libwebp: Sync with upstream 1.3.1

https://chromium.googlesource.com/webm/libwebp/+/1.3.1/NEWS (cherry picked from commit 2529ad6)
akien-mga · Aug 28, 2023 · 2051e38 · 2051e38
1 parent 6a9c714
commit 2051e38
Show file tree

Hide file tree

Showing 47 changed files with 360 additions and 151 deletions.
diff --git a/thirdparty/README.md b/thirdparty/README.md
@@ -267,7 +267,7 @@ from the Android NDK r18.
 ## libwebp
 
 - Upstream: https://chromium.googlesource.com/webm/libwebp/
-- Version: 1.3.0 (b557776962a3dcc985d83bd4ed94e1e2e50d0fa2, 2022)
+- Version: 1.3.1 (fd7bb21c0cb56e8a82e9bfa376164b842f433f3b, 2023)
 - License: BSD-3-Clause
 
 Files extracted from upstream source:

diff --git a/thirdparty/libwebp/AUTHORS b/thirdparty/libwebp/AUTHORS
@@ -32,6 +32,7 @@ Contributors:
 - Mislav Bradac (mislavm at google dot com)
 - Nico Weber (thakis at chromium dot org)
 - Noel Chromium (noel at chromium dot org)
+- Nozomi Isozaki (nontan at pixiv dot co dot jp)
 - Oliver Wolff (oliver dot wolff at qt dot io)
 - Owen Rodley (orodley at google dot com)
 - Parag Salasakar (img dot mips1 at gmail dot com)
@@ -47,6 +48,7 @@ Contributors:
 - Somnath Banerjee (somnath dot banerjee at gmail dot com)
 - Sriraman Tallam (tmsriram at google dot com)
 - Tamar Levy (tamar dot levy at intel dot com)
+- Thiago Perrotta (tperrotta at google dot com)
 - Timothy Gu (timothygu99 at gmail dot com)
 - Urvang Joshi (urvang at google dot com)
 - Vikas Arora (vikasa at google dot com)

diff --git a/thirdparty/libwebp/sharpyuv/sharpyuv.c b/thirdparty/libwebp/sharpyuv/sharpyuv.c
@@ -440,6 +440,7 @@ static int DoSharpArgbToYuv(const uint8_t* r_ptr, const uint8_t* g_ptr,
 // By default SharpYuvConvert calls it with SharpYuvGetCPUInfo. If needed,
 // users can declare it as extern and call it with an alternate VP8CPUInfo
 // function.
+extern VP8CPUInfo SharpYuvGetCPUInfo;
 SHARPYUV_EXTERN void SharpYuvInit(VP8CPUInfo cpu_info_func);
 void SharpYuvInit(VP8CPUInfo cpu_info_func) {
   static volatile VP8CPUInfo sharpyuv_last_cpuinfo_used =

diff --git a/thirdparty/libwebp/sharpyuv/sharpyuv.h b/thirdparty/libwebp/sharpyuv/sharpyuv.h
@@ -37,7 +37,7 @@ extern "C" {
 // SharpYUV API version following the convention from semver.org
 #define SHARPYUV_VERSION_MAJOR 0
 #define SHARPYUV_VERSION_MINOR 2
-#define SHARPYUV_VERSION_PATCH 0
+#define SHARPYUV_VERSION_PATCH 1
 // Version as a uint32_t. The major number is the high 8 bits.
 // The minor number is the middle 8 bits. The patch number is the low 16 bits.
 #define SHARPYUV_MAKE_VERSION(MAJOR, MINOR, PATCH) \

diff --git a/thirdparty/libwebp/sharpyuv/sharpyuv_dsp.c b/thirdparty/libwebp/sharpyuv/sharpyuv_dsp.c
@@ -72,6 +72,7 @@ void (*SharpYuvFilterRow)(const int16_t* A, const int16_t* B, int len,
                           const uint16_t* best_y, uint16_t* out,
                           int bit_depth);
 
+extern VP8CPUInfo SharpYuvGetCPUInfo;
 extern void InitSharpYuvSSE2(void);
 extern void InitSharpYuvNEON(void);
 

diff --git a/thirdparty/libwebp/src/dec/tree_dec.c b/thirdparty/libwebp/src/dec/tree_dec.c
@@ -12,10 +12,11 @@
 // Author: Skal (pascal.massimino@gmail.com)
 
 #include "src/dec/vp8i_dec.h"
+#include "src/dsp/cpu.h"
 #include "src/utils/bit_reader_inl_utils.h"
 
 #if !defined(USE_GENERIC_TREE)
-#if !defined(__arm__) && !defined(_M_ARM) && !defined(__aarch64__)
+#if !defined(__arm__) && !defined(_M_ARM) && !WEBP_AARCH64
 // using a table is ~1-2% slower on ARM. Prefer the coded-tree approach then.
 #define USE_GENERIC_TREE 1   // ALTERNATE_CODE
 #else

diff --git a/thirdparty/libwebp/src/dec/vp8_dec.c b/thirdparty/libwebp/src/dec/vp8_dec.c
@@ -494,6 +494,8 @@ static int GetCoeffsAlt(VP8BitReader* const br,
   return 16;
 }
 
+extern VP8CPUInfo VP8GetCPUInfo;
+
 WEBP_DSP_INIT_FUNC(InitGetCoeffs) {
   if (VP8GetCPUInfo != NULL && VP8GetCPUInfo(kSlowSSSE3)) {
     GetCoeffs = GetCoeffsAlt;

diff --git a/thirdparty/libwebp/src/dec/vp8i_dec.h b/thirdparty/libwebp/src/dec/vp8i_dec.h
@@ -32,7 +32,7 @@ extern "C" {
 // version numbers
 #define DEC_MAJ_VERSION 1
 #define DEC_MIN_VERSION 3
-#define DEC_REV_VERSION 0
+#define DEC_REV_VERSION 1
 
 // YUV-cache parameters. Cache is 32-bytes wide (= one cacheline).
 // Constraints are: We need to store one 16x16 block of luma samples (y),

diff --git a/thirdparty/libwebp/src/dec/webp_dec.c b/thirdparty/libwebp/src/dec/webp_dec.c
@@ -658,19 +658,26 @@ uint8_t* WebPDecodeBGRA(const uint8_t* data, size_t data_size,
 uint8_t* WebPDecodeYUV(const uint8_t* data, size_t data_size,
                        int* width, int* height, uint8_t** u, uint8_t** v,
                        int* stride, int* uv_stride) {
-  WebPDecBuffer output;   // only to preserve the side-infos
-  uint8_t* const out = Decode(MODE_YUV, data, data_size,
-                              width, height, &output);
-
-  if (out != NULL) {
-    const WebPYUVABuffer* const buf = &output.u.YUVA;
-    *u = buf->u;
-    *v = buf->v;
-    *stride = buf->y_stride;
-    *uv_stride = buf->u_stride;
-    assert(buf->u_stride == buf->v_stride);
-  }
-  return out;
+  // data, width and height are checked by Decode().
+  if (u == NULL || v == NULL || stride == NULL || uv_stride == NULL) {
+    return NULL;
+  }
+
+  {
+    WebPDecBuffer output;   // only to preserve the side-infos
+    uint8_t* const out = Decode(MODE_YUV, data, data_size,
+                                width, height, &output);
+
+    if (out != NULL) {
+      const WebPYUVABuffer* const buf = &output.u.YUVA;
+      *u = buf->u;
+      *v = buf->v;
+      *stride = buf->y_stride;
+      *uv_stride = buf->u_stride;
+      assert(buf->u_stride == buf->v_stride);
+    }
+    return out;
+  }
 }
 
 static void DefaultFeatures(WebPBitstreamFeatures* const features) {

diff --git a/thirdparty/libwebp/src/demux/demux.c b/thirdparty/libwebp/src/demux/demux.c
@@ -25,7 +25,7 @@
 
 #define DMUX_MAJ_VERSION 1
 #define DMUX_MIN_VERSION 3
-#define DMUX_REV_VERSION 0
+#define DMUX_REV_VERSION 1
 
 typedef struct {
   size_t start_;        // start location of the data

diff --git a/thirdparty/libwebp/src/dsp/alpha_processing.c b/thirdparty/libwebp/src/dsp/alpha_processing.c
@@ -425,6 +425,7 @@ void (*WebPAlphaReplace)(uint32_t* src, int length, uint32_t color);
 //------------------------------------------------------------------------------
 // Init function
 
+extern VP8CPUInfo VP8GetCPUInfo;
 extern void WebPInitAlphaProcessingMIPSdspR2(void);
 extern void WebPInitAlphaProcessingSSE2(void);
 extern void WebPInitAlphaProcessingSSE41(void);

diff --git a/thirdparty/libwebp/src/dsp/cost.c b/thirdparty/libwebp/src/dsp/cost.c
@@ -374,6 +374,7 @@ static void SetResidualCoeffs_C(const int16_t* const coeffs,
 VP8GetResidualCostFunc VP8GetResidualCost;
 VP8SetResidualCoeffsFunc VP8SetResidualCoeffs;
 
+extern VP8CPUInfo VP8GetCPUInfo;
 extern void VP8EncDspCostInitMIPS32(void);
 extern void VP8EncDspCostInitMIPSdspR2(void);
 extern void VP8EncDspCostInitSSE2(void);

diff --git a/thirdparty/libwebp/src/dsp/cost_neon.c b/thirdparty/libwebp/src/dsp/cost_neon.c
@@ -29,7 +29,7 @@ static void SetResidualCoeffs_NEON(const int16_t* const coeffs,
   const uint8x16_t eob = vcombine_u8(vqmovn_u16(eob_0), vqmovn_u16(eob_1));
   const uint8x16_t masked = vandq_u8(eob, vld1q_u8(position));
 
-#ifdef __aarch64__
+#if WEBP_AARCH64
   res->last = vmaxvq_u8(masked) - 1;
 #else
   const uint8x8_t eob_8x8 = vmax_u8(vget_low_u8(masked), vget_high_u8(masked));
@@ -43,7 +43,7 @@ static void SetResidualCoeffs_NEON(const int16_t* const coeffs,
 
   vst1_lane_s32(&res->last, vreinterpret_s32_u32(eob_32x2), 0);
   --res->last;
-#endif  // __aarch64__
+#endif  // WEBP_AARCH64
 
   res->coeffs = coeffs;
 }

diff --git a/thirdparty/libwebp/src/dsp/cpu.c b/thirdparty/libwebp/src/dsp/cpu.c
@@ -173,6 +173,7 @@ static int x86CPUInfo(CPUFeature feature) {
   }
   return 0;
 }
+WEBP_EXTERN VP8CPUInfo VP8GetCPUInfo;
 VP8CPUInfo VP8GetCPUInfo = x86CPUInfo;
 #elif defined(WEBP_ANDROID_NEON)  // NB: needs to be before generic NEON test.
 static int AndroidCPUInfo(CPUFeature feature) {
@@ -184,6 +185,7 @@ static int AndroidCPUInfo(CPUFeature feature) {
   }
   return 0;
 }
+WEBP_EXTERN VP8CPUInfo VP8GetCPUInfo;
 VP8CPUInfo VP8GetCPUInfo = AndroidCPUInfo;
 #elif defined(EMSCRIPTEN) // also needs to be before generic NEON test
 // Use compile flags as an indicator of SIMD support instead of a runtime check.
@@ -208,6 +210,7 @@ static int wasmCPUInfo(CPUFeature feature) {
   }
   return 0;
 }
+WEBP_EXTERN VP8CPUInfo VP8GetCPUInfo;
 VP8CPUInfo VP8GetCPUInfo = wasmCPUInfo;
 #elif defined(WEBP_HAVE_NEON)
 // In most cases this function doesn't check for NEON support (it's assumed by
@@ -236,6 +239,7 @@ static int armCPUInfo(CPUFeature feature) {
   return 1;
 #endif
 }
+WEBP_EXTERN VP8CPUInfo VP8GetCPUInfo;
 VP8CPUInfo VP8GetCPUInfo = armCPUInfo;
 #elif defined(WEBP_USE_MIPS32) || defined(WEBP_USE_MIPS_DSP_R2) || \
       defined(WEBP_USE_MSA)
@@ -247,7 +251,9 @@ static int mipsCPUInfo(CPUFeature feature) {
   }
 
 }
+WEBP_EXTERN VP8CPUInfo VP8GetCPUInfo;
 VP8CPUInfo VP8GetCPUInfo = mipsCPUInfo;
 #else
+WEBP_EXTERN VP8CPUInfo VP8GetCPUInfo;
 VP8CPUInfo VP8GetCPUInfo = NULL;
 #endif
diff --git a/thirdparty/libwebp/src/dsp/cpu.h b/thirdparty/libwebp/src/dsp/cpu.h
@@ -43,6 +43,9 @@
 #define __has_builtin(x) 0
 #endif
 
+//------------------------------------------------------------------------------
+// x86 defines.
+
 #if !defined(HAVE_CONFIG_H)
 #if defined(_MSC_VER) && _MSC_VER > 1310 && \
     (defined(_M_X64) || defined(_M_IX86))
@@ -80,6 +83,9 @@
 #undef WEBP_MSC_SSE41
 #undef WEBP_MSC_SSE2
 
+//------------------------------------------------------------------------------
+// Arm defines.
+
 // The intrinsics currently cause compiler errors with arm-nacl-gcc and the
 // inline assembly would need to be modified for use with Native Client.
 #if ((defined(__ARM_NEON__) || defined(__aarch64__)) &&       \
@@ -98,16 +104,26 @@
 // inclusion of arm64_neon.h; Visual Studio 2019 includes this file in
 // arm_neon.h. Compile errors were seen with Visual Studio 2019 16.4 with
 // vtbl4_u8(); a fix was made in 16.6.
-#if defined(_MSC_VER) && ((_MSC_VER >= 1700 && defined(_M_ARM)) || \
-                          (_MSC_VER >= 1926 && defined(_M_ARM64)))
+#if defined(_MSC_VER) && \
+    ((_MSC_VER >= 1700 && defined(_M_ARM)) || \
+     (_MSC_VER >= 1926 && (defined(_M_ARM64) || defined(_M_ARM64EC))))
 #define WEBP_USE_NEON
 #define WEBP_USE_INTRINSICS
 #endif
 
+#if defined(__aarch64__) || defined(_M_ARM64) || defined(_M_ARM64EC)
+#define WEBP_AARCH64 1
+#else
+#define WEBP_AARCH64 0
+#endif
+
 #if defined(WEBP_USE_NEON) && !defined(WEBP_HAVE_NEON)
 #define WEBP_HAVE_NEON
 #endif
 
+//------------------------------------------------------------------------------
+// MIPS defines.
+
 #if defined(__mips__) && !defined(__mips64) && defined(__mips_isa_rev) && \
     (__mips_isa_rev >= 1) && (__mips_isa_rev < 6)
 #define WEBP_USE_MIPS32
@@ -123,6 +139,8 @@
 #define WEBP_USE_MSA
 #endif
 
+//------------------------------------------------------------------------------
+
 #ifndef WEBP_DSP_OMIT_C_CODE
 #define WEBP_DSP_OMIT_C_CODE 1
 #endif
@@ -133,13 +151,14 @@
 #define WEBP_NEON_OMIT_C_CODE 0
 #endif
 
-#if !(LOCAL_CLANG_PREREQ(3, 8) || LOCAL_GCC_PREREQ(4, 8) || \
-      defined(__aarch64__))
+#if !(LOCAL_CLANG_PREREQ(3, 8) || LOCAL_GCC_PREREQ(4, 8) || WEBP_AARCH64)
 #define WEBP_NEON_WORK_AROUND_GCC 1
 #else
 #define WEBP_NEON_WORK_AROUND_GCC 0
 #endif
 
+//------------------------------------------------------------------------------
+
 // This macro prevents thread_sanitizer from reporting known concurrent writes.
 #define WEBP_TSAN_IGNORE_FUNCTION
 #if defined(__has_feature)
@@ -241,16 +260,7 @@ typedef enum {
   kMSA
 } CPUFeature;
 
-#ifdef __cplusplus
-extern "C" {
-#endif
-
 // returns true if the CPU supports the feature.
 typedef int (*VP8CPUInfo)(CPUFeature feature);
-WEBP_EXTERN VP8CPUInfo VP8GetCPUInfo;
-
-#ifdef __cplusplus
-}    // extern "C"
-#endif
 
 #endif  // WEBP_DSP_CPU_H_
diff --git a/thirdparty/libwebp/src/dsp/dec.c b/thirdparty/libwebp/src/dsp/dec.c
@@ -734,6 +734,7 @@ VP8SimpleFilterFunc VP8SimpleHFilter16i;
 void (*VP8DitherCombine8x8)(const uint8_t* dither, uint8_t* dst,
                             int dst_stride);
 
+extern VP8CPUInfo VP8GetCPUInfo;
 extern void VP8DspInitSSE2(void);
 extern void VP8DspInitSSE41(void);
 extern void VP8DspInitNEON(void);

diff --git a/thirdparty/libwebp/src/dsp/dec_neon.c b/thirdparty/libwebp/src/dsp/dec_neon.c
@@ -1428,7 +1428,7 @@ static WEBP_INLINE void DC8_NEON(uint8_t* dst, int do_top, int do_left) {
 
   if (do_top) {
     const uint8x8_t A = vld1_u8(dst - BPS);  // top row
-#if defined(__aarch64__)
+#if WEBP_AARCH64
     const uint16_t p2 = vaddlv_u8(A);
     sum_top = vdupq_n_u16(p2);
 #else
@@ -1511,7 +1511,7 @@ static WEBP_INLINE void DC16_NEON(uint8_t* dst, int do_top, int do_left) {
 
   if (do_top) {
     const uint8x16_t A = vld1q_u8(dst - BPS);  // top row
-#if defined(__aarch64__)
+#if WEBP_AARCH64
     const uint16_t p3 = vaddlvq_u8(A);
     sum_top = vdupq_n_u16(p3);
 #else

diff --git a/thirdparty/libwebp/src/dsp/enc.c b/thirdparty/libwebp/src/dsp/enc.c
@@ -732,6 +732,7 @@ VP8QuantizeBlockWHT VP8EncQuantizeBlockWHT;
 VP8BlockCopy VP8Copy4x4;
 VP8BlockCopy VP8Copy16x8;
 
+extern VP8CPUInfo VP8GetCPUInfo;
 extern void VP8EncDspInitSSE2(void);
 extern void VP8EncDspInitSSE41(void);
 extern void VP8EncDspInitNEON(void);

diff --git a/thirdparty/libwebp/src/dsp/enc_neon.c b/thirdparty/libwebp/src/dsp/enc_neon.c
@@ -764,7 +764,7 @@ static WEBP_INLINE void AccumulateSSE16_NEON(const uint8_t* const a,
 
 // Horizontal sum of all four uint32_t values in 'sum'.
 static int SumToInt_NEON(uint32x4_t sum) {
-#if defined(__aarch64__)
+#if WEBP_AARCH64
   return (int)vaddvq_u32(sum);
 #else
   const uint64x2_t sum2 = vpaddlq_u32(sum);
@@ -865,7 +865,7 @@ static int QuantizeBlock_NEON(int16_t in[16], int16_t out[16],
   uint8x8x4_t shuffles;
   // vtbl?_u8 are marked unavailable for iOS arm64 with Xcode < 6.3, use
   // non-standard versions there.
-#if defined(__APPLE__) && defined(__aarch64__) && \
+#if defined(__APPLE__) && WEBP_AARCH64 && \
     defined(__apple_build_version__) && (__apple_build_version__< 6020037)
   uint8x16x2_t all_out;
   INIT_VECTOR2(all_out, vreinterpretq_u8_s16(out0), vreinterpretq_u8_s16(out1));