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: #32553

PR-URL: #32627
Reviewed-By: Gireesh Punathil <gpunathi@in.ibm.com>
Reviewed-By: Ben Noordhuis <info@bnoordhuis.nl>
Reviewed-By: Tobias Nießen <tniessen@tnie.de>
Reviewed-By: James M Snell <jasnell@gmail.com>
PR-URL: #45387
Reviewed-By: Rafael Gonzaga <rafael.nunu@hotmail.com>

Author: addaleax

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,

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,

deps/zlib/crc_folding.c

@@ -25,6 +25,10 @@
 #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);\
@@ -41,6 +45,7 @@
         _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)
@@ -55,6 +60,7 @@ 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)
@@ -81,6 +87,7 @@ 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)
@@ -115,6 +122,7 @@ 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)
@@ -155,6 +163,7 @@ 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)
@@ -221,6 +230,7 @@ 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,
@@ -271,6 +281,7 @@ 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)
 {
@@ -427,6 +438,7 @@ 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);