Many spelling fixes/typo's corrected.

Around 138 distinct errors found and fixed; thanks!

Reviewed-by: Kurt Roeckx <kurt@roeckx.be>
Reviewed-by: Tim Hudson <tjh@openssl.org>
Reviewed-by: Rich Salz <rsalz@openssl.org>
(Merged from https://github.com/openssl/openssl/pull/3459)

16 files changed, 31 insertions, 31 deletions

diff --git a/crypto/bn/asm/c64xplus-gf2m.pl b/crypto/bn/asm/c64xplus-gf2m.pl
index c0e5400807..9c46da3af8 100644
--- a/crypto/bn/asm/c64xplus-gf2m.pl
+++ b/crypto/bn/asm/c64xplus-gf2m.pl
@@ -43,7 +43,7 @@ $code.=<<___;
 	SHRU	$A,16,   $Ahi		; smash $A to two halfwords
 ||	EXTU	$A,16,16,$Alo
 
-	XORMPY	$Alo,$B_2,$Alox2	; 16x8 bits muliplication
+	XORMPY	$Alo,$B_2,$Alox2	; 16x8 bits multiplication
 ||	XORMPY	$Ahi,$B_2,$Ahix2
 ||	EXTU	$B,16,24,$B_1
 	XORMPY	$Alo,$B_0,$Alox0
diff --git a/crypto/bn/asm/ia64.S b/crypto/bn/asm/ia64.S
index 2bd4209d61..58f7628e81 100644
--- a/crypto/bn/asm/ia64.S
+++ b/crypto/bn/asm/ia64.S
@@ -20,7 +20,7 @@
 // disclaimed.
 // ====================================================================
 //
-// Version 2.x is Itanium2 re-tune. Few words about how Itanum2 is
+// Version 2.x is Itanium2 re-tune. Few words about how Itanium2 is
 // different from Itanium to this module viewpoint. Most notably, is it
 // "wider" than Itanium? Can you experience loop scalability as
 // discussed in commentary sections? Not really:-( Itanium2 has 6
@@ -141,7 +141,7 @@
 //	User Mask I want to excuse the kernel from preserving upper
 //	(f32-f128) FP register bank over process context switch, thus
 //	minimizing bus bandwidth consumption during the switch (i.e.
-//	after PKI opration completes and the program is off doing
+//	after PKI operation completes and the program is off doing
 //	something else like bulk symmetric encryption). Having said
 //	this, I also want to point out that it might be good idea
 //	to compile the whole toolkit (as well as majority of the
@@ -162,7 +162,7 @@
 //
 // bn_[add|sub]_words routines.
 //
-// Loops are spinning in 2*(n+5) ticks on Itanuim (provided that the
+// Loops are spinning in 2*(n+5) ticks on Itanium (provided that the
 // data reside in L1 cache, i.e. 2 ticks away). It's possible to
 // compress the epilogue and get down to 2*n+6, but at the cost of
 // scalability (the neat feature of this implementation is that it
@@ -500,7 +500,7 @@ bn_sqr_words:
 // possible to compress the epilogue (I'm getting tired to write this
 // comment over and over) and get down to 2*n+16 at the cost of
 // scalability. The decision will very likely be reconsidered after the
-// benchmark program is profiled. I.e. if perfomance gain on Itanium
+// benchmark program is profiled. I.e. if performance gain on Itanium
 // will appear larger than loss on "wider" IA-64, then the loop should
 // be explicitly split and the epilogue compressed.
 .L_bn_sqr_words_ctop:
@@ -936,7 +936,7 @@ bn_mul_comba8:
 		xma.hu	f118=f39,f127,f117	}
 { .mfi;		xma.lu	f117=f39,f127,f117	};;//
 //-------------------------------------------------//
-// Leaving muliplier's heaven... Quite a ride, huh?
+// Leaving multiplier's heaven... Quite a ride, huh?
 
 { .mii;	getf.sig	r31=f47
 	add		r25=r25,r24
diff --git a/crypto/bn/asm/parisc-mont.pl b/crypto/bn/asm/parisc-mont.pl
index 5b1c5eacca..a705e16392 100644
--- a/crypto/bn/asm/parisc-mont.pl
+++ b/crypto/bn/asm/parisc-mont.pl
@@ -21,7 +21,7 @@
 # optimal in respect to instruction set capabilities. Fair comparison
 # with vendor compiler is problematic, because OpenSSL doesn't define
 # BN_LLONG [presumably] for historical reasons, which drives compiler
-# toward 4 times 16x16=32-bit multiplicatons [plus complementary
+# toward 4 times 16x16=32-bit multiplications [plus complementary
 # shifts and additions] instead. This means that you should observe
 # several times improvement over code generated by vendor compiler
 # for PA-RISC 1.1, but the "baseline" is far from optimal. The actual
diff --git a/crypto/bn/asm/ppc-mont.pl b/crypto/bn/asm/ppc-mont.pl
index 213c7ec777..9aa96c8e87 100644
--- a/crypto/bn/asm/ppc-mont.pl
+++ b/crypto/bn/asm/ppc-mont.pl
@@ -37,7 +37,7 @@
 # and squaring procedure operating on lengths divisible by 8. Length
 # is expressed in number of limbs. RSA private key operations are
 # ~35-50% faster (more for longer keys) on contemporary high-end POWER
-# processors in 64-bit builds, [mysterously enough] more in 32-bit
+# processors in 64-bit builds, [mysteriously enough] more in 32-bit
 # builds. On low-end 32-bit processors performance improvement turned
 # to be marginal...
 
diff --git a/crypto/bn/asm/ppc64-mont.pl b/crypto/bn/asm/ppc64-mont.pl
index 1e19c958a1..0b2bb39f26 100644
--- a/crypto/bn/asm/ppc64-mont.pl
+++ b/crypto/bn/asm/ppc64-mont.pl
@@ -35,7 +35,7 @@
 # key lengths. As it's obviously inappropriate as "best all-round"
 # alternative, it has to be complemented with run-time CPU family
 # detection. Oh! It should also be noted that unlike other PowerPC
-# implementation IALU ppc-mont.pl module performs *suboptimaly* on
+# implementation IALU ppc-mont.pl module performs *suboptimally* on
 # >=1024-bit key lengths on Power 6. It should also be noted that
 # *everything* said so far applies to 64-bit builds! As far as 32-bit
 # application executed on 64-bit CPU goes, this module is likely to
@@ -1353,7 +1353,7 @@ $code.=<<___;
 	std	$t3,-16($tp)		; tp[j-1]
 	std	$t5,-8($tp)		; tp[j]
 
-	add	$carry,$carry,$ovf	; comsume upmost overflow
+	add	$carry,$carry,$ovf	; consume upmost overflow
 	add	$t6,$t6,$carry		; can not overflow
 	srdi	$carry,$t6,16
 	add	$t7,$t7,$carry
diff --git a/crypto/bn/asm/s390x-gf2m.pl b/crypto/bn/asm/s390x-gf2m.pl
index 57b0032d67..06181bf9b9 100644
--- a/crypto/bn/asm/s390x-gf2m.pl
+++ b/crypto/bn/asm/s390x-gf2m.pl
@@ -20,7 +20,7 @@
 # in bn_gf2m.c. It's kind of low-hanging mechanical port from C for
 # the time being... gcc 4.3 appeared to generate poor code, therefore
 # the effort. And indeed, the module delivers 55%-90%(*) improvement
-# on haviest ECDSA verify and ECDH benchmarks for 163- and 571-bit
+# on heaviest ECDSA verify and ECDH benchmarks for 163- and 571-bit
 # key lengths on z990, 30%-55%(*) - on z10, and 70%-110%(*) - on z196.
 # This is for 64-bit build. In 32-bit "highgprs" case improvement is
 # even higher, for example on z990 it was measured 80%-150%. ECDSA
diff --git a/crypto/bn/asm/sparcv8.S b/crypto/bn/asm/sparcv8.S
index 46d247353b..75d72eb92c 100644
--- a/crypto/bn/asm/sparcv8.S
+++ b/crypto/bn/asm/sparcv8.S
@@ -13,7 +13,7 @@
  */
 
 /*
- * This is my modest contributon to OpenSSL project (see
+ * This is my modest contribution to OpenSSL project (see
  * http://www.openssl.org/ for more information about it) and is
  * a drop-in SuperSPARC ISA replacement for crypto/bn/bn_asm.c
  * module. For updates see http://fy.chalmers.se/~appro/hpe/.
@@ -159,12 +159,12 @@ bn_mul_add_words:
  */
 bn_mul_words:
 	cmp	%o2,0
-	bg,a	.L_bn_mul_words_proceeed
+	bg,a	.L_bn_mul_words_proceed
 	ld	[%o1],%g2
 	retl
 	clr	%o0
 
-.L_bn_mul_words_proceeed:
+.L_bn_mul_words_proceed:
 	andcc	%o2,-4,%g0
 	bz	.L_bn_mul_words_tail
 	clr	%o5
@@ -251,12 +251,12 @@ bn_mul_words:
  */
 bn_sqr_words:
 	cmp	%o2,0
-	bg,a	.L_bn_sqr_words_proceeed
+	bg,a	.L_bn_sqr_words_proceed
 	ld	[%o1],%g2
 	retl
 	clr	%o0
 
-.L_bn_sqr_words_proceeed:
+.L_bn_sqr_words_proceed:
 	andcc	%o2,-4,%g0
 	bz	.L_bn_sqr_words_tail
 	clr	%o5
diff --git a/crypto/bn/asm/sparcv8plus.S b/crypto/bn/asm/sparcv8plus.S
index fded2fa358..fe4699b2bd 100644
--- a/crypto/bn/asm/sparcv8plus.S
+++ b/crypto/bn/asm/sparcv8plus.S
@@ -13,7 +13,7 @@
  */
 
 /*
- * This is my modest contributon to OpenSSL project (see
+ * This is my modest contribution to OpenSSL project (see
  * http://www.openssl.org/ for more information about it) and is
  * a drop-in UltraSPARC ISA replacement for crypto/bn/bn_asm.c
  * module. For updates see http://fy.chalmers.se/~appro/hpe/.
@@ -278,7 +278,7 @@ bn_mul_add_words:
  */
 bn_mul_words:
 	sra	%o2,%g0,%o2	! signx %o2
-	brgz,a	%o2,.L_bn_mul_words_proceeed
+	brgz,a	%o2,.L_bn_mul_words_proceed
 	lduw	[%o1],%g2
 	retl
 	clr	%o0
@@ -286,7 +286,7 @@ bn_mul_words:
 	nop
 	nop
 
-.L_bn_mul_words_proceeed:
+.L_bn_mul_words_proceed:
 	srl	%o3,%g0,%o3	! clruw	%o3
 	andcc	%o2,-4,%g0
 	bz,pn	%icc,.L_bn_mul_words_tail
@@ -366,7 +366,7 @@ bn_mul_words:
  */
 bn_sqr_words:
 	sra	%o2,%g0,%o2	! signx %o2
-	brgz,a	%o2,.L_bn_sqr_words_proceeed
+	brgz,a	%o2,.L_bn_sqr_words_proceed
 	lduw	[%o1],%g2
 	retl
 	clr	%o0
@@ -374,7 +374,7 @@ bn_sqr_words:
 	nop
 	nop
 
-.L_bn_sqr_words_proceeed:
+.L_bn_sqr_words_proceed:
 	andcc	%o2,-4,%g0
 	nop
 	bz,pn	%icc,.L_bn_sqr_words_tail
diff --git a/crypto/bn/asm/sparcv9-mont.pl b/crypto/bn/asm/sparcv9-mont.pl
index 3268846dfc..44d28ac496 100644
--- a/crypto/bn/asm/sparcv9-mont.pl
+++ b/crypto/bn/asm/sparcv9-mont.pl
@@ -611,7 +611,7 @@ $code.=<<___;
 	add	$tp,8,$tp
 .type	$fname,#function
 .size	$fname,(.-$fname)
-.asciz	"Montgomery Multipltication for SPARCv9, CRYPTOGAMS by <appro\@openssl.org>"
+.asciz	"Montgomery Multiplication for SPARCv9, CRYPTOGAMS by <appro\@openssl.org>"
 .align	32
 ___
 $code =~ s/\`([^\`]*)\`/eval($1)/gem;
diff --git a/crypto/bn/asm/sparcv9a-mont.pl b/crypto/bn/asm/sparcv9a-mont.pl
index 69ef9e2d4f..c8f759df9f 100755
--- a/crypto/bn/asm/sparcv9a-mont.pl
+++ b/crypto/bn/asm/sparcv9a-mont.pl
@@ -865,7 +865,7 @@ $fname:
 	restore
 .type   $fname,#function
 .size	$fname,(.-$fname)
-.asciz	"Montgomery Multipltication for UltraSPARC, CRYPTOGAMS by <appro\@openssl.org>"
+.asciz	"Montgomery Multiplication for UltraSPARC, CRYPTOGAMS by <appro\@openssl.org>"
 .align	32
 ___
 
diff --git a/crypto/bn/asm/vis3-mont.pl b/crypto/bn/asm/vis3-mont.pl
index 64dba4480f..04694a4c6c 100644
--- a/crypto/bn/asm/vis3-mont.pl
+++ b/crypto/bn/asm/vis3-mont.pl
@@ -16,7 +16,7 @@
 
 # October 2012.
 #
-# SPARCv9 VIS3 Montgomery multiplicaion procedure suitable for T3 and
+# SPARCv9 VIS3 Montgomery multiplication procedure suitable for T3 and
 # onward. There are three new instructions used here: umulxhi,
 # addxc[cc] and initializing store. On T3 RSA private key operations
 # are 1.54/1.87/2.11/2.26 times faster for 512/1024/2048/4096-bit key
diff --git a/crypto/bn/asm/x86-gf2m.pl b/crypto/bn/asm/x86-gf2m.pl
index 562f539943..d03efcc750 100644
--- a/crypto/bn/asm/x86-gf2m.pl
+++ b/crypto/bn/asm/x86-gf2m.pl
@@ -152,7 +152,7 @@ $R="mm0";
 	 &xor	($a4,$a2);		# a2=a4^a2^a4
 	 &mov	(&DWP(5*4,"esp"),$a1);	# a1^a4
 	 &xor	($a4,$a1);		# a1^a2^a4
-	&sar	(@i[1],31);		# broardcast 30th bit
+	&sar	(@i[1],31);		# broadcast 30th bit
 	&and	($lo,$b);
 	 &mov	(&DWP(6*4,"esp"),$a2);	# a2^a4
 	&and	(@i[1],$b);
diff --git a/crypto/bn/asm/x86-mont.pl b/crypto/bn/asm/x86-mont.pl
index 32daf5c215..66997e279b 100755
--- a/crypto/bn/asm/x86-mont.pl
+++ b/crypto/bn/asm/x86-mont.pl
@@ -78,7 +78,7 @@ $frame=32;				# size of above frame rounded up to 16n
 	&lea	("ebp",&DWP(-$frame,"esp","edi",4));	# future alloca($frame+4*(num+2))
 	&neg	("edi");
 
-	# minimize cache contention by arraning 2K window between stack
+	# minimize cache contention by arranging 2K window between stack
 	# pointer and ap argument [np is also position sensitive vector,
 	# but it's assumed to be near ap, as it's allocated at ~same
 	# time].
diff --git a/crypto/bn/asm/x86_64-gf2m.pl b/crypto/bn/asm/x86_64-gf2m.pl
index 0181f52ca4..0fd6e985d7 100644
--- a/crypto/bn/asm/x86_64-gf2m.pl
+++ b/crypto/bn/asm/x86_64-gf2m.pl
@@ -68,7 +68,7 @@ _mul_1x1:
 	sar	\$63,$i0		# broadcast 62nd bit
 	lea	(,$a1,4),$a4
 	and	$b,$a
-	sar	\$63,$i1		# boardcast 61st bit
+	sar	\$63,$i1		# broadcast 61st bit
 	mov	$a,$hi			# $a is $lo
 	shl	\$63,$lo
 	and	$b,$i0
diff --git a/crypto/bn/asm/x86_64-mont.pl b/crypto/bn/asm/x86_64-mont.pl
index a4da3de7fa..7e6e9027de 100755
--- a/crypto/bn/asm/x86_64-mont.pl
+++ b/crypto/bn/asm/x86_64-mont.pl
@@ -319,7 +319,7 @@ $code.=<<___;
 	mov	%rax,($rp,$i,8)		# rp[i]=tp[i]-np[i]
 	mov	8($ap,$i,8),%rax	# tp[i+1]
 	lea	1($i),$i		# i++
-	dec	$j			# doesnn't affect CF!
+	dec	$j			# doesn't affect CF!
 	jnz	.Lsub
 
 	sbb	\$0,%rax		# handle upmost overflow bit
@@ -750,7 +750,7 @@ $code.=<<___;
 	mov	56($ap,$i,8),@ri[3]
 	sbb	40($np,$i,8),@ri[1]
 	lea	4($i),$i		# i++
-	dec	$j			# doesnn't affect CF!
+	dec	$j			# doesn't affect CF!
 	jnz	.Lsub4x
 
 	mov	@ri[0],0($rp,$i,8)	# rp[i]=tp[i]-np[i]
diff --git a/crypto/bn/asm/x86_64-mont5.pl b/crypto/bn/asm/x86_64-mont5.pl
index 1666fbd7a2..263543579f 100755
--- a/crypto/bn/asm/x86_64-mont5.pl
+++ b/crypto/bn/asm/x86_64-mont5.pl
@@ -419,7 +419,7 @@ $code.=<<___;
 	mov	%rax,($rp,$i,8)		# rp[i]=tp[i]-np[i]
 	mov	8($ap,$i,8),%rax	# tp[i+1]
 	lea	1($i),$i		# i++
-	dec	$j			# doesnn't affect CF!
+	dec	$j			# doesn't affect CF!
 	jnz	.Lsub
 
 	sbb	\$0,%rax		# handle upmost overflow bit
@@ -2421,7 +2421,7 @@ my $N=$STRIDE/4;		# should match cache line size
 $code.=<<___;
 	movdqa	0(%rax),%xmm0		# 00000001000000010000000000000000
 	movdqa	16(%rax),%xmm1		# 00000002000000020000000200000002
-	lea	88-112(%rsp,%r10),%r10	# place the mask after tp[num+1] (+ICache optimizaton)
+	lea	88-112(%rsp,%r10),%r10	# place the mask after tp[num+1] (+ICache optimization)
 	lea	128($bp),$bptr		# size optimization
 
 	pshufd	\$0,%xmm5,%xmm5		# broadcast index