chacha/asm/chacha-*.pl: fix typos in tail processing.

RT#4323
Reviewed-by: NRich Salz <rsalz@openssl.org>

crypto/chacha/asm/chacha-armv4.pl

@@ -440,9 +440,9 @@ $code.=<<___;
 	eorhs	@x[4],@x[4],@t[0]
 	eorhs	@x[5],@x[5],@t[1]
 # ifdef	__thumb2__
-	it	hi
+	 it	ne
 # endif
-	 ldrhi	@t[0],[sp,#4*(32+2)]	@ re-load len
+	 ldrne	@t[0],[sp,#4*(32+2)]	@ re-load len
 # ifdef	__thumb2__
 	itt	hs
 # endif
@@ -584,9 +584,9 @@ ___
 }
 $code.=<<___;
 # ifdef	__thumb2__
-	it	hi
+	it	ne
 # endif
-	ldrhi	@t[0],[sp,#4*(32+2)]		@ re-load len
+	ldrne	@t[0],[sp,#4*(32+2)]		@ re-load len
 # ifdef	__thumb2__
 	it	hs
 # endif
@@ -598,15 +598,15 @@ $code.=<<___;
 
 .Ltail:
 	ldr	r12,[sp,#4*(32+1)]	@ load inp
-	add	@t[2],sp,#4*(0)
+	add	@t[1],sp,#4*(0)
 	ldr	r14,[sp,#4*(32+0)]	@ load out
 
 .Loop_tail:
-	ldrb	@t[0],[@t[2]],#1	@ read buffer on stack
-	ldrb	@t[1],[r12],#1		@ read input
-	subs	@t[3],@t[3],#1
-	eor	@t[0],@t[0],@t[1]
-	strb	@t[0],[r14],#1		@ store output
+	ldrb	@t[2],[@t[1]],#1	@ read buffer on stack
+	ldrb	@t[3],[r12],#1		@ read input
+	subs	@t[0],@t[0],#1
+	eor	@t[3],@t[3],@t[2]
+	strb	@t[3],[r14],#1		@ store output
 	bne	.Loop_tail
 
 .Ldone:
@@ -1120,7 +1120,7 @@ $code.=<<___;
 # endif
 	stmia		@t[0],{@x[0]-@x[7]}
 	 add		@t[2],sp,#4*(0)
-	 sub		@t[3],@t[0],#64*3	@ len-=64*3
+	 sub		@t[3],@t[3],#64*3	@ len-=64*3
 
 .Loop_tail_neon:
 	ldrb		@t[0],[@t[2]],#1	@ read buffer on stack

crypto/chacha/asm/chacha-s390x.pl

@@ -257,11 +257,11 @@ $code.=<<___;
 	 st	@x[1],4*9(@t[0])
 	 x	@x[3],4*11(%r14)
 	 st	@x[2],4*10(@t[0])
-	la	%r14,64(%r14)
 	 st	@x[3],4*11(@t[0])
 
 	cl${g}r	%r14,@t[1]			# done yet?
-	jle	.Loop_outer
+	la	%r14,64(%r14)
+	jl	.Loop_outer
 
 .Ldone:
 	xgr	%r0,%r0
@@ -291,7 +291,7 @@ $code.=<<___;
 	lrvr	@x[1],@x[1]
 	lrvr	@x[2],@x[2]
 	lrvr	@x[3],@x[3]
-	stm	@x[0],@x[3],$stdframe+4*8+4*8($sp)
+	stm	@x[0],@x[3],$stdframe+4*8($sp)
 
 .Loop_tail:
 	llgc	@x[4],0(@x[6],%r14)

crypto/chacha/asm/chacha-x86_64.pl

@@ -1544,13 +1544,13 @@ $code.=<<___;
 	je		.Ldone4xop
 
 	lea		0x40($inp),$inp		# inp+=64*3
-	vmovdqa		$xa2,0x00(%rsp)
+	vmovdqa		$xa3,0x00(%rsp)
 	xor		%r10,%r10
-	vmovdqa		$xb2,0x10(%rsp)
+	vmovdqa		$xb3,0x10(%rsp)
 	lea		0x40($out),$out		# out+=64*3
-	vmovdqa		$xc2,0x20(%rsp)
+	vmovdqa		$xc3,0x20(%rsp)
 	sub		\$192,$len		# len-=64*3
-	vmovdqa		$xd2,0x30(%rsp)
+	vmovdqa		$xd3,0x30(%rsp)
 
 .Loop_tail4xop:
 	movzb		($inp,%r10),%eax