@ Sigma1(e)
+	add	r2,r2,r1			@ X[i]
+	ldr	r3,[r14],#4			@ *K256++
+	add	r8,r8,r2			@ h+=X[i]
+	str	r2,[sp,#3*4]
+	eor	r2,r6,r7
+	add	r8,r8,r0,ror#6	@ h+=Sigma1(e)
+	and	r2,r2,r5
+	add	r8,r8,r3			@ h+=K256[i]
+	eor	r2,r2,r7			@ Ch(e,f,g)
+	eor	r0,r9,r9,ror#11
+	add	r8,r8,r2			@ h+=Ch(e,f,g)
+#if 19==31
+	and	r3,r3,#0xff
+	cmp	r3,#0xf2			@ done?
+#endif
+#if 19<15
+# if __ARM_ARCH__>=7
+	ldr	r2,[r1],#4			@ prefetch
+# else
+	ldrb	r2,[r1,#3]
+# endif
+	eor	r3,r9,r10			@ a^b, b^c in next round
+#else
+	ldr	r2,[sp,#5*4]		@ from future BODY_16_xx
+	eor	r3,r9,r10			@ a^b, b^c in next round
+	ldr	r1,[sp,#2*4]	@ from future BODY_16_xx
+#endif
+	eor	r0,r0,r9,ror#20	@ Sigma0(a)
+	and	r12,r12,r3			@ (b^c)&=(a^b)
+	add	r4,r4,r8			@ d+=h
+	eor	r12,r12,r10			@ Maj(a,b,c)
+	add	r8,r8,r0,ror#2	@ h+=Sigma0(a)
+	@ add	r8,r8,r12			@ h+=Maj(a,b,c)
+	@ ldr	r2,[sp,#5*4]		@ 20
+	@ ldr	r1,[sp,#2*4]
+	mov	r0,r2,ror#7
+	add	r8,r8,r12			@ h+=Maj(a,b,c) from the past
+	mov	r12,r1,ror#17
+	eor	r0,r0,r2,ror#18
+	eor	r12,r12,r1,ror#19
+	eor	r0,r0,r2,lsr#3	@ sigma0(X[i+1])
+	ldr	r2,[sp,#4*4]
+	eor	r12,r12,r1,lsr#10	@ sigma1(X[i+14])
+	ldr	r1,[sp,#13*4]
+
+	add	r12,r12,r0
+	eor	r0,r4,r4,ror#5	@ from BODY_00_15
+	add	r2,r2,r12
+	eor	r0,r0,r4,ror#19	@ Sigma1(e)
+	add	r2,r2,r1			@ X[i]
+	ldr	r12,[r14],#4			@ *K256++
+	add	r7,r7,r2			@ h+=X[i]
+	str	r2,[sp,#4*4]
+	eor	r2,r5,r6
+	add	r7,r7,r0,ror#6	@ h+=Sigma1(e)
+	and	r2,r2,r4
+	add	r7,r7,r12			@ h+=K256[i]
+	eor	r2,r2,r6			@ Ch(e,f,g)
+	eor	r0,r8,r8,ror#11
+	add	r7,r7,r2			@ h+=Ch(e,f,g)
+#if 20==31
+	and	r12,r12,#0xff
+	cmp	r12,#0xf2			@ done?
+#endif
+#if 20<15
+# if __ARM_ARCH__>=7
+	ldr	r2,[r1],#4			@ prefetch
+# else
+	ldrb	r2,[r1,#3]
+# endif
+	eor	r12,r8,r9			@ a^b, b^c in next round
+#else
+	ldr	r2,[sp,#6*4]		@ from future BODY_16_xx
+	eor	r12,r8,r9			@ a^b, b^c in next round
+	ldr	r1,[sp,#3*4]	@ from future BODY_16_xx
+#endif
+	eor	r0,r0,r8,ror#20	@ Sigma0(a)
+	and	r3,r3,r12			@ (b^c)&=(a^b)
+	add	r11,r11,r7			@ d+=h
+	eor	r3,r3,r9			@ Maj(a,b,c)
+	add	r7,r7,r0,ror#2	@ h+=Sigma0(a)
+	@ add	r7,r7,r3			@ h+=Maj(a,b,c)
+	@ ldr	r2,[sp,#6*4]		@ 21
+	@ ldr	r1,[sp,#3*4]
+	mov	r0,r2,ror#7
+	add	r7,r7,r3			@ h+=Maj(a,b,c) from the past
+	mov	r3,r1,ror#17
+	eor	r0,r0,r2,ror#18
+	eor	r3,r3,r1,ror#19
+	eor	r0,r0,r2,lsr#3	@ sigma0(X[i+1])
+	ldr	r2,[sp,#5*4]
+	eor	r3,r3,r1,lsr#10	@ sigma1(X[i+14])
+	ldr	r1,[sp,#14*4]
+
+	add	r3,r3,r0
+	eor	r0,r11,r11,ror#5	@ from BODY_00_15
+	add	r2,r2,r3
+	eor	r0,r0,r11,ror#19	@ Sigma1(e)
+	add	r2,r2,r1			@ X[i]
+	ldr	r3,[r14],#4			@ *K256++
+	add	r6,r6,r2			@ h+=X[i]
+	str	r2,[sp,#5*4]
+	eor	r2,r4,r5
+	add	r6,r6,r0,ror#6	@ h+=Sigma1(e)
+	and	r2,r2,r11
+	add	r6,r6,r3			@ h+=K256[i]
+	eor	r2,r2,r5			@ Ch(e,f,g)
+	eor	r0,r7,r7,ror#11
+	add	r6,r6,r2			@ h+=Ch(e,f,g)
+#if 21==31
+	and	r3,r3,#0xff
+	cmp	r3,#0xf2			@ done?
+#endif
+#if 21<15
+# if __ARM_ARCH__>=7
+	ldr	r2,[r1],#4			@ prefetch
+# else
+	ldrb	r2,[r1,#3]
+# endif
+	eor	r3,r7,r8			@ a^b, b^c in next round
+#else
+	ldr	r2,[sp,#7*4]		@ from future BODY_16_xx
+	eor	r3,r7,r8			@ a^b, b^c in next round
+	ldr	r1,[sp,#4*4]	@ from future BODY_16_xx
+#endif
+	eor	r0,r0,r7,ror#20	@ Sigma0(a)
+	and	r12,r12,r3			@ (b^c)&=(a^b)
+	add	r10,r10,r6			@ d+=h
+	eor	r12,r12,r8			@ Maj(a,b,c)
+	add	r6,r6,r0,ror#2	@ h+=Sigma0(a)
+	@ add	r6,r6,r12			@ h+=Maj(a,b,c)
+	@ ldr	r2,[sp,#7*4]		@ 22
+	@ ldr	r1,[sp,#4*4]
+	mov	r0,r2,ror#7
+	add	r6,r6,r12			@ h+=Maj(a,b,c) from the past
+	mov	r12,r1,ror#17
+	eor	r0,r0,r2,ror#18
+	eor	r12,r12,r1,ror#19
+	eor	r0,r0,r2,lsr#3	@ sigma0(X[i+1])
+	ldr	r2,[sp,#6*4]
+	eor	r12,r12,r1,lsr#10	@ sigma1(X[i+14])
+	ldr	r1,[sp,#15*4]
+
+	add	r12,r12,r0
+	eor	r0,r10,r10,ror#5	@ from BODY_00_15
+	add	r2,r2,r12
+	eor	r0,r0,r10,ror#19	@ Sigma1(e)
+	add	r2,r2,r1			@ X[i]
+	ldr	r12,[r14],#4			@ *K256++
+	add	r5,r5,r2			@ h+=X[i]
+	str	r2,[sp,#6*4]
+	eor	r2,r11,r4
+	add	r5,r5,r0,ror#6	@ h+=Sigma1(e)
+	and	r2,r2,r10
+	add	r5,r5,r12			@ h+=K256[i]
+	eor	r2,r2,r4			@ Ch(e,f,g)
+	eor	r0,r6,r6,ror#11
+	add	r5,r5,r2			@ h+=Ch(e,f,g)
+#if 22==31
+	and	r12,r12,#0xff
+	cmp	r12,#0xf2			@ done?
+#endif
+#if 22<15
+# if __ARM_ARCH__>=7
+	ldr	r2,[r1],#4			@ prefetch
+# else
+	ldrb	r2,[r1,#3]
+# endif
+	eor	r12,r6,r7			@ a^b, b^c in next round
+#else
+	ldr	r2,[sp,#8*4]		@ from future BODY_16_xx
+	eor	r12,r6,r7			@ a^b, b^c in next round
+	ldr	r1,[sp,#5*4]	@ from future BODY_16_xx
+#endif
+	eor	r0,r0,r6,ror#20	@ Sigma0(a)
+	and	r3,r3,r12			@ (b^c)&=(a^b)
+	add	r9,r9,r5			@ d+=h
+	eor	r3,r3,r7			@ Maj(a,b,c)
+	add	r5,r5,r0,ror#2	@ h+=Sigma0(a)
+	@ add	r5,r5,r3			@ h+=Maj(a,b,c)
+	@ ldr	r2,[sp,#8*4]		@ 23
+	@ ldr	r1,[sp,#5*4]
+	mov	r0,r2,ror#7
+	add	r5,r5,r3			@ h+=Maj(a,b,c) from the past
+	mov	r3,r1,ror#17
+	eor	r0,r0,r2,ror#18
+	eor	r3,r3,r1,ror#19
+	eor	r0,r0,r2,lsr#3	@ sigma0(X[i+1])
+	ldr	r2,[sp,#7*4]
+	eor	r3,r3,r1,lsr#10	@ sigma1(X[i+14])
+	ldr	r1,[sp,#0*4]
+
+	add	r3,r3,r0
+	eor	r0,r9,r9,ror#5	@ from BODY_00_15
+	add	r2,r2,r3
+	eor	r0,r0,r9,ror#19	@ Sigma1(e)
+	add	r2,r2,r1			@ X[i]
+	ldr	r3,[r14],#4			@ *K256++
+	add	r4,r4,r2			@ h+=X[i]
+	str	r2,[sp,#7*4]
+	eor	r2,r10,r11
+	add	r4,r4,r0,ror#6	@ h+=Sigma1(e)
+	and	r2,r2,r9
+	add	r4,r4,r3			@ h+=K256[i]
+	eor	r2,r2,r11			@ Ch(e,f,g)
+	eor	r0,r5,r5,ror#11
+	add	r4,r4,r2			@ h+=Ch(e,f,g)
+#if 23==31
+	and	r3,r3,#0xff
+	cmp	r3,#0xf2			@ done?
+#endif
+#if 23<15
+# if __ARM_ARCH__>=7
+	ldr	r2,[r1],#4			@ prefetch
+# else
+	ldrb	r2,[r1,#3]
+# endif
+	eor	r3,r5,r6			@ a^b, b^c in next round
+#else
+	ldr	r2,[sp,#9*4]		@ from future BODY_16_xx
+	eor	r3,r5,r6			@ a^b, b^c in next round
+	ldr	r1,[sp,#6*4]	@ from future BODY_16_xx
+#endif
+	eor	r0,r0,r5,ror#20	@ Sigma0(a)
+	and	r12,r12,r3			@ (b^c)&=(a^b)
+	add	r8,r8,r4			@ d+=h
+	eor	r12,r12,r6			@ Maj(a,b,c)
+	add	r4,r4,r0,ror#2	@ h+=Sigma0(a)
+	@ add	r4,r4,r12			@ h+=Maj(a,b,c)
+	@ ldr	r2,[sp,#9*4]		@ 24
+	@ ldr	r1,[sp,#6*4]
+	mov	r0,r2,ror#7
+	add	r4,r4,r12			@ h+=Maj(a,b,c) from the past
+	mov	r12,r1,ror#17
+	eor	r0,r0,r2,ror#18
+	eor	r12,r12,r1,ror#19
+	eor	r0,r0,r2,lsr#3	@ sigma0(X[i+1])
+	ldr	r2,[sp,#8*4]
+	eor	r12,r12,r1,lsr#10	@ sigma1(X[i+14])
+	ldr	r1,[sp,#1*4]
+
+	add	r12,r12,r0
+	eor	r0,r8,r8,ror#5	@ from BODY_00_15
+	add	r2,r2,r12
+	eor	r0,r0,r8,ror#19	@ Sigma1(e)
+	add	r2,r2,r1			@ X[i]
+	ldr	r12,[r14],#4			@ *K256++
+	add	r11,r11,r2			@ h+=X[i]
+	str	r2,[sp,#8*4]
+	eor	r2,r9,r10
+	add	r11,r11,r0,ror#6	@ h+=Sigma1(e)
+	and	r2,r2,r8
+	add	r11,r11,r12			@ h+=K256[i]
+	eor	r2,r2,r10			@ Ch(e,f,g)
+	eor	r0,r4,r4,ror#11
+	add	r11,r11,r2			@ h+=Ch(e,f,g)
+#if 24==31
+	and	r12,r12,#0xff
+	cmp	r12,#0xf2			@ done?
+#endif
+#if 24<15
+# if __ARM_ARCH__>=7
+	ldr	r2,[r1],#4			@ prefetch
+# else
+	ldrb	r2,[r1,#3]
+# endif
+	eor	r12,r4,r5			@ a^b, b^c in next round
+#else
+	ldr	r2,[sp,#10*4]		@ from future BODY_16_xx
+	eor	r12,r4,r5			@ a^b, b^c in next round
+	ldr	r1,[sp,#7*4]	@ from future BODY_16_xx
+#endif
+	eor	r0,r0,r4,ror#20	@ Sigma0(a)
+	and	r3,r3,r12			@ (b^c)&=(a^b)
+	add	r7,r7,r11			@ d+=h
+	eor	r3,r3,r5			@ Maj(a,b,c)
+	add	r11,r11,r0,ror#2	@ h+=Sigma0(a)
+	@ add	r11,r11,r3			@ h+=Maj(a,b,c)
+	@ ldr	r2,[sp,#10*4]		@ 25
+	@ ldr	r1,[sp,#7*4]
+	mov	r0,r2,ror#7
+	add	r11,r11,r3			@ h+=Maj(a,b,c) from the past
+	mov	r3,r1,ror#17
+	eor	r0,r0,r2,ror#18
+	eor	r3,r3,r1,ror#19
+	eor	r0,r0,r2,lsr#3	@ sigma0(X[i+1])
+	ldr	r2,[sp,#9*4]
+	eor	r3,r3,r1,lsr#10	@ sigma1(X[i+14])
+	ldr	r1,[sp,#2*4]
+
+	add	r3,r3,r0
+	eor	r0,r7,r7,ror#5	@ from BODY_00_15
+	add	r2,r2,r3
+	eor	r0,r0,r7,ror#19	@ Sigma1(e)
+	add	r2,r2,r1			@ X[i]
+	ldr	r3,[r14],#4			@ *K256++
+	add	r10,r10,r2			@ h+=X[i]
+	str	r2,[sp,#9*4]
+	eor	r2,r8,r9
+	add	r10,r10,r0,ror#6	@ h+=Sigma1(e)
+	and	r2,r2,r7
+	add	r10,r10,r3			@ h+=K256[i]
+	eor	r2,r2,r9			@ Ch(e,f,g)
+	eor	r0,r11,r11,ror#11
+	add	r10,r10,r2			@ h+=Ch(e,f,g)
+#if 25==31
+	and	r3,r3,#0xff
+	cmp	r3,#0xf2			@ done?
+#endif
+#if 25<15
+# if __ARM_ARCH__>=7
+	ldr	r2,[r1],#4			@ prefetch
+# else
+	ldrb	r2,[r1,#3]
+# endif
+	eor	r3,r11,r4			@ a^b, b^c in next round
+#else
+	ldr	r2,[sp,#11*4]		@ from future BODY_16_xx
+	eor	r3,r11,r4			@ a^b, b^c in next round
+	ldr	r1,[sp,#8*4]	@ from future BODY_16_xx
+#endif
+	eor	r0,r0,r11,ror#20	@ Sigma0(a)
+	and	r12,r12,r3			@ (b^c)&=(a^b)
+	add	r6,r6,r10			@ d+=h
+	eor	r12,r12,r4			@ Maj(a,b,c)
+	add	r10,r10,r0,ror#2	@ h+=Sigma0(a)
+	@ add	r10,r10,r12			@ h+=Maj(a,b,c)
+	@ ldr	r2,[sp,#11*4]		@ 26
+	@ ldr	r1,[sp,#8*4]
+	mov	r0,r2,ror#7
+	add	r10,r10,r12			@ h+=Maj(a,b,c) from the past
+	mov	r12,r1,ror#17
+	eor	r0,r0,r2,ror#18
+	eor	r12,r12,r1,ror#19
+	eor	r0,r0,r2,lsr#3	@ sigma0(X[i+1])
+	ldr	r2,[sp,#10*4]
+	eor	r12,r12,r1,lsr#10	@ sigma1(X[i+14])
+	ldr	r1,[sp,#3*4]
+
+	add	r12,r12,r0
+	eor	r0,r6,r6,ror#5	@ from BODY_00_15
+	add	r2,r2,r12
+	eor	r0,r0,r6,ror#19	@ Sigma1(e)
+	add	r2,r2,r1			@ X[i]
+	ldr	r12,[r14],#4			@ *K256++
+	add	r9,r9,r2			@ h+=X[i]
+	str	r2,[sp,#10*4]
+	eor	r2,r7,r8
+	add	r9,r9,r0,ror#6	@ h+=Sigma1(e)
+	and	r2,r2,r6
+	add	r9,r9,r12			@ h+=K256[i]
+	eor	r2,r2,r8			@ Ch(e,f,g)
+	eor	r0,r10,r10,ror#11
+	add	r9,r9,r2			@ h+=Ch(e,f,g)
+#if 26==31
+	and	r12,r12,#0xff
+	cmp	r12,#0xf2			@ done?
+#endif
+#if 26<15
+# if __ARM_ARCH__>=7
+	ldr	r2,[r1],#4			@ prefetch
+# else
+	ldrb	r2,[r1,#3]
+# endif
+	eor	r12,r10,r11			@ a^b, b^c in next round
+#else
+	ldr	r2,[sp,#12*4]		@ from future BODY_16_xx
+	eor	r12,r10,r11			@ a^b, b^c in next round
+	ldr	r1,[sp,#9*4]	@ from future BODY_16_xx
+#endif
+	eor	r0,r0,r10,ror#20	@ Sigma0(a)
+	and	r3,r3,r12			@ (b^c)&=(a^b)
+	add	r5,r5,r9			@ d+=h
+	eor	r3,r3,r11			@ Maj(a,b,c)
+	add	r9,r9,r0,ror#2	@ h+=Sigma0(a)
+	@ add	r9,r9,r3			@ h+=Maj(a,b,c)
+	@ ldr	r2,[sp,#12*4]		@ 27
+	@ ldr	r1,[sp,#9*4]
+	mov	r0,r2,ror#7
+	add	r9,r9,r3			@ h+=Maj(a,b,c) from the past
+	mov	r3,r1,ror#17
+	eor	r0,r0,r2,ror#18
+	eor	r3,r3,r1,ror#19
+	eor	r0,r0,r2,lsr#3	@ sigma0(X[i+1])
+	ldr	r2,[sp,#11*4]
+	eor	r3,r3,r1,lsr#10	@ sigma1(X[i+14])
+	ldr	r1,[sp,#4*4]
+
+	add	r3,r3,r0
+	eor	r0,r5,r5,ror#5	@ from BODY_00_15
+	add	r2,r2,r3
+	eor	r0,r0,r5,ror#19	@ Sigma1(e)
+	add	r2,r2,r1			@ X[i]
+	ldr	r3,[r14],#4			@ *K256++
+	add	r8,r8,r2			@ h+=X[i]
+	str	r2,[sp,#11*4]
+	eor	r2,r6,r7
+	add	r8,r8,r0,ror#6	@ h+=Sigma1(e)
+	and	r2,r2,r5
+	add	r8,r8,r3			@ h+=K256[i]
+	eor	r2,r2,r7			@ Ch(e,f,g)
+	eor	r0,r9,r9,ror#11
+	add	r8,r8,r2			@ h+=Ch(e,f,g)
+#if 27==31
+	and	r3,r3,#0xff
+	cmp	r3,#0xf2			@ done?
+#endif
+#if 27<15
+# if __ARM_ARCH__>=7
+	ldr	r2,[r1],#4			@ prefetch
+# else
+	ldrb	r2,[r1,#3]
+# endif
+	eor	r3,r9,r10			@ a^b, b^c in next round
+#else
+	ldr	r2,[sp,#13*4]		@ from future BODY_16_xx
+	eor	r3,r9,r10			@ a^b, b^c in next round
+	ldr	r1,[sp,#10*4]	@ from future BODY_16_xx
+#endif
+	eor	r0,r0,r9,ror#20	@ Sigma0(a)
+	and	r12,r12,r3			@ (b^c)&=(a^b)
+	add	r4,r4,r8			@ d+=h
+	eor	r12,r12,r10			@ Maj(a,b,c)
+	add	r8,r8,r0,ror#2	@ h+=Sigma0(a)
+	@ add	r8,r8,r12			@ h+=Maj(a,b,c)
+	@ ldr	r2,[sp,#13*4]		@ 28
+	@ ldr	r1,[sp,#10*4]
+	mov	r0,r2,ror#7
+	add	r8,r8,r12			@ h+=Maj(a,b,c) from the past
+	mov	r12,r1,ror#17
+	eor	r0,r0,r2,ror#18
+	eor	r12,r12,r1,ror#19
+	eor	r0,r0,r2,lsr#3	@ sigma0(X[i+1])
+	ldr	r2,[sp,#12*4]
+	eor	r12,r12,r1,lsr#10	@ sigma1(X[i+14])
+	ldr	r1,[sp,#5*4]
+
+	add	r12,r12,r0
+	eor	r0,r4,r4,ror#5	@ from BODY_00_15
+	add	r2,r2,r12
+	eor	r0,r0,r4,ror#19	@ Sigma1(e)
+	add	r2,r2,r1			@ X[i]
+	ldr	r12,[r14],#4			@ *K256++
+	add	r7,r7,r2			@ h+=X[i]
+	str	r2,[sp,#12*4]
+	eor	r2,r5,r6
+	add	r7,r7,r0,ror#6	@ h+=Sigma1(e)
+	and	r2,r2,r4
+	add	r7,r7,r12			@ h+=K256[i]
+	eor	r2,r2,r6			@ Ch(e,f,g)
+	eor	r0,r8,r8,ror#11
+	add	r7,r7,r2			@ h+=Ch(e,f,g)
+#if 28==31
+	and	r12,r12,#0xff
+	cmp	r12,#0xf2			@ done?
+#endif
+#if 28<15
+# if __ARM_ARCH__>=7
+	ldr	r2,[r1],#4			@ prefetch
+# else
+	ldrb	r2,[r1,#3]
+# endif
+	eor	r12,r8,r9			@ a^b, b^c in next round
+#else
+	ldr	r2,[sp,#14*4]		@ from future BODY_16_xx
+	eor	r12,r8,r9			@ a^b, b^c in next round
+	ldr	r1,[sp,#11*4]	@ from future BODY_16_xx
+#endif
+	eor	r0,r0,r8,ror#20	@ Sigma0(a)
+	and	r3,r3,r12			@ (b^c)&=(a^b)
+	add	r11,r11,r7			@ d+=h
+	eor	r3,r3,r9			@ Maj(a,b,c)
+	add	r7,r7,r0,ror#2	@ h+=Sigma0(a)
+	@ add	r7,r7,r3			@ h+=Maj(a,b,c)
+	@ ldr	r2,[sp,#14*4]		@ 29
+	@ ldr	r1,[sp,#11*4]
+	mov	r0,r2,ror#7
+	add	r7,r7,r3			@ h+=Maj(a,b,c) from the past
+	mov	r3,r1,ror#17
+	eor	r0,r0,r2,ror#18
+	eor	r3,r3,r1,ror#19
+	eor	r0,r0,r2,lsr#3	@ sigma0(X[i+1])
+	ldr	r2,[sp,#13*4]
+	eor	r3,r3,r1,lsr#10	@ sigma1(X[i+14])
+	ldr	r1,[sp,#6*4]
+
+	add	r3,r3,r0
+	eor	r0,r11,r11,ror#5	@ from BODY_00_15
+	add	r2,r2,r3
+	eor	r0,r0,r11,ror#19	@ Sigma1(e)
+	add	r2,r2,r1			@ X[i]
+	ldr	r3,[r14],#4			@ *K256++
+	add	r6,r6,r2			@ h+=X[i]
+	str	r2,[sp,#13*4]
+	eor	r2,r4,r5
+	add	r6,r6,r0,ror#6	@ h+=Sigma1(e)
+	and	r2,r2,r11
+	add	r6,r6,r3			@ h+=K256[i]
+	eor	r2,r2,r5			@ Ch(e,f,g)
+	eor	r0,r7,r7,ror#11
+	add	r6,r6,r2			@ h+=Ch(e,f,g)
+#if 29==31
+	and	r3,r3,#0xff
+	cmp	r3,#0xf2			@ done?
+#endif
+#if 29<15
+# if __ARM_ARCH__>=7
+	ldr	r2,[r1],#4			@ prefetch
+# else
+	ldrb	r2,[r1,#3]
+# endif
+	eor	r3,r7,r8			@ a^b, b^c in next round
+#else
+	ldr	r2,[sp,#15*4]		@ from future BODY_16_xx
+	eor	r3,r7,r8			@ a^b, b^c in next round
+	ldr	r1,[sp,#12*4]	@ from future BODY_16_xx
+#endif
+	eor	r0,r0,r7,ror#20	@ Sigma0(a)
+	and	r12,r12,r3			@ (b^c)&=(a^b)
+	add	r10,r10,r6			@ d+=h
+	eor	r12,r12,r8			@ Maj(a,b,c)
+	add	r6,r6,r0,ror#2	@ h+=Sigma0(a)
+	@ add	r6,r6,r12			@ h+=Maj(a,b,c)
+	@ ldr	r2,[sp,#15*4]		@ 30
+	@ ldr	r1,[sp,#12*4]
+	mov	r0,r2,ror#7
+	add	r6,r6,r12			@ h+=Maj(a,b,c) from the past
+	mov	r12,r1,ror#17
+	eor	r0,r0,r2,ror#18
+	eor	r12,r12,r1,ror#19
+	eor	r0,r0,r2,lsr#3	@ sigma0(X[i+1])
+	ldr	r2,[sp,#14*4]
+	eor	r12,r12,r1,lsr#10	@ sigma1(X[i+14])
+	ldr	r1,[sp,#7*4]
+
+	add	r12,r12,r0
+	eor	r0,r10,r10,ror#5	@ from BODY_00_15
+	add	r2,r2,r12
+	eor	r0,r0,r10,ror#19	@ Sigma1(e)
+	add	r2,r2,r1			@ X[i]
+	ldr	r12,[r14],#4			@ *K256++
+	add	r5,r5,r2			@ h+=X[i]
+	str	r2,[sp,#14*4]
+	eor	r2,r11,r4
+	add	r5,r5,r0,ror#6	@ h+=Sigma1(e)
+	and	r2,r2,r10
+	add	r5,r5,r12			@ h+=K256[i]
+	eor	r2,r2,r4			@ Ch(e,f,g)
+	eor	r0,r6,r6,ror#11
+	add	r5,r5,r2			@ h+=Ch(e,f,g)
+#if 30==31
+	and	r12,r12,#0xff
+	cmp	r12,#0xf2			@ done?
+#endif
+#if 30<15
+# if __ARM_ARCH__>=7
+	ldr	r2,[r1],#4			@ prefetch
+# else
+	ldrb	r2,[r1,#3]
+# endif
+	eor	r12,r6,r7			@ a^b, b^c in next round
+#else
+	ldr	r2,[sp,#0*4]		@ from future BODY_16_xx
+	eor	r12,r6,r7			@ a^b, b^c in next round
+	ldr	r1,[sp,#13*4]	@ from future BODY_16_xx
+#endif
+	eor	r0,r0,r6,ror#20	@ Sigma0(a)
+	and	r3,r3,r12			@ (b^c)&=(a^b)
+	add	r9,r9,r5			@ d+=h
+	eor	r3,r3,r7			@ Maj(a,b,c)
+	add	r5,r5,r0,ror#2	@ h+=Sigma0(a)
+	@ add	r5,r5,r3			@ h+=Maj(a,b,c)
+	@ ldr	r2,[sp,#0*4]		@ 31
+	@ ldr	r1,[sp,#13*4]
+	mov	r0,r2,ror#7
+	add	r5,r5,r3			@ h+=Maj(a,b,c) from the past
+	mov	r3,r1,ror#17
+	eor	r0,r0,r2,ror#18
+	eor	r3,r3,r1,ror#19
+	eor	r0,r0,r2,lsr#3	@ sigma0(X[i+1])
+	ldr	r2,[sp,#15*4]
+	eor	r3,r3,r1,lsr#10	@ sigma1(X[i+14])
+	ldr	r1,[sp,#8*4]
+
+	add	r3,r3,r0
+	eor	r0,r9,r9,ror#5	@ from BODY_00_15
+	add	r2,r2,r3
+	eor	r0,r0,r9,ror#19	@ Sigma1(e)
+	add	r2,r2,r1			@ X[i]
+	ldr	r3,[r14],#4			@ *K256++
+	add	r4,r4,r2			@ h+=X[i]
+	str	r2,[sp,#15*4]
+	eor	r2,r10,r11
+	add	r4,r4,r0,ror#6	@ h+=Sigma1(e)
+	and	r2,r2,r9
+	add	r4,r4,r3			@ h+=K256[i]
+	eor	r2,r2,r11			@ Ch(e,f,g)
+	eor	r0,r5,r5,ror#11
+	add	r4,r4,r2			@ h+=Ch(e,f,g)
+#if 31==31
+	and	r3,r3,#0xff
+	cmp	r3,#0xf2			@ done?
+#endif
+#if 31<15
+# if __ARM_ARCH__>=7
+	ldr	r2,[r1],#4			@ prefetch
+# else
+	ldrb	r2,[r1,#3]
+# endif
+	eor	r3,r5,r6			@ a^b, b^c in next round
+#else
+	ldr	r2,[sp,#1*4]		@ from future BODY_16_xx
+	eor	r3,r5,r6			@ a^b, b^c in next round
+	ldr	r1,[sp,#14*4]	@ from future BODY_16_xx
+#endif
+	eor	r0,r0,r5,ror#20	@ Sigma0(a)
+	and	r12,r12,r3			@ (b^c)&=(a^b)
+	add	r8,r8,r4			@ d+=h
+	eor	r12,r12,r6			@ Maj(a,b,c)
+	add	r4,r4,r0,ror#2	@ h+=Sigma0(a)
+	@ add	r4,r4,r12			@ h+=Maj(a,b,c)
+#if __ARM_ARCH__>=7
+	ite	eq			@ Thumb2 thing, sanity check in ARM
+#endif
+	ldreq	r3,[sp,#16*4]		@ pull ctx
+	bne	.Lrounds_16_xx
+
+	add	r4,r4,r12		@ h+=Maj(a,b,c) from the past
+	ldr	r0,[r3,#0]
+	ldr	r2,[r3,#4]
+	ldr	r12,[r3,#8]
+	add	r4,r4,r0
+	ldr	r0,[r3,#12]
+	add	r5,r5,r2
+	ldr	r2,[r3,#16]
+	add	r6,r6,r12
+	ldr	r12,[r3,#20]
+	add	r7,r7,r0
+	ldr	r0,[r3,#24]
+	add	r8,r8,r2
+	ldr	r2,[r3,#28]
+	add	r9,r9,r12
+	ldr	r1,[sp,#17*4]		@ pull inp
+	ldr	r12,[sp,#18*4]		@ pull inp+len
+	add	r10,r10,r0
+	add	r11,r11,r2
+	stmia	r3,{r4,r5,r6,r7,r8,r9,r10,r11}
+	cmp	r1,r12
+	sub	r14,r14,#256	@ rewind Ktbl
+	bne	.Loop
+
+	add	sp,sp,#19*4	@ destroy frame
+#if __ARM_ARCH__>=5
+	ldmia	sp!,{r4-r11,pc}
+#else
+	ldmia	sp!,{r4-r11,lr}
+	tst	lr,#1
+	moveq	pc,lr			@ be binary compatible with V4, yet
+	.word	0xe12fff1e			@ interoperable with Thumb ISA:-)
+#endif
+.size	sha256_block_data_order,.-sha256_block_data_order
+#if __ARM_MAX_ARCH__>=7
+.arch	armv7-a
+.fpu	neon
+
+.global	sha256_block_data_order_neon
+.type	sha256_block_data_order_neon,%function
+.align	4
+sha256_block_data_order_neon:
+.LNEON:
+	stmdb	sp!,{r4-r12,lr}
+
+	sub	r11,sp,#16*4+16
+	adrl	r14,K256
+	bic	r11,r11,#15		@ align for 128-bit stores
+	mov	r12,sp
+	mov	sp,r11			@ alloca
+	add	r2,r1,r2,lsl#6	@ len to point at the end of inp
+
+	vld1.8		{q0},[r1]!
+	vld1.8		{q1},[r1]!
+	vld1.8		{q2},[r1]!
+	vld1.8		{q3},[r1]!
+	vld1.32		{q8},[r14,:128]!
+	vld1.32		{q9},[r14,:128]!
+	vld1.32		{q10},[r14,:128]!
+	vld1.32		{q11},[r14,:128]!
+	vrev32.8	q0,q0		@ yes, even on
+	str		r0,[sp,#64]
+	vrev32.8	q1,q1		@ big-endian
+	str		r1,[sp,#68]
+	mov		r1,sp
+	vrev32.8	q2,q2
+	str		r2,[sp,#72]
+	vrev32.8	q3,q3
+	str		r12,[sp,#76]		@ save original sp
+	vadd.i32	q8,q8,q0
+	vadd.i32	q9,q9,q1
+	vst1.32		{q8},[r1,:128]!
+	vadd.i32	q10,q10,q2
+	vst1.32		{q9},[r1,:128]!
+	vadd.i32	q11,q11,q3
+	vst1.32		{q10},[r1,:128]!
+	vst1.32		{q11},[r1,:128]!
+
+	ldmia		r0,{r4-r11}
+	sub		r1,r1,#64
+	ldr		r2,[sp,#0]
+	eor		r12,r12,r12
+	eor		r3,r5,r6
+	b		.L_00_48
+
+.align	4
+.L_00_48:
+	vext.8	q8,q0,q1,#4
+	add	r11,r11,r2
+	eor	r2,r9,r10
+	eor	r0,r8,r8,ror#5
+	vext.8	q9,q2,q3,#4
+	add	r4,r4,r12
+	and	r2,r2,r8
+	eor	r12,r0,r8,ror#19
+	vshr.u32	q10,q8,#7
+	eor	r0,r4,r4,ror#11
+	eor	r2,r2,r10
+	vadd.i32	q0,q0,q9
+	add	r11,r11,r12,ror#6
+	eor	r12,r4,r5
+	vshr.u32	q9,q8,#3
+	eor	r0,r0,r4,ror#20
+	add	r11,r11,r2
+	vsli.32	q10,q8,#25
+	ldr	r2,[sp,#4]
+	and	r3,r3,r12
+	vshr.u32	q11,q8,#18
+	add	r7,r7,r11
+	add	r11,r11,r0,ror#2
+	eor	r3,r3,r5
+	veor	q9,q9,q10
+	add	r10,r10,r2
+	vsli.32	q11,q8,#14
+	eor	r2,r8,r9
+	eor	r0,r7,r7,ror#5
+	vshr.u32	d24,d7,#17
+	add	r11,r11,r3
+	and	r2,r2,r7
+	veor	q9,q9,q11
+	eor	r3,r0,r7,ror#19
+	eor	r0,r11,r11,ror#11
+	vsli.32	d24,d7,#15
+	eor	r2,r2,r9
+	add	r10,r10,r3,ror#6
+	vshr.u32	d25,d7,#10
+	eor	r3,r11,r4
+	eor	r0,r0,r11,ror#20
+	vadd.i32	q0,q0,q9
+	add	r10,r10,r2
+	ldr	r2,[sp,#8]
+	veor	d25,d25,d24
+	and	r12,r12,r3
+	add	r6,r6,r10
+	vshr.u32	d24,d7,#19
+	add	r10,r10,r0,ror#2
+	eor	r12,r12,r4
+	vsli.32	d24,d7,#13
+	add	r9,r9,r2
+	eor	r2,r7,r8
+	veor	d25,d25,d24
+	eor	r0,r6,r6,ror#5
+	add	r10,r10,r12
+	vadd.i32	d0,d0,d25
+	and	r2,r2,r6
+	eor	r12,r0,r6,ror#19
+	vshr.u32	d24,d0,#17
+	eor	r0,r10,r10,ror#11
+	eor	r2,r2,r8
+	vsli.32	d24,d0,#15
+	add	r9,r9,r12,ror#6
+	eor	r12,r10,r11
+	vshr.u32	d25,d0,#10
+	eor	r0,r0,r10,ror#20
+	add	r9,r9,r2
+	veor	d25,d25,d24
+	ldr	r2,[sp,#12]
+	and	r3,r3,r12
+	vshr.u32	d24,d0,#19
+	add	r5,r5,r9
+	add	r9,r9,r0,ror#2
+	eor	r3,r3,r11
+	vld1.32	{q8},[r14,:128]!
+	add	r8,r8,r2
+	vsli.32	d24,d0,#13
+	eor	r2,r6,r7
+	eor	r0,r5,r5,ror#5
+	veor	d25,d25,d24
+	add	r9,r9,r3
+	and	r2,r2,r5
+	vadd.i32	d1,d1,d25
+	eor	r3,r0,r5,ror#19
+	eor	r0,r9,r9,ror#11
+	vadd.i32	q8,q8,q0
+	eor	r2,r2,r7
+	add	r8,r8,r3,ror#6
+	eor	r3,r9,r10
+	eor	r0,r0,r9,ror#20
+	add	r8,r8,r2
+	ldr	r2,[sp,#16]
+	and	r12,r12,r3
+	add	r4,r4,r8
+	vst1.32	{q8},[r1,:128]!
+	add	r8,r8,r0,ror#2
+	eor	r12,r12,r10
+	vext.8	q8,q1,q2,#4
+	add	r7,r7,r2
+	eor	r2,r5,r6
+	eor	r0,r4,r4,ror#5
+	vext.8	q9,q3,q0,#4
+	add	r8,r8,r12
+	and	r2,r2,r4
+	eor	r12,r0,r4,ror#19
+	vshr.u32	q10,q8,#7
+	eor	r0,r8,r8,ror#11
+	eor	r2,r2,r6
+	vadd.i32	q1,q1,q9
+	add	r7,r7,r12,ror#6
+	eor	r12,r8,r9
+	vshr.u32	q9,q8,#3
+	eor	r0,r0,r8,ror#20
+	add	r7,r7,r2
+	vsli.32	q10,q8,#25
+	ldr	r2,[sp,#20]
+	and	r3,r3,r12
+	vshr.u32	q11,q8,#18
+	add	r11,r11,r7
+	add	r7,r7,r0,ror#2
+	eor	r3,r3,r9
+	veor	q9,q9,q10
+	add	r6,r6,r2
+	vsli.32	q11,q8,#14
+	eor	r2,r4,r5
+	eor	r0,r11,r11,ror#5
+	vshr.u32	d24,d1,#17
+	add	r7,r7,r3
+	and	r2,r2,r11
+	veor	q9,q9,q11
+	eor	r3,r0,r11,ror#19
+	eor	r0,r7,r7,ror#11
+	vsli.32	d24,d1,#15
+	eor	r2,r2,r5
+	add	r6,r6,r3,ror#6
+	vshr.u32	d25,d1,#10
+	eor	r3,r7,r8
+	eor	r0,r0,r7,ror#20
+	vadd.i32	q1,q1,q9
+	add	r6,r6,r2
+	ldr	r2,[sp,#24]
+	veor	d25,d25,d24
+	and	r12,r12,r3
+	add	r10,r10,r6
+	vshr.u32	d24,d1,#19
+	add	r6,r6,r0,ror#2
+	eor	r12,r12,r8
+	vsli.32	d24,d1,#13
+	add	r5,r5,r2
+	eor	r2,r11,r4
+	veor	d25,d25,d24
+	eor	r0,r10,r10,ror#5
+	add	r6,r6,r12
+	vadd.i32	d2,d2,d25
+	and	r2,r2,r10
+	eor	r12,r0,r10,ror#19
+	vshr.u32	d24,d2,#17
+	eor	r0,r6,r6,ror#11
+	eor	r2,r2,r4
+	vsli.32	d24,d2,#15
+	add	r5,r5,r12,ror#6
+	eor	r12,r6,r7
+	vshr.u32	d25,d2,#10
+	eor	r0,r0,r6,ror#20
+	add	r5,r5,r2
+	veor	d25,d25,d24
+	ldr	r2,[sp,#28]
+	and	r3,r3,r12
+	vshr.u32	d24,d2,#19
+	add	r9,r9,r5
+	add	r5,r5,r0,ror#2
+	eor	r3,r3,r7
+	vld1.32	{q8},[r14,:128]!
+	add	r4,r4,r2
+	vsli.32	d24,d2,#13
+	eor	r2,r10,r11
+	eor	r0,r9,r9,ror#5
+	veor	d25,d25,d24
+	add	r5,r5,r3
+	and	r2,r2,r9
+	vadd.i32	d3,d3,d25
+	eor	r3,r0,r9,ror#19
+	eor	r0,r5,r5,ror#11
+	vadd.i32	q8,q8,q1
+	eor	r2,r2,r11
+	add	r4,r4,r3,ror#6
+	eor	r3,r5,r6
+	eor	r0,r0,r5,ror#20
+	add	r4,r4,r2
+	ldr	r2,[sp,#32]
+	and	r12,r12,r3
+	add	r8,r8,r4
+	vst1.32	{q8},[r1,:128]!
+	add	r4,r4,r0,ror#2
+	eor	r12,r12,r6
+	vext.8	q8,q2,q3,#4
+	add	r11,r11,r2
+	eor	r2,r9,r10
+	eor	r0,r8,r8,ror#5
+	vext.8	q9,q0,q1,#4
+	add	r4,r4,r12
+	and	r2,r2,r8
+	eor	r12,r0,r8,ror#19
+	vshr.u32	q10,q8,#7
+	eor	r0,r4,r4,ror#11
+	eor	r2,r2,r10
+	vadd.i32	q2,q2,q9
+	add	r11,r11,r12,ror#6
+	eor	r12,r4,r5
+	vshr.u32	q9,q8,#3
+	eor	r0,r0,r4,ror#20
+	add	r11,r11,r2
+	vsli.32	q10,q8,#25
+	ldr	r2,[sp,#36]
+	and	r3,r3,r12
+	vshr.u32	q11,q8,#18
+	add	r7,r7,r11
+	add	r11,r11,r0,ror#2
+	eor	r3,r3,r5
+	veor	q9,q9,q10
+	add	r10,r10,r2
+	vsli.32	q11,q8,#14
+	eor	r2,r8,r9
+	eor	r0,r7,r7,ror#5
+	vshr.u32	d24,d3,#17
+	add	r11,r11,r3
+	and	r2,r2,r7
+	veor	q9,q9,q11
+	eor	r3,r0,r7,ror#19
+	eor	r0,r11,r11,ror#11
+	vsli.32	d24,d3,#15
+	eor	r2,r2,r9
+	add	r10,r10,r3,ror#6
+	vshr.u32	d25,d3,#10
+	eor	r3,r11,r4
+	eor	r0,r0,r11,ror#20
+	vadd.i32	q2,q2,q9
+	add	r10,r10,r2
+	ldr	r2,[sp,#40]
+	veor	d25,d25,d24
+	and	r12,r12,r3
+	add	r6,r6,r10
+	vshr.u32	d24,d3,#19
+	add	r10,r10,r0,ror#2
+	eor	r12,r12,r4
+	vsli.32	d24,d3,#13
+	add	r9,r9,r2
+	eor	r2,r7,r8
+	veor	d25,d25,d24
+	eor	r0,r6,r6,ror#5
+	add	r10,r10,r12
+	vadd.i32	d4,d4,d25
+	and	r2,r2,r6
+	eor	r12,r0,r6,ror#19
+	vshr.u32	d24,d4,#17
+	eor	r0,r10,r10,ror#11
+	eor	r2,r2,r8
+	vsli.32	d24,d4,#15
+	add	r9,r9,r12,ror#6
+	eor	r12,r10,r11
+	vshr.u32	d25,d4,#10
+	eor	r0,r0,r10,ror#20
+	add	r9,r9,r2
+	veor	d25,d25,d24
+	ldr	r2,[sp,#44]
+	and	r3,r3,r12
+	vshr.u32	d24,d4,#19
+	add	r5,r5,r9
+	add	r9,r9,r0,ror#2
+	eor	r3,r3,r11
+	vld1.32	{q8},[r14,:128]!
+	add	r8,r8,r2
+	vsli.32	d24,d4,#13
+	eor	r2,r6,r7
+	eor	r0,r5,r5,ror#5
+	veor	d25,d25,d24
+	add	r9,r9,r3
+	and	r2,r2,r5
+	vadd.i32	d5,d5,d25
+	eor	r3,r0,r5,ror#19
+	eor	r0,r9,r9,ror#11
+	vadd.i32	q8,q8,q2
+	eor	r2,r2,r7
+	add	r8,r8,r3,ror#6
+	eor	r3,r9,r10
+	eor	r0,r0,r9,ror#20
+	add	r8,r8,r2
+	ldr	r2,[sp,#48]
+	and	r12,r12,r3
+	add	r4,r4,r8
+	vst1.32	{q8},[r1,:128]!
+	add	r8,r8,r0,ror#2
+	eor	r12,r12,r10
+	vext.8	q8,q3,q0,#4
+	add	r7,r7,r2
+	eor	r2,r5,r6
+	eor	r0,r4,r4,ror#5
+	vext.8	q9,q1,q2,#4
+	add	r8,r8,r12
+	and	r2,r2,r4
+	eor	r12,r0,r4,ror#19
+	vshr.u32	q10,q8,#7
+	eor	r0,r8,r8,ror#11
+	eor	r2,r2,r6
+	vadd.i32	q3,q3,q9
+	add	r7,r7,r12,ror#6
+	eor	r12,r8,r9
+	vshr.u32	q9,q8,#3
+	eor	r0,r0,r8,ror#20
+	add	r7,r7,r2
+	vsli.32	q10,q8,#25
+	ldr	r2,[sp,#52]
+	and	r3,r3,r12
+	vshr.u32	q11,q8,#18
+	add	r11,r11,r7
+	add	r7,r7,r0,ror#2
+	eor	r3,r3,r9
+	veor	q9,q9,q10
+	add	r6,r6,r2
+	vsli.32	q11,q8,#14
+	eor	r2,r4,r5
+	eor	r0,r11,r11,ror#5
+	vshr.u32	d24,d5,#17
+	add	r7,r7,r3
+	and	r2,r2,r11
+	veor	q9,q9,q11
+	eor	r3,r0,r11,ror#19
+	eor	r0,r7,r7,ror#11
+	vsli.32	d24,d5,#15
+	eor	r2,r2,r5
+	add	r6,r6,r3,ror#6
+	vshr.u32	d25,d5,#10
+	eor	r3,r7,r8
+	eor	r0,r0,r7,ror#20
+	vadd.i32	q3,q3,q9
+	add	r6,r6,r2
+	ldr	r2,[sp,#56]
+	veor	d25,d25,d24
+	and	r12,r12,r3
+	add	r10,r10,r6
+	vshr.u32	d24,d5,#19
+	add	r6,r6,r0,ror#2
+	eor	r12,r12,r8
+	vsli.32	d24,d5,#13
+	add	r5,r5,r2
+	eor	r2,r11,r4
+	veor	d25,d25,d24
+	eor	r0,r10,r10,ror#5
+	add	r6,r6,r12
+	vadd.i32	d6,d6,d25
+	and	r2,r2,r10
+	eor	r12,r0,r10,ror#19
+	vshr.u32	d24,d6,#17
+	eor	r0,r6,r6,ror#11
+	eor	r2,r2,r4
+	vsli.32	d24,d6,#15
+	add	r5,r5,r12,ror#6
+	eor	r12,r6,r7
+	vshr.u32	d25,d6,#10
+	eor	r0,r0,r6,ror#20
+	add	r5,r5,r2
+	veor	d25,d25,d24
+	ldr	r2,[sp,#60]
+	and	r3,r3,r12
+	vshr.u32	d24,d6,#19
+	add	r9,r9,r5
+	add	r5,r5,r0,ror#2
+	eor	r3,r3,r7
+	vld1.32	{q8},[r14,:128]!
+	add	r4,r4,r2
+	vsli.32	d24,d6,#13
+	eor	r2,r10,r11
+	eor	r0,r9,r9,ror#5
+	veor	d25,d25,d24
+	add	r5,r5,r3
+	and	r2,r2,r9
+	vadd.i32	d7,d7,d25
+	eor	r3,r0,r9,ror#19
+	eor	r0,r5,r5,ror#11
+	vadd.i32	q8,q8,q3
+	eor	r2,r2,r11
+	add	r4,r4,r3,ror#6
+	eor	r3,r5,r6
+	eor	r0,r0,r5,ror#20
+	add	r4,r4,r2
+	ldr	r2,[r14]
+	and	r12,r12,r3
+	add	r8,r8,r4
+	vst1.32	{q8},[r1,:128]!
+	add	r4,r4,r0,ror#2
+	eor	r12,r12,r6
+	teq	r2,#0				@ check for K256 terminator
+	ldr	r2,[sp,#0]
+	sub	r1,r1,#64
+	bne	.L_00_48
+
+	ldr		r1,[sp,#68]
+	ldr		r0,[sp,#72]
+	sub		r14,r14,#256	@ rewind r14
+	teq		r1,r0
+	it		eq
+	subeq		r1,r1,#64		@ avoid SEGV
+	vld1.8		{q0},[r1]!		@ load next input block
+	vld1.8		{q1},[r1]!
+	vld1.8		{q2},[r1]!
+	vld1.8		{q3},[r1]!
+	it		ne
+	strne		r1,[sp,#68]
+	mov		r1,sp
+	add	r11,r11,r2
+	eor	r2,r9,r10
+	eor	r0,r8,r8,ror#5
+	add	r4,r4,r12
+	vld1.32	{q8},[r14,:128]!
+	and	r2,r2,r8
+	eor	r12,r0,r8,ror#19
+	eor	r0,r4,r4,ror#11
+	eor	r2,r2,r10
+	vrev32.8	q0,q0
+	add	r11,r11,r12,ror#6
+	eor	r12,r4,r5
+	eor	r0,r0,r4,ror#20
+	add	r11,r11,r2
+	vadd.i32	q8,q8,q0
+	ldr	r2,[sp,#4]
+	and	r3,r3,r12
+	add	r7,r7,r11
+	add	r11,r11,r0,ror#2
+	eor	r3,r3,r5
+	add	r10,r10,r2
+	eor	r2,r8,r9
+	eor	r0,r7,r7,ror#5
+	add	r11,r11,r3
+	and	r2,r2,r7
+	eor	r3,r0,r7,ror#19
+	eor	r0,r11,r11,ror#11
+	eor	r2,r2,r9
+	add	r10,r10,r3,ror#6
+	eor	r3,r11,r4
+	eor	r0,r0,r11,ror#20
+	add	r10,r10,r2
+	ldr	r2,[sp,#8]
+	and	r12,r12,r3
+	add	r6,r6,r10
+	add	r10,r10,r0,ror#2
+	eor	r12,r12,r4
+	add	r9,r9,r2
+	eor	r2,r7,r8
+	eor	r0,r6,r6,ror#5
+	add	r10,r10,r12
+	and	r2,r2,r6
+	eor	r12,r0,r6,ror#19
+	eor	r0,r10,r10,ror#11
+	eor	r2,r2,r8
+	add	r9,r9,r12,ror#6
+	eor	r12,r10,r11
+	eor	r0,r0,r10,ror#20
+	add	r9,r9,r2
+	ldr	r2,[sp,#12]
+	and	r3,r3,r12
+	add	r5,r5,r9
+	add	r9,r9,r0,ror#2
+	eor	r3,r3,r11
+	add	r8,r8,r2
+	eor	r2,r6,r7
+	eor	r0,r5,r5,ror#5
+	add	r9,r9,r3
+	and	r2,r2,r5
+	eor	r3,r0,r5,ror#19
+	eor	r0,r9,r9,ror#11
+	eor	r2,r2,r7
+	add	r8,r8,r3,ror#6
+	eor	r3,r9,r10
+	eor	r0,r0,r9,ror#20
+	add	r8,r8,r2
+	ldr	r2,[sp,#16]
+	and	r12,r12,r3
+	add	r4,r4,r8
+	add	r8,r8,r0,ror#2
+	eor	r12,r12,r10
+	vst1.32	{q8},[r1,:128]!
+	add	r7,r7,r2
+	eor	r2,r5,r6
+	eor	r0,r4,r4,ror#5
+	add	r8,r8,r12
+	vld1.32	{q8},[r14,:128]!
+	and	r2,r2,r4
+	eor	r12,r0,r4,ror#19
+	eor	r0,r8,r8,ror#11
+	eor	r2,r2,r6
+	vrev32.8	q1,q1
+	add	r7,r7,r12,ror#6
+	eor	r12,r8,r9
+	eor	r0,r0,r8,ror#20
+	add	r7,r7,r2
+	vadd.i32	q8,q8,q1
+	ldr	r2,[sp,#20]
+	and	r3,r3,r12
+	add	r11,r11,r7
+	add	r7,r7,r0,ror#2
+	eor	r3,r3,r9
+	add	r6,r6,r2
+	eor	r2,r4,r5
+	eor	r0,r11,r11,ror#5
+	add	r7,r7,r3
+	and	r2,r2,r11
+	eor	r3,r0,r11,ror#19
+	eor	r0,r7,r7,ror#11
+	eor	r2,r2,r5
+	add	r6,r6,r3,ror#6
+	eor	r3,r7,r8
+	eor	r0,r0,r7,ror#20
+	add	r6,r6,r2
+	ldr	r2,[sp,#24]
+	and	r12,r12,r3
+	add	r10,r10,r6
+	add	r6,r6,r0,ror#2
+	eor	r12,r12,r8
+	add	r5,r5,r2
+	eor	r2,r11,r4
+	eor	r0,r10,r10,ror#5
+	add	r6,r6,r12
+	and	r2,r2,r10
+	eor	r12,r0,r10,ror#19
+	eor	r0,r6,r6,ror#11
+	eor	r2,r2,r4
+	add	r5,r5,r12,ror#6
+	eor	r12,r6,r7
+	eor	r0,r0,r6,ror#20
+	add	r5,r5,r2
+	ldr	r2,[sp,#28]
+	and	r3,r3,r12
+	add	r9,r9,r5
+	add	r5,r5,r0,ror#2
+	eor	r3,r3,r7
+	add	r4,r4,r2
+	eor	r2,r10,r11
+	eor	r0,r9,r9,ror#5
+	add	r5,r5,r3
+	and	r2,r2,r9
+	eor	r3,r0,r9,ror#19
+	eor	r0,r5,r5,ror#11
+	eor	r2,r2,r11
+	add	r4,r4,r3,ror#6
+	eor	r3,r5,r6
+	eor	r0,r0,r5,ror#20
+	add	r4,r4,r2
+	ldr	r2,[sp,#32]
+	and	r12,r12,r3
+	add	r8,r8,r4
+	add	r4,r4,r0,ror#2
+	eor	r12,r12,r6
+	vst1.32	{q8},[r1,:128]!
+	add	r11,r11,r2
+	eor	r2,r9,r10
+	eor	r0,r8,r8,ror#5
+	add	r4,r4,r12
+	vld1.32	{q8},[r14,:128]!
+	and	r2,r2,r8
+	eor	r12,r0,r8,ror#19
+	eor	r0,r4,r4,ror#11
+	eor	r2,r2,r10
+	vrev32.8	q2,q2
+	add	r11,r11,r12,ror#6
+	eor	r12,r4,r5
+	eor	r0,r0,r4,ror#20
+	add	r11,r11,r2
+	vadd.i32	q8,q8,q2
+	ldr	r2,[sp,#36]
+	and	r3,r3,r12
+	add	r7,r7,r11
+	add	r11,r11,r0,ror#2
+	eor	r3,r3,r5
+	add	r10,r10,r2
+	eor	r2,r8,r9
+	eor	r0,r7,r7,ror#5
+	add	r11,r11,r3
+	and	r2,r2,r7
+	eor	r3,r0,r7,ror#19
+	eor	r0,r11,r11,ror#11
+	eor	r2,r2,r9
+	add	r10,r10,r3,ror#6
+	eor	r3,r11,r4
+	eor	r0,r0,r11,ror#20
+	add	r10,r10,r2
+	ldr	r2,[sp,#40]
+	and	r12,r12,r3
+	add	r6,r6,r10
+	add	r10,r10,r0,ror#2
+	eor	r12,r12,r4
+	add	r9,r9,r2
+	eor	r2,r7,r8
+	eor	r0,r6,r6,ror#5
+	add	r10,r10,r12
+	and	r2,r2,r6
+	eor	r12,r0,r6,ror#19
+	eor	r0,r10,r10,ror#11
+	eor	r2,r2,r8
+	add	r9,r9,r12,ror#6
+	eor	r12,r10,r11
+	eor	r0,r0,r10,ror#20
+	add	r9,r9,r2
+	ldr	r2,[sp,#44]
+	and	r3,r3,r12
+	add	r5,r5,r9
+	add	r9,r9,r0,ror#2
+	eor	r3,r3,r11
+	add	r8,r8,r2
+	eor	r2,r6,r7
+	eor	r0,r5,r5,ror#5
+	add	r9,r9,r3
+	and	r2,r2,r5
+	eor	r3,r0,r5,ror#19
+	eor	r0,r9,r9,ror#11
+	eor	r2,r2,r7
+	add	r8,r8,r3,ror#6
+	eor	r3,r9,r10
+	eor	r0,r0,r9,ror#20
+	add	r8,r8,r2
+	ldr	r2,[sp,#48]
+	and	r12,r12,r3
+	add	r4,r4,r8
+	add	r8,r8,r0,ror#2
+	eor	r12,r12,r10
+	vst1.32	{q8},[r1,:128]!
+	add	r7,r7,r2
+	eor	r2,r5,r6
+	eor	r0,r4,r4,ror#5
+	add	r8,r8,r12
+	vld1.32	{q8},[r14,:128]!
+	and	r2,r2,r4
+	eor	r12,r0,r4,ror#19
+	eor	r0,r8,r8,ror#11
+	eor	r2,r2,r6
+	vrev32.8	q3,q3
+	add	r7,r7,r12,ror#6
+	eor	r12,r8,r9
+	eor	r0,r0,r8,ror#20
+	add	r7,r7,r2
+	vadd.i32	q8,q8,q3
+	ldr	r2,[sp,#52]
+	and	r3,r3,r12
+	add	r11,r11,r7
+	add	r7,r7,r0,ror#2
+	eor	r3,r3,r9
+	add	r6,r6,r2
+	eor	r2,r4,r5
+	eor	r0,r11,r11,ror#5
+	add	r7,r7,r3
+	and	r2,r2,r11
+	eor	r3,r0,r11,ror#19
+	eor	r0,r7,r7,ror#11
+	eor	r2,r2,r5
+	add	r6,r6,r3,ror#6
+	eor	r3,r7,r8
+	eor	r0,r0,r7,ror#20
+	add	r6,r6,r2
+	ldr	r2,[sp,#56]
+	and	r12,r12,r3
+	add	r10,r10,r6
+	add	r6,r6,r0,ror#2
+	eor	r12,r12,r8
+	add	r5,r5,r2
+	eor	r2,r11,r4
+	eor	r0,r10,r10,ror#5
+	add	r6,r6,r12
+	and	r2,r2,r10
+	eor	r12,r0,r10,ror#19
+	eor	r0,r6,r6,ror#11
+	eor	r2,r2,r4
+	add	r5,r5,r12,ror#6
+	eor	r12,r6,r7
+	eor	r0,r0,r6,ror#20
+	add	r5,r5,r2
+	ldr	r2,[sp,#60]
+	and	r3,r3,r12
+	add	r9,r9,r5
+	add	r5,r5,r0,ror#2
+	eor	r3,r3,r7
+	add	r4,r4,r2
+	eor	r2,r10,r11
+	eor	r0,r9,r9,ror#5
+	add	r5,r5,r3
+	and	r2,r2,r9
+	eor	r3,r0,r9,ror#19
+	eor	r0,r5,r5,ror#11
+	eor	r2,r2,r11
+	add	r4,r4,r3,ror#6
+	eor	r3,r5,r6
+	eor	r0,r0,r5,ror#20
+	add	r4,r4,r2
+	ldr	r2,[sp,#64]
+	and	r12,r12,r3
+	add	r8,r8,r4
+	add	r4,r4,r0,ror#2
+	eor	r12,r12,r6
+	vst1.32	{q8},[r1,:128]!
+	ldr	r0,[r2,#0]
+	add	r4,r4,r12			@ h+=Maj(a,b,c) from the past
+	ldr	r12,[r2,#4]
+	ldr	r3,[r2,#8]
+	ldr	r1,[r2,#12]
+	add	r4,r4,r0			@ accumulate
+	ldr	r0,[r2,#16]
+	add	r5,r5,r12
+	ldr	r12,[r2,#20]
+	add	r6,r6,r3
+	ldr	r3,[r2,#24]
+	add	r7,r7,r1
+	ldr	r1,[r2,#28]
+	add	r8,r8,r0
+	str	r4,[r2],#4
+	add	r9,r9,r12
+	str	r5,[r2],#4
+	add	r10,r10,r3
+	str	r6,[r2],#4
+	add	r11,r11,r1
+	str	r7,[r2],#4
+	stmia	r2,{r8-r11}
+
+	ittte	ne
+	movne	r1,sp
+	ldrne	r2,[sp,#0]
+	eorne	r12,r12,r12
+	ldreq	sp,[sp,#76]			@ restore original sp
+	itt	ne
+	eorne	r3,r5,r6
+	bne	.L_00_48
+
+	ldmia	sp!,{r4-r12,pc}
+.size	sha256_block_data_order_neon,.-sha256_block_data_order_neon
+#endif
+#if __ARM_MAX_ARCH__>=7 && !defined(__KERNEL__)
+
+# ifdef __thumb2__
+#  define INST(a,b,c,d)	.byte	c,d|0xc,a,b
+# else
+#  define INST(a,b,c,d)	.byte	a,b,c,d
+# endif
+
+.type	sha256_block_data_order_armv8,%function
+.align	5
+sha256_block_data_order_armv8:
+.LARMv8:
+	vld1.32	{q0,q1},[r0]
+# ifdef __thumb2__
+	adr	r3,.LARMv8
+	sub	r3,r3,#.LARMv8-K256
+# else
+	adrl	r3,K256
+# endif
+	add	r2,r1,r2,lsl#6	@ len to point at the end of inp
+
+.Loop_v8:
+	vld1.8		{q8-q9},[r1]!
+	vld1.8		{q10-q11},[r1]!
+	vld1.32		{q12},[r3]!
+	vrev32.8	q8,q8
+	vrev32.8	q9,q9
+	vrev32.8	q10,q10
+	vrev32.8	q11,q11
+	vmov		q14,q0	@ offload
+	vmov		q15,q1
+	teq		r1,r2
+	vld1.32		{q13},[r3]!
+	vadd.i32	q12,q12,q8
+	INST(0xe2,0x03,0xfa,0xf3)	@ sha256su0 q8,q9
+	vmov		q2,q0
+	INST(0x68,0x0c,0x02,0xf3)	@ sha256h q0,q1,q12
+	INST(0x68,0x2c,0x14,0xf3)	@ sha256h2 q1,q2,q12
+	INST(0xe6,0x0c,0x64,0xf3)	@ sha256su1 q8,q10,q11
+	vld1.32		{q12},[r3]!
+	vadd.i32	q13,q13,q9
+	INST(0xe4,0x23,0xfa,0xf3)	@ sha256su0 q9,q10
+	vmov		q2,q0
+	INST(0x6a,0x0c,0x02,0xf3)	@ sha256h q0,q1,q13
+	INST(0x6a,0x2c,0x14,0xf3)	@ sha256h2 q1,q2,q13
+	INST(0xe0,0x2c,0x66,0xf3)	@ sha256su1 q9,q11,q8
+	vld1.32		{q13},[r3]!
+	vadd.i32	q12,q12,q10
+	INST(0xe6,0x43,0xfa,0xf3)	@ sha256su0 q10,q11
+	vmov		q2,q0
+	INST(0x68,0x0c,0x02,0xf3)	@ sha256h q0,q1,q12
+	INST(0x68,0x2c,0x14,0xf3)	@ sha256h2 q1,q2,q12
+	INST(0xe2,0x4c,0x60,0xf3)	@ sha256su1 q10,q8,q9
+	vld1.32		{q12},[r3]!
+	vadd.i32	q13,q13,q11
+	INST(0xe0,0x63,0xfa,0xf3)	@ sha256su0 q11,q8
+	vmov		q2,q0
+	INST(0x6a,0x0c,0x02,0xf3)	@ sha256h q0,q1,q13
+	INST(0x6a,0x2c,0x14,0xf3)	@ sha256h2 q1,q2,q13
+	INST(0xe4,0x6c,0x62,0xf3)	@ sha256su1 q11,q9,q10
+	vld1.32		{q13},[r3]!
+	vadd.i32	q12,q12,q8
+	INST(0xe2,0x03,0xfa,0xf3)	@ sha256su0 q8,q9
+	vmov		q2,q0
+	INST(0x68,0x0c,0x02,0xf3)	@ sha256h q0,q1,q12
+	INST(0x68,0x2c,0x14,0xf3)	@ sha256h2 q1,q2,q12
+	INST(0xe6,0x0c,0x64,0xf3)	@ sha256su1 q8,q10,q11
+	vld1.32		{q12},[r3]!
+	vadd.i32	q13,q13,q9
+	INST(0xe4,0x23,0xfa,0xf3)	@ sha256su0 q9,q10
+	vmov		q2,q0
+	INST(0x6a,0x0c,0x02,0xf3)	@ sha256h q0,q1,q13
+	INST(0x6a,0x2c,0x14,0xf3)	@ sha256h2 q1,q2,q13
+	INST(0xe0,0x2c,0x66,0xf3)	@ sha256su1 q9,q11,q8
+	vld1.32		{q13},[r3]!
+	vadd.i32	q12,q12,q10
+	INST(0xe6,0x43,0xfa,0xf3)	@ sha256su0 q10,q11
+	vmov		q2,q0
+	INST(0x68,0x0c,0x02,0xf3)	@ sha256h q0,q1,q12
+	INST(0x68,0x2c,0x14,0xf3)	@ sha256h2 q1,q2,q12
+	INST(0xe2,0x4c,0x60,0xf3)	@ sha256su1 q10,q8,q9
+	vld1.32		{q12},[r3]!
+	vadd.i32	q13,q13,q11
+	INST(0xe0,0x63,0xfa,0xf3)	@ sha256su0 q11,q8
+	vmov		q2,q0
+	INST(0x6a,0x0c,0x02,0xf3)	@ sha256h q0,q1,q13
+	INST(0x6a,0x2c,0x14,0xf3)	@ sha256h2 q1,q2,q13
+	INST(0xe4,0x6c,0x62,0xf3)	@ sha256su1 q11,q9,q10
+	vld1.32		{q13},[r3]!
+	vadd.i32	q12,q12,q8
+	INST(0xe2,0x03,0xfa,0xf3)	@ sha256su0 q8,q9
+	vmov		q2,q0
+	INST(0x68,0x0c,0x02,0xf3)	@ sha256h q0,q1,q12
+	INST(0x68,0x2c,0x14,0xf3)	@ sha256h2 q1,q2,q12
+	INST(0xe6,0x0c,0x64,0xf3)	@ sha256su1 q8,q10,q11
+	vld1.32		{q12},[r3]!
+	vadd.i32	q13,q13,q9
+	INST(0xe4,0x23,0xfa,0xf3)	@ sha256su0 q9,q10
+	vmov		q2,q0
+	INST(0x6a,0x0c,0x02,0xf3)	@ sha256h q0,q1,q13
+	INST(0x6a,0x2c,0x14,0xf3)	@ sha256h2 q1,q2,q13
+	INST(0xe0,0x2c,0x66,0xf3)	@ sha256su1 q9,q11,q8
+	vld1.32		{q13},[r3]!
+	vadd.i32	q12,q12,q10
+	INST(0xe6,0x43,0xfa,0xf3)	@ sha256su0 q10,q11
+	vmov		q2,q0
+	INST(0x68,0x0c,0x02,0xf3)	@ sha256h q0,q1,q12
+	INST(0x68,0x2c,0x14,0xf3)	@ sha256h2 q1,q2,q12
+	INST(0xe2,0x4c,0x60,0xf3)	@ sha256su1 q10,q8,q9
+	vld1.32		{q12},[r3]!
+	vadd.i32	q13,q13,q11
+	INST(0xe0,0x63,0xfa,0xf3)	@ sha256su0 q11,q8
+	vmov		q2,q0
+	INST(0x6a,0x0c,0x02,0xf3)	@ sha256h q0,q1,q13
+	INST(0x6a,0x2c,0x14,0xf3)	@ sha256h2 q1,q2,q13
+	INST(0xe4,0x6c,0x62,0xf3)	@ sha256su1 q11,q9,q10
+	vld1.32		{q13},[r3]!
+	vadd.i32	q12,q12,q8
+	vmov		q2,q0
+	INST(0x68,0x0c,0x02,0xf3)	@ sha256h q0,q1,q12
+	INST(0x68,0x2c,0x14,0xf3)	@ sha256h2 q1,q2,q12
+
+	vld1.32		{q12},[r3]!
+	vadd.i32	q13,q13,q9
+	vmov		q2,q0
+	INST(0x6a,0x0c,0x02,0xf3)	@ sha256h q0,q1,q13
+	INST(0x6a,0x2c,0x14,0xf3)	@ sha256h2 q1,q2,q13
+
+	vld1.32		{q13},[r3]
+	vadd.i32	q12,q12,q10
+	sub		r3,r3,#256-16	@ rewind
+	vmov		q2,q0
+	INST(0x68,0x0c,0x02,0xf3)	@ sha256h q0,q1,q12
+	INST(0x68,0x2c,0x14,0xf3)	@ sha256h2 q1,q2,q12
+
+	vadd.i32	q13,q13,q11
+	vmov		q2,q0
+	INST(0x6a,0x0c,0x02,0xf3)	@ sha256h q0,q1,q13
+	INST(0x6a,0x2c,0x14,0xf3)	@ sha256h2 q1,q2,q13
+
+	vadd.i32	q0,q0,q14
+	vadd.i32	q1,q1,q15
+	it		ne
+	bne		.Loop_v8
+
+	vst1.32		{q0,q1},[r0]
+
+	bx	lr		@ bx lr
+.size	sha256_block_data_order_armv8,.-sha256_block_data_order_armv8
+#endif
+.asciz  "SHA256 block transform for ARMv4/NEON/ARMv8, CRYPTOGAMS by <appro@openssl.org>"
+.align	2
+#if __ARM_MAX_ARCH__>=7 && !defined(__KERNEL__)
+.comm   OPENSSL_armcap_P,4,4
+#endif
diff --git a/arch/arm/crypto/sha256_glue.c b/arch/arm/crypto/sha256_glue.c
new file mode 100644
index 000000000000..bb03482e53e2
--- /dev/null
+++ b/arch/arm/crypto/sha256_glue.c
@@ -0,0 +1,246 @@
+/*
+ * Glue code for the SHA256 Secure Hash Algorithm assembly implementation
+ * using optimized ARM assembler and NEON instructions.
+ *
+ * Copyright © 2015 Google Inc.
+ *
+ * This file is based on sha256_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/crypto.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>
+#include "sha256_glue.h"
+
+asmlinkage void sha256_block_data_order(u32 *digest, const void *data,
+				      unsigned int num_blks);
+
+
+int sha256_init(struct shash_desc *desc)
+{
+	struct sha256_state *sctx = shash_desc_ctx(desc);
+
+	sctx->state[0] = SHA256_H0;
+	sctx->state[1] = SHA256_H1;
+	sctx->state[2] = SHA256_H2;
+	sctx->state[3] = SHA256_H3;
+	sctx->state[4] = SHA256_H4;
+	sctx->state[5] = SHA256_H5;
+	sctx->state[6] = SHA256_H6;
+	sctx->state[7] = SHA256_H7;
+	sctx->count = 0;
+
+	return 0;
+}
+
+int sha224_init(struct shash_desc *desc)
+{
+	struct sha256_state *sctx = shash_desc_ctx(desc);
+
+	sctx->state[0] = SHA224_H0;
+	sctx->state[1] = SHA224_H1;
+	sctx->state[2] = SHA224_H2;
+	sctx->state[3] = SHA224_H3;
+	sctx->state[4] = SHA224_H4;
+	sctx->state[5] = SHA224_H5;
+	sctx->state[6] = SHA224_H6;
+	sctx->state[7] = SHA224_H7;
+	sctx->count = 0;
+
+	return 0;
+}
+
+int __sha256_update(struct shash_desc *desc, const u8 *data, unsigned int len,
+		    unsigned int partial)
+{
+	struct sha256_state *sctx = shash_desc_ctx(desc);
+	unsigned int done = 0;
+
+	sctx->count += len;
+
+	if (partial) {
+		done = SHA256_BLOCK_SIZE - partial;
+		memcpy(sctx->buf + partial, data, done);
+		sha256_block_data_order(sctx->state, sctx->buf, 1);
+	}
+
+	if (len - done >= SHA256_BLOCK_SIZE) {
+		const unsigned int rounds = (len - done) / SHA256_BLOCK_SIZE;
+
+		sha256_block_data_order(sctx->state, data + done, rounds);
+		done += rounds * SHA256_BLOCK_SIZE;
+	}
+
+	memcpy(sctx->buf, data + done, len - done);
+
+	return 0;
+}
+
+int sha256_update(struct shash_desc *desc, const u8 *data, unsigned int len)
+{
+	struct sha256_state *sctx = shash_desc_ctx(desc);
+	unsigned int partial = sctx->count % SHA256_BLOCK_SIZE;
+
+	/* Handle the fast case right here */
+	if (partial + len < SHA256_BLOCK_SIZE) {
+		sctx->count += len;
+		memcpy(sctx->buf + partial, data, len);
+
+		return 0;
+	}
+
+	return __sha256_update(desc, data, len, partial);
+}
+
+/* Add padding and return the message digest. */
+static int sha256_final(struct shash_desc *desc, u8 *out)
+{
+	struct sha256_state *sctx = shash_desc_ctx(desc);
+	unsigned int i, index, padlen;
+	__be32 *dst = (__be32 *)out;
+	__be64 bits;
+	static const u8 padding[SHA256_BLOCK_SIZE] = { 0x80, };
+
+	/* save number of bits */
+	bits = cpu_to_be64(sctx->count << 3);
+
+	/* Pad out to 56 mod 64 and append length */
+	index = sctx->count % SHA256_BLOCK_SIZE;
+	padlen = (index < 56) ? (56 - index) : ((SHA256_BLOCK_SIZE+56)-index);
+
+	/* We need to fill a whole block for __sha256_update */
+	if (padlen <= 56) {
+		sctx->count += padlen;
+		memcpy(sctx->buf + index, padding, padlen);
+	} else {
+		__sha256_update(desc, padding, padlen, index);
+	}
+	__sha256_update(desc, (const u8 *)&bits, sizeof(bits), 56);
+
+	/* Store state in digest */
+	for (i = 0; i < 8; i++)
+		dst[i] = cpu_to_be32(sctx->state[i]);
+
+	/* Wipe context */
+	memset(sctx, 0, sizeof(*sctx));
+
+	return 0;
+}
+
+static int sha224_final(struct shash_desc *desc, u8 *out)
+{
+	u8 D[SHA256_DIGEST_SIZE];
+
+	sha256_final(desc, D);
+
+	memcpy(out, D, SHA224_DIGEST_SIZE);
+	memset(D, 0, SHA256_DIGEST_SIZE);
+
+	return 0;
+}
+
+int sha256_export(struct shash_desc *desc, void *out)
+{
+	struct sha256_state *sctx = shash_desc_ctx(desc);
+
+	memcpy(out, sctx, sizeof(*sctx));
+
+	return 0;
+}
+
+int sha256_import(struct shash_desc *desc, const void *in)
+{
+	struct sha256_state *sctx = shash_desc_ctx(desc);
+
+	memcpy(sctx, in, sizeof(*sctx));
+
+	return 0;
+}
+
+static struct shash_alg algs[] = { {
+	.digestsize	=	SHA256_DIGEST_SIZE,
+	.init		=	sha256_init,
+	.update		=	sha256_update,
+	.final		=	sha256_final,
+	.export		=	sha256_export,
+	.import		=	sha256_import,
+	.descsize	=	sizeof(struct sha256_state),
+	.statesize	=	sizeof(struct sha256_state),
+	.base		=	{
+		.cra_name	=	"sha256",
+		.cra_driver_name =	"sha256-asm",
+		.cra_priority	=	150,
+		.cra_flags	=	CRYPTO_ALG_TYPE_SHASH,
+		.cra_blocksize	=	SHA256_BLOCK_SIZE,
+		.cra_module	=	THIS_MODULE,
+	}
+}, {
+	.digestsize	=	SHA224_DIGEST_SIZE,
+	.init		=	sha224_init,
+	.update		=	sha256_update,
+	.final		=	sha224_final,
+	.export		=	sha256_export,
+	.import		=	sha256_import,
+	.descsize	=	sizeof(struct sha256_state),
+	.statesize	=	sizeof(struct sha256_state),
+	.base		=	{
+		.cra_name	=	"sha224",
+		.cra_driver_name =	"sha224-asm",
+		.cra_priority	=	150,
+		.cra_flags	=	CRYPTO_ALG_TYPE_SHASH,
+		.cra_blocksize	=	SHA224_BLOCK_SIZE,
+		.cra_module	=	THIS_MODULE,
+	}
+} };
+
+static int __init sha256_mod_init(void)
+{
+	int res = crypto_register_shashes(algs, ARRAY_SIZE(algs));
+
+	if (res < 0)
+		return res;
+
+	if (IS_ENABLED(CONFIG_KERNEL_MODE_NEON) && cpu_has_neon()) {
+		res = crypto_register_shashes(sha256_neon_algs,
+					      ARRAY_SIZE(sha256_neon_algs));
+
+		if (res < 0)
+			crypto_unregister_shashes(algs, ARRAY_SIZE(algs));
+	}
+
+	return res;
+}
+
+static void __exit sha256_mod_fini(void)
+{
+	crypto_unregister_shashes(algs, ARRAY_SIZE(algs));
+
+	if (IS_ENABLED(CONFIG_KERNEL_MODE_NEON) && cpu_has_neon())
+		crypto_unregister_shashes(sha256_neon_algs,
+					  ARRAY_SIZE(sha256_neon_algs));
+}
+
+module_init(sha256_mod_init);
+module_exit(sha256_mod_fini);
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("SHA256 Secure Hash Algorithm (ARM), including NEON");
+
+MODULE_ALIAS_CRYPTO("sha256");
diff --git a/arch/arm/crypto/sha256_glue.h b/arch/arm/crypto/sha256_glue.h
new file mode 100644
index 000000000000..0312f4ffe8cc
--- /dev/null
+++ b/arch/arm/crypto/sha256_glue.h
@@ -0,0 +1,23 @@
+#ifndef _CRYPTO_SHA256_GLUE_H
+#define _CRYPTO_SHA256_GLUE_H
+
+#include <linux/crypto.h>
+#include <crypto/sha.h>
+
+extern struct shash_alg sha256_neon_algs[2];
+
+extern int sha256_init(struct shash_desc *desc);
+
+extern int sha224_init(struct shash_desc *desc);
+
+extern int __sha256_update(struct shash_desc *desc, const u8 *data,
+			   unsigned int len, unsigned int partial);
+
+extern int sha256_update(struct shash_desc *desc, const u8 *data,
+			 unsigned int len);
+
+extern int sha256_export(struct shash_desc *desc, void *out);
+
+extern int sha256_import(struct shash_desc *desc, const void *in);
+
+#endif /* _CRYPTO_SHA256_GLUE_H */
diff --git a/arch/arm/crypto/sha256_neon_glue.c b/arch/arm/crypto/sha256_neon_glue.c
new file mode 100644
index 000000000000..3ff0a7f1d092
--- /dev/null
+++ b/arch/arm/crypto/sha256_neon_glue.c
@@ -0,0 +1,172 @@
+/*
+ * Glue code for the SHA256 Secure Hash Algorithm assembly implementation
+ * using NEON instructions.
+ *
+ * Copyright © 2015 Google Inc.
+ *
+ * This file is based on sha512_neon_glue.c:
+ *   Copyright © 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 <crypto/internal/hash.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>
+#include "sha256_glue.h"
+
+asmlinkage void sha256_block_data_order_neon(u32 *digest, const void *data,
+				      unsigned int num_blks);
+
+
+static int __sha256_neon_update(struct shash_desc *desc, const u8 *data,
+				unsigned int len, unsigned int partial)
+{
+	struct sha256_state *sctx = shash_desc_ctx(desc);
+	unsigned int done = 0;
+
+	sctx->count += len;
+
+	if (partial) {
+		done = SHA256_BLOCK_SIZE - partial;
+		memcpy(sctx->buf + partial, data, done);
+		sha256_block_data_order_neon(sctx->state, sctx->buf, 1);
+	}
+
+	if (len - done >= SHA256_BLOCK_SIZE) {
+		const unsigned int rounds = (len - done) / SHA256_BLOCK_SIZE;
+
+		sha256_block_data_order_neon(sctx->state, data + done, rounds);
+		done += rounds * SHA256_BLOCK_SIZE;
+	}
+
+	memcpy(sctx->buf, data + done, len - done);
+
+	return 0;
+}
+
+static int sha256_neon_update(struct shash_desc *desc, const u8 *data,
+			      unsigned int len)
+{
+	struct sha256_state *sctx = shash_desc_ctx(desc);
+	unsigned int partial = sctx->count % SHA256_BLOCK_SIZE;
+	int res;
+
+	/* Handle the fast case right here */
+	if (partial + len < SHA256_BLOCK_SIZE) {
+		sctx->count += len;
+		memcpy(sctx->buf + partial, data, len);
+
+		return 0;
+	}
+
+	if (!may_use_simd()) {
+		res = __sha256_update(desc, data, len, partial);
+	} else {
+		kernel_neon_begin();
+		res = __sha256_neon_update(desc, data, len, partial);
+		kernel_neon_end();
+	}
+
+	return res;
+}
+
+/* Add padding and return the message digest. */
+static int sha256_neon_final(struct shash_desc *desc, u8 *out)
+{
+	struct sha256_state *sctx = shash_desc_ctx(desc);
+	unsigned int i, index, padlen;
+	__be32 *dst = (__be32 *)out;
+	__be64 bits;
+	static const u8 padding[SHA256_BLOCK_SIZE] = { 0x80, };
+
+	/* save number of bits */
+	bits = cpu_to_be64(sctx->count << 3);
+
+	/* Pad out to 56 mod 64 and append length */
+	index = sctx->count % SHA256_BLOCK_SIZE;
+	padlen = (index < 56) ? (56 - index) : ((SHA256_BLOCK_SIZE+56)-index);
+
+	if (!may_use_simd()) {
+		sha256_update(desc, padding, padlen);
+		sha256_update(desc, (const u8 *)&bits, sizeof(bits));
+	} else {
+		kernel_neon_begin();
+		/* We need to fill a whole block for __sha256_neon_update() */
+		if (padlen <= 56) {
+			sctx->count += padlen;
+			memcpy(sctx->buf + index, padding, padlen);
+		} else {
+			__sha256_neon_update(desc, padding, padlen, index);
+		}
+		__sha256_neon_update(desc, (const u8 *)&bits,
+					sizeof(bits), 56);
+		kernel_neon_end();
+	}
+
+	/* Store state in digest */
+	for (i = 0; i < 8; i++)
+		dst[i] = cpu_to_be32(sctx->state[i]);
+
+	/* Wipe context */
+	memset(sctx, 0, sizeof(*sctx));
+
+	return 0;
+}
+
+static int sha224_neon_final(struct shash_desc *desc, u8 *out)
+{
+	u8 D[SHA256_DIGEST_SIZE];
+
+	sha256_neon_final(desc, D);
+
+	memcpy(out, D, SHA224_DIGEST_SIZE);
+	memset(D, 0, SHA256_DIGEST_SIZE);
+
+	return 0;
+}
+
+struct shash_alg sha256_neon_algs[] = { {
+	.digestsize	=	SHA256_DIGEST_SIZE,
+	.init		=	sha256_init,
+	.update		=	sha256_neon_update,
+	.final		=	sha256_neon_final,
+	.export		=	sha256_export,
+	.import		=	sha256_import,
+	.descsize	=	sizeof(struct sha256_state),
+	.statesize	=	sizeof(struct sha256_state),
+	.base		=	{
+		.cra_name	=	"sha256",
+		.cra_driver_name =	"sha256-neon",
+		.cra_priority	=	250,
+		.cra_flags	=	CRYPTO_ALG_TYPE_SHASH,
+		.cra_blocksize	=	SHA256_BLOCK_SIZE,
+		.cra_module	=	THIS_MODULE,
+	}
+}, {
+	.digestsize	=	SHA224_DIGEST_SIZE,
+	.init		=	sha224_init,
+	.update		=	sha256_neon_update,
+	.final		=	sha224_neon_final,
+	.export		=	sha256_export,
+	.import		=	sha256_import,
+	.descsize	=	sizeof(struct sha256_state),
+	.statesize	=	sizeof(struct sha256_state),
+	.base		=	{
+		.cra_name	=	"sha224",
+		.cra_driver_name =	"sha224-neon",
+		.cra_priority	=	250,
+		.cra_flags	=	CRYPTO_ALG_TYPE_SHASH,
+		.cra_blocksize	=	SHA224_BLOCK_SIZE,
+		.cra_module	=	THIS_MODULE,
+	}
+} };
diff --git a/crypto/Kconfig b/crypto/Kconfig
index b7cc3cb3a613..fa7e2a8cc608 100644
--- a/crypto/Kconfig
+++ b/crypto/Kconfig
@@ -556,6 +556,13 @@ config CRYPTO_SHA256
 	  This code also includes SHA-224, a 224 bit hash with 112 bits
 	  of security against collision attacks.
 
+config CRYPTO_SHA256_ARM
+	tristate "SHA-224/256 digest algorithm (ARM-asm and NEON)"
+	select CRYPTO_HASH
+	help
+	  SHA-256 secure hash standard (DFIPS 180-2) implemented
+	  using optimized ARM assembler and NEON, when available.
+
 config CRYPTO_SHA256_SPARC64
 	tristate "SHA224 and SHA256 digest algorithm (SPARC64)"
 	depends on SPARC64
diff --git a/drivers/base/power/wakeup.c b/drivers/base/power/wakeup.c
index bea700736f24..4b35cc08c3b6 100644
--- a/drivers/base/power/wakeup.c
+++ b/drivers/base/power/wakeup.c
@@ -14,6 +14,7 @@
 #include <linux/suspend.h>
 #include <linux/seq_file.h>
 #include <linux/debugfs.h>
+#include <linux/types.h>
 #include <trace/events/power.h>
 
 #include "power.h"
@@ -661,16 +662,31 @@ EXPORT_SYMBOL_GPL(pm_wakeup_event);
 
 void pm_get_active_wakeup_sources(char *pending_wakeup_source, size_t max)
 {
-	struct wakeup_source *ws;
+	struct wakeup_source *ws, *last_active_ws = NULL;
 	int len = 0;
+	bool active = false;
+
 	rcu_read_lock();
-	len += snprintf(pending_wakeup_source, max, "Pending Wakeup Sources: ");
 	list_for_each_entry_rcu(ws, &wakeup_sources, entry) {
 		if (ws->active) {
-			len += snprintf(pending_wakeup_source + len, max,
+			if (!active)
+				len += scnprintf(pending_wakeup_source, max,
+						"Pending Wakeup Sources: ");
+			len += scnprintf(pending_wakeup_source + len, max - len,
 				"%s ", ws->name);
+			active = true;
+		} else if (!active &&
+			   (!last_active_ws ||
+			    ktime_to_ns(ws->last_time) >
+			    ktime_to_ns(last_active_ws->last_time))) {
+			last_active_ws = ws;
 		}
 	}
+	if (!active && last_active_ws) {
+		scnprintf(pending_wakeup_source, max,
+				"Last active Wakeup Source: %s",
+				last_active_ws->name);
+	}
 	rcu_read_unlock();
 }
 EXPORT_SYMBOL_GPL(pm_get_active_wakeup_sources);
diff --git a/drivers/cpuidle/governors/menu.c b/drivers/cpuidle/governors/menu.c
index 33305fb3d5fc..efe23dd391ed 100644
--- a/drivers/cpuidle/governors/menu.c
+++ b/drivers/cpuidle/governors/menu.c
@@ -126,7 +126,7 @@ struct menu_device {
 #define LOAD_INT(x) ((x) >> FSHIFT)
 #define LOAD_FRAC(x) LOAD_INT(((x) & (FIXED_1-1)) * 100)
 
-static int get_loadavg(void)
+static int __maybe_unused get_loadavg(void)
 {
 	unsigned long this = this_cpu_load();
 
diff --git a/drivers/misc/Kconfig b/drivers/misc/Kconfig
index 3f5743424ff7..181fc59fec04 100644
--- a/drivers/misc/Kconfig
+++ b/drivers/misc/Kconfig
@@ -531,6 +531,12 @@ config SRAM
 	  the genalloc API. It is supposed to be used for small on-chip SRAM
 	  areas found on many SoCs.
 
+config UID_CPUTIME
+	tristate "Per-UID cpu time statistics"
+	depends on PROFILING
+	help
+	  Per UID based cpu time statistics exported to /proc/uid_cputime
+
 source "drivers/misc/c2port/Kconfig"
 source "drivers/misc/eeprom/Kconfig"
 source "drivers/misc/cb710/Kconfig"
diff --git a/drivers/misc/Makefile b/drivers/misc/Makefile
index a57666cec342..89435c9a182c 100644
--- a/drivers/misc/Makefile
+++ b/drivers/misc/Makefile
@@ -54,3 +54,4 @@ obj-$(CONFIG_INTEL_MEI)		+= mei/
 obj-$(CONFIG_VMWARE_VMCI)	+= vmw_vmci/
 obj-$(CONFIG_LATTICE_ECP3_CONFIG)	+= lattice-ecp3-config.o
 obj-$(CONFIG_SRAM)		+= sram.o
+obj-$(CONFIG_UID_CPUTIME) += uid_cputime.o
diff --git a/drivers/misc/uid_cputime.c b/drivers/misc/uid_cputime.c
new file mode 100644
index 000000000000..acd7046ce497
--- /dev/null
+++ b/drivers/misc/uid_cputime.c
@@ -0,0 +1,237 @@
+/* drivers/misc/uid_cputime.c
+ *
+ * Copyright (C) 2014 - 2015 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * 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.
+ *
+ */
+
+#include <linux/atomic.h>
+#include <linux/err.h>
+#include <linux/hashtable.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/list.h>
+#include <linux/proc_fs.h>
+#include <linux/profile.h>
+#include <linux/sched.h>
+#include <linux/seq_file.h>
+#include <linux/slab.h>
+#include <linux/uaccess.h>
+
+#define UID_HASH_BITS	10
+DECLARE_HASHTABLE(hash_table, UID_HASH_BITS);
+
+static DEFINE_MUTEX(uid_lock);
+static struct proc_dir_entry *parent;
+
+struct uid_entry {
+	uid_t uid;
+	cputime_t utime;
+	cputime_t stime;
+	cputime_t active_utime;
+	cputime_t active_stime;
+	struct hlist_node hash;
+};
+
+static struct uid_entry *find_uid_entry(uid_t uid)
+{
+	struct uid_entry *uid_entry;
+	hash_for_each_possible(hash_table, uid_entry, hash, uid) {
+		if (uid_entry->uid == uid)
+			return uid_entry;
+	}
+	return NULL;
+}
+
+static struct uid_entry *find_or_register_uid(uid_t uid)
+{
+	struct uid_entry *uid_entry;
+
+	uid_entry = find_uid_entry(uid);
+	if (uid_entry)
+		return uid_entry;
+
+	uid_entry = kzalloc(sizeof(struct uid_entry), GFP_ATOMIC);
+	if (!uid_entry)
+		return NULL;
+
+	uid_entry->uid = uid;
+
+	hash_add(hash_table, &uid_entry->hash, uid);
+
+	return uid_entry;
+}
+
+static int uid_stat_show(struct seq_file *m, void *v)
+{
+	struct uid_entry *uid_entry;
+	struct task_struct *task;
+	cputime_t utime;
+	cputime_t stime;
+	unsigned long bkt;
+
+	mutex_lock(&uid_lock);
+
+	hash_for_each(hash_table, bkt, uid_entry, hash) {
+		uid_entry->active_stime = 0;
+		uid_entry->active_utime = 0;
+	}
+
+	read_lock(&tasklist_lock);
+	for_each_process(task) {
+		uid_entry = find_or_register_uid(from_kuid_munged(
+			current_user_ns(), task_uid(task)));
+		if (!uid_entry) {
+			read_unlock(&tasklist_lock);
+			mutex_unlock(&uid_lock);
+			pr_err("%s: failed to find the uid_entry for uid %d\n",
+				__func__, from_kuid_munged(current_user_ns(),
+				task_uid(task)));
+			return -ENOMEM;
+		}
+		task_cputime_adjusted(task, &utime, &stime);
+		uid_entry->active_utime += utime;
+		uid_entry->active_stime += stime;
+	}
+	read_unlock(&tasklist_lock);
+
+	hash_for_each(hash_table, bkt, uid_entry, hash) {
+		cputime_t total_utime = uid_entry->utime +
+							uid_entry->active_utime;
+		cputime_t total_stime = uid_entry->stime +
+							uid_entry->active_stime;
+		seq_printf(m, "%d: %u %u\n", uid_entry->uid,
+						cputime_to_usecs(total_utime),
+						cputime_to_usecs(total_stime));
+	}
+
+	mutex_unlock(&uid_lock);
+	return 0;
+}
+
+static int uid_stat_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, uid_stat_show, PDE_DATA(inode));
+}
+
+static const struct file_operations uid_stat_fops = {
+	.open		= uid_stat_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
+static int uid_remove_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, NULL, NULL);
+}
+
+static ssize_t uid_remove_write(struct file *file,
+			const char __user *buffer, size_t count, loff_t *ppos)
+{
+	struct uid_entry *uid_entry;
+	struct hlist_node *tmp;
+	char uids[128];
+	char *start_uid, *end_uid = NULL;
+	long int uid_start = 0, uid_end = 0;
+
+	if (count >= sizeof(uids))
+		count = sizeof(uids) - 1;
+
+	if (copy_from_user(uids, buffer, count))
+		return -EFAULT;
+
+	uids[count] = '\0';
+	end_uid = uids;
+	start_uid = strsep(&end_uid, "-");
+
+	if (!start_uid || !end_uid)
+		return -EINVAL;
+
+	if (kstrtol(start_uid, 10, &uid_start) != 0 ||
+		kstrtol(end_uid, 10, &uid_end) != 0) {
+		return -EINVAL;
+	}
+
+	mutex_lock(&uid_lock);
+
+	for (; uid_start <= uid_end; uid_start++) {
+		hash_for_each_possible_safe(hash_table, uid_entry, tmp,
+							hash, uid_start) {
+			hash_del(&uid_entry->hash);
+			kfree(uid_entry);
+		}
+	}
+
+	mutex_unlock(&uid_lock);
+	return count;
+}
+
+static const struct file_operations uid_remove_fops = {
+	.open		= uid_remove_open,
+	.release	= single_release,
+	.write		= uid_remove_write,
+};
+
+static int process_notifier(struct notifier_block *self,
+			unsigned long cmd, void *v)
+{
+	struct task_struct *task = v;
+	struct uid_entry *uid_entry;
+	cputime_t utime, stime;
+	uid_t uid;
+
+	if (!task)
+		return NOTIFY_OK;
+
+	mutex_lock(&uid_lock);
+	uid = from_kuid_munged(current_user_ns(), task_uid(task));
+	uid_entry = find_or_register_uid(uid);
+	if (!uid_entry) {
+		pr_err("%s: failed to find uid %d\n", __func__, uid);
+		goto exit;
+	}
+
+	task_cputime_adjusted(task, &utime, &stime);
+	uid_entry->utime += utime;
+	uid_entry->stime += stime;
+
+exit:
+	mutex_unlock(&uid_lock);
+	return NOTIFY_OK;
+}
+
+static struct notifier_block process_notifier_block = {
+	.notifier_call	= process_notifier,
+};
+
+static int __init proc_uid_cputime_init(void)
+{
+	hash_init(hash_table);
+
+	parent = proc_mkdir("uid_cputime", NULL);
+	if (!parent) {
+		pr_err("%s: failed to create proc entry\n", __func__);
+		return -ENOMEM;
+	}
+
+	proc_create_data("remove_uid_range", S_IWUGO, parent, &uid_remove_fops,
+					NULL);
+
+	proc_create_data("show_uid_stat", S_IWUGO, parent, &uid_stat_fops,
+					NULL);
+
+	profile_event_register(PROFILE_TASK_EXIT, &process_notifier_block);
+
+	return 0;
+}
+
+early_initcall(proc_uid_cputime_init);
diff --git a/drivers/staging/android/Kconfig b/drivers/staging/android/Kconfig
index a817875bbf85..b3c054e4fd58 100644
--- a/drivers/staging/android/Kconfig
+++ b/drivers/staging/android/Kconfig
@@ -20,23 +20,6 @@ config ASHMEM
 	  It is, in theory, a good memory allocator for low-memory devices,
 	  because it can discard shared memory units when under memory pressure.
 
-config ANDROID_LOGGER
-	tristate "Android log driver"
-	default n
-	---help---
-	  This adds support for system-wide logging using four log buffers.
-
-	  These are:
-
-	      1: main
-	      2: events
-	      3: radio
-	      4: system
-
-	  Log reading and writing is performed via normal Linux reads and
-	  optimized writes. This optimization avoids logging having too
-	  much overhead in the system.
-
 config ANDROID_TIMED_OUTPUT
 	bool "Timed output class driver"
 	default y
@@ -61,15 +44,6 @@ config ANDROID_LOW_MEMORY_KILLER_AUTODETECT_OOM_ADJ_VALUES
 	  /sys/module/lowmemorykiller/parameters/adj and convert them
 	  to oom_score_adj values.
 
-config ANDROID_INTF_ALARM_DEV
-	bool "Android alarm driver"
-	depends on RTC_CLASS
-	default n
-	---help---
-	  Provides non-wakeup and rtc backed wakeup alarms based on rtc or
-	  elapsed realtime, and a non-wakeup alarm on the monotonic clock.
-	  Also exports the alarm interface to user-space.
-
 config SYNC
 	bool "Synchronization framework"
 	default n
diff --git a/drivers/staging/android/Makefile b/drivers/staging/android/Makefile
index c223ef72bb38..30ba2f0cb084 100644
--- a/drivers/staging/android/Makefile
+++ b/drivers/staging/android/Makefile
@@ -4,10 +4,8 @@ obj-y					+= ion/
 obj-$(CONFIG_FIQ_DEBUGGER)		+= fiq_debugger/
 
 obj-$(CONFIG_ASHMEM)			+= ashmem.o
-obj-$(CONFIG_ANDROID_LOGGER)		+= logger.o
 obj-$(CONFIG_ANDROID_TIMED_OUTPUT)	+= timed_output.o
 obj-$(CONFIG_ANDROID_TIMED_GPIO)	+= timed_gpio.o
 obj-$(CONFIG_ANDROID_LOW_MEMORY_KILLER)	+= lowmemorykiller.o
-obj-$(CONFIG_ANDROID_INTF_ALARM_DEV)	+= alarm-dev.o
 obj-$(CONFIG_SYNC)			+= sync.o
 obj-$(CONFIG_SW_SYNC)			+= sw_sync.o
diff --git a/drivers/staging/android/alarm-dev.c b/drivers/staging/android/alarm-dev.c
deleted file mode 100644
index 053233c5dec1..000000000000
--- a/drivers/staging/android/alarm-dev.c
+++ /dev/null
@@ -1,444 +0,0 @@
-/* drivers/rtc/alarm-dev.c
- *
- * Copyright (C) 2007-2009 Google, Inc.
- *
- * This software is licensed under the terms of the GNU General Public
- * License version 2, as published by the Free Software Foundation, and
- * may be copied, distributed, and modified under those terms.
- *
- * 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.
- *
- */
-
-#include <linux/time.h>
-#include <linux/module.h>
-#include <linux/device.h>
-#include <linux/miscdevice.h>
-#include <linux/fs.h>
-#include <linux/platform_device.h>
-#include <linux/sched.h>
-#include <linux/spinlock.h>
-#include <linux/uaccess.h>
-#include <linux/alarmtimer.h>
-#include "android_alarm.h"
-
-#define ANDROID_ALARM_PRINT_INFO (1U << 0)
-#define ANDROID_ALARM_PRINT_IO (1U << 1)
-#define ANDROID_ALARM_PRINT_INT (1U << 2)
-
-static int debug_mask = ANDROID_ALARM_PRINT_INFO;
-module_param_named(debug_mask, debug_mask, int, S_IRUGO | S_IWUSR | S_IWGRP);
-
-#define alarm_dbg(debug_level_mask, fmt, ...)				\
-do {									\
-	if (debug_mask & ANDROID_ALARM_PRINT_##debug_level_mask)	\
-		pr_info(fmt, ##__VA_ARGS__);				\
-} while (0)
-
-#define ANDROID_ALARM_WAKEUP_MASK ( \
-	ANDROID_ALARM_RTC_WAKEUP_MASK | \
-	ANDROID_ALARM_ELAPSED_REALTIME_WAKEUP_MASK)
-
-static int alarm_opened;
-static DEFINE_SPINLOCK(alarm_slock);
-static struct wakeup_source alarm_wake_lock;
-static DECLARE_WAIT_QUEUE_HEAD(alarm_wait_queue);
-static uint32_t alarm_pending;
-static uint32_t alarm_enabled;
-static uint32_t wait_pending;
-
-struct devalarm {
-	union {
-		struct hrtimer hrt;
-		struct alarm alrm;
-	} u;
-	enum android_alarm_type type;
-};
-
-static struct devalarm alarms[ANDROID_ALARM_TYPE_COUNT];
-
-
-static int is_wakeup(enum android_alarm_type type)
-{
-	return (type == ANDROID_ALARM_RTC_WAKEUP ||
-		type == ANDROID_ALARM_ELAPSED_REALTIME_WAKEUP);
-}
-
-
-static void devalarm_start(struct devalarm *alrm, ktime_t exp)
-{
-	if (is_wakeup(alrm->type))
-		alarm_start(&alrm->u.alrm, exp);
-	else
-		hrtimer_start(&alrm->u.hrt, exp, HRTIMER_MODE_ABS);
-}
-
-
-static int devalarm_try_to_cancel(struct devalarm *alrm)
-{
-	if (is_wakeup(alrm->type))
-		return alarm_try_to_cancel(&alrm->u.alrm);
-	return hrtimer_try_to_cancel(&alrm->u.hrt);
-}
-
-static void devalarm_cancel(struct devalarm *alrm)
-{
-	if (is_wakeup(alrm->type))
-		alarm_cancel(&alrm->u.alrm);
-	else
-		hrtimer_cancel(&alrm->u.hrt);
-}
-
-static void alarm_clear(enum android_alarm_type alarm_type)
-{
-	uint32_t alarm_type_mask = 1U << alarm_type;
-	unsigned long flags;
-
-	spin_lock_irqsave(&alarm_slock, flags);
-	alarm_dbg(IO, "alarm %d clear\n", alarm_type);
-	devalarm_try_to_cancel(&alarms[alarm_type]);
-	if (alarm_pending) {
-		alarm_pending &= ~alarm_type_mask;
-		if (!alarm_pending && !wait_pending)
-			__pm_relax(&alarm_wake_lock);
-	}
-	alarm_enabled &= ~alarm_type_mask;
-	spin_unlock_irqrestore(&alarm_slock, flags);
-
-}
-
-static void alarm_set(enum android_alarm_type alarm_type,
-							struct timespec *ts)
-{
-	uint32_t alarm_type_mask = 1U << alarm_type;
-	unsigned long flags;
-
-	spin_lock_irqsave(&alarm_slock, flags);
-	alarm_dbg(IO, "alarm %d set %ld.%09ld\n",
-			alarm_type, ts->tv_sec, ts->tv_nsec);
-	alarm_enabled |= alarm_type_mask;
-	devalarm_start(&alarms[alarm_type], timespec_to_ktime(*ts));
-	spin_unlock_irqrestore(&alarm_slock, flags);
-}
-
-static int alarm_wait(void)
-{
-	unsigned long flags;
-	int rv = 0;
-
-	spin_lock_irqsave(&alarm_slock, flags);
-	alarm_dbg(IO, "alarm wait\n");
-	if (!alarm_pending && wait_pending) {
-		__pm_relax(&alarm_wake_lock);
-		wait_pending = 0;
-	}
-	spin_unlock_irqrestore(&alarm_slock, flags);
-
-	rv = wait_event_interruptible(alarm_wait_queue, alarm_pending);
-	if (rv)
-		return rv;
-
-	spin_lock_irqsave(&alarm_slock, flags);
-	rv = alarm_pending;
-	wait_pending = 1;
-	alarm_pending = 0;
-	spin_unlock_irqrestore(&alarm_slock, flags);
-
-	return rv;
-}
-
-static int alarm_set_rtc(struct timespec *ts)
-{
-	struct rtc_time new_rtc_tm;
-	struct rtc_device *rtc_dev;
-	unsigned long flags;
-	int rv = 0;
-
-	rtc_time_to_tm(ts->tv_sec, &new_rtc_tm);
-	rtc_dev = alarmtimer_get_rtcdev();
-	rv = do_settimeofday(ts);
-	if (rv < 0)
-		return rv;
-	if (rtc_dev)
-		rv = rtc_set_time(rtc_dev, &new_rtc_tm);
-
-	spin_lock_irqsave(&alarm_slock, flags);
-	alarm_pending |= ANDROID_ALARM_TIME_CHANGE_MASK;
-	wake_up(&alarm_wait_queue);
-	spin_unlock_irqrestore(&alarm_slock, flags);
-
-	return rv;
-}
-
-static int alarm_get_time(enum android_alarm_type alarm_type,
-							struct timespec *ts)
-{
-	int rv = 0;
-
-	switch (alarm_type) {
-	case ANDROID_ALARM_RTC_WAKEUP:
-	case ANDROID_ALARM_RTC:
-		getnstimeofday(ts);
-		break;
-	case ANDROID_ALARM_ELAPSED_REALTIME_WAKEUP:
-	case ANDROID_ALARM_ELAPSED_REALTIME:
-		get_monotonic_boottime(ts);
-		break;
-	case ANDROID_ALARM_SYSTEMTIME:
-		ktime_get_ts(ts);
-		break;
-	default:
-		rv = -EINVAL;
-	}
-	return rv;
-}
-
-static long alarm_do_ioctl(struct file *file, unsigned int cmd,
-							struct timespec *ts)
-{
-	int rv = 0;
-	unsigned long flags;
-	enum android_alarm_type alarm_type = ANDROID_ALARM_IOCTL_TO_TYPE(cmd);
-
-	if (alarm_type >= ANDROID_ALARM_TYPE_COUNT)
-		return -EINVAL;
-
-	if (ANDROID_ALARM_BASE_CMD(cmd) != ANDROID_ALARM_GET_TIME(0)) {
-		if ((file->f_flags & O_ACCMODE) == O_RDONLY)
-			return -EPERM;
-		if (file->private_data == NULL &&
-		    cmd != ANDROID_ALARM_SET_RTC) {
-			spin_lock_irqsave(&alarm_slock, flags);
-			if (alarm_opened) {
-				spin_unlock_irqrestore(&alarm_slock, flags);
-				return -EBUSY;
-			}
-			alarm_opened = 1;
-			file->private_data = (void *)1;
-			spin_unlock_irqrestore(&alarm_slock, flags);
-		}
-	}
-
-	switch (ANDROID_ALARM_BASE_CMD(cmd)) {
-	case ANDROID_ALARM_CLEAR(0):
-		alarm_clear(alarm_type);
-		break;
-	case ANDROID_ALARM_SET(0):
-		alarm_set(alarm_type, ts);
-		break;
-	case ANDROID_ALARM_SET_AND_WAIT(0):
-		alarm_set(alarm_type, ts);
-		/* fall though */
-	case ANDROID_ALARM_WAIT:
-		rv = alarm_wait();
-		break;
-	case ANDROID_ALARM_SET_RTC:
-		rv = alarm_set_rtc(ts);
-		break;
-	case ANDROID_ALARM_GET_TIME(0):
-		rv = alarm_get_time(alarm_type, ts);
-		break;
-
-	default:
-		rv = -EINVAL;
-	}
-	return rv;
-}
-
-static long alarm_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
-{
-
-	struct timespec ts;
-	int rv;
-
-	switch (ANDROID_ALARM_BASE_CMD(cmd)) {
-	case ANDROID_ALARM_SET_AND_WAIT(0):
-	case ANDROID_ALARM_SET(0):
-	case ANDROID_ALARM_SET_RTC:
-		if (copy_from_user(&ts, (void __user *)arg, sizeof(ts)))
-			return -EFAULT;
-		break;
-	}
-
-	rv = alarm_do_ioctl(file, cmd, &ts);
-	if (rv)
-		return rv;
-
-	switch (ANDROID_ALARM_BASE_CMD(cmd)) {
-	case ANDROID_ALARM_GET_TIME(0):
-		if (copy_to_user((void __user *)arg, &ts, sizeof(ts)))
-			return -EFAULT;
-		break;
-	}
-
-	return 0;
-}
-#ifdef CONFIG_COMPAT
-static long alarm_compat_ioctl(struct file *file, unsigned int cmd,
-							unsigned long arg)
-{
-
-	struct timespec ts;
-	int rv;
-
-	switch (ANDROID_ALARM_BASE_CMD(cmd)) {
-	case ANDROID_ALARM_SET_AND_WAIT_COMPAT(0):
-	case ANDROID_ALARM_SET_COMPAT(0):
-	case ANDROID_ALARM_SET_RTC_COMPAT:
-		if (compat_get_timespec(&ts, (void __user *)arg))
-			return -EFAULT;
-		/* fall through */
-	case ANDROID_ALARM_GET_TIME_COMPAT(0):
-		cmd = ANDROID_ALARM_COMPAT_TO_NORM(cmd);
-		break;
-	}
-
-	rv = alarm_do_ioctl(file, cmd, &ts);
-	if (rv)
-		return rv;
-
-	switch (ANDROID_ALARM_BASE_CMD(cmd)) {
-	case ANDROID_ALARM_GET_TIME(0): /* NOTE: we modified cmd above */
-		if (compat_put_timespec(&ts, (void __user *)arg))
-			return -EFAULT;
-		break;
-	}
-
-	return 0;
-}
-#endif
-
-static int alarm_open(struct inode *inode, struct file *file)
-{
-	file->private_data = NULL;
-	return 0;
-}
-
-static int alarm_release(struct inode *inode, struct file *file)
-{
-	int i;
-	unsigned long flags;
-
-	spin_lock_irqsave(&alarm_slock, flags);
-	if (file->private_data) {
-		for (i = 0; i < ANDROID_ALARM_TYPE_COUNT; i++) {
-			uint32_t alarm_type_mask = 1U << i;
-
-			if (alarm_enabled & alarm_type_mask) {
-				alarm_dbg(INFO,
-					  "%s: clear alarm, pending %d\n",
-					  __func__,
-					  !!(alarm_pending & alarm_type_mask));
-				alarm_enabled &= ~alarm_type_mask;
-			}
-			spin_unlock_irqrestore(&alarm_slock, flags);
-			devalarm_cancel(&alarms[i]);
-			spin_lock_irqsave(&alarm_slock, flags);
-		}
-		if (alarm_pending | wait_pending) {
-			if (alarm_pending)
-				alarm_dbg(INFO, "%s: clear pending alarms %x\n",
-					  __func__, alarm_pending);
-			__pm_relax(&alarm_wake_lock);
-			wait_pending = 0;
-			alarm_pending = 0;
-		}
-		alarm_opened = 0;
-	}
-	spin_unlock_irqrestore(&alarm_slock, flags);
-	return 0;
-}
-
-static void devalarm_triggered(struct devalarm *alarm)
-{
-	unsigned long flags;
-	uint32_t alarm_type_mask = 1U << alarm->type;
-
-	alarm_dbg(INT, "%s: type %d\n", __func__, alarm->type);
-	spin_lock_irqsave(&alarm_slock, flags);
-	if (alarm_enabled & alarm_type_mask) {
-		__pm_wakeup_event(&alarm_wake_lock, 5000); /* 5secs */
-		alarm_enabled &= ~alarm_type_mask;
-		alarm_pending |= alarm_type_mask;
-		wake_up(&alarm_wait_queue);
-	}
-	spin_unlock_irqrestore(&alarm_slock, flags);
-}
-
-
-static enum hrtimer_restart devalarm_hrthandler(struct hrtimer *hrt)
-{
-	struct devalarm *devalrm = container_of(hrt, struct devalarm, u.hrt);
-
-	devalarm_triggered(devalrm);
-	return HRTIMER_NORESTART;
-}
-
-static enum alarmtimer_restart devalarm_alarmhandler(struct alarm *alrm,
-							ktime_t now)
-{
-	struct devalarm *devalrm = container_of(alrm, struct devalarm, u.alrm);
-
-	devalarm_triggered(devalrm);
-	return ALARMTIMER_NORESTART;
-}
-
-
-static const struct file_operations alarm_fops = {
-	.owner = THIS_MODULE,
-	.unlocked_ioctl = alarm_ioctl,
-	.open = alarm_open,
-	.release = alarm_release,
-#ifdef CONFIG_COMPAT
-	.compat_ioctl = alarm_compat_ioctl,
-#endif
-};
-
-static struct miscdevice alarm_device = {
-	.minor = MISC_DYNAMIC_MINOR,
-	.name = "alarm",
-	.fops = &alarm_fops,
-};
-
-static int __init alarm_dev_init(void)
-{
-	int err;
-	int i;
-
-	err = misc_register(&alarm_device);
-	if (err)
-		return err;
-
-	alarm_init(&alarms[ANDROID_ALARM_RTC_WAKEUP].u.alrm,
-			ALARM_REALTIME, devalarm_alarmhandler);
-	hrtimer_init(&alarms[ANDROID_ALARM_RTC].u.hrt,
-			CLOCK_REALTIME, HRTIMER_MODE_ABS);
-	alarm_init(&alarms[ANDROID_ALARM_ELAPSED_REALTIME_WAKEUP].u.alrm,
-			ALARM_BOOTTIME, devalarm_alarmhandler);
-	hrtimer_init(&alarms[ANDROID_ALARM_ELAPSED_REALTIME].u.hrt,
-			CLOCK_BOOTTIME, HRTIMER_MODE_ABS);
-	hrtimer_init(&alarms[ANDROID_ALARM_SYSTEMTIME].u.hrt,
-			CLOCK_MONOTONIC, HRTIMER_MODE_ABS);
-
-	for (i = 0; i < ANDROID_ALARM_TYPE_COUNT; i++) {
-		alarms[i].type = i;
-		if (!is_wakeup(i))
-			alarms[i].u.hrt.function = devalarm_hrthandler;
-	}
-
-	wakeup_source_init(&alarm_wake_lock, "alarm");
-	return 0;
-}
-
-static void  __exit alarm_dev_exit(void)
-{
-	misc_deregister(&alarm_device);
-	wakeup_source_trash(&alarm_wake_lock);
-}
-
-module_init(alarm_dev_init);
-module_exit(alarm_dev_exit);
-
diff --git a/drivers/staging/android/android_alarm.h b/drivers/staging/android/android_alarm.h
deleted file mode 100644
index 495b20cf3bf6..000000000000
--- a/drivers/staging/android/android_alarm.h
+++ /dev/null
@@ -1,41 +0,0 @@
-/* include/linux/android_alarm.h
- *
- * Copyright (C) 2006-2007 Google, Inc.
- *
- * This software is licensed under the terms of the GNU General Public
- * License version 2, as published by the Free Software Foundation, and
- * may be copied, distributed, and modified under those terms.
- *
- * 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.
- *
- */
-
-#ifndef _LINUX_ANDROID_ALARM_H
-#define _LINUX_ANDROID_ALARM_H
-
-#include <linux/compat.h>
-#include <linux/ioctl.h>
-
-#include "uapi/android_alarm.h"
-
-#ifdef CONFIG_COMPAT
-#define ANDROID_ALARM_SET_COMPAT(type)		ALARM_IOW(2, type, \
-							struct compat_timespec)
-#define ANDROID_ALARM_SET_AND_WAIT_COMPAT(type)	ALARM_IOW(3, type, \
-							struct compat_timespec)
-#define ANDROID_ALARM_GET_TIME_COMPAT(type)	ALARM_IOW(4, type, \
-							struct compat_timespec)
-#define ANDROID_ALARM_SET_RTC_COMPAT		_IOW('a', 5, \
-							struct compat_timespec)
-#define ANDROID_ALARM_IOCTL_NR(cmd)		(_IOC_NR(cmd) & ((1<<4)-1))
-#define ANDROID_ALARM_COMPAT_TO_NORM(cmd)  \
-				ALARM_IOW(ANDROID_ALARM_IOCTL_NR(cmd), \
-					ANDROID_ALARM_IOCTL_TO_TYPE(cmd), \
-					struct timespec)
-
-#endif
-
-#endif
diff --git a/drivers/staging/android/logger.c b/drivers/staging/android/logger.c
deleted file mode 100644
index 5f563acd34cc..000000000000
--- a/drivers/staging/android/logger.c
+++ /dev/null
@@ -1,854 +0,0 @@
-/*
- * drivers/misc/logger.c
- *
- * A Logging Subsystem
- *
- * Copyright (C) 2007-2008 Google, Inc.
- *
- * Robert Love <rlove@google.com>
- *
- * This software is licensed under the terms of the GNU General Public
- * License version 2, as published by the Free Software Foundation, and
- * may be copied, distributed, and modified under those terms.
- *
- * 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.
- */
-
-#define pr_fmt(fmt) "logger: " fmt
-
-#include <linux/sched.h>
-#include <linux/module.h>
-#include <linux/fs.h>
-#include <linux/miscdevice.h>
-#include <linux/uaccess.h>
-#include <linux/poll.h>
-#include <linux/slab.h>
-#include <linux/time.h>
-#include <linux/vmalloc.h>
-#include <linux/aio.h>
-#include "logger.h"
-
-#include <asm/ioctls.h>
-
-/**
- * struct logger_log - represents a specific log, such as 'main' or 'radio'
- * @buffer:	The actual ring buffer
- * @misc:	The "misc" device representing the log
- * @wq:		The wait queue for @readers
- * @readers:	This log's readers
- * @mutex:	The mutex that protects the @buffer
- * @w_off:	The current write head offset
- * @head:	The head, or location that readers start reading at.
- * @size:	The size of the log
- * @logs:	The list of log channels
- *
- * This structure lives from module insertion until module removal, so it does
- * not need additional reference counting. The structure is protected by the
- * mutex 'mutex'.
- */
-struct logger_log {
-	unsigned char		*buffer;
-	struct miscdevice	misc;
-	wait_queue_head_t	wq;
-	struct list_head	readers;
-	struct mutex		mutex;
-	size_t			w_off;
-	size_t			head;
-	size_t			size;
-	struct list_head	logs;
-};
-
-static LIST_HEAD(log_list);
-
-
-/**
- * struct logger_reader - a logging device open for reading
- * @log:	The associated log
- * @list:	The associated entry in @logger_log's list
- * @r_off:	The current read head offset.
- * @r_all:	Reader can read all entries
- * @r_ver:	Reader ABI version
- *
- * This object lives from open to release, so we don't need additional
- * reference counting. The structure is protected by log->mutex.
- */
-struct logger_reader {
-	struct logger_log	*log;
-	struct list_head	list;
-	size_t			r_off;
-	bool			r_all;
-	int			r_ver;
-};
-
-/* logger_offset - returns index 'n' into the log via (optimized) modulus */
-static size_t logger_offset(struct logger_log *log, size_t n)
-{
-	return n & (log->size - 1);
-}
-
-
-/*
- * file_get_log - Given a file structure, return the associated log
- *
- * This isn't aesthetic. We have several goals:
- *
- *	1) Need to quickly obtain the associated log during an I/O operation
- *	2) Readers need to maintain state (logger_reader)
- *	3) Writers need to be very fast (open() should be a near no-op)
- *
- * In the reader case, we can trivially go file->logger_reader->logger_log.
- * For a writer, we don't want to maintain a logger_reader, so we just go
- * file->logger_log. Thus what file->private_data points at depends on whether
- * or not the file was opened for reading. This function hides that dirtiness.
- */
-static inline struct logger_log *file_get_log(struct file *file)
-{
-	if (file->f_mode & FMODE_READ) {
-		struct logger_reader *reader = file->private_data;
-
-		return reader->log;
-	} else
-		return file->private_data;
-}
-
-/*
- * get_entry_header - returns a pointer to the logger_entry header within
- * 'log' starting at offset 'off'. A temporary logger_entry 'scratch' must
- * be provided. Typically the return value will be a pointer within
- * 'logger->buf'.  However, a pointer to 'scratch' may be returned if
- * the log entry spans the end and beginning of the circular buffer.
- */
-static struct logger_entry *get_entry_header(struct logger_log *log,
-		size_t off, struct logger_entry *scratch)
-{
-	size_t len = min(sizeof(struct logger_entry), log->size - off);
-
-	if (len != sizeof(struct logger_entry)) {
-		memcpy(((void *) scratch), log->buffer + off, len);
-		memcpy(((void *) scratch) + len, log->buffer,
-			sizeof(struct logger_entry) - len);
-		return scratch;
-	}
-
-	return (struct logger_entry *) (log->buffer + off);
-}
-
-/*
- * get_entry_msg_len - Grabs the length of the message of the entry
- * starting from from 'off'.
- *
- * An entry length is 2 bytes (16 bits) in host endian order.
- * In the log, the length does not include the size of the log entry structure.
- * This function returns the size including the log entry structure.
- *
- * Caller needs to hold log->mutex.
- */
-static __u32 get_entry_msg_len(struct logger_log *log, size_t off)
-{
-	struct logger_entry scratch;
-	struct logger_entry *entry;
-
-	entry = get_entry_header(log, off, &scratch);
-	return entry->len;
-}
-
-static size_t get_user_hdr_len(int ver)
-{
-	if (ver < 2)
-		return sizeof(struct user_logger_entry_compat);
-	else
-		return sizeof(struct logger_entry);
-}
-
-static ssize_t copy_header_to_user(int ver, struct logger_entry *entry,
-					 char __user *buf)
-{
-	void *hdr;
-	size_t hdr_len;
-	struct user_logger_entry_compat v1;
-
-	if (ver < 2) {
-		v1.len      = entry->len;
-		v1.__pad    = 0;
-		v1.pid      = entry->pid;
-		v1.tid      = entry->tid;
-		v1.sec      = entry->sec;
-		v1.nsec     = entry->nsec;
-		hdr         = &v1;
-		hdr_len     = sizeof(struct user_logger_entry_compat);
-	} else {
-		hdr         = entry;
-		hdr_len     = sizeof(struct logger_entry);
-	}
-
-	return copy_to_user(buf, hdr, hdr_len);
-}
-
-/*
- * do_read_log_to_user - reads exactly 'count' bytes from 'log' into the
- * user-space buffer 'buf'. Returns 'count' on success.
- *
- * Caller must hold log->mutex.
- */
-static ssize_t do_read_log_to_user(struct logger_log *log,
-				   struct logger_reader *reader,
-				   char __user *buf,
-				   size_t count)
-{
-	struct logger_entry scratch;
-	struct logger_entry *entry;
-	size_t len;
-	size_t msg_start;
-
-	/*
-	 * First, copy the header to userspace, using the version of
-	 * the header requested
-	 */
-	entry = get_entry_header(log, reader->r_off, &scratch);
-	if (copy_header_to_user(reader->r_ver, entry, buf))
-		return -EFAULT;
-
-	count -= get_user_hdr_len(reader->r_ver);
-	buf += get_user_hdr_len(reader->r_ver);
-	msg_start = logger_offset(log,
-		reader->r_off + sizeof(struct logger_entry));
-
-	/*
-	 * We read from the msg in two disjoint operations. First, we read from
-	 * the current msg head offset up to 'count' bytes or to the end of
-	 * the log, whichever comes first.
-	 */
-	len = min(count, log->size - msg_start);
-	if (copy_to_user(buf, log->buffer + msg_start, len))
-		return -EFAULT;
-
-	/*
-	 * Second, we read any remaining bytes, starting back at the head of
-	 * the log.
-	 */
-	if (count != len)
-		if (copy_to_user(buf + len, log->buffer, count - len))
-			return -EFAULT;
-
-	reader->r_off = logger_offset(log, reader->r_off +
-		sizeof(struct logger_entry) + count);
-
-	return count + get_user_hdr_len(reader->r_ver);
-}
-
-/*
- * get_next_entry_by_uid - Starting at 'off', returns an offset into
- * 'log->buffer' which contains the first entry readable by 'euid'
- */
-static size_t get_next_entry_by_uid(struct logger_log *log,
-		size_t off, kuid_t euid)
-{
-	while (off != log->w_off) {
-		struct logger_entry *entry;
-		struct logger_entry scratch;
-		size_t next_len;
-
-		entry = get_entry_header(log, off, &scratch);
-
-		if (uid_eq(entry->euid, euid))
-			return off;
-
-		next_len = sizeof(struct logger_entry) + entry->len;
-		off = logger_offset(log, off + next_len);
-	}
-
-	return off;
-}
-
-/*
- * logger_read - our log's read() method
- *
- * Behavior:
- *
- *	- O_NONBLOCK works
- *	- If there are no log entries to read, blocks until log is written to
- *	- Atomically reads exactly one log entry
- *
- * Will set errno to EINVAL if read
- * buffer is insufficient to hold next entry.
- */
-static ssize_t logger_read(struct file *file, char __user *buf,
-			   size_t count, loff_t *pos)
-{
-	struct logger_reader *reader = file->private_data;
-	struct logger_log *log = reader->log;
-	ssize_t ret;
-	DEFINE_WAIT(wait);
-
-start:
-	while (1) {
-		mutex_lock(&log->mutex);
-
-		prepare_to_wait(&log->wq, &wait, TASK_INTERRUPTIBLE);
-
-		ret = (log->w_off == reader->r_off);
-		mutex_unlock(&log->mutex);
-		if (!ret)
-			break;
-
-		if (file->f_flags & O_NONBLOCK) {
-			ret = -EAGAIN;
-			break;
-		}
-
-		if (signal_pending(current)) {
-			ret = -EINTR;
-			break;
-		}
-
-		schedule();
-	}
-
-	finish_wait(&log->wq, &wait);
-	if (ret)
-		return ret;
-
-	mutex_lock(&log->mutex);
-
-	if (!reader->r_all)
-		reader->r_off = get_next_entry_by_uid(log,
-			reader->r_off, current_euid());
-
-	/* is there still something to read or did we race? */
-	if (unlikely(log->w_off == reader->r_off)) {
-		mutex_unlock(&log->mutex);
-		goto start;
-	}
-
-	/* get the size of the next entry */
-	ret = get_user_hdr_len(reader->r_ver) +
-		get_entry_msg_len(log, reader->r_off);
-	if (count < ret) {
-		ret = -EINVAL;
-		goto out;
-	}
-
-	/* get exactly one entry from the log */
-	ret = do_read_log_to_user(log, reader, buf, ret);
-
-out:
-	mutex_unlock(&log->mutex);
-
-	return ret;
-}
-
-/*
- * get_next_entry - return the offset of the first valid entry at least 'len'
- * bytes after 'off'.
- *
- * Caller must hold log->mutex.
- */
-static size_t get_next_entry(struct logger_log *log, size_t off, size_t len)
-{
-	size_t count = 0;
-
-	do {
-		size_t nr = sizeof(struct logger_entry) +
-			get_entry_msg_len(log, off);
-		off = logger_offset(log, off + nr);
-		count += nr;
-	} while (count < len);
-
-	return off;
-}
-
-/*
- * is_between - is a < c < b, accounting for wrapping of a, b, and c
- *    positions in the buffer
- *
- * That is, if a<b, check for c between a and b
- * and if a>b, check for c outside (not between) a and b
- *
- * |------- a xxxxxxxx b --------|
- *               c^
- *
- * |xxxxx b --------- a xxxxxxxxx|
- *    c^
- *  or                    c^
- */
-static inline int is_between(size_t a, size_t b, size_t c)
-{
-	if (a < b) {
-		/* is c between a and b? */
-		if (a < c && c <= b)
-			return 1;
-	} else {
-		/* is c outside of b through a? */
-		if (c <= b || a < c)
-			return 1;
-	}
-
-	return 0;
-}
-
-/*
- * fix_up_readers - walk the list of all readers and "fix up" any who were
- * lapped by the writer; also do the same for the default "start head".
- * We do this by "pulling forward" the readers and start head to the first
- * entry after the new write head.
- *
- * The caller needs to hold log->mutex.
- */
-static void fix_up_readers(struct logger_log *log, size_t len)
-{
-	size_t old = log->w_off;
-	size_t new = logger_offset(log, old + len);
-	struct logger_reader *reader;
-
-	if (is_between(old, new, log->head))
-		log->head = get_next_entry(log, log->head, len);
-
-	list_for_each_entry(reader, &log->readers, list)
-		if (is_between(old, new, reader->r_off))
-			reader->r_off = get_next_entry(log, reader->r_off, len);
-}
-
-/*
- * do_write_log - writes 'len' bytes from 'buf' to 'log'
- *
- * The caller needs to hold log->mutex.
- */
-static void do_write_log(struct logger_log *log, const void *buf, size_t count)
-{
-	size_t len;
-
-	len = min(count, log->size - log->w_off);
-	memcpy(log->buffer + log->w_off, buf, len);
-
-	if (count != len)
-		memcpy(log->buffer, buf + len, count - len);
-
-	log->w_off = logger_offset(log, log->w_off + count);
-
-}
-
-/*
- * do_write_log_user - writes 'len' bytes from the user-space buffer 'buf' to
- * the log 'log'
- *
- * The caller needs to hold log->mutex.
- *
- * Returns 'count' on success, negative error code on failure.
- */
-static ssize_t do_write_log_from_user(struct logger_log *log,
-				      const void __user *buf, size_t count)
-{
-	size_t len;
-
-	len = min(count, log->size - log->w_off);
-	if (len && copy_from_user(log->buffer + log->w_off, buf, len))
-		return -EFAULT;
-
-	if (count != len)
-		if (copy_from_user(log->buffer, buf + len, count - len))
-			/*
-			 * Note that by not updating w_off, this abandons the
-			 * portion of the new entry that *was* successfully
-			 * copied, just above.  This is intentional to avoid
-			 * message corruption from missing fragments.
-			 */
-			return -EFAULT;
-
-	log->w_off = logger_offset(log, log->w_off + count);
-
-	return count;
-}
-
-/*
- * logger_aio_write - our write method, implementing support for write(),
- * writev(), and aio_write(). Writes are our fast path, and we try to optimize
- * them above all else.
- */
-static ssize_t logger_aio_write(struct kiocb *iocb, const struct iovec *iov,
-			 unsigned long nr_segs, loff_t ppos)
-{
-	struct logger_log *log = file_get_log(iocb->ki_filp);
-	size_t orig;
-	struct logger_entry header;
-	struct timespec now;
-	ssize_t ret = 0;
-
-	now = current_kernel_time();
-
-	header.pid = current->tgid;
-	header.tid = current->pid;
-	header.sec = now.tv_sec;
-	header.nsec = now.tv_nsec;
-	header.euid = current_euid();
-	header.len = min_t(size_t, iocb->ki_left, LOGGER_ENTRY_MAX_PAYLOAD);
-	header.hdr_size = sizeof(struct logger_entry);
-
-	/* null writes succeed, return zero */
-	if (unlikely(!header.len))
-		return 0;
-
-	mutex_lock(&log->mutex);
-
-	orig = log->w_off;
-
-	/*
-	 * Fix up any readers, pulling them forward to the first readable
-	 * entry after (what will be) the new write offset. We do this now
-	 * because if we partially fail, we can end up with clobbered log
-	 * entries that encroach on readable buffer.
-	 */
-	fix_up_readers(log, sizeof(struct logger_entry) + header.len);
-
-	do_write_log(log, &header, sizeof(struct logger_entry));
-
-	while (nr_segs-- > 0) {
-		size_t len;
-		ssize_t nr;
-
-		/* figure out how much of this vector we can keep */
-		len = min_t(size_t, iov->iov_len, header.len - ret);
-
-		/* write out this segment's payload */
-		nr = do_write_log_from_user(log, iov->iov_base, len);
-		if (unlikely(nr < 0)) {
-			log->w_off = orig;
-			mutex_unlock(&log->mutex);
-			return nr;
-		}
-
-		iov++;
-		ret += nr;
-	}
-
-	mutex_unlock(&log->mutex);
-
-	/* wake up any blocked readers */
-	wake_up_interruptible(&log->wq);
-
-	return ret;
-}
-
-static struct logger_log *get_log_from_minor(int minor)
-{
-	struct logger_log *log;
-
-	list_for_each_entry(log, &log_list, logs)
-		if (log->misc.minor == minor)
-			return log;
-	return NULL;
-}
-
-/*
- * logger_open - the log's open() file operation
- *
- * Note how near a no-op this is in the write-only case. Keep it that way!
- */
-static int logger_open(struct inode *inode, struct file *file)
-{
-	struct logger_log *log;
-	int ret;
-
-	ret = nonseekable_open(inode, file);
-	if (ret)
-		return ret;
-
-	log = get_log_from_minor(MINOR(inode->i_rdev));
-	if (!log)
-		return -ENODEV;
-
-	if (file->f_mode & FMODE_READ) {
-		struct logger_reader *reader;
-
-		reader = kmalloc(sizeof(struct logger_reader), GFP_KERNEL);
-		if (!reader)
-			return -ENOMEM;
-
-		reader->log = log;
-		reader->r_ver = 1;
-		reader->r_all = in_egroup_p(inode->i_gid) ||
-			capable(CAP_SYSLOG);
-
-		INIT_LIST_HEAD(&reader->list);
-
-		mutex_lock(&log->mutex);
-		reader->r_off = log->head;
-		list_add_tail(&reader->list, &log->readers);
-		mutex_unlock(&log->mutex);
-
-		file->private_data = reader;
-	} else
-		file->private_data = log;
-
-	return 0;
-}
-
-/*
- * logger_release - the log's release file operation
- *
- * Note this is a total no-op in the write-only case. Keep it that way!
- */
-static int logger_release(struct inode *ignored, struct file *file)
-{
-	if (file->f_mode & FMODE_READ) {
-		struct logger_reader *reader = file->private_data;
-		struct logger_log *log = reader->log;
-
-		mutex_lock(&log->mutex);
-		list_del(&reader->list);
-		mutex_unlock(&log->mutex);
-
-		kfree(reader);
-	}
-
-	return 0;
-}
-
-/*
- * logger_poll - the log's poll file operation, for poll/select/epoll
- *
- * Note we always return POLLOUT, because you can always write() to the log.
- * Note also that, strictly speaking, a return value of POLLIN does not
- * guarantee that the log is readable without blocking, as there is a small
- * chance that the writer can lap the reader in the interim between poll()
- * returning and the read() request.
- */
-static unsigned int logger_poll(struct file *file, poll_table *wait)
-{
-	struct logger_reader *reader;
-	struct logger_log *log;
-	unsigned int ret = POLLOUT | POLLWRNORM;
-
-	if (!(file->f_mode & FMODE_READ))
-		return ret;
-
-	reader = file->private_data;
-	log = reader->log;
-
-	poll_wait(file, &log->wq, wait);
-
-	mutex_lock(&log->mutex);
-	if (!reader->r_all)
-		reader->r_off = get_next_entry_by_uid(log,
-			reader->r_off, current_euid());
-
-	if (log->w_off != reader->r_off)
-		ret |= POLLIN | POLLRDNORM;
-	mutex_unlock(&log->mutex);
-
-	return ret;
-}
-
-static long logger_set_version(struct logger_reader *reader, void __user *arg)
-{
-	int version;
-
-	if (copy_from_user(&version, arg, sizeof(int)))
-		return -EFAULT;
-
-	if ((version < 1) || (version > 2))
-		return -EINVAL;
-
-	reader->r_ver = version;
-	return 0;
-}
-
-static long logger_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
-{
-	struct logger_log *log = file_get_log(file);
-	struct logger_reader *reader;
-	long ret = -EINVAL;
-	void __user *argp = (void __user *) arg;
-
-	mutex_lock(&log->mutex);
-
-	switch (cmd) {
-	case LOGGER_GET_LOG_BUF_SIZE:
-		ret = log->size;
-		break;
-	case LOGGER_GET_LOG_LEN:
-		if (!(file->f_mode & FMODE_READ)) {
-			ret = -EBADF;
-			break;
-		}
-		reader = file->private_data;
-		if (log->w_off >= reader->r_off)
-			ret = log->w_off - reader->r_off;
-		else
-			ret = (log->size - reader->r_off) + log->w_off;
-		break;
-	case LOGGER_GET_NEXT_ENTRY_LEN:
-		if (!(file->f_mode & FMODE_READ)) {
-			ret = -EBADF;
-			break;
-		}
-		reader = file->private_data;
-
-		if (!reader->r_all)
-			reader->r_off = get_next_entry_by_uid(log,
-				reader->r_off, current_euid());
-
-		if (log->w_off != reader->r_off)
-			ret = get_user_hdr_len(reader->r_ver) +
-				get_entry_msg_len(log, reader->r_off);
-		else
-			ret = 0;
-		break;
-	case LOGGER_FLUSH_LOG:
-		if (!(file->f_mode & FMODE_WRITE)) {
-			ret = -EBADF;
-			break;
-		}
-		if (!(in_egroup_p(file->f_dentry->d_inode->i_gid) ||
-				capable(CAP_SYSLOG))) {
-			ret = -EPERM;
-			break;
-		}
-		list_for_each_entry(reader, &log->readers, list)
-			reader->r_off = log->w_off;
-		log->head = log->w_off;
-		ret = 0;
-		break;
-	case LOGGER_GET_VERSION:
-		if (!(file->f_mode & FMODE_READ)) {
-			ret = -EBADF;
-			break;
-		}
-		reader = file->private_data;
-		ret = reader->r_ver;
-		break;
-	case LOGGER_SET_VERSION:
-		if (!(file->f_mode & FMODE_READ)) {
-			ret = -EBADF;
-			break;
-		}
-		reader = file->private_data;
-		ret = logger_set_version(reader, argp);
-		break;
-	}
-
-	mutex_unlock(&log->mutex);
-
-	return ret;
-}
-
-static const struct file_operations logger_fops = {
-	.owner = THIS_MODULE,
-	.read = logger_read,
-	.aio_write = logger_aio_write,
-	.poll = logger_poll,
-	.unlocked_ioctl = logger_ioctl,
-	.compat_ioctl = logger_ioctl,
-	.open = logger_open,
-	.release = logger_release,
-};
-
-/*
- * Log size must must be a power of two, and greater than
- * (LOGGER_ENTRY_MAX_PAYLOAD + sizeof(struct logger_entry)).
- */
-static int __init create_log(char *log_name, int size)
-{
-	int ret = 0;
-	struct logger_log *log;
-	unsigned char *buffer;
-
-	buffer = vmalloc(size);
-	if (buffer == NULL)
-		return -ENOMEM;
-
-	log = kzalloc(sizeof(struct logger_log), GFP_KERNEL);
-	if (log == NULL) {
-		ret = -ENOMEM;
-		goto out_free_buffer;
-	}
-	log->buffer = buffer;
-
-	log->misc.minor = MISC_DYNAMIC_MINOR;
-	log->misc.name = kstrdup(log_name, GFP_KERNEL);
-	if (log->misc.name == NULL) {
-		ret = -ENOMEM;
-		goto out_free_log;
-	}
-
-	log->misc.fops = &logger_fops;
-	log->misc.parent = NULL;
-
-	init_waitqueue_head(&log->wq);
-	INIT_LIST_HEAD(&log->readers);
-	mutex_init(&log->mutex);
-	log->w_off = 0;
-	log->head = 0;
-	log->size = size;
-
-	INIT_LIST_HEAD(&log->logs);
-	list_add_tail(&log->logs, &log_list);
-
-	/* finally, initialize the misc device for this log */
-	ret = misc_register(&log->misc);
-	if (unlikely(ret)) {
-		pr_err("failed to register misc device for log '%s'!\n",
-				log->misc.name);
-		goto out_free_log;
-	}
-
-	pr_info("created %luK log '%s'\n",
-		(unsigned long) log->size >> 10, log->misc.name);
-
-	return 0;
-
-out_free_log:
-	kfree(log);
-
-out_free_buffer:
-	vfree(buffer);
-	return ret;
-}
-
-static int __init logger_init(void)
-{
-	int ret;
-
-	ret = create_log(LOGGER_LOG_MAIN, 256*1024);
-	if (unlikely(ret))
-		goto out;
-
-	ret = create_log(LOGGER_LOG_EVENTS, 256*1024);
-	if (unlikely(ret))
-		goto out;
-
-	ret = create_log(LOGGER_LOG_RADIO, 256*1024);
-	if (unlikely(ret))
-		goto out;
-
-	ret = create_log(LOGGER_LOG_SYSTEM, 256*1024);
-	if (unlikely(ret))
-		goto out;
-
-out:
-	return ret;
-}
-
-static void __exit logger_exit(void)
-{
-	struct logger_log *current_log, *next_log;
-
-	list_for_each_entry_safe(current_log, next_log, &log_list, logs) {
-		/* we have to delete all the entry inside log_list */
-		misc_deregister(&current_log->misc);
-		vfree(current_log->buffer);
-		kfree(current_log->misc.name);
-		list_del(&current_log->logs);
-		kfree(current_log);
-	}
-}
-
-
-device_initcall(logger_init);
-module_exit(logger_exit);
-
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Robert Love, <rlove@google.com>");
-MODULE_DESCRIPTION("Android Logger");
diff --git a/drivers/staging/android/logger.h b/drivers/staging/android/logger.h
deleted file mode 100644
index 70af7d805dff..000000000000
--- a/drivers/staging/android/logger.h
+++ /dev/null
@@ -1,89 +0,0 @@
-/* include/linux/logger.h
- *
- * Copyright (C) 2007-2008 Google, Inc.
- * Author: Robert Love <rlove@android.com>
- *
- * This software is licensed under the terms of the GNU General Public
- * License version 2, as published by the Free Software Foundation, and
- * may be copied, distributed, and modified under those terms.
- *
- * 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.
- *
- */
-
-#ifndef _LINUX_LOGGER_H
-#define _LINUX_LOGGER_H
-
-#include <linux/types.h>
-#include <linux/ioctl.h>
-
-/**
- * struct user_logger_entry_compat - defines a single entry that is given to a logger
- * @len:	The length of the payload
- * @__pad:	Two bytes of padding that appear to be required
- * @pid:	The generating process' process ID
- * @tid:	The generating process' thread ID
- * @sec:	The number of seconds that have elapsed since the Epoch
- * @nsec:	The number of nanoseconds that have elapsed since @sec
- * @msg:	The message that is to be logged
- *
- * The userspace structure for version 1 of the logger_entry ABI.
- * This structure is returned to userspace unless the caller requests
- * an upgrade to a newer ABI version.
- */
-struct user_logger_entry_compat {
-	__u16		len;
-	__u16		__pad;
-	__s32		pid;
-	__s32		tid;
-	__s32		sec;
-	__s32		nsec;
-	char		msg[0];
-};
-
-/**
- * struct logger_entry - defines a single entry that is given to a logger
- * @len:	The length of the payload
- * @hdr_size:	sizeof(struct logger_entry_v2)
- * @pid:	The generating process' process ID
- * @tid:	The generating process' thread ID
- * @sec:	The number of seconds that have elapsed since the Epoch
- * @nsec:	The number of nanoseconds that have elapsed since @sec
- * @euid:	Effective UID of logger
- * @msg:	The message that is to be logged
- *
- * The structure for version 2 of the logger_entry ABI.
- * This structure is returned to userspace if ioctl(LOGGER_SET_VERSION)
- * is called with version >= 2
- */
-struct logger_entry {
-	__u16		len;
-	__u16		hdr_size;
-	__s32		pid;
-	__s32		tid;
-	__s32		sec;
-	__s32		nsec;
-	kuid_t		euid;
-	char		msg[0];
-};
-
-#define LOGGER_LOG_RADIO	"log_radio"	/* radio-related messages */
-#define LOGGER_LOG_EVENTS	"log_events"	/* system/hardware events */
-#define LOGGER_LOG_SYSTEM	"log_system"	/* system/framework messages */
-#define LOGGER_LOG_MAIN		"log_main"	/* everything else */
-
-#define LOGGER_ENTRY_MAX_PAYLOAD	4076
-
-#define __LOGGERIO	0xAE
-
-#define LOGGER_GET_LOG_BUF_SIZE		_IO(__LOGGERIO, 1) /* size of log */
-#define LOGGER_GET_LOG_LEN		_IO(__LOGGERIO, 2) /* used log len */
-#define LOGGER_GET_NEXT_ENTRY_LEN	_IO(__LOGGERIO, 3) /* next entry len */
-#define LOGGER_FLUSH_LOG		_IO(__LOGGERIO, 4) /* flush log */
-#define LOGGER_GET_VERSION		_IO(__LOGGERIO, 5) /* abi version */
-#define LOGGER_SET_VERSION		_IO(__LOGGERIO, 6) /* abi version */
-
-#endif /* _LINUX_LOGGER_H */
diff --git a/drivers/staging/android/uapi/android_alarm.h b/drivers/staging/android/uapi/android_alarm.h
deleted file mode 100644
index aa013f6f5f3a..000000000000
--- a/drivers/staging/android/uapi/android_alarm.h
+++ /dev/null
@@ -1,62 +0,0 @@
-/* drivers/staging/android/uapi/android_alarm.h
- *
- * Copyright (C) 2006-2007 Google, Inc.
- *
- * This software is licensed under the terms of the GNU General Public
- * License version 2, as published by the Free Software Foundation, and
- * may be copied, distributed, and modified under those terms.
- *
- * 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.
- *
- */
-
-#ifndef _UAPI_LINUX_ANDROID_ALARM_H
-#define _UAPI_LINUX_ANDROID_ALARM_H
-
-#include <linux/ioctl.h>
-#include <linux/time.h>
-
-enum android_alarm_type {
-	/* return code bit numbers or set alarm arg */
-	ANDROID_ALARM_RTC_WAKEUP,
-	ANDROID_ALARM_RTC,
-	ANDROID_ALARM_ELAPSED_REALTIME_WAKEUP,
-	ANDROID_ALARM_ELAPSED_REALTIME,
-	ANDROID_ALARM_SYSTEMTIME,
-
-	ANDROID_ALARM_TYPE_COUNT,
-
-	/* return code bit numbers */
-	/* ANDROID_ALARM_TIME_CHANGE = 16 */
-};
-
-enum android_alarm_return_flags {
-	ANDROID_ALARM_RTC_WAKEUP_MASK = 1U << ANDROID_ALARM_RTC_WAKEUP,
-	ANDROID_ALARM_RTC_MASK = 1U << ANDROID_ALARM_RTC,
-	ANDROID_ALARM_ELAPSED_REALTIME_WAKEUP_MASK =
-				1U << ANDROID_ALARM_ELAPSED_REALTIME_WAKEUP,
-	ANDROID_ALARM_ELAPSED_REALTIME_MASK =
-				1U << ANDROID_ALARM_ELAPSED_REALTIME,
-	ANDROID_ALARM_SYSTEMTIME_MASK = 1U << ANDROID_ALARM_SYSTEMTIME,
-	ANDROID_ALARM_TIME_CHANGE_MASK = 1U << 16
-};
-
-/* Disable alarm */
-#define ANDROID_ALARM_CLEAR(type)           _IO('a', 0 | ((type) << 4))
-
-/* Ack last alarm and wait for next */
-#define ANDROID_ALARM_WAIT                  _IO('a', 1)
-
-#define ALARM_IOW(c, type, size)            _IOW('a', (c) | ((type) << 4), size)
-/* Set alarm */
-#define ANDROID_ALARM_SET(type)             ALARM_IOW(2, type, struct timespec)
-#define ANDROID_ALARM_SET_AND_WAIT(type)    ALARM_IOW(3, type, struct timespec)
-#define ANDROID_ALARM_GET_TIME(type)        ALARM_IOW(4, type, struct timespec)
-#define ANDROID_ALARM_SET_RTC               _IOW('a', 5, struct timespec)
-#define ANDROID_ALARM_BASE_CMD(cmd)         (cmd & ~(_IOC(0, 0, 0xf0, 0)))
-#define ANDROID_ALARM_IOCTL_TO_TYPE(cmd)    (_IOC_NR(cmd) >> 4)
-
-#endif
diff --git a/drivers/usb/gadget/android.c b/drivers/usb/gadget/android.c
index 83b1240d9b19..61c5e582bf47 100644
--- a/drivers/usb/gadget/android.c
+++ b/drivers/usb/gadget/android.c
@@ -32,6 +32,7 @@
 
 #include "f_fs.c"
 #include "f_audio_source.c"
+#include "f_midi.c"
 #include "f_mass_storage.c"
 #include "f_mtp.c"
 #include "f_accessory.c"
@@ -51,6 +52,12 @@ static const char longname[] = "Gadget Android";
 #define VENDOR_ID		0x18D1
 #define PRODUCT_ID		0x0001
 
+/* f_midi configuration */
+#define MIDI_INPUT_PORTS    1
+#define MIDI_OUTPUT_PORTS   1
+#define MIDI_BUFFER_SIZE    256
+#define MIDI_QUEUE_LENGTH   32
+
 struct android_usb_function {
 	char *name;
 	void *config;
@@ -933,6 +940,60 @@ static struct android_usb_function audio_source_function = {
 	.attributes	= audio_source_function_attributes,
 };
 
+static int midi_function_init(struct android_usb_function *f,
+					struct usb_composite_dev *cdev)
+{
+	struct midi_alsa_config *config;
+
+	config = kzalloc(sizeof(struct midi_alsa_config), GFP_KERNEL);
+	f->config = config;
+	if (!config)
+		return -ENOMEM;
+	config->card = -1;
+	config->device = -1;
+	return 0;
+}
+
+static void midi_function_cleanup(struct android_usb_function *f)
+{
+	kfree(f->config);
+}
+
+static int midi_function_bind_config(struct android_usb_function *f,
+						struct usb_configuration *c)
+{
+	struct midi_alsa_config *config = f->config;
+
+	return f_midi_bind_config(c, SNDRV_DEFAULT_IDX1, SNDRV_DEFAULT_STR1,
+			MIDI_INPUT_PORTS, MIDI_OUTPUT_PORTS, MIDI_BUFFER_SIZE,
+			MIDI_QUEUE_LENGTH, config);
+}
+
+static ssize_t midi_alsa_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	struct android_usb_function *f = dev_get_drvdata(dev);
+	struct midi_alsa_config *config = f->config;
+
+	/* print ALSA card and device numbers */
+	return sprintf(buf, "%d %d\n", config->card, config->device);
+}
+
+static DEVICE_ATTR(alsa, S_IRUGO, midi_alsa_show, NULL);
+
+static struct device_attribute *midi_function_attributes[] = {
+	&dev_attr_alsa,
+	NULL
+};
+
+static struct android_usb_function midi_function = {
+	.name		= "midi",
+	.init		= midi_function_init,
+	.cleanup	= midi_function_cleanup,
+	.bind_config	= midi_function_bind_config,
+	.attributes	= midi_function_attributes,
+};
+
 static struct android_usb_function *supported_functions[] = {
 	&ffs_function,
 	&acm_function,
@@ -942,10 +1003,10 @@ static struct android_usb_function *supported_functions[] = {
 	&mass_storage_function,
 	&accessory_function,
 	&audio_source_function,
+	&midi_function,
 	NULL
 };
 
-
 static int android_init_functions(struct android_usb_function **functions,
 				  struct usb_composite_dev *cdev)
 {
diff --git a/drivers/usb/gadget/f_audio_source.c b/drivers/usb/gadget/f_audio_source.c
index 21ced13c83d8..07a1a3c28f3d 100644
--- a/drivers/usb/gadget/f_audio_source.c
+++ b/drivers/usb/gadget/f_audio_source.c
@@ -34,7 +34,7 @@
 #define AUDIO_NUM_INTERFACES	2
 
 /* B.3.1  Standard AC Interface Descriptor */
-static struct usb_interface_descriptor ac_interface_desc = {
+static struct usb_interface_descriptor audio_ac_interface_desc = {
 	.bLength =		USB_DT_INTERFACE_SIZE,
 	.bDescriptorType =	USB_DT_INTERFACE,
 	.bNumEndpoints =	0,
@@ -50,7 +50,7 @@ DECLARE_UAC_AC_HEADER_DESCRIPTOR(2);
 	+ UAC_DT_INPUT_TERMINAL_SIZE + UAC_DT_OUTPUT_TERMINAL_SIZE \
 	+ UAC_DT_FEATURE_UNIT_SIZE(0))
 /* B.3.2  Class-Specific AC Interface Descriptor */
-static struct uac1_ac_header_descriptor_2 ac_header_desc = {
+static struct uac1_ac_header_descriptor_2 audio_ac_header_desc = {
 	.bLength =		UAC_DT_AC_HEADER_LENGTH,
 	.bDescriptorType =	USB_DT_CS_INTERFACE,
 	.bDescriptorSubtype =	UAC_HEADER,
@@ -64,7 +64,7 @@ static struct uac1_ac_header_descriptor_2 ac_header_desc = {
 };
 
 #define INPUT_TERMINAL_ID	1
-static struct uac_input_terminal_descriptor input_terminal_desc = {
+static struct uac_input_terminal_descriptor audio_input_terminal_desc = {
 	.bLength =		UAC_DT_INPUT_TERMINAL_SIZE,
 	.bDescriptorType =	USB_DT_CS_INTERFACE,
 	.bDescriptorSubtype =	UAC_INPUT_TERMINAL,
@@ -77,7 +77,7 @@ static struct uac_input_terminal_descriptor input_terminal_desc = {
 DECLARE_UAC_FEATURE_UNIT_DESCRIPTOR(0);
 
 #define FEATURE_UNIT_ID		2
-static struct uac_feature_unit_descriptor_0 feature_unit_desc = {
+static struct uac_feature_unit_descriptor_0 audio_feature_unit_desc = {
 	.bLength		= UAC_DT_FEATURE_UNIT_SIZE(0),
 	.bDescriptorType	= USB_DT_CS_INTERFACE,
 	.bDescriptorSubtype	= UAC_FEATURE_UNIT,
@@ -87,7 +87,7 @@ static struct uac_feature_unit_descriptor_0 feature_unit_desc = {
 };
 
 #define OUTPUT_TERMINAL_ID	3
-static struct uac1_output_terminal_descriptor output_terminal_desc = {
+static struct uac1_output_terminal_descriptor audio_output_terminal_desc = {
 	.bLength		= UAC_DT_OUTPUT_TERMINAL_SIZE,
 	.bDescriptorType	= USB_DT_CS_INTERFACE,
 	.bDescriptorSubtype	= UAC_OUTPUT_TERMINAL,
@@ -98,7 +98,7 @@ static struct uac1_output_terminal_descriptor output_terminal_desc = {
 };
 
 /* B.4.1  Standard AS Interface Descriptor */
-static struct usb_interface_descriptor as_interface_alt_0_desc = {
+static struct usb_interface_descriptor audio_as_interface_alt_0_desc = {
 	.bLength =		USB_DT_INTERFACE_SIZE,
 	.bDescriptorType =	USB_DT_INTERFACE,
 	.bAlternateSetting =	0,
@@ -107,7 +107,7 @@ static struct usb_interface_descriptor as_interface_alt_0_desc = {
 	.bInterfaceSubClass =	USB_SUBCLASS_AUDIOSTREAMING,
 };
 
-static struct usb_interface_descriptor as_interface_alt_1_desc = {
+static struct usb_interface_descriptor audio_as_interface_alt_1_desc = {
 	.bLength =		USB_DT_INTERFACE_SIZE,
 	.bDescriptorType =	USB_DT_INTERFACE,
 	.bAlternateSetting =	1,
@@ -117,7 +117,7 @@ static struct usb_interface_descriptor as_interface_alt_1_desc = {
 };
 
 /* B.4.2  Class-Specific AS Interface Descriptor */
-static struct uac1_as_header_descriptor as_header_desc = {
+static struct uac1_as_header_descriptor audio_as_header_desc = {
 	.bLength =		UAC_DT_AS_HEADER_SIZE,
 	.bDescriptorType =	USB_DT_CS_INTERFACE,
 	.bDescriptorSubtype =	UAC_AS_GENERAL,
@@ -128,7 +128,7 @@ static struct uac1_as_header_descriptor as_header_desc = {
 
 DECLARE_UAC_FORMAT_TYPE_I_DISCRETE_DESC(1);
 
-static struct uac_format_type_i_discrete_descriptor_1 as_type_i_desc = {
+static struct uac_format_type_i_discrete_descriptor_1 audio_as_type_i_desc = {
 	.bLength =		UAC_FORMAT_TYPE_I_DISCRETE_DESC_SIZE(1),
 	.bDescriptorType =	USB_DT_CS_INTERFACE,
 	.bDescriptorSubtype =	UAC_FORMAT_TYPE,
@@ -139,7 +139,7 @@ static struct uac_format_type_i_discrete_descriptor_1 as_type_i_desc = {
 };
 
 /* Standard ISO IN Endpoint Descriptor for highspeed */
-static struct usb_endpoint_descriptor hs_as_in_ep_desc  = {
+static struct usb_endpoint_descriptor audio_hs_as_in_ep_desc  = {
 	.bLength =		USB_DT_ENDPOINT_AUDIO_SIZE,
 	.bDescriptorType =	USB_DT_ENDPOINT,
 	.bEndpointAddress =	USB_DIR_IN,
@@ -150,7 +150,7 @@ static struct usb_endpoint_descriptor hs_as_in_ep_desc  = {
 };
 
 /* Standard ISO IN Endpoint Descriptor for highspeed */
-static struct usb_endpoint_descriptor fs_as_in_ep_desc  = {
+static struct usb_endpoint_descriptor audio_fs_as_in_ep_desc  = {
 	.bLength =		USB_DT_ENDPOINT_AUDIO_SIZE,
 	.bDescriptorType =	USB_DT_ENDPOINT,
 	.bEndpointAddress =	USB_DIR_IN,
@@ -161,7 +161,7 @@ static struct usb_endpoint_descriptor fs_as_in_ep_desc  = {
 };
 
 /* Class-specific AS ISO OUT Endpoint Descriptor */
-static struct uac_iso_endpoint_descriptor as_iso_in_desc = {
+static struct uac_iso_endpoint_descriptor audio_as_iso_in_desc = {
 	.bLength =		UAC_ISO_ENDPOINT_DESC_SIZE,
 	.bDescriptorType =	USB_DT_CS_ENDPOINT,
 	.bDescriptorSubtype =	UAC_EP_GENERAL,
@@ -171,40 +171,40 @@ static struct uac_iso_endpoint_descriptor as_iso_in_desc = {
 };
 
 static struct usb_descriptor_header *hs_audio_desc[] = {
-	(struct usb_descriptor_header *)&ac_interface_desc,
-	(struct usb_descriptor_header *)&ac_header_desc,
+	(struct usb_descriptor_header *)&audio_ac_interface_desc,
+	(struct usb_descriptor_header *)&audio_ac_header_desc,
 
-	(struct usb_descriptor_header *)&input_terminal_desc,
-	(struct usb_descriptor_header *)&output_terminal_desc,
-	(struct usb_descriptor_header *)&feature_unit_desc,
+	(struct usb_descriptor_header *)&audio_input_terminal_desc,
+	(struct usb_descriptor_header *)&audio_output_terminal_desc,
+	(struct usb_descriptor_header *)&audio_feature_unit_desc,
 
-	(struct usb_descriptor_header *)&as_interface_alt_0_desc,
-	(struct usb_descriptor_header *)&as_interface_alt_1_desc,
-	(struct usb_descriptor_header *)&as_header_desc,
+	(struct usb_descriptor_header *)&audio_as_interface_alt_0_desc,
+	(struct usb_descriptor_header *)&audio_as_interface_alt_1_desc,
+	(struct usb_descriptor_header *)&audio_as_header_desc,
 
-	(struct usb_descriptor_header *)&as_type_i_desc,
+	(struct usb_descriptor_header *)&audio_as_type_i_desc,
 
-	(struct usb_descriptor_header *)&hs_as_in_ep_desc,
-	(struct usb_descriptor_header *)&as_iso_in_desc,
+	(struct usb_descriptor_header *)&audio_hs_as_in_ep_desc,
+	(struct usb_descriptor_header *)&audio_as_iso_in_desc,
 	NULL,
 };
 
 static struct usb_descriptor_header *fs_audio_desc[] = {
-	(struct usb_descriptor_header *)&ac_interface_desc,
-	(struct usb_descriptor_header *)&ac_header_desc,
+	(struct usb_descriptor_header *)&audio_ac_interface_desc,
+	(struct usb_descriptor_header *)&audio_ac_header_desc,
 
-	(struct usb_descriptor_header *)&input_terminal_desc,
-	(struct usb_descriptor_header *)&output_terminal_desc,
-	(struct usb_descriptor_header *)&feature_unit_desc,
+	(struct usb_descriptor_header *)&audio_input_terminal_desc,
+	(struct usb_descriptor_header *)&audio_output_terminal_desc,
+	(struct usb_descriptor_header *)&audio_feature_unit_desc,
 
-	(struct usb_descriptor_header *)&as_interface_alt_0_desc,
-	(struct usb_descriptor_header *)&as_interface_alt_1_desc,
-	(struct usb_descriptor_header *)&as_header_desc,
+	(struct usb_descriptor_header *)&audio_as_interface_alt_0_desc,
+	(struct usb_descriptor_header *)&audio_as_interface_alt_1_desc,
+	(struct usb_descriptor_header *)&audio_as_header_desc,
 
-	(struct usb_descriptor_header *)&as_type_i_desc,
+	(struct usb_descriptor_header *)&audio_as_type_i_desc,
 
-	(struct usb_descriptor_header *)&fs_as_in_ep_desc,
-	(struct usb_descriptor_header *)&as_iso_in_desc,
+	(struct usb_descriptor_header *)&audio_fs_as_in_ep_desc,
+	(struct usb_descriptor_header *)&audio_as_iso_in_desc,
 	NULL,
 };
 
@@ -552,12 +552,12 @@ static void audio_build_desc(struct audio_dev *audio)
 	int rate;
 
 	/* Set channel numbers */
-	input_terminal_desc.bNrChannels = 2;
-	as_type_i_desc.bNrChannels = 2;
+	audio_input_terminal_desc.bNrChannels = 2;
+	audio_as_type_i_desc.bNrChannels = 2;
 
 	/* Set sample rates */
 	rate = SAMPLE_RATE;
-	sam_freq = as_type_i_desc.tSamFreq[0];
+	sam_freq = audio_as_type_i_desc.tSamFreq[0];
 	memcpy(sam_freq, &rate, 3);
 }
 
@@ -578,32 +578,32 @@ audio_bind(struct usb_configuration *c, struct usb_function *f)
 	status = usb_interface_id(c, f);
 	if (status < 0)
 		goto fail;
-	ac_interface_desc.bInterfaceNumber = status;
+	audio_ac_interface_desc.bInterfaceNumber = status;
 
 	/* AUDIO_AC_INTERFACE */
-	ac_header_desc.baInterfaceNr[0] = status;
+	audio_ac_header_desc.baInterfaceNr[0] = status;
 
 	status = usb_interface_id(c, f);
 	if (status < 0)
 		goto fail;
-	as_interface_alt_0_desc.bInterfaceNumber = status;
-	as_interface_alt_1_desc.bInterfaceNumber = status;
+	audio_as_interface_alt_0_desc.bInterfaceNumber = status;
+	audio_as_interface_alt_1_desc.bInterfaceNumber = status;
 
 	/* AUDIO_AS_INTERFACE */
-	ac_header_desc.baInterfaceNr[1] = status;
+	audio_ac_header_desc.baInterfaceNr[1] = status;
 
 	status = -ENODEV;
 
 	/* allocate our endpoint */
-	ep = usb_ep_autoconfig(cdev->gadget, &fs_as_in_ep_desc);
+	ep = usb_ep_autoconfig(cdev->gadget, &audio_fs_as_in_ep_desc);
 	if (!ep)
 		goto fail;
 	audio->in_ep = ep;
 	ep->driver_data = audio; /* claim */
 
 	if (gadget_is_dualspeed(c->cdev->gadget))
-		hs_as_in_ep_desc.bEndpointAddress =
-			fs_as_in_ep_desc.bEndpointAddress;
+		audio_hs_as_in_ep_desc.bEndpointAddress =
+			audio_fs_as_in_ep_desc.bEndpointAddress;
 
 	f->fs_descriptors = fs_audio_desc;
 	f->hs_descriptors = hs_audio_desc;
diff --git a/drivers/usb/gadget/f_midi.c b/drivers/usb/gadget/f_midi.c
index 263e721c2694..b0bce7ea31fa 100644
--- a/drivers/usb/gadget/f_midi.c
+++ b/drivers/usb/gadget/f_midi.c
@@ -65,6 +65,11 @@ struct gmidi_in_port {
 	uint8_t data[2];
 };
 
+struct midi_alsa_config {
+	int	card;
+	int	device;
+};
+
 struct f_midi {
 	struct usb_function	func;
 	struct usb_gadget	*gadget;
@@ -97,7 +102,7 @@ DECLARE_USB_MIDI_OUT_JACK_DESCRIPTOR(1);
 DECLARE_USB_MS_ENDPOINT_DESCRIPTOR(16);
 
 /* B.3.1  Standard AC Interface Descriptor */
-static struct usb_interface_descriptor ac_interface_desc __initdata = {
+static struct usb_interface_descriptor ac_interface_desc /* __initdata */ = {
 	.bLength =		USB_DT_INTERFACE_SIZE,
 	.bDescriptorType =	USB_DT_INTERFACE,
 	/* .bInterfaceNumber =	DYNAMIC */
@@ -108,7 +113,7 @@ static struct usb_interface_descriptor ac_interface_desc __initdata = {
 };
 
 /* B.3.2  Class-Specific AC Interface Descriptor */
-static struct uac1_ac_header_descriptor_1 ac_header_desc __initdata = {
+static struct uac1_ac_header_descriptor_1 ac_header_desc /* __initdata */ = {
 	.bLength =		UAC_DT_AC_HEADER_SIZE(1),
 	.bDescriptorType =	USB_DT_CS_INTERFACE,
 	.bDescriptorSubtype =	USB_MS_HEADER,
@@ -119,7 +124,7 @@ static struct uac1_ac_header_descriptor_1 ac_header_desc __initdata = {
 };
 
 /* B.4.1  Standard MS Interface Descriptor */
-static struct usb_interface_descriptor ms_interface_desc __initdata = {
+static struct usb_interface_descriptor ms_interface_desc /* __initdata */ = {
 	.bLength =		USB_DT_INTERFACE_SIZE,
 	.bDescriptorType =	USB_DT_INTERFACE,
 	/* .bInterfaceNumber =	DYNAMIC */
@@ -130,7 +135,7 @@ static struct usb_interface_descriptor ms_interface_desc __initdata = {
 };
 
 /* B.4.2  Class-Specific MS Interface Descriptor */
-static struct usb_ms_header_descriptor ms_header_desc __initdata = {
+static struct usb_ms_header_descriptor ms_header_desc /* __initdata */ = {
 	.bLength =		USB_DT_MS_HEADER_SIZE,
 	.bDescriptorType =	USB_DT_CS_INTERFACE,
 	.bDescriptorSubtype =	USB_MS_HEADER,
@@ -191,7 +196,7 @@ static struct usb_gadget_strings *midi_strings[] = {
 	NULL,
 };
 
-static struct usb_request *alloc_ep_req(struct usb_ep *ep, unsigned length)
+static struct usb_request *midi_alloc_ep_req(struct usb_ep *ep, unsigned length)
 {
 	struct usb_request *req;
 
@@ -207,7 +212,7 @@ static struct usb_request *alloc_ep_req(struct usb_ep *ep, unsigned length)
 	return req;
 }
 
-static void free_ep_req(struct usb_ep *ep, struct usb_request *req)
+static void midi_free_ep_req(struct usb_ep *ep, struct usb_request *req)
 {
 	kfree(req->buf);
 	usb_ep_free_request(ep, req);
@@ -278,7 +283,7 @@ f_midi_complete(struct usb_ep *ep, struct usb_request *req)
 		if (ep == midi->out_ep)
 			f_midi_handle_out_data(ep, req);
 
-		free_ep_req(ep, req);
+		midi_free_ep_req(ep, req);
 		return;
 
 	case -EOVERFLOW:	/* buffer overrun on read means that
@@ -365,7 +370,7 @@ static int f_midi_set_alt(struct usb_function *f, unsigned intf, unsigned alt)
 	/* allocate a bunch of read buffers and queue them all at once. */
 	for (i = 0; i < midi->qlen && err == 0; i++) {
 		struct usb_request *req =
-			alloc_ep_req(midi->out_ep, midi->buflen);
+			midi_alloc_ep_req(midi->out_ep, midi->buflen);
 		if (req == NULL)
 			return -ENOMEM;
 
@@ -409,7 +414,7 @@ static void f_midi_unbind(struct usb_configuration *c, struct usb_function *f)
 	card = midi->card;
 	midi->card = NULL;
 	if (card)
-		snd_card_free(card);
+		snd_card_free_when_closed(card);
 
 	kfree(midi->id);
 	midi->id = NULL;
@@ -546,10 +551,10 @@ static void f_midi_transmit(struct f_midi *midi, struct usb_request *req)
 		return;
 
 	if (!req)
-		req = alloc_ep_req(ep, midi->buflen);
+		req = midi_alloc_ep_req(ep, midi->buflen);
 
 	if (!req) {
-		ERROR(midi, "gmidi_transmit: alloc_ep_request failed\n");
+		ERROR(midi, "gmidi_transmit: midi_alloc_ep_request failed\n");
 		return;
 	}
 	req->length = 0;
@@ -575,7 +580,7 @@ static void f_midi_transmit(struct f_midi *midi, struct usb_request *req)
 	if (req->length > 0)
 		usb_ep_queue(ep, req, GFP_ATOMIC);
 	else
-		free_ep_req(ep, req);
+		midi_free_ep_req(ep, req);
 }
 
 static void f_midi_in_tasklet(unsigned long data)
@@ -733,7 +738,7 @@ fail:
 
 /* MIDI function driver setup/binding */
 
-static int __init
+static int /* __init */
 f_midi_bind(struct usb_configuration *c, struct usb_function *f)
 {
 	struct usb_descriptor_header **midi_function;
@@ -923,16 +928,22 @@ fail:
  *
  * Returns zero on success, else negative errno.
  */
-int __init f_midi_bind_config(struct usb_configuration *c,
+int /* __init */ f_midi_bind_config(struct usb_configuration *c,
 			      int index, char *id,
 			      unsigned int in_ports,
 			      unsigned int out_ports,
 			      unsigned int buflen,
-			      unsigned int qlen)
+			      unsigned int qlen,
+			      struct midi_alsa_config* config)
 {
 	struct f_midi *midi;
 	int status, i;
 
+	if (config) {
+		config->card = -1;
+		config->device = -1;
+	}
+
 	/* sanity check */
 	if (in_ports > MAX_PORTS || out_ports > MAX_PORTS)
 		return -EINVAL;
@@ -961,6 +972,10 @@ int __init f_midi_bind_config(struct usb_configuration *c,
 	tasklet_init(&midi->tasklet, f_midi_in_tasklet, (unsigned long) midi);
 
 	/* set up ALSA midi devices */
+	midi->id = kstrdup(id, GFP_KERNEL);
+	midi->index = index;
+	midi->buflen = buflen;
+	midi->qlen = qlen;
 	midi->in_ports = in_ports;
 	midi->out_ports = out_ports;
 	status = f_midi_register_card(midi);
@@ -974,15 +989,16 @@ int __init f_midi_bind_config(struct usb_configuration *c,
 	midi->func.set_alt     = f_midi_set_alt;
 	midi->func.disable     = f_midi_disable;
 
-	midi->id = kstrdup(id, GFP_KERNEL);
-	midi->index = index;
-	midi->buflen = buflen;
-	midi->qlen = qlen;
-
 	status = usb_add_function(c, &midi->func);
 	if (status)
 		goto setup_fail;
 
+
+	if (config) {
+		config->card = midi->rmidi->card->number;
+		config->device = midi->rmidi->device;
+	}
+
 	return 0;
 
 setup_fail:
diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index a6fc777288ab..a3997d560114 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -903,11 +903,6 @@ static inline int cgroup_attach_task_all(struct task_struct *from,
 	return 0;
 }
 
-static inline int subsys_cgroup_allow_attach(struct cgroup *cgrp,
-					     struct cgroup_taskset *tset)
-{
-	return 0;
-}
 #endif /* !CONFIG_CGROUPS */
 
 #endif /* _LINUX_CGROUP_H */
diff --git a/include/linux/lsm_audit.h b/include/linux/lsm_audit.h
index 1cc89e9df480..ffb9c9da4f39 100644
--- a/include/linux/lsm_audit.h
+++ b/include/linux/lsm_audit.h
@@ -40,6 +40,11 @@ struct lsm_network_audit {
 	} fam;
 };
 
+struct lsm_ioctlop_audit {
+	struct path path;
+	u16 cmd;
+};
+
 /* Auxiliary data to use in generating the audit record. */
 struct common_audit_data {
 	char type;
@@ -53,6 +58,7 @@ struct common_audit_data {
 #define LSM_AUDIT_DATA_KMOD	8
 #define LSM_AUDIT_DATA_INODE	9
 #define LSM_AUDIT_DATA_DENTRY	10
+#define LSM_AUDIT_DATA_IOCTL_OP	11
 	union 	{
 		struct path path;
 		struct dentry *dentry;
@@ -68,6 +74,7 @@ struct common_audit_data {
 		} key_struct;
 #endif
 		char *kmod_name;
+		struct lsm_ioctlop_audit *op;
 	} u;
 	/* this union contains LSM specific data */
 	union {
diff --git a/kernel/power/wakeup_reason.c b/kernel/power/wakeup_reason.c
index 085c99edca06..76b53400cb16 100644
--- a/kernel/power/wakeup_reason.c
+++ b/kernel/power/wakeup_reason.c
@@ -36,6 +36,11 @@ static char abort_reason[MAX_SUSPEND_ABORT_LEN];
 static struct kobject *wakeup_reason;
 static DEFINE_SPINLOCK(resume_reason_lock);
 
+static struct timespec last_xtime; /* wall time before last suspend */
+static struct timespec curr_xtime; /* wall time after last suspend */
+static struct timespec last_stime; /* total_sleep_time before last suspend */
+static struct timespec curr_stime; /* total_sleep_time after last suspend */
+
 static ssize_t last_resume_reason_show(struct kobject *kobj, struct kobj_attribute *attr,
 		char *buf)
 {
@@ -59,10 +64,32 @@ static ssize_t last_resume_reason_show(struct kobject *kobj, struct kobj_attribu
 	return buf_offset;
 }
 
+static ssize_t last_suspend_time_show(struct kobject *kobj,
+			struct kobj_attribute *attr, char *buf)
+{
+	struct timespec sleep_time;
+	struct timespec total_time;
+	struct timespec suspend_resume_time;
+
+	sleep_time = timespec_sub(curr_stime, last_stime);
+	total_time = timespec_sub(curr_xtime, last_xtime);
+	suspend_resume_time = timespec_sub(total_time, sleep_time);
+
+	/*
+	 * suspend_resume_time is calculated from sleep_time. Userspace would
+	 * always need both. Export them in pair here.
+	 */
+	return sprintf(buf, "%lu.%09lu %lu.%09lu\n",
+				suspend_resume_time.tv_sec, suspend_resume_time.tv_nsec,
+				sleep_time.tv_sec, sleep_time.tv_nsec);
+}
+
 static struct kobj_attribute resume_reason = __ATTR_RO(last_resume_reason);
+static struct kobj_attribute suspend_time = __ATTR_RO(last_suspend_time);
 
 static struct attribute *attrs[] = {
 	&resume_reason.attr,
+	&suspend_time.attr,
 	NULL,
 };
 static struct attribute_group attr_group = {
@@ -133,12 +160,21 @@ void log_suspend_abort_reason(const char *fmt, ...)
 static int wakeup_reason_pm_event(struct notifier_block *notifier,
 		unsigned long pm_event, void *unused)
 {
+	struct timespec xtom; /* wall_to_monotonic, ignored */
+
 	switch (pm_event) {
 	case PM_SUSPEND_PREPARE:
 		spin_lock(&resume_reason_lock);
 		irqcount = 0;
 		suspend_abort = false;
 		spin_unlock(&resume_reason_lock);
+
+		get_xtime_and_monotonic_and_sleep_offset(&last_xtime, &xtom,
+			&last_stime);
+		break;
+	case PM_POST_SUSPEND:
+		get_xtime_and_monotonic_and_sleep_offset(&curr_xtime, &xtom,
+			&curr_stime);
 		break;
 	default:
 		break;
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index aabb52855662..8cc9b5499013 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -3510,7 +3510,7 @@ int tcp_nuke_addr(struct net *net, struct sockaddr *addr)
 
 	struct in_addr *in;
 #if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
-	struct in6_addr *in6;
+	struct in6_addr *in6 = NULL;
 #endif
 	if (family == AF_INET) {
 		in = &((struct sockaddr_in *)addr)->sin_addr;
diff --git a/security/lsm_audit.c b/security/lsm_audit.c
index 8d8d97dbb389..8f6b8e8a4cc8 100644
--- a/security/lsm_audit.c
+++ b/security/lsm_audit.c
@@ -245,6 +245,21 @@ static void dump_common_audit_data(struct audit_buffer *ab,
 		}
 		break;
 	}
+	case LSM_AUDIT_DATA_IOCTL_OP: {
+		struct inode *inode;
+
+		audit_log_d_path(ab, " path=", &a->u.op->path);
+
+		inode = a->u.op->path.dentry->d_inode;
+		if (inode) {
+			audit_log_format(ab, " dev=");
+			audit_log_untrustedstring(ab, inode->i_sb->s_id);
+			audit_log_format(ab, " ino=%lu", inode->i_ino);
+		}
+
+		audit_log_format(ab, " ioctlcmd=%hx", a->u.op->cmd);
+		break;
+	}
 	case LSM_AUDIT_DATA_DENTRY: {
 		struct inode *inode;
 
diff --git a/security/selinux/avc.c b/security/selinux/avc.c
index c223a32c0bb3..5c8e7cfa9de3 100644
--- a/security/selinux/avc.c
+++ b/security/selinux/avc.c
@@ -22,6 +22,7 @@
 #include <linux/init.h>
 #include <linux/skbuff.h>
 #include <linux/percpu.h>
+#include <linux/list.h>
 #include <net/sock.h>
 #include <linux/un.h>
 #include <net/af_unix.h>
@@ -48,6 +49,7 @@ struct avc_entry {
 	u32			tsid;
 	u16			tclass;
 	struct av_decision	avd;
+	struct avc_operation_node *ops_node;
 };
 
 struct avc_node {
@@ -64,6 +66,16 @@ struct avc_cache {
 	u32			latest_notif;	/* latest revocation notification */
 };
 
+struct avc_operation_decision_node {
+	struct operation_decision od;
+	struct list_head od_list;
+};
+
+struct avc_operation_node {
+	struct operation ops;
+	struct list_head od_head; /* list of operation_decision_node */
+};
+
 struct avc_callback_node {
 	int (*callback) (u32 event);
 	u32 events;
@@ -80,6 +92,9 @@ DEFINE_PER_CPU(struct avc_cache_stats, avc_cache_stats) = { 0 };
 static struct avc_cache avc_cache;
 static struct avc_callback_node *avc_callbacks;
 static struct kmem_cache *avc_node_cachep;
+static struct kmem_cache *avc_operation_decision_node_cachep;
+static struct kmem_cache *avc_operation_node_cachep;
+static struct kmem_cache *avc_operation_perm_cachep;
 
 static inline int avc_hash(u32 ssid, u32 tsid, u16 tclass)
 {
@@ -171,6 +186,16 @@ void __init avc_init(void)
 
 	avc_node_cachep = kmem_cache_create("avc_node", sizeof(struct avc_node),
 					     0, SLAB_PANIC, NULL);
+	avc_operation_node_cachep = kmem_cache_create("avc_operation_node",
+				sizeof(struct avc_operation_node),
+				0, SLAB_PANIC, NULL);
+	avc_operation_decision_node_cachep = kmem_cache_create(
+				"avc_operation_decision_node",
+				sizeof(struct avc_operation_decision_node),
+				0, SLAB_PANIC, NULL);
+	avc_operation_perm_cachep = kmem_cache_create("avc_operation_perm",
+				sizeof(struct operation_perm),
+				0, SLAB_PANIC, NULL);
 
 	audit_log(current->audit_context, GFP_KERNEL, AUDIT_KERNEL, "AVC INITIALIZED\n");
 }
@@ -205,9 +230,269 @@ int avc_get_hash_stats(char *page)
 			 slots_used, AVC_CACHE_SLOTS, max_chain_len);
 }
 
+/*
+ * using a linked list for operation_decision lookup because the list is
+ * always small. i.e. less than 5, typically 1
+ */
+static struct operation_decision *avc_operation_lookup(u8 type,
+					struct avc_operation_node *ops_node)
+{
+	struct avc_operation_decision_node *od_node;
+	struct operation_decision *od = NULL;
+
+	list_for_each_entry(od_node, &ops_node->od_head, od_list) {
+		if (od_node->od.type != type)
+			continue;
+		od = &od_node->od;
+		break;
+	}
+	return od;
+}
+
+static inline unsigned int avc_operation_has_perm(struct operation_decision *od,
+						u16 cmd, u8 specified)
+{
+	unsigned int rc = 0;
+	u8 num = cmd & 0xff;
+
+	if ((specified == OPERATION_ALLOWED) &&
+			(od->specified & OPERATION_ALLOWED))
+		rc = security_operation_test(od->allowed->perms, num);
+	else if ((specified == OPERATION_AUDITALLOW) &&
+			(od->specified & OPERATION_AUDITALLOW))
+		rc = security_operation_test(od->auditallow->perms, num);
+	else if ((specified == OPERATION_DONTAUDIT) &&
+			(od->specified & OPERATION_DONTAUDIT))
+		rc = security_operation_test(od->dontaudit->perms, num);
+	return rc;
+}
+
+static void avc_operation_allow_perm(struct avc_operation_node *node, u16 cmd)
+{
+	struct operation_decision *od;
+	u8 type;
+	u8 num;
+
+	type = cmd >> 8;
+	num = cmd & 0xff;
+	security_operation_set(node->ops.type, type);
+	od = avc_operation_lookup(type, node);
+	if (od && od->allowed)
+		security_operation_set(od->allowed->perms, num);
+}
+
+static void avc_operation_decision_free(
+				struct avc_operation_decision_node *od_node)
+{
+	struct operation_decision *od;
+
+	od = &od_node->od;
+	if (od->allowed)
+		kmem_cache_free(avc_operation_perm_cachep, od->allowed);
+	if (od->auditallow)
+		kmem_cache_free(avc_operation_perm_cachep, od->auditallow);
+	if (od->dontaudit)
+		kmem_cache_free(avc_operation_perm_cachep, od->dontaudit);
+	kmem_cache_free(avc_operation_decision_node_cachep, od_node);
+}
+
+static void avc_operation_free(struct avc_operation_node *ops_node)
+{
+	struct avc_operation_decision_node *od_node;
+
+	if (!ops_node)
+		return;
+
+	list_for_each_entry(od_node, &ops_node->od_head, od_list)
+		avc_operation_decision_free(od_node);
+	kmem_cache_free(avc_operation_node_cachep, ops_node);
+}
+
+static void avc_copy_operation_decision(struct operation_decision *dest,
+					struct operation_decision *src)
+{
+	dest->type = src->type;
+	dest->specified = src->specified;
+	if (dest->specified & OPERATION_ALLOWED)
+		memcpy(dest->allowed->perms, src->allowed->perms,
+				sizeof(src->allowed->perms));
+	if (dest->specified & OPERATION_AUDITALLOW)
+		memcpy(dest->auditallow->perms, src->auditallow->perms,
+				sizeof(src->auditallow->perms));
+	if (dest->specified & OPERATION_DONTAUDIT)
+		memcpy(dest->dontaudit->perms, src->dontaudit->perms,
+				sizeof(src->dontaudit->perms));
+}
+
+/*
+ * similar to avc_copy_operation_decision, but only copy decision
+ * information relevant to this command
+ */
+static inline void avc_quick_copy_operation_decision(u16 cmd,
+			struct operation_decision *dest,
+			struct operation_decision *src)
+{
+	/*
+	 * compute index of the u32 of the 256 bits (8 u32s) that contain this
+	 * command permission
+	 */
+	u8 i = (0xff & cmd) >> 5;
+
+	dest->specified = src->specified;
+	if (dest->specified & OPERATION_ALLOWED)
+		dest->allowed->perms[i] = src->allowed->perms[i];
+	if (dest->specified & OPERATION_AUDITALLOW)
+		dest->auditallow->perms[i] = src->auditallow->perms[i];
+	if (dest->specified & OPERATION_DONTAUDIT)
+		dest->dontaudit->perms[i] = src->dontaudit->perms[i];
+}
+
+static struct avc_operation_decision_node
+		*avc_operation_decision_alloc(u8 specified)
+{
+	struct avc_operation_decision_node *node;
+	struct operation_decision *od;
+
+	node = kmem_cache_zalloc(avc_operation_decision_node_cachep,
+				GFP_ATOMIC | __GFP_NOMEMALLOC);
+	if (!node)
+		return NULL;
+
+	od = &node->od;
+	if (specified & OPERATION_ALLOWED) {
+		od->allowed = kmem_cache_zalloc(avc_operation_perm_cachep,
+						GFP_ATOMIC | __GFP_NOMEMALLOC);
+		if (!od->allowed)
+			goto error;
+	}
+	if (specified & OPERATION_AUDITALLOW) {
+		od->auditallow = kmem_cache_zalloc(avc_operation_perm_cachep,
+						GFP_ATOMIC | __GFP_NOMEMALLOC);
+		if (!od->auditallow)
+			goto error;
+	}
+	if (specified & OPERATION_DONTAUDIT) {
+		od->dontaudit = kmem_cache_zalloc(avc_operation_perm_cachep,
+						GFP_ATOMIC | __GFP_NOMEMALLOC);
+		if (!od->dontaudit)
+			goto error;
+	}
+	return node;
+error:
+	avc_operation_decision_free(node);
+	return NULL;
+}
+
+static int avc_add_operation(struct avc_node *node,
+			struct operation_decision *od)
+{
+	struct avc_operation_decision_node *dest_od;
+
+	node->ae.ops_node->ops.len++;
+	dest_od = avc_operation_decision_alloc(od->specified);
+	if (!dest_od)
+		return -ENOMEM;
+	avc_copy_operation_decision(&dest_od->od, od);
+	list_add(&dest_od->od_list, &node->ae.ops_node->od_head);
+	return 0;
+}
+
+static struct avc_operation_node *avc_operation_alloc(void)
+{
+	struct avc_operation_node *ops;
+
+	ops = kmem_cache_zalloc(avc_operation_node_cachep,
+				GFP_ATOMIC|__GFP_NOMEMALLOC);
+	if (!ops)
+		return ops;
+	INIT_LIST_HEAD(&ops->od_head);
+	return ops;
+}
+
+static int avc_operation_populate(struct avc_node *node,
+				struct avc_operation_node *src)
+{
+	struct avc_operation_node *dest;
+	struct avc_operation_decision_node *dest_od;
+	struct avc_operation_decision_node *src_od;
+
+	if (src->ops.len == 0)
+		return 0;
+	dest = avc_operation_alloc();
+	if (!dest)
+		return -ENOMEM;
+
+	memcpy(dest->ops.type, &src->ops.type, sizeof(dest->ops.type));
+	dest->ops.len = src->ops.len;
+
+	/* for each source od allocate a destination od and copy */
+	list_for_each_entry(src_od, &src->od_head, od_list) {
+		dest_od = avc_operation_decision_alloc(src_od->od.specified);
+		if (!dest_od)
+			goto error;
+		avc_copy_operation_decision(&dest_od->od, &src_od->od);
+		list_add(&dest_od->od_list, &dest->od_head);
+	}
+	node->ae.ops_node = dest;
+	return 0;
+error:
+	avc_operation_free(dest);
+	return -ENOMEM;
+
+}
+
+static inline u32 avc_operation_audit_required(u32 requested,
+					struct av_decision *avd,
+					struct operation_decision *od,
+					u16 cmd,
+					int result,
+					u32 *deniedp)
+{
+	u32 denied, audited;
+
+	denied = requested & ~avd->allowed;
+	if (unlikely(denied)) {
+		audited = denied & avd->auditdeny;
+		if (audited && od) {
+			if (avc_operation_has_perm(od, cmd,
+						OPERATION_DONTAUDIT))
+				audited &= ~requested;
+		}
+	} else if (result) {
+		audited = denied = requested;
+	} else {
+		audited = requested & avd->auditallow;
+		if (audited && od) {
+			if (!avc_operation_has_perm(od, cmd,
+						OPERATION_AUDITALLOW))
+				audited &= ~requested;
+		}
+	}
+
+	*deniedp = denied;
+	return audited;
+}
+
+static inline int avc_operation_audit(u32 ssid, u32 tsid, u16 tclass,
+				u32 requested, struct av_decision *avd,
+				struct operation_decision *od,
+				u16 cmd, int result,
+				struct common_audit_data *ad)
+{
+	u32 audited, denied;
+
+	audited = avc_operation_audit_required(
+			requested, avd, od, cmd, result, &denied);
+	if (likely(!audited))
+		return 0;
+	return slow_avc_audit(ssid, tsid, tclass, requested,
+			audited, denied, result, ad, 0);
+}
+
 static void avc_node_free(struct rcu_head *rhead)
 {
 	struct avc_node *node = container_of(rhead, struct avc_node, rhead);
+	avc_operation_free(node->ae.ops_node);
 	kmem_cache_free(avc_node_cachep, node);
 	avc_cache_stats_incr(frees);
 }
@@ -221,6 +506,7 @@ static void avc_node_delete(struct avc_node *node)
 
 static void avc_node_kill(struct avc_node *node)
 {
+	avc_operation_free(node->ae.ops_node);
 	kmem_cache_free(avc_node_cachep, node);
 	avc_cache_stats_incr(frees);
 	atomic_dec(&avc_cache.active_nodes);
@@ -367,6 +653,7 @@ static int avc_latest_notif_update(int seqno, int is_insert)
  * @tsid: target security identifier
  * @tclass: target security class
  * @avd: resulting av decision
+ * @ops: resulting operation decisions
  *
  * Insert an AVC entry for the SID pair
  * (@ssid, @tsid) and class @tclass.
@@ -378,7 +665,9 @@ static int avc_latest_notif_update(int seqno, int is_insert)
  * the access vectors into a cache entry, returns
  * avc_node inserted. Otherwise, this function returns NULL.
  */
-static struct avc_node *avc_insert(u32 ssid, u32 tsid, u16 tclass, struct av_decision *avd)
+static struct avc_node *avc_insert(u32 ssid, u32 tsid, u16 tclass,
+				struct av_decision *avd,
+				struct avc_operation_node *ops_node)
 {
 	struct avc_node *pos, *node = NULL;
 	int hvalue;
@@ -391,10 +680,15 @@ static struct avc_node *avc_insert(u32 ssid, u32 tsid, u16 tclass, struct av_dec
 	if (node) {
 		struct hlist_head *head;
 		spinlock_t *lock;
+		int rc = 0;
 
 		hvalue = avc_hash(ssid, tsid, tclass);
 		avc_node_populate(node, ssid, tsid, tclass, avd);
-
+		rc = avc_operation_populate(node, ops_node);
+		if (rc) {
+			kmem_cache_free(avc_node_cachep, node);
+			return NULL;
+		}
 		head = &avc_cache.slots[hvalue];
 		lock = &avc_cache.slots_lock[hvalue];
 
@@ -528,14 +822,17 @@ static inline int avc_sidcmp(u32 x, u32 y)
  * @perms : Permission mask bits
  * @ssid,@tsid,@tclass : identifier of an AVC entry
  * @seqno : sequence number when decision was made
+ * @od: operation_decision to be added to the node
  *
  * if a valid AVC entry doesn't exist,this function returns -ENOENT.
  * if kmalloc() called internal returns NULL, this function returns -ENOMEM.
  * otherwise, this function updates the AVC entry. The original AVC-entry object
  * will release later by RCU.
  */
-static int avc_update_node(u32 event, u32 perms, u32 ssid, u32 tsid, u16 tclass,
-			   u32 seqno)
+static int avc_update_node(u32 event, u32 perms, u16 cmd, u32 ssid, u32 tsid,
+			u16 tclass, u32 seqno,
+			struct operation_decision *od,
+			u32 flags)
 {
 	int hvalue, rc = 0;
 	unsigned long flag;
@@ -579,9 +876,19 @@ static int avc_update_node(u32 event, u32 perms, u32 ssid, u32 tsid, u16 tclass,
 
 	avc_node_populate(node, ssid, tsid, tclass, &orig->ae.avd);
 
+	if (orig->ae.ops_node) {
+		rc = avc_operation_populate(node, orig->ae.ops_node);
+		if (rc) {
+			kmem_cache_free(avc_node_cachep, node);
+			goto out_unlock;
+		}
+	}
+
 	switch (event) {
 	case AVC_CALLBACK_GRANT:
 		node->ae.avd.allowed |= perms;
+		if (node->ae.ops_node && (flags & AVC_OPERATION_CMD))
+			avc_operation_allow_perm(node->ae.ops_node, cmd);
 		break;
 	case AVC_CALLBACK_TRY_REVOKE:
 	case AVC_CALLBACK_REVOKE:
@@ -599,6 +906,9 @@ static int avc_update_node(u32 event, u32 perms, u32 ssid, u32 tsid, u16 tclass,
 	case AVC_CALLBACK_AUDITDENY_DISABLE:
 		node->ae.avd.auditdeny &= ~perms;
 		break;
+	case AVC_CALLBACK_ADD_OPERATION:
+		avc_add_operation(node, od);
+		break;
 	}
 	avc_node_replace(node, orig);
 out_unlock:
@@ -670,18 +980,20 @@ int avc_ss_reset(u32 seqno)
  * results in a bigger stack frame.
  */
 static noinline struct avc_node *avc_compute_av(u32 ssid, u32 tsid,
-			 u16 tclass, struct av_decision *avd)
+			 u16 tclass, struct av_decision *avd,
+			 struct avc_operation_node *ops_node)
 {
 	rcu_read_unlock();
-	security_compute_av(ssid, tsid, tclass, avd);
+	INIT_LIST_HEAD(&ops_node->od_head);
+	security_compute_av(ssid, tsid, tclass, avd, &ops_node->ops);
 	rcu_read_lock();
-	return avc_insert(ssid, tsid, tclass, avd);
+	return avc_insert(ssid, tsid, tclass, avd, ops_node);
 }
 
 static noinline int avc_denied(u32 ssid, u32 tsid,
-			 u16 tclass, u32 requested,
-			 unsigned flags,
-			 struct av_decision *avd)
+				u16 tclass, u32 requested,
+				u16 cmd, unsigned flags,
+				struct av_decision *avd)
 {
 	if (flags & AVC_STRICT)
 		return -EACCES;
@@ -689,11 +1001,92 @@ static noinline int avc_denied(u32 ssid, u32 tsid,
 	if (selinux_enforcing && !(avd->flags & AVD_FLAGS_PERMISSIVE))
 		return -EACCES;
 
-	avc_update_node(AVC_CALLBACK_GRANT, requested, ssid,
-				tsid, tclass, avd->seqno);
+	avc_update_node(AVC_CALLBACK_GRANT, requested, cmd, ssid,
+				tsid, tclass, avd->seqno, NULL, flags);
 	return 0;
 }
 
+/*
+ * ioctl commands are comprised of four fields, direction, size, type, and
+ * number. The avc operation logic filters based on two of them:
+ *
+ * type: or code, typically unique to each driver
+ * number: or function
+ *
+ * For example, 0x89 is a socket type, and number 0x27 is the get hardware
+ * address function.
+ */
+int avc_has_operation(u32 ssid, u32 tsid, u16 tclass, u32 requested,
+			u16 cmd, struct common_audit_data *ad)
+{
+	struct avc_node *node;
+	struct av_decision avd;
+	u32 denied;
+	struct operation_decision *od = NULL;
+	struct operation_decision od_local;
+	struct operation_perm allowed;
+	struct operation_perm auditallow;
+	struct operation_perm dontaudit;
+	struct avc_operation_node local_ops_node;
+	struct avc_operation_node *ops_node;
+	u8 type = cmd >> 8;
+	int rc = 0, rc2;
+
+	ops_node = &local_ops_node;
+	BUG_ON(!requested);
+
+	rcu_read_lock();
+
+	node = avc_lookup(ssid, tsid, tclass);
+	if (unlikely(!node)) {
+		node = avc_compute_av(ssid, tsid, tclass, &avd, ops_node);
+	} else {
+		memcpy(&avd, &node->ae.avd, sizeof(avd));
+		ops_node = node->ae.ops_node;
+	}
+	/* if operations are not defined, only consider av_decision */
+	if (!ops_node || !ops_node->ops.len)
+		goto decision;
+
+	od_local.allowed = &allowed;
+	od_local.auditallow = &auditallow;
+	od_local.dontaudit = &dontaudit;
+
+	/* lookup operation decision */
+	od = avc_operation_lookup(type, ops_node);
+	if (unlikely(!od)) {
+		/* Compute operation decision if type is flagged */
+		if (!security_operation_test(ops_node->ops.type, type)) {
+			avd.allowed &= ~requested;
+			goto decision;
+		}
+		rcu_read_unlock();
+		security_compute_operation(ssid, tsid, tclass, type, &od_local);
+		rcu_read_lock();
+		avc_update_node(AVC_CALLBACK_ADD_OPERATION, requested, cmd,
+				ssid, tsid, tclass, avd.seqno, &od_local, 0);
+	} else {
+		avc_quick_copy_operation_decision(cmd, &od_local, od);
+	}
+	od = &od_local;
+
+	if (!avc_operation_has_perm(od, cmd, OPERATION_ALLOWED))
+		avd.allowed &= ~requested;
+
+decision:
+	denied = requested & ~(avd.allowed);
+	if (unlikely(denied))
+		rc = avc_denied(ssid, tsid, tclass, requested, cmd,
+				AVC_OPERATION_CMD, &avd);
+
+	rcu_read_unlock();
+
+	rc2 = avc_operation_audit(ssid, tsid, tclass, requested,
+			&avd, od, cmd, rc, ad);
+	if (rc2)
+		return rc2;
+	return rc;
+}
 
 /**
  * avc_has_perm_noaudit - Check permissions but perform no auditing.
@@ -721,6 +1114,7 @@ inline int avc_has_perm_noaudit(u32 ssid, u32 tsid,
 			 struct av_decision *avd)
 {
 	struct avc_node *node;
+	struct avc_operation_node ops_node;
 	int rc = 0;
 	u32 denied;
 
@@ -729,16 +1123,14 @@ inline int avc_has_perm_noaudit(u32 ssid, u32 tsid,
 	rcu_read_lock();
 
 	node = avc_lookup(ssid, tsid, tclass);
-	if (unlikely(!node)) {
-		node = avc_compute_av(ssid, tsid, tclass, avd);
-	} else {
+	if (unlikely(!node))
+		node = avc_compute_av(ssid, tsid, tclass, avd, &ops_node);
+	else
 		memcpy(avd, &node->ae.avd, sizeof(*avd));
-		avd = &node->ae.avd;
-	}
 
 	denied = requested & ~(avd->allowed);
 	if (unlikely(denied))
-		rc = avc_denied(ssid, tsid, tclass, requested, flags, avd);
+		rc = avc_denied(ssid, tsid, tclass, requested, 0, flags, avd);
 
 	rcu_read_unlock();
 	return rc;
diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c
index fdc96f6e50f5..607c3d58a691 100644
--- a/security/selinux/hooks.c
+++ b/security/selinux/hooks.c
@@ -3109,6 +3109,44 @@ static void selinux_file_free_security(struct file *file)
 	file_free_security(file);
 }
 
+/*
+ * Check whether a task has the ioctl permission and cmd
+ * operation to an inode.
+ */
+int ioctl_has_perm(const struct cred *cred, struct file *file,
+		u32 requested, u16 cmd)
+{
+	struct common_audit_data ad;
+	struct file_security_struct *fsec = file->f_security;
+	struct inode *inode = file_inode(file);
+	struct inode_security_struct *isec = inode->i_security;
+	struct lsm_ioctlop_audit ioctl;
+	u32 ssid = cred_sid(cred);
+	int rc;
+
+	ad.type = LSM_AUDIT_DATA_IOCTL_OP;
+	ad.u.op = &ioctl;
+	ad.u.op->cmd = cmd;
+	ad.u.op->path = file->f_path;
+
+	if (ssid != fsec->sid) {
+		rc = avc_has_perm(ssid, fsec->sid,
+				SECCLASS_FD,
+				FD__USE,
+				&ad);
+		if (rc)
+			goto out;
+	}
+
+	if (unlikely(IS_PRIVATE(inode)))
+		return 0;
+
+	rc = avc_has_operation(ssid, isec->sid, isec->sclass,
+			requested, cmd, &ad);
+out:
+	return rc;
+}
+
 static int selinux_file_ioctl(struct file *file, unsigned int cmd,
 			      unsigned long arg)
 {
@@ -3151,7 +3189,7 @@ static int selinux_file_ioctl(struct file *file, unsigned int cmd,
 	 * to the file's ioctl() function.
 	 */
 	default:
-		error = file_has_perm(cred, file, FILE__IOCTL);
+		error = ioctl_has_perm(cred, file, FILE__IOCTL, (u16) cmd);
 	}
 	return error;
 }
diff --git a/security/selinux/include/avc.h b/security/selinux/include/avc.h
index 28a08a891704..8109ad846e99 100644
--- a/security/selinux/include/avc.h
+++ b/security/selinux/include/avc.h
@@ -142,11 +142,15 @@ static inline int avc_audit(u32 ssid, u32 tsid,
 }
 
 #define AVC_STRICT 1 /* Ignore permissive mode. */
+#define AVC_OPERATION_CMD 2	/* ignore command when updating operations */
 int avc_has_perm_noaudit(u32 ssid, u32 tsid,
 			 u16 tclass, u32 requested,
 			 unsigned flags,
 			 struct av_decision *avd);
 
+int avc_has_operation(u32 ssid, u32 tsid, u16 tclass, u32 requested,
+		u16 cmd, struct common_audit_data *ad);
+
 int avc_has_perm_flags(u32 ssid, u32 tsid,
 		       u16 tclass, u32 requested,
 		       struct common_audit_data *auditdata,
@@ -169,6 +173,7 @@ u32 avc_policy_seqno(void);
 #define AVC_CALLBACK_AUDITALLOW_DISABLE	32
 #define AVC_CALLBACK_AUDITDENY_ENABLE	64
 #define AVC_CALLBACK_AUDITDENY_DISABLE	128
+#define AVC_CALLBACK_ADD_OPERATION	256
 
 int avc_add_callback(int (*callback)(u32 event), u32 events);
 
diff --git a/security/selinux/include/security.h b/security/selinux/include/security.h
index b214ef5f86e1..e72d8de93725 100644
--- a/security/selinux/include/security.h
+++ b/security/selinux/include/security.h
@@ -34,13 +34,14 @@
 #define POLICYDB_VERSION_NEW_OBJECT_DEFAULTS	27
 #define POLICYDB_VERSION_DEFAULT_TYPE	28
 #define POLICYDB_VERSION_CONSTRAINT_NAMES	29
+#define POLICYDB_VERSION_IOCTL_OPERATIONS	30
 
 /* Range of policy versions we understand*/
 #define POLICYDB_VERSION_MIN   POLICYDB_VERSION_BASE
 #ifdef CONFIG_SECURITY_SELINUX_POLICYDB_VERSION_MAX
 #define POLICYDB_VERSION_MAX	CONFIG_SECURITY_SELINUX_POLICYDB_VERSION_MAX_VALUE
 #else
-#define POLICYDB_VERSION_MAX	POLICYDB_VERSION_CONSTRAINT_NAMES
+#define POLICYDB_VERSION_MAX	POLICYDB_VERSION_IOCTL_OPERATIONS
 #endif
 
 /* Mask for just the mount related flags */
@@ -103,11 +104,40 @@ struct av_decision {
 	u32 flags;
 };
 
+#define security_operation_set(perms, x) (perms[x >> 5] |= 1 << (x & 0x1f))
+#define security_operation_test(perms, x) (1 & (perms[x >> 5] >> (x & 0x1f)))
+
+struct operation_perm {
+	u32 perms[8];
+};
+
+struct operation_decision {
+	u8 type;
+	u8 specified;
+	struct operation_perm *allowed;
+	struct operation_perm *auditallow;
+	struct operation_perm *dontaudit;
+};
+
+#define OPERATION_ALLOWED 1
+#define OPERATION_AUDITALLOW 2
+#define OPERATION_DONTAUDIT 4
+#define OPERATION_ALL (OPERATION_ALLOWED | OPERATION_AUDITALLOW |\
+			OPERATION_DONTAUDIT)
+struct operation {
+	u16 len;	/* length of operation decision chain */
+	u32 type[8];	/* 256 types */
+};
+
 /* definitions of av_decision.flags */
 #define AVD_FLAGS_PERMISSIVE	0x0001
 
 void security_compute_av(u32 ssid, u32 tsid,
-			 u16 tclass, struct av_decision *avd);
+			 u16 tclass, struct av_decision *avd,
+			 struct operation *ops);
+
+void security_compute_operation(u32 ssid, u32 tsid, u16 tclass,
+			 u8 type, struct operation_decision *od);
 
 void security_compute_av_user(u32 ssid, u32 tsid,
 			     u16 tclass, struct av_decision *avd);
diff --git a/security/selinux/nlmsgtab.c b/security/selinux/nlmsgtab.c
index 855e464e92ef..4c29bcc7fad2 100644
--- a/security/selinux/nlmsgtab.c
+++ b/security/selinux/nlmsgtab.c
@@ -17,6 +17,7 @@
 #include <linux/inet_diag.h>
 #include <linux/xfrm.h>
 #include <linux/audit.h>
+#include <linux/sock_diag.h>
 
 #include "flask.h"
 #include "av_permissions.h"
@@ -78,6 +79,7 @@ static struct nlmsg_perm nlmsg_tcpdiag_perms[] =
 {
 	{ TCPDIAG_GETSOCK,	NETLINK_TCPDIAG_SOCKET__NLMSG_READ },
 	{ DCCPDIAG_GETSOCK,	NETLINK_TCPDIAG_SOCKET__NLMSG_READ },
+	{ SOCK_DIAG_BY_FAMILY,	NETLINK_TCPDIAG_SOCKET__NLMSG_READ },
 };
 
 static struct nlmsg_perm nlmsg_xfrm_perms[] =
@@ -98,6 +100,13 @@ static struct nlmsg_perm nlmsg_xfrm_perms[] =
 	{ XFRM_MSG_FLUSHPOLICY,	NETLINK_XFRM_SOCKET__NLMSG_WRITE },
 	{ XFRM_MSG_NEWAE,	NETLINK_XFRM_SOCKET__NLMSG_WRITE },
 	{ XFRM_MSG_GETAE,	NETLINK_XFRM_SOCKET__NLMSG_READ  },
+	{ XFRM_MSG_REPORT,	NETLINK_XFRM_SOCKET__NLMSG_READ  },
+	{ XFRM_MSG_MIGRATE,	NETLINK_XFRM_SOCKET__NLMSG_WRITE },
+	{ XFRM_MSG_NEWSADINFO,	NETLINK_XFRM_SOCKET__NLMSG_READ  },
+	{ XFRM_MSG_GETSADINFO,	NETLINK_XFRM_SOCKET__NLMSG_READ  },
+	{ XFRM_MSG_NEWSPDINFO,	NETLINK_XFRM_SOCKET__NLMSG_WRITE },
+	{ XFRM_MSG_GETSPDINFO,	NETLINK_XFRM_SOCKET__NLMSG_READ  },
+	{ XFRM_MSG_MAPPING,	NETLINK_XFRM_SOCKET__NLMSG_READ  },
 };
 
 static struct nlmsg_perm nlmsg_audit_perms[] =
diff --git a/security/selinux/ss/avtab.c b/security/selinux/ss/avtab.c
index a3dd9faa19c0..2e4ff003abcd 100644
--- a/security/selinux/ss/avtab.c
+++ b/security/selinux/ss/avtab.c
@@ -24,6 +24,7 @@
 #include "policydb.h"
 
 static struct kmem_cache *avtab_node_cachep;
+static struct kmem_cache *avtab_operation_cachep;
 
 static inline int avtab_hash(struct avtab_key *keyp, u16 mask)
 {
@@ -37,11 +38,24 @@ avtab_insert_node(struct avtab *h, int hvalue,
 		  struct avtab_key *key, struct avtab_datum *datum)
 {
 	struct avtab_node *newnode;
+	struct avtab_operation *ops;
 	newnode = kmem_cache_zalloc(avtab_node_cachep, GFP_KERNEL);
 	if (newnode == NULL)
 		return NULL;
 	newnode->key = *key;
-	newnode->datum = *datum;
+
+	if (key->specified & AVTAB_OP) {
+		ops = kmem_cache_zalloc(avtab_operation_cachep, GFP_KERNEL);
+		if (ops == NULL) {
+			kmem_cache_free(avtab_node_cachep, newnode);
+			return NULL;
+		}
+		*ops = *(datum->u.ops);
+		newnode->datum.u.ops = ops;
+	} else {
+		newnode->datum.u.data = datum->u.data;
+	}
+
 	if (prev) {
 		newnode->next = prev->next;
 		prev->next = newnode;
@@ -70,8 +84,11 @@ static int avtab_insert(struct avtab *h, struct avtab_key *key, struct avtab_dat
 		if (key->source_type == cur->key.source_type &&
 		    key->target_type == cur->key.target_type &&
 		    key->target_class == cur->key.target_class &&
-		    (specified & cur->key.specified))
+		    (specified & cur->key.specified)) {
+			if (specified & AVTAB_OPNUM)
+				break;
 			return -EEXIST;
+		}
 		if (key->source_type < cur->key.source_type)
 			break;
 		if (key->source_type == cur->key.source_type &&
@@ -232,6 +249,9 @@ void avtab_destroy(struct avtab *h)
 		while (cur) {
 			temp = cur;
 			cur = cur->next;
+			if (temp->key.specified & AVTAB_OP)
+				kmem_cache_free(avtab_operation_cachep,
+							temp->datum.u.ops);
 			kmem_cache_free(avtab_node_cachep, temp);
 		}
 		h->htable[i] = NULL;
@@ -320,7 +340,13 @@ static uint16_t spec_order[] = {
 	AVTAB_AUDITALLOW,
 	AVTAB_TRANSITION,
 	AVTAB_CHANGE,
-	AVTAB_MEMBER
+	AVTAB_MEMBER,
+	AVTAB_OPNUM_ALLOWED,
+	AVTAB_OPNUM_AUDITALLOW,
+	AVTAB_OPNUM_DONTAUDIT,
+	AVTAB_OPTYPE_ALLOWED,
+	AVTAB_OPTYPE_AUDITALLOW,
+	AVTAB_OPTYPE_DONTAUDIT
 };
 
 int avtab_read_item(struct avtab *a, void *fp, struct policydb *pol,
@@ -330,10 +356,11 @@ int avtab_read_item(struct avtab *a, void *fp, struct policydb *pol,
 {
 	__le16 buf16[4];
 	u16 enabled;
-	__le32 buf32[7];
 	u32 items, items2, val, vers = pol->policyvers;
 	struct avtab_key key;
 	struct avtab_datum datum;
+	struct avtab_operation ops;
+	__le32 buf32[ARRAY_SIZE(ops.op.perms)];
 	int i, rc;
 	unsigned set;
 
@@ -390,11 +417,15 @@ int avtab_read_item(struct avtab *a, void *fp, struct policydb *pol,
 			printk(KERN_ERR "SELinux: avtab: entry has both access vectors and types\n");
 			return -EINVAL;
 		}
+		if (val & AVTAB_OP) {
+			printk(KERN_ERR "SELinux: avtab: entry has operations\n");
+			return -EINVAL;
+		}
 
 		for (i = 0; i < ARRAY_SIZE(spec_order); i++) {
 			if (val & spec_order[i]) {
 				key.specified = spec_order[i] | enabled;
-				datum.data = le32_to_cpu(buf32[items++]);
+				datum.u.data = le32_to_cpu(buf32[items++]);
 				rc = insertf(a, &key, &datum, p);
 				if (rc)
 					return rc;
@@ -413,7 +444,6 @@ int avtab_read_item(struct avtab *a, void *fp, struct policydb *pol,
 		printk(KERN_ERR "SELinux: avtab: truncated entry\n");
 		return rc;
 	}
-
 	items = 0;
 	key.source_type = le16_to_cpu(buf16[items++]);
 	key.target_type = le16_to_cpu(buf16[items++]);
@@ -437,14 +467,32 @@ int avtab_read_item(struct avtab *a, void *fp, struct policydb *pol,
 		return -EINVAL;
 	}
 
-	rc = next_entry(buf32, fp, sizeof(u32));
-	if (rc) {
-		printk(KERN_ERR "SELinux: avtab: truncated entry\n");
-		return rc;
+	if ((vers < POLICYDB_VERSION_IOCTL_OPERATIONS)
+			|| !(key.specified & AVTAB_OP)) {
+		rc = next_entry(buf32, fp, sizeof(u32));
+		if (rc) {
+			printk(KERN_ERR "SELinux: avtab: truncated entry\n");
+			return rc;
+		}
+		datum.u.data = le32_to_cpu(*buf32);
+	} else {
+		memset(&ops, 0, sizeof(struct avtab_operation));
+		rc = next_entry(&ops.type, fp, sizeof(u8));
+		if (rc) {
+			printk(KERN_ERR "SELinux: avtab: truncated entry\n");
+			return rc;
+		}
+		rc = next_entry(buf32, fp, sizeof(u32)*ARRAY_SIZE(ops.op.perms));
+		if (rc) {
+			printk(KERN_ERR "SELinux: avtab: truncated entry\n");
+			return rc;
+		}
+		for (i = 0; i < ARRAY_SIZE(ops.op.perms); i++)
+			ops.op.perms[i] = le32_to_cpu(buf32[i]);
+		datum.u.ops = &ops;
 	}
-	datum.data = le32_to_cpu(*buf32);
 	if ((key.specified & AVTAB_TYPE) &&
-	    !policydb_type_isvalid(pol, datum.data)) {
+	    !policydb_type_isvalid(pol, datum.u.data)) {
 		printk(KERN_ERR "SELinux: avtab: invalid type\n");
 		return -EINVAL;
 	}
@@ -504,8 +552,9 @@ bad:
 int avtab_write_item(struct policydb *p, struct avtab_node *cur, void *fp)
 {
 	__le16 buf16[4];
-	__le32 buf32[1];
+	__le32 buf32[ARRAY_SIZE(cur->datum.u.ops->op.perms)];
 	int rc;
+	unsigned int i;
 
 	buf16[0] = cpu_to_le16(cur->key.source_type);
 	buf16[1] = cpu_to_le16(cur->key.target_type);
@@ -514,8 +563,16 @@ int avtab_write_item(struct policydb *p, struct avtab_node *cur, void *fp)
 	rc = put_entry(buf16, sizeof(u16), 4, fp);
 	if (rc)
 		return rc;
-	buf32[0] = cpu_to_le32(cur->datum.data);
-	rc = put_entry(buf32, sizeof(u32), 1, fp);
+
+	if (cur->key.specified & AVTAB_OP) {
+		for (i = 0; i < ARRAY_SIZE(cur->datum.u.ops->op.perms); i++)
+			buf32[i] = cpu_to_le32(cur->datum.u.ops->op.perms[i]);
+		rc = put_entry(buf32, sizeof(u32),
+				ARRAY_SIZE(cur->datum.u.ops->op.perms), fp);
+	} else {
+		buf32[0] = cpu_to_le32(cur->datum.u.data);
+		rc = put_entry(buf32, sizeof(u32), 1, fp);
+	}
 	if (rc)
 		return rc;
 	return 0;
@@ -548,9 +605,13 @@ void avtab_cache_init(void)
 	avtab_node_cachep = kmem_cache_create("avtab_node",
 					      sizeof(struct avtab_node),
 					      0, SLAB_PANIC, NULL);
+	avtab_operation_cachep = kmem_cache_create("avtab_operation",
+					      sizeof(struct avtab_operation),
+					      0, SLAB_PANIC, NULL);
 }
 
 void avtab_cache_destroy(void)
 {
 	kmem_cache_destroy(avtab_node_cachep);
+	kmem_cache_destroy(avtab_operation_cachep);
 }
diff --git a/security/selinux/ss/avtab.h b/security/selinux/ss/avtab.h
index 63ce2f9e441d..97acd6fa705e 100644
--- a/security/selinux/ss/avtab.h
+++ b/security/selinux/ss/avtab.h
@@ -23,6 +23,8 @@
 #ifndef _SS_AVTAB_H_
 #define _SS_AVTAB_H_
 
+#include "security.h"
+
 struct avtab_key {
 	u16 source_type;	/* source type */
 	u16 target_type;	/* target type */
@@ -35,13 +37,34 @@ struct avtab_key {
 #define AVTAB_MEMBER		0x0020
 #define AVTAB_CHANGE		0x0040
 #define AVTAB_TYPE		(AVTAB_TRANSITION | AVTAB_MEMBER | AVTAB_CHANGE)
+#define AVTAB_OPNUM_ALLOWED	0x0100
+#define AVTAB_OPNUM_AUDITALLOW	0x0200
+#define AVTAB_OPNUM_DONTAUDIT	0x0400
+#define AVTAB_OPNUM		(AVTAB_OPNUM_ALLOWED | \
+				AVTAB_OPNUM_AUDITALLOW | \
+				AVTAB_OPNUM_DONTAUDIT)
+#define AVTAB_OPTYPE_ALLOWED	0x1000
+#define AVTAB_OPTYPE_AUDITALLOW	0x2000
+#define AVTAB_OPTYPE_DONTAUDIT	0x4000
+#define AVTAB_OPTYPE		(AVTAB_OPTYPE_ALLOWED | \
+				AVTAB_OPTYPE_AUDITALLOW | \
+				AVTAB_OPTYPE_DONTAUDIT)
+#define AVTAB_OP		(AVTAB_OPNUM | AVTAB_OPTYPE)
 #define AVTAB_ENABLED_OLD   0x80000000 /* reserved for used in cond_avtab */
 #define AVTAB_ENABLED		0x8000 /* reserved for used in cond_avtab */
 	u16 specified;	/* what field is specified */
 };
 
+struct avtab_operation {
+	u8 type;
+	struct operation_perm op;
+};
+
 struct avtab_datum {
-	u32 data; /* access vector or type value */
+	union {
+		u32 data; /* access vector or type value */
+		struct avtab_operation *ops; /* ioctl operations */
+	} u;
 };
 
 struct avtab_node {
diff --git a/security/selinux/ss/conditional.c b/security/selinux/ss/conditional.c
index 377d148e7157..16651c7a1541 100644
--- a/security/selinux/ss/conditional.c
+++ b/security/selinux/ss/conditional.c
@@ -15,6 +15,7 @@
 
 #include "security.h"
 #include "conditional.h"
+#include "services.h"
 
 /*
  * cond_evaluate_expr evaluates a conditional expr
@@ -617,21 +618,39 @@ int cond_write_list(struct policydb *p, struct cond_node *list, void *fp)
 
 	return 0;
 }
+
+void cond_compute_operation(struct avtab *ctab, struct avtab_key *key,
+		struct operation_decision *od)
+{
+	struct avtab_node *node;
+
+	if (!ctab || !key || !od)
+		return;
+
+	for (node = avtab_search_node(ctab, key); node;
+			node = avtab_search_node_next(node, key->specified)) {
+		if (node->key.specified & AVTAB_ENABLED)
+			services_compute_operation_num(od, node);
+	}
+	return;
+
+}
 /* Determine whether additional permissions are granted by the conditional
  * av table, and if so, add them to the result
  */
-void cond_compute_av(struct avtab *ctab, struct avtab_key *key, struct av_decision *avd)
+void cond_compute_av(struct avtab *ctab, struct avtab_key *key,
+		struct av_decision *avd, struct operation *ops)
 {
 	struct avtab_node *node;
 
-	if (!ctab || !key || !avd)
+	if (!ctab || !key || !avd || !ops)
 		return;
 
 	for (node = avtab_search_node(ctab, key); node;
 				node = avtab_search_node_next(node, key->specified)) {
 		if ((u16)(AVTAB_ALLOWED|AVTAB_ENABLED) ==
 		    (node->key.specified & (AVTAB_ALLOWED|AVTAB_ENABLED)))
-			avd->allowed |= node->datum.data;
+			avd->allowed |= node->datum.u.data;
 		if ((u16)(AVTAB_AUDITDENY|AVTAB_ENABLED) ==
 		    (node->key.specified & (AVTAB_AUDITDENY|AVTAB_ENABLED)))
 			/* Since a '0' in an auditdeny mask represents a
@@ -639,10 +658,13 @@ void cond_compute_av(struct avtab *ctab, struct avtab_key *key, struct av_decisi
 			 * the '&' operand to ensure that all '0's in the mask
 			 * are retained (much unlike the allow and auditallow cases).
 			 */
-			avd->auditdeny &= node->datum.data;
+			avd->auditdeny &= node->datum.u.data;
 		if ((u16)(AVTAB_AUDITALLOW|AVTAB_ENABLED) ==
 		    (node->key.specified & (AVTAB_AUDITALLOW|AVTAB_ENABLED)))
-			avd->auditallow |= node->datum.data;
+			avd->auditallow |= node->datum.u.data;
+		if ((node->key.specified & AVTAB_ENABLED) &&
+				(node->key.specified & AVTAB_OP))
+			services_compute_operation_type(ops, node);
 	}
 	return;
 }
diff --git a/security/selinux/ss/conditional.h b/security/selinux/ss/conditional.h
index 4d1f87466508..80ee2bb20eee 100644
--- a/security/selinux/ss/conditional.h
+++ b/security/selinux/ss/conditional.h
@@ -73,8 +73,10 @@ int cond_read_list(struct policydb *p, void *fp);
 int cond_write_bool(void *key, void *datum, void *ptr);
 int cond_write_list(struct policydb *p, struct cond_node *list, void *fp);
 
-void cond_compute_av(struct avtab *ctab, struct avtab_key *key, struct av_decision *avd);
-
+void cond_compute_av(struct avtab *ctab, struct avtab_key *key,
+		struct av_decision *avd, struct operation *ops);
+void cond_compute_operation(struct avtab *ctab, struct avtab_key *key,
+		struct operation_decision *od);
 int evaluate_cond_node(struct policydb *p, struct cond_node *node);
 
 #endif /* _CONDITIONAL_H_ */
diff --git a/security/selinux/ss/policydb.c b/security/selinux/ss/policydb.c
index fc6950b8ec99..a683475e1635 100644
--- a/security/selinux/ss/policydb.c
+++ b/security/selinux/ss/policydb.c
@@ -148,6 +148,11 @@ static struct policydb_compat_info policydb_compat[] = {
 		.sym_num	= SYM_NUM,
 		.ocon_num	= OCON_NUM,
 	},
+	{
+		.version	= POLICYDB_VERSION_IOCTL_OPERATIONS,
+		.sym_num	= SYM_NUM,
+		.ocon_num	= OCON_NUM,
+	},
 };
 
 static struct policydb_compat_info *policydb_lookup_compat(int version)
diff --git a/security/selinux/ss/services.c b/security/selinux/ss/services.c
index 18caa16de27b..88178da2b834 100644
--- a/security/selinux/ss/services.c
+++ b/security/selinux/ss/services.c
@@ -92,9 +92,10 @@ static int context_struct_to_string(struct context *context, char **scontext,
 				    u32 *scontext_len);
 
 static void context_struct_compute_av(struct context *scontext,
-				      struct context *tcontext,
-				      u16 tclass,
-				      struct av_decision *avd);
+					struct context *tcontext,
+					u16 tclass,
+					struct av_decision *avd,
+					struct operation *ops);
 
 struct selinux_mapping {
 	u16 value; /* policy value */
@@ -564,7 +565,8 @@ static void type_attribute_bounds_av(struct context *scontext,
 		context_struct_compute_av(&lo_scontext,
 					  tcontext,
 					  tclass,
-					  &lo_avd);
+					  &lo_avd,
+					  NULL);
 		if ((lo_avd.allowed & avd->allowed) == avd->allowed)
 			return;		/* no masked permission */
 		masked = ~lo_avd.allowed & avd->allowed;
@@ -579,7 +581,8 @@ static void type_attribute_bounds_av(struct context *scontext,
 		context_struct_compute_av(scontext,
 					  &lo_tcontext,
 					  tclass,
-					  &lo_avd);
+					  &lo_avd,
+					  NULL);
 		if ((lo_avd.allowed & avd->allowed) == avd->allowed)
 			return;		/* no masked permission */
 		masked = ~lo_avd.allowed & avd->allowed;
@@ -595,7 +598,8 @@ static void type_attribute_bounds_av(struct context *scontext,
 		context_struct_compute_av(&lo_scontext,
 					  &lo_tcontext,
 					  tclass,
-					  &lo_avd);
+					  &lo_avd,
+					  NULL);
 		if ((lo_avd.allowed & avd->allowed) == avd->allowed)
 			return;		/* no masked permission */
 		masked = ~lo_avd.allowed & avd->allowed;
@@ -611,14 +615,39 @@ static void type_attribute_bounds_av(struct context *scontext,
 	}
 }
 
+/* flag ioctl types that have operation permissions */
+void services_compute_operation_type(
+		struct operation *ops,
+		struct avtab_node *node)
+{
+	u8 type;
+	unsigned int i;
+
+	if (node->key.specified & AVTAB_OPTYPE) {
+		/* if allowing one or more complete types */
+		for (i = 0; i < ARRAY_SIZE(ops->type); i++)
+			ops->type[i] |= node->datum.u.ops->op.perms[i];
+	} else {
+		/* if allowing operations within a type */
+		type = node->datum.u.ops->type;
+		security_operation_set(ops->type, type);
+	}
+
+	/* If no ioctl commands are allowed, ignore auditallow and auditdeny */
+	if (node->key.specified & AVTAB_OPTYPE_ALLOWED ||
+			node->key.specified & AVTAB_OPNUM_ALLOWED)
+		ops->len = 1;
+}
+
 /*
- * Compute access vectors based on a context structure pair for
- * the permissions in a particular class.
+ * Compute access vectors and operations ranges based on a context
+ * structure pair for the permissions in a particular class.
  */
 static void context_struct_compute_av(struct context *scontext,
-				      struct context *tcontext,
-				      u16 tclass,
-				      struct av_decision *avd)
+					struct context *tcontext,
+					u16 tclass,
+					struct av_decision *avd,
+					struct operation *ops)
 {
 	struct constraint_node *constraint;
 	struct role_allow *ra;
@@ -632,6 +661,10 @@ static void context_struct_compute_av(struct context *scontext,
 	avd->allowed = 0;
 	avd->auditallow = 0;
 	avd->auditdeny = 0xffffffff;
+	if (ops) {
+		memset(&ops->type, 0, sizeof(ops->type));
+		ops->len = 0;
+	}
 
 	if (unlikely(!tclass || tclass > policydb.p_classes.nprim)) {
 		if (printk_ratelimit())
@@ -646,7 +679,7 @@ static void context_struct_compute_av(struct context *scontext,
 	 * this permission check, then use it.
 	 */
 	avkey.target_class = tclass;
-	avkey.specified = AVTAB_AV;
+	avkey.specified = AVTAB_AV | AVTAB_OP;
 	sattr = flex_array_get(policydb.type_attr_map_array, scontext->type - 1);
 	BUG_ON(!sattr);
 	tattr = flex_array_get(policydb.type_attr_map_array, tcontext->type - 1);
@@ -659,15 +692,17 @@ static void context_struct_compute_av(struct context *scontext,
 			     node;
 			     node = avtab_search_node_next(node, avkey.specified)) {
 				if (node->key.specified == AVTAB_ALLOWED)
-					avd->allowed |= node->datum.data;
+					avd->allowed |= node->datum.u.data;
 				else if (node->key.specified == AVTAB_AUDITALLOW)
-					avd->auditallow |= node->datum.data;
+					avd->auditallow |= node->datum.u.data;
 				else if (node->key.specified == AVTAB_AUDITDENY)
-					avd->auditdeny &= node->datum.data;
+					avd->auditdeny &= node->datum.u.data;
+				else if (ops && (node->key.specified & AVTAB_OP))
+					services_compute_operation_type(ops, node);
 			}
 
 			/* Check conditional av table for additional permissions */
-			cond_compute_av(&policydb.te_cond_avtab, &avkey, avd);
+			cond_compute_av(&policydb.te_cond_avtab, &avkey, avd, ops);
 
 		}
 	}
@@ -898,13 +933,138 @@ static void avd_init(struct av_decision *avd)
 	avd->flags = 0;
 }
 
+void services_compute_operation_num(struct operation_decision *od,
+					struct avtab_node *node)
+{
+	unsigned int i;
 
+	if (node->key.specified & AVTAB_OPNUM) {
+		if (od->type != node->datum.u.ops->type)
+			return;
+	} else {
+		if (!security_operation_test(node->datum.u.ops->op.perms,
+					od->type))
+			return;
+	}
+
+	if (node->key.specified == AVTAB_OPTYPE_ALLOWED) {
+		od->specified |= OPERATION_ALLOWED;
+		memset(od->allowed->perms, 0xff,
+				sizeof(od->allowed->perms));
+	} else if (node->key.specified == AVTAB_OPTYPE_AUDITALLOW) {
+		od->specified |= OPERATION_AUDITALLOW;
+		memset(od->auditallow->perms, 0xff,
+				sizeof(od->auditallow->perms));
+	} else if (node->key.specified == AVTAB_OPTYPE_DONTAUDIT) {
+		od->specified |= OPERATION_DONTAUDIT;
+		memset(od->dontaudit->perms, 0xff,
+				sizeof(od->dontaudit->perms));
+	} else if (node->key.specified == AVTAB_OPNUM_ALLOWED) {
+		od->specified |= OPERATION_ALLOWED;
+		for (i = 0; i < ARRAY_SIZE(od->allowed->perms); i++)
+			od->allowed->perms[i] |=
+					node->datum.u.ops->op.perms[i];
+	} else if (node->key.specified == AVTAB_OPNUM_AUDITALLOW) {
+		od->specified |= OPERATION_AUDITALLOW;
+		for (i = 0; i < ARRAY_SIZE(od->auditallow->perms); i++)
+			od->auditallow->perms[i] |=
+					node->datum.u.ops->op.perms[i];
+	} else if (node->key.specified == AVTAB_OPNUM_DONTAUDIT) {
+		od->specified |= OPERATION_DONTAUDIT;
+		for (i = 0; i < ARRAY_SIZE(od->dontaudit->perms); i++)
+			od->dontaudit->perms[i] |=
+					node->datum.u.ops->op.perms[i];
+	} else {
+		BUG();
+	}
+}
+
+void security_compute_operation(u32 ssid,
+				u32 tsid,
+				u16 orig_tclass,
+				u8 type,
+				struct operation_decision *od)
+{
+	u16 tclass;
+	struct context *scontext, *tcontext;
+	struct avtab_key avkey;
+	struct avtab_node *node;
+	struct ebitmap *sattr, *tattr;
+	struct ebitmap_node *snode, *tnode;
+	unsigned int i, j;
+
+	od->type = type;
+	od->specified = 0;
+	memset(od->allowed->perms, 0, sizeof(od->allowed->perms));
+	memset(od->auditallow->perms, 0, sizeof(od->auditallow->perms));
+	memset(od->dontaudit->perms, 0, sizeof(od->dontaudit->perms));
+
+	read_lock(&policy_rwlock);
+	if (!ss_initialized)
+		goto allow;
+
+	scontext = sidtab_search(&sidtab, ssid);
+	if (!scontext) {
+		printk(KERN_ERR "SELinux: %s:  unrecognized SID %d\n",
+		       __func__, ssid);
+		goto out;
+	}
+
+	tcontext = sidtab_search(&sidtab, tsid);
+	if (!tcontext) {
+		printk(KERN_ERR "SELinux: %s:  unrecognized SID %d\n",
+		       __func__, tsid);
+		goto out;
+	}
+
+	tclass = unmap_class(orig_tclass);
+	if (unlikely(orig_tclass && !tclass)) {
+		if (policydb.allow_unknown)
+			goto allow;
+		goto out;
+	}
+
+
+	if (unlikely(!tclass || tclass > policydb.p_classes.nprim)) {
+		pr_warn_ratelimited("SELinux:  Invalid class %hu\n", tclass);
+		goto out;
+	}
+
+	avkey.target_class = tclass;
+	avkey.specified = AVTAB_OP;
+	sattr = flex_array_get(policydb.type_attr_map_array,
+				scontext->type - 1);
+	BUG_ON(!sattr);
+	tattr = flex_array_get(policydb.type_attr_map_array,
+				tcontext->type - 1);
+	BUG_ON(!tattr);
+	ebitmap_for_each_positive_bit(sattr, snode, i) {
+		ebitmap_for_each_positive_bit(tattr, tnode, j) {
+			avkey.source_type = i + 1;
+			avkey.target_type = j + 1;
+			for (node = avtab_search_node(&policydb.te_avtab, &avkey);
+			     node;
+			     node = avtab_search_node_next(node, avkey.specified))
+				services_compute_operation_num(od, node);
+
+			cond_compute_operation(&policydb.te_cond_avtab,
+						&avkey, od);
+		}
+	}
+out:
+	read_unlock(&policy_rwlock);
+	return;
+allow:
+	memset(od->allowed->perms, 0xff, sizeof(od->allowed->perms));
+	goto out;
+}
 /**
  * security_compute_av - Compute access vector decisions.
  * @ssid: source security identifier
  * @tsid: target security identifier
  * @tclass: target security class
  * @avd: access vector decisions
+ * @od: operation decisions
  *
  * Compute a set of access vector decisions based on the
  * SID pair (@ssid, @tsid) for the permissions in @tclass.
@@ -912,13 +1072,15 @@ static void avd_init(struct av_decision *avd)
 void security_compute_av(u32 ssid,
 			 u32 tsid,
 			 u16 orig_tclass,
-			 struct av_decision *avd)
+			 struct av_decision *avd,
+			 struct operation *ops)
 {
 	u16 tclass;
 	struct context *scontext = NULL, *tcontext = NULL;
 
 	read_lock(&policy_rwlock);
 	avd_init(avd);
+	ops->len = 0;
 	if (!ss_initialized)
 		goto allow;
 
@@ -946,7 +1108,7 @@ void security_compute_av(u32 ssid,
 			goto allow;
 		goto out;
 	}
-	context_struct_compute_av(scontext, tcontext, tclass, avd);
+	context_struct_compute_av(scontext, tcontext, tclass, avd, ops);
 	map_decision(orig_tclass, avd, policydb.allow_unknown);
 out:
 	read_unlock(&policy_rwlock);
@@ -992,7 +1154,7 @@ void security_compute_av_user(u32 ssid,
 		goto out;
 	}
 
-	context_struct_compute_av(scontext, tcontext, tclass, avd);
+	context_struct_compute_av(scontext, tcontext, tclass, avd, NULL);
  out:
 	read_unlock(&policy_rwlock);
 	return;
@@ -1512,7 +1674,7 @@ static int security_compute_sid(u32 ssid,
 
 	if (avdatum) {
 		/* Use the type from the type transition/member/change rule. */
-		newcontext.type = avdatum->data;
+		newcontext.type = avdatum->u.data;
 	}
 
 	/* if we have a objname this is a file trans check so check those rules */
diff --git a/security/selinux/ss/services.h b/security/selinux/ss/services.h
index e8d907e903cd..569757484d05 100644
--- a/security/selinux/ss/services.h
+++ b/security/selinux/ss/services.h
@@ -11,5 +11,11 @@
 
 extern struct policydb policydb;
 
+void services_compute_operation_type(struct operation *ops,
+				struct avtab_node *node);
+
+void services_compute_operation_num(struct operation_decision *od,
+					struct avtab_node *node);
+
 #endif	/* _SS_SERVICES_H_ */