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)

12 files changed, 22 insertions, 22 deletions

diff --git a/crypto/sha/asm/sha1-586.pl b/crypto/sha/asm/sha1-586.pl
index c6c977ab03..ca3763991c 100644
--- a/crypto/sha/asm/sha1-586.pl
+++ b/crypto/sha/asm/sha1-586.pl
@@ -35,7 +35,7 @@
 # P4		+85%(!)			+45%
 #
 # As you can see Pentium came out as looser:-( Yet I reckoned that
-# improvement on P4 outweights the loss and incorporate this
+# improvement on P4 outweighs the loss and incorporate this
 # re-tuned code to 0.9.7 and later.
 # ----------------------------------------------------------------
 
@@ -549,7 +549,7 @@ for($i=0;$i<20-4;$i+=2) {
 # being implemented in SSSE3). Once 8 quadruples or 32 elements are
 # collected, it switches to routine proposed by Max Locktyukhin.
 #
-# Calculations inevitably require temporary reqisters, and there are
+# Calculations inevitably require temporary registers, and there are
 # no %xmm registers left to spare. For this reason part of the ring
 # buffer, X[2..4] to be specific, is offloaded to 3 quadriples ring
 # buffer on the stack. Keep in mind that X[2] is alias X[-6], X[3] -
diff --git a/crypto/sha/asm/sha1-mb-x86_64.pl b/crypto/sha/asm/sha1-mb-x86_64.pl
index 56e15292a7..443b649830 100644
--- a/crypto/sha/asm/sha1-mb-x86_64.pl
+++ b/crypto/sha/asm/sha1-mb-x86_64.pl
@@ -444,7 +444,7 @@ for(;$i<80;$i++)	{ &BODY_20_39($i,@V); unshift(@V,pop(@V)); }
 $code.=<<___;
 	movdqa	(%rbx),@Xi[0]			# pull counters
 	mov	\$1,%ecx
-	cmp	4*0(%rbx),%ecx			# examinte counters
+	cmp	4*0(%rbx),%ecx			# examine counters
 	pxor	$t2,$t2
 	cmovge	$Tbl,@ptr[0]			# cancel input
 	cmp	4*1(%rbx),%ecx
@@ -1508,10 +1508,10 @@ avx2_handler:
 	mov	-48(%rax),%r15
 	mov	%rbx,144($context)	# restore context->Rbx
 	mov	%rbp,160($context)	# restore context->Rbp
-	mov	%r12,216($context)	# restore cotnext->R12
-	mov	%r13,224($context)	# restore cotnext->R13
-	mov	%r14,232($context)	# restore cotnext->R14
-	mov	%r15,240($context)	# restore cotnext->R15
+	mov	%r12,216($context)	# restore context->R12
+	mov	%r13,224($context)	# restore context->R13
+	mov	%r14,232($context)	# restore context->R14
+	mov	%r15,240($context)	# restore context->R15
 
 	lea	-56-10*16(%rax),%rsi
 	lea	512($context),%rdi	# &context.Xmm6
diff --git a/crypto/sha/asm/sha1-x86_64.pl b/crypto/sha/asm/sha1-x86_64.pl
index 8b7bbfc261..60819f6186 100755
--- a/crypto/sha/asm/sha1-x86_64.pl
+++ b/crypto/sha/asm/sha1-x86_64.pl
@@ -1984,9 +1984,9 @@ ssse3_handler:
 	mov	-40(%rax),%r14
 	mov	%rbx,144($context)	# restore context->Rbx
 	mov	%rbp,160($context)	# restore context->Rbp
-	mov	%r12,216($context)	# restore cotnext->R12
-	mov	%r13,224($context)	# restore cotnext->R13
-	mov	%r14,232($context)	# restore cotnext->R14
+	mov	%r12,216($context)	# restore context->R12
+	mov	%r13,224($context)	# restore context->R13
+	mov	%r14,232($context)	# restore context->R14
 
 .Lcommon_seh_tail:
 	mov	8(%rax),%rdi
diff --git a/crypto/sha/asm/sha256-586.pl b/crypto/sha/asm/sha256-586.pl
index bc25b2dab5..48830728e7 100644
--- a/crypto/sha/asm/sha256-586.pl
+++ b/crypto/sha/asm/sha256-586.pl
@@ -18,7 +18,7 @@
 #
 # Performance improvement over compiler generated code varies from
 # 10% to 40% [see below]. Not very impressive on some µ-archs, but
-# it's 5 times smaller and optimizies amount of writes.
+# it's 5 times smaller and optimizes amount of writes.
 #
 # May 2012.
 #
diff --git a/crypto/sha/asm/sha256-mb-x86_64.pl b/crypto/sha/asm/sha256-mb-x86_64.pl
index 24276f9e67..73978dbd81 100644
--- a/crypto/sha/asm/sha256-mb-x86_64.pl
+++ b/crypto/sha/asm/sha256-mb-x86_64.pl
@@ -1508,10 +1508,10 @@ avx2_handler:
 	mov	-48(%rax),%r15
 	mov	%rbx,144($context)	# restore context->Rbx
 	mov	%rbp,160($context)	# restore context->Rbp
-	mov	%r12,216($context)	# restore cotnext->R12
-	mov	%r13,224($context)	# restore cotnext->R13
-	mov	%r14,232($context)	# restore cotnext->R14
-	mov	%r15,240($context)	# restore cotnext->R15
+	mov	%r12,216($context)	# restore context->R12
+	mov	%r13,224($context)	# restore context->R13
+	mov	%r14,232($context)	# restore context->R14
+	mov	%r15,240($context)	# restore context->R15
 
 	lea	-56-10*16(%rax),%rsi
 	lea	512($context),%rdi	# &context.Xmm6
diff --git a/crypto/sha/asm/sha512-586.pl b/crypto/sha/asm/sha512-586.pl
index 35006e8b9f..867ce30b97 100644
--- a/crypto/sha/asm/sha512-586.pl
+++ b/crypto/sha/asm/sha512-586.pl
@@ -42,7 +42,7 @@
 # (*)	whichever best applicable.
 # (**)	x86_64 assembler performance is presented for reference
 #	purposes, the results are for integer-only code.
-# (***)	paddq is increadibly slow on Atom.
+# (***)	paddq is incredibly slow on Atom.
 #
 # IALU code-path is optimized for elder Pentiums. On vanilla Pentium
 # performance improvement over compiler generated code reaches ~60%,
diff --git a/crypto/sha/asm/sha512-armv8.pl b/crypto/sha/asm/sha512-armv8.pl
index c55efb3085..88ad44ee5e 100644
--- a/crypto/sha/asm/sha512-armv8.pl
+++ b/crypto/sha/asm/sha512-armv8.pl
@@ -35,7 +35,7 @@
 #	on Cortex-A53 (or by 4 cycles per round).
 # (***)	Super-impressive coefficients over gcc-generated code are
 #	indication of some compiler "pathology", most notably code
-#	generated with -mgeneral-regs-only is significanty faster
+#	generated with -mgeneral-regs-only is significantly faster
 #	and the gap is only 40-90%.
 #
 # October 2016.
diff --git a/crypto/sha/asm/sha512-parisc.pl b/crypto/sha/asm/sha512-parisc.pl
index 1469bedbd6..5a082ba623 100755
--- a/crypto/sha/asm/sha512-parisc.pl
+++ b/crypto/sha/asm/sha512-parisc.pl
@@ -773,7 +773,7 @@ foreach (split("\n",$code)) {
 	s/shd\s+(%r[0-9]+),(%r[0-9]+),([0-9]+)/
 		$3>31 ? sprintf("shd\t%$2,%$1,%d",$3-32)	# rotation for >=32
 		:       sprintf("shd\t%$1,%$2,%d",$3)/e			or
-	# translate made up instructons: _ror, _shr, _align, _shl
+	# translate made up instructions: _ror, _shr, _align, _shl
 	s/_ror(\s+)(%r[0-9]+),/
 		($SZ==4 ? "shd" : "shrpd")."$1$2,$2,"/e			or
 
diff --git a/crypto/sha/asm/sha512-ppc.pl b/crypto/sha/asm/sha512-ppc.pl
index fe95b01509..71699f6637 100755
--- a/crypto/sha/asm/sha512-ppc.pl
+++ b/crypto/sha/asm/sha512-ppc.pl
@@ -26,7 +26,7 @@
 #
 # (*)	64-bit code in 32-bit application context, which actually is
 #	on TODO list. It should be noted that for safe deployment in
-#	32-bit *mutli-threaded* context asyncronous signals should be
+#	32-bit *multi-threaded* context asynchronous signals should be
 #	blocked upon entry to SHA512 block routine. This is because
 #	32-bit signaling procedure invalidates upper halves of GPRs.
 #	Context switch procedure preserves them, but not signaling:-(
diff --git a/crypto/sha/asm/sha512p8-ppc.pl b/crypto/sha/asm/sha512p8-ppc.pl
index 5457c4aa16..93dfef20a9 100755
--- a/crypto/sha/asm/sha512p8-ppc.pl
+++ b/crypto/sha/asm/sha512p8-ppc.pl
@@ -25,7 +25,7 @@
 # sha1-ppc.pl and 1.6x slower than aes-128-cbc. Another interesting
 # result is degree of computational resources' utilization. POWER8 is
 # "massively multi-threaded chip" and difference between single- and
-# maximum multi-process benchmark results tells that utlization is
+# maximum multi-process benchmark results tells that utilization is
 # whooping 94%. For sha512-ppc.pl we get [not unimpressive] 84% and
 # for sha1-ppc.pl - 73%. 100% means that multi-process result equals
 # to single-process one, given that all threads end up on the same
diff --git a/crypto/sha/keccak1600.c b/crypto/sha/keccak1600.c
index d925734a17..e7223486af 100644
--- a/crypto/sha/keccak1600.c
+++ b/crypto/sha/keccak1600.c
@@ -1055,7 +1055,7 @@ static uint64_t BitDeinterleave(uint64_t Ai)
  * as blocksize. It is commonly (1600 - 256*n)/8, e.g. 168, 136, 104,
  * 72, but can also be (1600 - 448)/8 = 144. All this means that message
  * padding and intermediate sub-block buffering, byte- or bitwise, is
- * caller's reponsibility.
+ * caller's responsibility.
  */
 size_t SHA3_absorb(uint64_t A[5][5], const unsigned char *inp, size_t len,
                    size_t r)
diff --git a/crypto/sha/sha_locl.h b/crypto/sha/sha_locl.h
index 93b0f1ac01..4e5a090382 100644
--- a/crypto/sha/sha_locl.h
+++ b/crypto/sha/sha_locl.h
@@ -68,7 +68,7 @@ int HASH_INIT(SHA_CTX *c)
 
 /*
  * As pointed out by Wei Dai, F() below can be simplified to the code in
- * F_00_19.  Wei attributes these optimisations to Peter Gutmann's SHS code,
+ * F_00_19.  Wei attributes these optimizations to Peter Gutmann's SHS code,
  * and he attributes it to Rich Schroeppel.
  *      #define F(x,y,z) (((x) & (y)) | ((~(x)) & (z)))
  * I've just become aware of another tweak to be made, again from Wei Dai,