Question

我正在使用SSE2NEON（特别是Android（API 21）设备）编译RHMiner，用于配置ARM 32设备（armv7-a）。我是C / C ++的新手，所以这可能是一个简单的问题，但是我找不到符合我情况的在线资源。该应用程序可以在Intel 64位处理器上编译并正常运行。 segfault仅在32位平台上发生-这当然是在删除static_assert。

static_assert(sizeof(U64) == sizeof(void*), "Incorrect Pointer Size");

这失败了，我不知道为什么当U64的大小为8而void *的大小为4时。

考虑到此问题，最终代码以分段错误结尾。在valgrind上：

Process terminating with default action of signal 11 (SIGSEGV)
==3055==  Access not within mapped region at address 0xE5F3460
==3055==    at 0x48E46DE: __memcpy_base (in /system/lib/libc.so)
==3055==    by 0x14811B: RandomHash_blake2s(unsigned char*, unsigned char*) (in /data/data/com.termux/files/home/rhminer/rhminer/rhminer)
==3055==  If you believe this happened as a result of a stack
==3055==  overflow in your program's main thread (unlikely but
==3055==  possible), you can try to increase the size of the
==3055==  main thread stack using the --main-stacksize= flag.
==3055==  The main thread stack size used in this run was 8388608.

...

2 errors in context 14 of 24:
==3055== Thread 6:
==3055== Invalid write of size 8
==3055==    at 0x48E46DE: __memcpy_base (in /system/lib/libc.so)
==3055==    by 0x14811B: RandomHash_blake2s(unsigned char*, unsigned char*) (in /data/data/com.termux/files/home/rhminer/rhminer/rhminer)
==3055==  Address 0xe5f3460 is not stack'd, malloc'd or (recently) free'd

如何通过断言和分段错误？

我认为令人反感的代码就在这里，但是考虑到具体情况，可能还有更多的代码会失败：

   void CUDA_SYM_DECL(RandomHash_blake2s)(RH_StridePtr roundInput, RH_StridePtr output)
{
    uint32_t *in = (uint32_t*)RH_STRIDE_GET_DATA(roundInput);

    RH_ALIGN(64) blake2s_state S;
    RH_ALIGN(64) blake2s_param P[1];
    const int outlen = BLAKE2S_OUTBYTES;
    /* Move interval verification here? */

    P->digest_length = outlen;
    P->key_length    = 0;
    P->fanout        = 1;
    P->depth         = 1;
    store32_SSE2( &P->leaf_length, 0 ); 
    P->node_offset[0] = 0;
    P->node_offset[1] = 0;
    P->node_offset[2] = 0;
    P->node_offset[3] = 0;
    P->node_offset[4] = 0;
    P->node_offset[5] = 0;
    P->node_depth    = 0;
    P->inner_length  = 0;

#if defined(_WIN32_WINNT) || defined(__CUDA_ARCH__)
    RH_memzero_8(P->salt, sizeof( P->salt ))
    RH_memzero_8(P->personal, sizeof( P->personal ) );
#else
    memset(P->salt, 0, sizeof( P->salt ));
    memset(P->personal, 0, sizeof( P->personal ) );
#endif

    RH_memzero_of16(&S, sizeof( blake2s_state ) );    

    for( int i = 0; i < 8; ++i ) S.h[i] = blake2s_IV[i];

    uint32_t *p = ( uint32_t * )( P );

    /* IV XOR ParamBlock */
    for( size_t i = 0; i < 8; ++i )
        S.h[i] ^= load32_SSE2( &p[i] );

    _CM(blake2s_update_SSE2)( &S, ( uint8_t * )in, RH_STRIDE_GET_SIZE(roundInput) );
    _CM(blake2s_final_SSE2)( &S, RH_STRIDE_GET_DATA(output), BLAKE2S_OUTBYTES );
    RH_STRIDE_SET_SIZE(output, BLAKE2S_OUTBYTES)
}

static_assert（sizeof（U64）== sizeof（void *）在C ++ ARM（32位）上失败，代码导致分段错误

0 个答案: