libwebp: update to 0.4.3-rc1

rolls up local cherry-picks on 0.4.2

BUG=

Review URL: https://codereview.chromium.org/983613002

Cr-Commit-Position: refs/heads/master@{#319347}

9 files changed, 84 insertions, 19 deletions

diff --git a/third_party/libwebp/dsp/alpha_processing.c b/third_party/libwebp/dsp/alpha_processing.c
index d0f7a6c..c8e0b4b 100644
--- a/third_party/libwebp/dsp/alpha_processing.c
+++ b/third_party/libwebp/dsp/alpha_processing.c
@@ -311,7 +311,12 @@ int (*WebPExtractAlpha)(const uint8_t*, int, int, int, uint8_t*, int);
 
 extern void WebPInitAlphaProcessingSSE2(void);
 
+static volatile VP8CPUInfo alpha_processing_last_cpuinfo_used =
+    (VP8CPUInfo)&alpha_processing_last_cpuinfo_used;
+
 void WebPInitAlphaProcessing(void) {
+  if (alpha_processing_last_cpuinfo_used == VP8GetCPUInfo) return;
+
   WebPMultARGBRow = MultARGBRow;
   WebPMultRow = MultRow;
   WebPApplyAlphaMultiply = ApplyAlphaMultiply;
@@ -326,4 +331,5 @@ void WebPInitAlphaProcessing(void) {
     }
 #endif
   }
+  alpha_processing_last_cpuinfo_used = VP8GetCPUInfo;
 }
diff --git a/third_party/libwebp/dsp/cpu.c b/third_party/libwebp/dsp/cpu.c
index 8754f87..ef04a75 100644
--- a/third_party/libwebp/dsp/cpu.c
+++ b/third_party/libwebp/dsp/cpu.c
@@ -29,16 +29,18 @@ static WEBP_INLINE void GetCPUInfo(int cpu_info[4], int info_type) {
     "cpuid\n"
     "xchg %%edi, %%ebx\n"
     : "=a"(cpu_info[0]), "=D"(cpu_info[1]), "=c"(cpu_info[2]), "=d"(cpu_info[3])
-    : "a"(info_type));
+    : "a"(info_type), "c"(0));
 }
 #elif defined(__i386__) || defined(__x86_64__)
 static WEBP_INLINE void GetCPUInfo(int cpu_info[4], int info_type) {
   __asm__ volatile (
     "cpuid\n"
     : "=a"(cpu_info[0]), "=b"(cpu_info[1]), "=c"(cpu_info[2]), "=d"(cpu_info[3])
-    : "a"(info_type));
+    : "a"(info_type), "c"(0));
 }
-#elif defined(_MSC_FULL_VER) && _MSC_FULL_VER >= 150030729  // >= VS2008 SP1
+#elif (defined(_M_X64) || defined(_M_IX86)) && \
+      defined(_MSC_FULL_VER) && _MSC_FULL_VER >= 150030729  // >= VS2008 SP1
+#include <intrin.h>
 #define GetCPUInfo(info, type) __cpuidex(info, type, 0)  // set ecx=0
 #elif defined(WEBP_MSC_SSE2)
 #define GetCPUInfo __cpuid
@@ -55,7 +57,9 @@ static WEBP_INLINE uint64_t xgetbv(void) {
     : "=a"(eax), "=d"(edx) : "c" (ecx));
   return ((uint64_t)edx << 32) | eax;
 }
-#elif defined(_MSC_FULL_VER) && _MSC_FULL_VER >= 160040219  // >= VS2010 SP1
+#elif (defined(_M_X64) || defined(_M_IX86)) && \
+      defined(_MSC_FULL_VER) && _MSC_FULL_VER >= 160040219  // >= VS2010 SP1
+#include <immintrin.h>
 #define xgetbv() _xgetbv(0)
 #elif defined(_MSC_VER) && defined(_M_IX86)
 static WEBP_INLINE uint64_t xgetbv(void) {
diff --git a/third_party/libwebp/dsp/dec.c b/third_party/libwebp/dsp/dec.c
index 65a2a88..3a8dc81 100644
--- a/third_party/libwebp/dsp/dec.c
+++ b/third_party/libwebp/dsp/dec.c
@@ -688,7 +688,12 @@ extern void VP8DspInitSSE2(void);
 extern void VP8DspInitNEON(void);
 extern void VP8DspInitMIPS32(void);
 
+static volatile VP8CPUInfo dec_last_cpuinfo_used =
+    (VP8CPUInfo)&dec_last_cpuinfo_used;
+
 void VP8DspInit(void) {
+  if (dec_last_cpuinfo_used == VP8GetCPUInfo) return;
+
   VP8InitClipTables();
 
   VP8TransformWHT = TransformWHT;
@@ -727,5 +732,5 @@ void VP8DspInit(void) {
     }
 #endif
   }
+  dec_last_cpuinfo_used = VP8GetCPUInfo;
 }
-
diff --git a/third_party/libwebp/dsp/enc.c b/third_party/libwebp/dsp/enc.c
index e4ea8cb..f4e72d4 100644
--- a/third_party/libwebp/dsp/enc.c
+++ b/third_party/libwebp/dsp/enc.c
@@ -692,7 +692,12 @@ extern void VP8EncDspInitAVX2(void);
 extern void VP8EncDspInitNEON(void);
 extern void VP8EncDspInitMIPS32(void);
 
+static volatile VP8CPUInfo enc_last_cpuinfo_used =
+    (VP8CPUInfo)&enc_last_cpuinfo_used;
+
 void VP8EncDspInit(void) {
+  if (enc_last_cpuinfo_used == VP8GetCPUInfo) return;
+
   VP8DspInit();  // common inverse transforms
   InitTables();
 
@@ -737,5 +742,6 @@ void VP8EncDspInit(void) {
     }
 #endif
   }
+  enc_last_cpuinfo_used = VP8GetCPUInfo;
 }
 
diff --git a/third_party/libwebp/dsp/enc_neon.c b/third_party/libwebp/dsp/enc_neon.c
index bcab8ff..5814fac 100644
--- a/third_party/libwebp/dsp/enc_neon.c
+++ b/third_party/libwebp/dsp/enc_neon.c
@@ -1012,9 +1012,10 @@ static int QuantizeBlock(int16_t in[16], int16_t out[16],
   const int16x8_t out0 = Quantize(in, mtx, 0);
   const int16x8_t out1 = Quantize(in, mtx, 8);
   uint8x8x4_t shuffles;
-  // vtbl4_u8 is marked unavailable for iOS arm64, use wider versions there.
+  // vtbl?_u8 are marked unavailable for iOS arm64 with Xcode < 6.3, use
+  // non-standard versions there.
 #if defined(__APPLE__) && defined(__aarch64__) && \
-    defined(__apple_build_version__)
+    defined(__apple_build_version__) && (__apple_build_version__< 6020037)
   uint8x16x2_t all_out;
   INIT_VECTOR2(all_out, vreinterpretq_u8_s16(out0), vreinterpretq_u8_s16(out1));
   INIT_VECTOR4(shuffles,
diff --git a/third_party/libwebp/dsp/lossless.c b/third_party/libwebp/dsp/lossless.c
index a1bf358..ee334bc 100644
--- a/third_party/libwebp/dsp/lossless.c
+++ b/third_party/libwebp/dsp/lossless.c
@@ -1590,7 +1590,12 @@ extern void VP8LDspInitSSE2(void);
 extern void VP8LDspInitNEON(void);
 extern void VP8LDspInitMIPS32(void);
 
+static volatile VP8CPUInfo lossless_last_cpuinfo_used =
+    (VP8CPUInfo)&lossless_last_cpuinfo_used;
+
 void VP8LDspInit(void) {
+  if (lossless_last_cpuinfo_used == VP8GetCPUInfo) return;
+
   memcpy(VP8LPredictors, kPredictorsC, sizeof(VP8LPredictors));
 
   VP8LSubtractGreenFromBlueAndRed = VP8LSubtractGreenFromBlueAndRed_C;
@@ -1634,6 +1639,7 @@ void VP8LDspInit(void) {
     }
 #endif
   }
+  lossless_last_cpuinfo_used = VP8GetCPUInfo;
 }
 
 //------------------------------------------------------------------------------
diff --git a/third_party/libwebp/dsp/lossless_neon.c b/third_party/libwebp/dsp/lossless_neon.c
index 987767b..8c82b19 100644
--- a/third_party/libwebp/dsp/lossless_neon.c
+++ b/third_party/libwebp/dsp/lossless_neon.c
@@ -259,20 +259,45 @@ static uint32_t Predictor13(uint32_t left, const uint32_t* const top) {
 //------------------------------------------------------------------------------
 // Subtract-Green Transform
 
-// vtbl? are unavailable in iOS/arm64 builds.
-#if !defined(__aarch64__)
+// vtbl?_u8 are marked unavailable for iOS arm64 with Xcode < 6.3, use
+// non-standard versions there.
+#if defined(__APPLE__) && defined(__aarch64__) && \
+    defined(__apple_build_version__) && (__apple_build_version__< 6020037)
+#define USE_VTBLQ
+#endif
+
+#ifdef USE_VTBLQ
+// 255 = byte will be zeroed
+static const uint8_t kGreenShuffle[16] = {
+  1, 255, 1, 255, 5, 255, 5, 255, 9, 255, 9, 255, 13, 255, 13, 255
+};
 
-// 255 = byte will be zero'd
+static WEBP_INLINE uint8x16_t DoGreenShuffle(const uint8x16_t argb,
+                                             const uint8x16_t shuffle) {
+  return vcombine_u8(vtbl1q_u8(argb, vget_low_u8(shuffle)),
+                     vtbl1q_u8(argb, vget_high_u8(shuffle)));
+}
+#else  // !USE_VTBLQ
+// 255 = byte will be zeroed
 static const uint8_t kGreenShuffle[8] = { 1, 255, 1, 255, 5, 255, 5, 255  };
 
+static WEBP_INLINE uint8x16_t DoGreenShuffle(const uint8x16_t argb,
+                                             const uint8x8_t shuffle) {
+  return vcombine_u8(vtbl1_u8(vget_low_u8(argb), shuffle),
+                     vtbl1_u8(vget_high_u8(argb), shuffle));
+}
+#endif  // USE_VTBLQ
+
 static void SubtractGreenFromBlueAndRed(uint32_t* argb_data, int num_pixels) {
   const uint32_t* const end = argb_data + (num_pixels & ~3);
+#ifdef USE_VTBLQ
+  const uint8x16_t shuffle = vld1q_u8(kGreenShuffle);
+#else
   const uint8x8_t shuffle = vld1_u8(kGreenShuffle);
+#endif
   for (; argb_data < end; argb_data += 4) {
     const uint8x16_t argb = vld1q_u8((uint8_t*)argb_data);
-    const uint8x16_t greens =
-        vcombine_u8(vtbl1_u8(vget_low_u8(argb), shuffle),
-                    vtbl1_u8(vget_high_u8(argb), shuffle));
+    const uint8x16_t greens = DoGreenShuffle(argb, shuffle);
     vst1q_u8((uint8_t*)argb_data, vsubq_u8(argb, greens));
   }
   // fallthrough and finish off with plain-C
@@ -281,19 +306,21 @@ static void SubtractGreenFromBlueAndRed(uint32_t* argb_data, int num_pixels) {
 
 static void AddGreenToBlueAndRed(uint32_t* argb_data, int num_pixels) {
   const uint32_t* const end = argb_data + (num_pixels & ~3);
+#ifdef USE_VTBLQ
+  const uint8x16_t shuffle = vld1q_u8(kGreenShuffle);
+#else
   const uint8x8_t shuffle = vld1_u8(kGreenShuffle);
+#endif
   for (; argb_data < end; argb_data += 4) {
     const uint8x16_t argb = vld1q_u8((uint8_t*)argb_data);
-    const uint8x16_t greens =
-        vcombine_u8(vtbl1_u8(vget_low_u8(argb), shuffle),
-                    vtbl1_u8(vget_high_u8(argb), shuffle));
+    const uint8x16_t greens = DoGreenShuffle(argb, shuffle);
     vst1q_u8((uint8_t*)argb_data, vaddq_u8(argb, greens));
   }
   // fallthrough and finish off with plain-C
   VP8LAddGreenToBlueAndRed_C(argb_data, num_pixels & 3);
 }
 
-#endif   // !__aarch64__
+#undef USE_VTBLQ
 
 #endif   // USE_INTRINSICS
 
@@ -320,11 +347,9 @@ void VP8LDspInitNEON(void) {
   VP8LPredictors[12] = Predictor12;
   VP8LPredictors[13] = Predictor13;
 
-#if !defined(__aarch64__)
   VP8LSubtractGreenFromBlueAndRed = SubtractGreenFromBlueAndRed;
   VP8LAddGreenToBlueAndRed = AddGreenToBlueAndRed;
 #endif
-#endif
 
 #endif   // WEBP_USE_NEON
 }
diff --git a/third_party/libwebp/dsp/upsampling.c b/third_party/libwebp/dsp/upsampling.c
index 2b1656b..53c68d5 100644
--- a/third_party/libwebp/dsp/upsampling.c
+++ b/third_party/libwebp/dsp/upsampling.c
@@ -189,7 +189,12 @@ const WebPYUV444Converter WebPYUV444Converters[MODE_LAST] = {
 extern void WebPInitUpsamplersSSE2(void);
 extern void WebPInitUpsamplersNEON(void);
 
+static volatile VP8CPUInfo upsampling_last_cpuinfo_used2 =
+    (VP8CPUInfo)&upsampling_last_cpuinfo_used2;
+
 void WebPInitUpsamplers(void) {
+  if (upsampling_last_cpuinfo_used2 == VP8GetCPUInfo) return;
+
 #ifdef FANCY_UPSAMPLING
   WebPUpsamplers[MODE_RGB]       = UpsampleRgbLinePair;
   WebPUpsamplers[MODE_RGBA]      = UpsampleRgbaLinePair;
@@ -217,6 +222,7 @@ void WebPInitUpsamplers(void) {
 #endif
   }
 #endif  // FANCY_UPSAMPLING
+  upsampling_last_cpuinfo_used2 = VP8GetCPUInfo;
 }
 
 //------------------------------------------------------------------------------
diff --git a/third_party/libwebp/dsp/yuv.c b/third_party/libwebp/dsp/yuv.c
index d7cb4eb..6f422da 100644
--- a/third_party/libwebp/dsp/yuv.c
+++ b/third_party/libwebp/dsp/yuv.c
@@ -123,7 +123,12 @@ WebPSamplerRowFunc WebPSamplers[MODE_LAST];
 extern void WebPInitSamplersSSE2(void);
 extern void WebPInitSamplersMIPS32(void);
 
+static volatile VP8CPUInfo yuv_last_cpuinfo_used =
+    (VP8CPUInfo)&yuv_last_cpuinfo_used;
+
 void WebPInitSamplers(void) {
+  if (yuv_last_cpuinfo_used == VP8GetCPUInfo) return;
+
   WebPSamplers[MODE_RGB]       = YuvToRgbRow;
   WebPSamplers[MODE_RGBA]      = YuvToRgbaRow;
   WebPSamplers[MODE_BGR]       = YuvToBgrRow;
@@ -149,6 +154,7 @@ void WebPInitSamplers(void) {
     }
 #endif  // WEBP_USE_MIPS32
   }
+  yuv_last_cpuinfo_used = VP8GetCPUInfo;
 }
 
 //-----------------------------------------------------------------------------