错误：使用 gcc 32 位时，“asm”操作数具有不可能的约束

Question

我正在尝试在 32 位 centos6 上编译 webrtc 并出现以下错误。但这在 64 位 centos 上运行良好。有人可以帮我吗？

row_gcc.cc:3574:4: error: ‘asm’ operand has impossible constraints

编译命令：

CXX obj/chromium/src/third_party/libyuv/source/libyuv.row_gcc.o
FAILED: obj/chromium/src/third_party/libyuv/source/libyuv.row_gcc.o 
c++ -MMD -MF obj/chromium/src/third_party/libyuv/source/libyuv.row_gcc.o.d 
-DV8_DEPRECATION_WARNINGS -D_FILE_OFFSET_BITS=64 -DCHROMIUM_BUILD 
-DUI_COMPOSITOR_IMAGE_TRANSPORT -DUSE_AURA=1 -DUSE_PANGO=1 -DUSE_CAIRO=1 
-DUSE_DEFAULT_RENDER_THEME=1 -DUSE_LIBJPEG_TURBO=1 -DUSE_X11=1 
-DUSE_CLIPBOARD_AURAX11=1 -DENABLE_WEBRTC=1 -DENABLE_MEDIA_ROUTER=1 
-DENABLE_PEPPER_CDMS -DENABLE_NOTIFICATIONS -DENABLE_TOPCHROME_MD=1 
-DUSE_UDEV -DFIELDTRIAL_TESTING_ENABLED -DENABLE_TASK_MANAGER=1 
-DENABLE_EXTENSIONS=1 -DENABLE_PDF=1 -DENABLE_PLUGINS=1 
-DENABLE_SESSION_SERVICE=1 -DENABLE_THEMES=1 -DENABLE_PRINTING=1 
-DENABLE_BASIC_PRINTING=1 -DENABLE_PRINT_PREVIEW=1 -DENABLE_SPELLCHECK=1 
-DENABLE_CAPTIVE_PORTAL_DETECTION=1 -DENABLE_APP_LIST=1 
-DENABLE_SETTINGS_APP=1 -DENABLE_SUPERVISED_USERS=1 -DENABLE_MDNS=1 
-DENABLE_SERVICE_DISCOVERY=1 -DV8_USE_EXTERNAL_STARTUP_DATA 
-DFULL_SAFE_BROWSING -DSAFE_BROWSING_CSD -DSAFE_BROWSING_DB_LOCAL 
-DHAVE_JPEG -DUSE_LIBPCI=1 -DUSE_GLIB=1 -DUSE_NSS_CERTS=1 
-D__STDC_CONSTANT_MACROS -D__STDC_FORMAT_MACROS 
-DDYNAMIC_ANNOTATIONS_ENABLED=1 -DWTF_USE_DYNAMIC_ANNOTATIONS=1 
-D_DEBUG -Igen 
-I../../chromium/src/third_party/libyuv/include 
-I../../chromium/src/third_party/libyuv 
-I../../chromium/src/third_party/libjpeg_turbo -fstack-protector 
--param=ssp-buffer-size=4  -pthread -fno-strict-aliasing -Wall -Wno-extra 
-Wno-unused-parameter -Wno-missing-field-initializers -fvisibility=hidden 
-pipe -fPIC 
-B/home/test/webrtc-checkout/src/third_party/binutils/Linux_ia32/Release/bin 
-Wno-unused-local-typedefs -msse2 -mfpmath=sse -mmmx -m32 -O0 -g 
-funwind-tables -fno-exceptions -fno-rtti -fno-threadsafe-statics 
-fvisibility-inlines-hidden 
-std=gnu++11 -Wno-narrowing  
-c ../../chromium/src/third_party/libyuv/source/row_gcc.cc 
-o  obj/chromium/src/third_party/libyuv/source/libyuv.row_gcc.o
../../chromium/src/third_party/libyuv/source/row_gcc.cc: 
In function ‘void libyuv::BlendPlaneRow_SSSE3(const uint8*, 
const uint8*, const uint8*, uint8*, int)’:
../../chromium/src/third_party/libyuv/source/row_gcc.cc:3574:4: 
error: ‘asm’ operand has impossible constraints

gcc 版本：4.8.5

作为版本：GNU assembler (GNU Binutils) 2.26.20160125

third_party/binutils/Linux_ia32/Release/bin/as --version
GNU assembler (GNU Binutils) 2.26.20160125
Copyright (C) 2015 Free Software Foundation, Inc.
This program is free software; you may redistribute it under the terms of
the GNU General Public License version 3 or later.
This program has absolutely no warranty.
This assembler was configured for a target of `i686-pc-linux-gnu'.

chromium/src/third_party/libyuv/source/row_gcc.cc中的代码：

void BlendPlaneRow_SSSE3(const uint8* src0, const uint8* src1,
                     const uint8* alpha, uint8* dst, int width) {
asm volatile (
"pcmpeqb    %%xmm5,%%xmm5                  \n"
"psllw      $0x8,%%xmm5                    \n"
"mov        $0x80808080,%%eax              \n"
"movd       %%eax,%%xmm6                   \n"
"pshufd     $0x0,%%xmm6,%%xmm6             \n"
"mov        $0x807f807f,%%eax              \n"
"movd       %%eax,%%xmm7                   \n"
"pshufd     $0x0,%%xmm7,%%xmm7             \n"
"sub        %2,%0                          \n"
"sub        %2,%1                          \n"
"sub        %2,%3                          \n"

// 8 pixel loop.
LABELALIGN
"1:                                          \n"
"movq       (%2),%%xmm0                    \n"
"punpcklbw  %%xmm0,%%xmm0                  \n"
"pxor       %%xmm5,%%xmm0                  \n"
"movq       (%0,%2,1),%%xmm1               \n"
"movq       (%1,%2,1),%%xmm2               \n"
"punpcklbw  %%xmm2,%%xmm1                  \n"
"psubb      %%xmm6,%%xmm1                  \n"
"pmaddubsw  %%xmm1,%%xmm0                  \n"
"paddw      %%xmm7,%%xmm0                  \n"
"psrlw      $0x8,%%xmm0                    \n"
"packuswb   %%xmm0,%%xmm0                  \n"
"movq       %%xmm0,(%3,%2,1)               \n"
"lea        0x8(%2),%2                     \n"
"sub        $0x8,%4                        \n"
"jg        1b                              \n"
: "+r"(src0),       // %0
"+r"(src1),       // %1
"+r"(alpha),      // %2
"+r"(dst),        // %3
"+r"(width)       // %4
:: "memory", "cc", "eax", "xmm0", "xmm1", "xmm2", "xmm5", "xmm6", "xmm7"
);

Answer 1

就像 David Wohlfred 所说的那样，问题在于您的寄存器用完了。有 8 个通用寄存器，其中一个是 ESP，堆栈指针，永远不能用于满足约束。由于您正在编译的选项，另外两个寄存器 EBP 和 EBX 也不能用于满足约束。由于您在没有优化的情况下进行编译，因此 EBP 寄存器为帧指针保留，并且因为您使用-fPIC 标志，EBX 寄存器被保留用于访问 GOT（全局对象表）。

因此留下五个可用于满足寄存器约束的寄存器，EAX、ECX、EDX、ESI 和 EDI。但是，您的 asm 语句破坏了 EAX，因此无法使用，只剩下四个寄存器。 asm 语句有五个具有寄存器约束的操作数，这意味着它需要五个单独的寄存器，但编译器只有四个可用。所以约束是不可能满足的。

一个简单的解决方案是通过在 asm 语句中删除 EAX 来释放寄存器。该寄存器用于将两个不同的常数值加载到两个不同的 XMM 寄存器中。相反，它可以直接从内存中加载常量。例如：

void BlendPlaneRow_SSSE3(const uint8* src0, const uint8* src1,
                     const uint8* alpha, uint8* dst, int width) {
        static unsigned const __attribute__((aligned(4))) xmm6[4] = {
                 0x80808080, 0x80808080, 0x80808080, 0x80808080
        };
        static unsigned const __attribute__((aligned(4))) xmm7[4] = {
                 0x807f807f, 0x807f807f, 0x807f807f, 0x807f807f
        };

asm volatile (
"pcmpeqb    %%xmm5,%%xmm5                  \n"
"psllw      $0x8,%%xmm5                    \n"
"movaps     %5,%%xmm6                      \n"
"movaps     %6,%%xmm7                      \n"
"sub        %2,%0                          \n"
"sub        %2,%1                          \n"
"sub        %2,%3                          \n"

// 8 pixel loop.
LABELALIGN
"1:                                          \n"
"movq       (%2),%%xmm0                    \n"
"punpcklbw  %%xmm0,%%xmm0                  \n"
"pxor       %%xmm5,%%xmm0                  \n"
"movq       (%0,%2,1),%%xmm1               \n"
"movq       (%1,%2,1),%%xmm2               \n"
"punpcklbw  %%xmm2,%%xmm1                  \n"
"psubb      %%xmm6,%%xmm1                  \n"
"pmaddubsw  %%xmm1,%%xmm0                  \n"
"paddw      %%xmm7,%%xmm0                  \n"
"psrlw      $0x8,%%xmm0                    \n"
"packuswb   %%xmm0,%%xmm0                  \n"
"movq       %%xmm0,(%3,%2,1)               \n"
"lea        0x8(%2),%2                     \n"
"sub        $0x8,%4                        \n"
"jg        1b                              \n"
: "+r"(src0),       // %0
"+r"(src1),       // %1
"+r"(alpha),      // %2
"+r"(dst),        // %3
"+r"(width)       // %4
: "m" (xmm6),
"m" (xmm7)
: "memory", "cc", "xmm0", "xmm1", "xmm2", "xmm5", "xmm6", "xmm7"
);
}

更好的解决方案是重写它以使用内在函数并让编译器完成所有寄存器分配。