From b211c4dea1bae6a8816321987e9da1e52e94db4d Mon Sep 17 00:00:00 2001
From: Anna Henningsen <anna@addaleax.net>
Date: Fri, 3 Apr 2020 04:13:23 +0200
Subject: [PATCH] deps: fix zlib compilation for CPUs without SIMD features

Fix the compile flags so that zlib can run on CPUs that do
not have SSSE3/SSE4.2/etc. Do not compile zlib with flags that
indicate that those features are available, and instead enable
them selectively for functions that use them.

There are probably better way to do this, e.g. through gyp file
modifications as suggested in the issue. However, this patch
should do just fine until that happens.

Fixes: https://github.com/nodejs/node/issues/32553
---
 deps/zlib/adler32_simd.c |  4 ++++
 deps/zlib/crc32_simd.c   |  4 ++++
 deps/zlib/crc_folding.c  | 12 ++++++++++++
 deps/zlib/zlib.gyp       | 14 --------------
 4 files changed, 20 insertions(+), 14 deletions(-)

diff --git a/deps/zlib/adler32_simd.c b/deps/zlib/adler32_simd.c
index 1354915cc099..f8b07297b938 100644
--- a/deps/zlib/adler32_simd.c
+++ b/deps/zlib/adler32_simd.c
@@ -50,9 +50,13 @@
 #define NMAX 5552
 
 #if defined(ADLER32_SIMD_SSSE3)
+#ifndef __GNUC__
+#define __attribute__()
+#endif
 
 #include <tmmintrin.h>
 
+__attribute__((target("ssse3")))
 uint32_t ZLIB_INTERNAL adler32_simd_(  /* SSSE3 */
     uint32_t adler,
     const unsigned char *buf,
diff --git a/deps/zlib/crc32_simd.c b/deps/zlib/crc32_simd.c
index c8e5592f38ef..27481847e97b 100644
--- a/deps/zlib/crc32_simd.c
+++ b/deps/zlib/crc32_simd.c
@@ -8,6 +8,9 @@
 #include "crc32_simd.h"
 
 #if defined(CRC32_SIMD_SSE42_PCLMUL)
+#ifndef __GNUC__
+#define __attribute__()
+#endif
 
 /*
  * crc32_sse42_simd_(): compute the crc32 of the buffer, where the buffer
@@ -21,6 +24,7 @@
 #include <smmintrin.h>
 #include <wmmintrin.h>
 
+__attribute__((target("sse4.2,pclmul")))
 uint32_t ZLIB_INTERNAL crc32_sse42_simd_(  /* SSE4.2+PCLMUL */
     const unsigned char *buf,
     z_size_t len,
diff --git a/deps/zlib/crc_folding.c b/deps/zlib/crc_folding.c
index 48d77744aaf4..54f4b5c94010 100644
--- a/deps/zlib/crc_folding.c
+++ b/deps/zlib/crc_folding.c
@@ -23,6 +23,10 @@
 #include <immintrin.h>
 #include <wmmintrin.h>
 
+#ifndef __GNUC__
+#define __attribute__()
+#endif
+
 #define CRC_LOAD(s) \
     do { \
         __m128i xmm_crc0 = _mm_loadu_si128((__m128i *)s->crc0 + 0);\
@@ -39,6 +43,7 @@
         _mm_storeu_si128((__m128i *)s->crc0 + 4, xmm_crc_part);\
     } while (0);
 
+__attribute__((target("sse4.2,pclmul")))
 ZLIB_INTERNAL void crc_fold_init(deflate_state *const s)
 {
     CRC_LOAD(s)
@@ -53,6 +58,7 @@ ZLIB_INTERNAL void crc_fold_init(deflate_state *const s)
     s->strm->adler = 0;
 }
 
+__attribute__((target("sse4.2,pclmul")))
 local void fold_1(deflate_state *const s,
         __m128i *xmm_crc0, __m128i *xmm_crc1,
         __m128i *xmm_crc2, __m128i *xmm_crc3)
@@ -79,6 +85,7 @@ local void fold_1(deflate_state *const s,
     *xmm_crc3 = _mm_castps_si128(ps_res);
 }
 
+__attribute__((target("sse4.2,pclmul")))
 local void fold_2(deflate_state *const s,
         __m128i *xmm_crc0, __m128i *xmm_crc1,
         __m128i *xmm_crc2, __m128i *xmm_crc3)
@@ -113,6 +120,7 @@ local void fold_2(deflate_state *const s,
     *xmm_crc3 = _mm_castps_si128(ps_res31);
 }
 
+__attribute__((target("sse4.2,pclmul")))
 local void fold_3(deflate_state *const s,
         __m128i *xmm_crc0, __m128i *xmm_crc1,
         __m128i *xmm_crc2, __m128i *xmm_crc3)
@@ -153,6 +161,7 @@ local void fold_3(deflate_state *const s,
     *xmm_crc3 = _mm_castps_si128(ps_res32);
 }
 
+__attribute__((target("sse4.2,pclmul")))
 local void fold_4(deflate_state *const s,
         __m128i *xmm_crc0, __m128i *xmm_crc1,
         __m128i *xmm_crc2, __m128i *xmm_crc3)
@@ -219,6 +228,7 @@ local const unsigned zalign(32) pshufb_shf_table[60] = {
 	0x0201008f,0x06050403,0x0a090807,0x0e0d0c0b  /* shl  1 (16 -15)/shr15*/
 };
 
+__attribute__((target("sse4.2,pclmul")))
 local void partial_fold(deflate_state *const s, const size_t len,
         __m128i *xmm_crc0, __m128i *xmm_crc1,
         __m128i *xmm_crc2, __m128i *xmm_crc3,
@@ -269,6 +279,7 @@ local void partial_fold(deflate_state *const s, const size_t len,
     *xmm_crc3 = _mm_castps_si128(ps_res);
 }
 
+__attribute__((target("sse4.2,pclmul")))
 ZLIB_INTERNAL void crc_fold_copy(deflate_state *const s,
         unsigned char *dst, const unsigned char *src, long len)
 {
@@ -425,6 +436,7 @@ local const unsigned zalign(16) crc_mask2[4] = {
     0x00000000, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF
 };
 
+__attribute__((target("sse4.2,pclmul")))
 unsigned ZLIB_INTERNAL crc_fold_512to32(deflate_state *const s)
 {
     const __m128i xmm_mask  = _mm_load_si128((__m128i *)crc_mask);
diff --git a/deps/zlib/zlib.gyp b/deps/zlib/zlib.gyp
index c73b9adba902..6f5a8ce3464b 100644
--- a/deps/zlib/zlib.gyp
+++ b/deps/zlib/zlib.gyp
@@ -91,20 +91,6 @@
                 'x86.c',
               ],
               'conditions': [
-                ['OS!="win" or llvm_version!="0.0"', {
-                  'cflags': [
-                    '-mssse3',
-                    '-msse4.2',
-                    '-mpclmul',
-                  ],
-                  'xcode_settings': {
-                    'OTHER_CFLAGS': [
-                      '-mssse3',
-                      '-msse4.2',
-                      '-mpclmul',
-                    ],
-                  },
-                }],
                 ['target_arch=="x64"', {
                   'defines': [ 'INFLATE_CHUNK_READ_64LE' ],
                 }],