Rename chacha20_poly1305_*_nohw to chacha20_poly1305_*_sse41

Brian Smith points out that the functions actually require SSE 4.1. I
just didn't notice because that check was inside the
chacha20_poly1305_asm_capable check.

Change-Id: Ib7a0b876cb760411dd0fc0011fc7d18b1984e39a
Reviewed-on: https://boringssl-review.googlesource.com/c/boringssl/+/75847
Reviewed-by: Bob Beck <bbe@google.com>
Auto-Submit: David Benjamin <davidben@google.com>
Commit-Queue: Bob Beck <bbe@google.com>
diff --git a/crypto/cipher/aead_test.cc b/crypto/cipher/aead_test.cc
index a68bf53..a2e5635 100644
--- a/crypto/cipher/aead_test.cc
+++ b/crypto/cipher/aead_test.cc
@@ -826,8 +826,8 @@
     SCOPED_TRACE(len);
     union chacha20_poly1305_open_data open_ctx = {};
 #if defined(OPENSSL_X86_64)
-    CHECK_ABI(chacha20_poly1305_open_nohw, buf.get(), buf.get(), len, buf.get(),
-              len % 128, &open_ctx);
+    CHECK_ABI(chacha20_poly1305_open_sse41, buf.get(), buf.get(), len,
+              buf.get(), len % 128, &open_ctx);
     if (CRYPTO_is_AVX2_capable() && CRYPTO_is_BMI2_capable()) {
       CHECK_ABI(chacha20_poly1305_open_avx2, buf.get(), buf.get(), len,
                 buf.get(), len % 128, &open_ctx);
@@ -842,8 +842,8 @@
     SCOPED_TRACE(len);
     union chacha20_poly1305_seal_data seal_ctx = {};
 #if defined(OPENSSL_X86_64)
-    CHECK_ABI(chacha20_poly1305_seal_nohw, buf.get(), buf.get(), len, buf.get(),
-              len % 128, &seal_ctx);
+    CHECK_ABI(chacha20_poly1305_seal_sse41, buf.get(), buf.get(), len,
+              buf.get(), len % 128, &seal_ctx);
     if (CRYPTO_is_AVX2_capable() && CRYPTO_is_BMI2_capable()) {
       CHECK_ABI(chacha20_poly1305_seal_avx2, buf.get(), buf.get(), len,
                 buf.get(), len % 128, &seal_ctx);
diff --git a/crypto/cipher/asm/chacha20_poly1305_x86_64.pl b/crypto/cipher/asm/chacha20_poly1305_x86_64.pl
index 9297052..7c25943 100644
--- a/crypto/cipher/asm/chacha20_poly1305_x86_64.pl
+++ b/crypto/cipher/asm/chacha20_poly1305_x86_64.pl
@@ -440,10 +440,10 @@
 #                             union chacha20_poly1305_open_data *aead_data)
 #
 $code.="
-.globl chacha20_poly1305_open_nohw
-.type chacha20_poly1305_open_nohw,\@function,6
+.globl chacha20_poly1305_open_sse41
+.type chacha20_poly1305_open_sse41,\@function,6
 .align 64
-chacha20_poly1305_open_nohw:
+chacha20_poly1305_open_sse41:
 .cfi_startproc
     _CET_ENDBR
     push %rbp
@@ -849,7 +849,7 @@
         movdqa $C2, $B2
         movdqa $D2, $C2
     jmp .Lopen_sse_128_xor_hash
-.size chacha20_poly1305_open_nohw, .-chacha20_poly1305_open_nohw
+.size chacha20_poly1305_open_sse41, .-chacha20_poly1305_open_sse41
 .cfi_endproc
 
 ################################################################################
@@ -858,10 +858,10 @@
 #                             size_t plaintext_len, const uint8_t *ad,
 #                             size_t ad_len,
 #                             union chacha20_poly1305_seal_data *data);
-.globl  chacha20_poly1305_seal_nohw
-.type chacha20_poly1305_seal_nohw,\@function,6
+.globl  chacha20_poly1305_seal_sse41
+.type chacha20_poly1305_seal_sse41,\@function,6
 .align 64
-chacha20_poly1305_seal_nohw:
+chacha20_poly1305_seal_sse41:
 .cfi_startproc
     _CET_ENDBR
     push %rbp
@@ -1357,7 +1357,7 @@
     mov %r8, $itr2
     call poly_hash_ad_internal
     jmp .Lseal_sse_128_tail_xor
-.size chacha20_poly1305_seal_nohw, .-chacha20_poly1305_seal_nohw
+.size chacha20_poly1305_seal_sse41, .-chacha20_poly1305_seal_sse41
 .cfi_endproc\n";
 }
 
diff --git a/crypto/cipher/internal.h b/crypto/cipher/internal.h
index c10766d..58d10e0 100644
--- a/crypto/cipher/internal.h
+++ b/crypto/cipher/internal.h
@@ -146,7 +146,7 @@
 // write calculated tag value to |aead_data->out.tag|, which the caller must
 // check.
 #if defined(OPENSSL_X86_64)
-extern void chacha20_poly1305_open_nohw(
+extern void chacha20_poly1305_open_sse41(
     uint8_t *out_plaintext, const uint8_t *ciphertext, size_t plaintext_len,
     const uint8_t *ad, size_t ad_len, union chacha20_poly1305_open_data *data);
 extern void chacha20_poly1305_open_avx2(
@@ -161,8 +161,8 @@
     chacha20_poly1305_open_avx2(out_plaintext, ciphertext, plaintext_len, ad,
                                 ad_len, data);
   } else {
-    chacha20_poly1305_open_nohw(out_plaintext, ciphertext, plaintext_len, ad,
-                                ad_len, data);
+    chacha20_poly1305_open_sse41(out_plaintext, ciphertext, plaintext_len, ad,
+                                 ad_len, data);
   }
 }
 #else
@@ -179,7 +179,7 @@
 // value is over the computed ciphertext concatenated with |extra_ciphertext|
 // and written to |aead_data->out.tag|.
 #if defined(OPENSSL_X86_64)
-extern void chacha20_poly1305_seal_nohw(
+extern void chacha20_poly1305_seal_sse41(
     uint8_t *out_ciphertext, const uint8_t *plaintext, size_t plaintext_len,
     const uint8_t *ad, size_t ad_len, union chacha20_poly1305_seal_data *data);
 extern void chacha20_poly1305_seal_avx2(
@@ -194,8 +194,8 @@
     chacha20_poly1305_seal_avx2(out_ciphertext, plaintext, plaintext_len, ad,
                                 ad_len, data);
   } else {
-    chacha20_poly1305_seal_nohw(out_ciphertext, plaintext, plaintext_len, ad,
-                                ad_len, data);
+    chacha20_poly1305_seal_sse41(out_ciphertext, plaintext, plaintext_len, ad,
+                                 ad_len, data);
   }
 }
 #else
diff --git a/gen/crypto/chacha20_poly1305_x86_64-apple.S b/gen/crypto/chacha20_poly1305_x86_64-apple.S
index 5ae5849..a261463 100644
--- a/gen/crypto/chacha20_poly1305_x86_64-apple.S
+++ b/gen/crypto/chacha20_poly1305_x86_64-apple.S
@@ -212,11 +212,11 @@
 
 
 
-.globl	_chacha20_poly1305_open_nohw
-.private_extern _chacha20_poly1305_open_nohw
+.globl	_chacha20_poly1305_open_sse41
+.private_extern _chacha20_poly1305_open_sse41
 
 .p2align	6
-_chacha20_poly1305_open_nohw:
+_chacha20_poly1305_open_sse41:
 
 _CET_ENDBR
 	pushq	%rbp
@@ -2079,11 +2079,11 @@
 
 
 
-.globl	_chacha20_poly1305_seal_nohw
-.private_extern _chacha20_poly1305_seal_nohw
+.globl	_chacha20_poly1305_seal_sse41
+.private_extern _chacha20_poly1305_seal_sse41
 
 .p2align	6
-_chacha20_poly1305_seal_nohw:
+_chacha20_poly1305_seal_sse41:
 
 _CET_ENDBR
 	pushq	%rbp
diff --git a/gen/crypto/chacha20_poly1305_x86_64-linux.S b/gen/crypto/chacha20_poly1305_x86_64-linux.S
index 22123ee..180b41e 100644
--- a/gen/crypto/chacha20_poly1305_x86_64-linux.S
+++ b/gen/crypto/chacha20_poly1305_x86_64-linux.S
@@ -212,11 +212,11 @@
 .cfi_endproc	
 .size	poly_hash_ad_internal, .-poly_hash_ad_internal
 
-.globl	chacha20_poly1305_open_nohw
-.hidden chacha20_poly1305_open_nohw
-.type	chacha20_poly1305_open_nohw,@function
+.globl	chacha20_poly1305_open_sse41
+.hidden chacha20_poly1305_open_sse41
+.type	chacha20_poly1305_open_sse41,@function
 .align	64
-chacha20_poly1305_open_nohw:
+chacha20_poly1305_open_sse41:
 .cfi_startproc	
 _CET_ENDBR
 	pushq	%rbp
@@ -2084,7 +2084,7 @@
 	movdqa	%xmm10,%xmm6
 	movdqa	%xmm14,%xmm10
 	jmp	.Lopen_sse_128_xor_hash
-.size	chacha20_poly1305_open_nohw, .-chacha20_poly1305_open_nohw
+.size	chacha20_poly1305_open_sse41, .-chacha20_poly1305_open_sse41
 .cfi_endproc	
 
 
@@ -2093,11 +2093,11 @@
 
 
 
-.globl	chacha20_poly1305_seal_nohw
-.hidden chacha20_poly1305_seal_nohw
-.type	chacha20_poly1305_seal_nohw,@function
+.globl	chacha20_poly1305_seal_sse41
+.hidden chacha20_poly1305_seal_sse41
+.type	chacha20_poly1305_seal_sse41,@function
 .align	64
-chacha20_poly1305_seal_nohw:
+chacha20_poly1305_seal_sse41:
 .cfi_startproc	
 _CET_ENDBR
 	pushq	%rbp
@@ -4085,7 +4085,7 @@
 	movq	%r8,%r8
 	call	poly_hash_ad_internal
 	jmp	.Lseal_sse_128_tail_xor
-.size	chacha20_poly1305_seal_nohw, .-chacha20_poly1305_seal_nohw
+.size	chacha20_poly1305_seal_sse41, .-chacha20_poly1305_seal_sse41
 .cfi_endproc	
 
 
diff --git a/gen/crypto/chacha20_poly1305_x86_64-win.asm b/gen/crypto/chacha20_poly1305_x86_64-win.asm
index 22dbdfe..25c69ef 100644
--- a/gen/crypto/chacha20_poly1305_x86_64-win.asm
+++ b/gen/crypto/chacha20_poly1305_x86_64-win.asm
@@ -220,14 +220,14 @@
 
 
 
-global	chacha20_poly1305_open_nohw
+global	chacha20_poly1305_open_sse41
 
 ALIGN	64
-chacha20_poly1305_open_nohw:
+chacha20_poly1305_open_sse41:
 	mov	QWORD[8+rsp],rdi	;WIN64 prologue
 	mov	QWORD[16+rsp],rsi
 	mov	rax,rsp
-$L$SEH_begin_chacha20_poly1305_open_nohw:
+$L$SEH_begin_chacha20_poly1305_open_sse41:
 	mov	rdi,rcx
 	mov	rsi,rdx
 	mov	rdx,r8
@@ -2113,7 +2113,7 @@
 	movdqa	xmm6,xmm10
 	movdqa	xmm10,xmm14
 	jmp	NEAR $L$open_sse_128_xor_hash
-$L$SEH_end_chacha20_poly1305_open_nohw:
+$L$SEH_end_chacha20_poly1305_open_sse41:
 
 
 
@@ -2122,14 +2122,14 @@
 
 
 
-global	chacha20_poly1305_seal_nohw
+global	chacha20_poly1305_seal_sse41
 
 ALIGN	64
-chacha20_poly1305_seal_nohw:
+chacha20_poly1305_seal_sse41:
 	mov	QWORD[8+rsp],rdi	;WIN64 prologue
 	mov	QWORD[16+rsp],rsi
 	mov	rax,rsp
-$L$SEH_begin_chacha20_poly1305_seal_nohw:
+$L$SEH_begin_chacha20_poly1305_seal_sse41:
 	mov	rdi,rcx
 	mov	rsi,rdx
 	mov	rdx,r8
@@ -4135,7 +4135,7 @@
 	mov	r8,r8
 	call	poly_hash_ad_internal
 	jmp	NEAR $L$seal_sse_128_tail_xor
-$L$SEH_end_chacha20_poly1305_seal_nohw:
+$L$SEH_end_chacha20_poly1305_seal_sse41: