[Bug c++/91043] New: GCC produces unaligned vmovdqa vector data access

[hhaim at cisco dot com]

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=91043

            Bug ID: 91043
           Summary: GCC produces unaligned vmovdqa vector data access
           Product: gcc
           Version: 8.3.0
            Status: UNCONFIRMED
          Severity: normal
          Priority: P3
         Component: c++
          Assignee: unassigned at gcc dot gnu.org
          Reporter: hhaim at cisco dot com
  Target Milestone: ---

**The project**: 
https://github.com/cisco-system-traffic-generator/trex-core

**how to compile**: 
https://github.com/cisco-system-traffic-generator/trex-core/wiki#how-to-build-trex

The commit with a workaround:

https://github.com/cisco-system-traffic-generator/trex-core/commit/39e7f535f96f0f5b4406db667be7bc775ce3e515

**The issue**: 
gcc 7/8 generate vector instruction on a variables that was allocated by the
gcc and it seems as not aligned 


the struct is defined like that 

static CGlobalTRex g_trex;

It includes 

CLatencyManager     m_mg; 

which includes 

CLatencyManagerPerPort  m_ports[TREX_MAX_PORTS];


class CLatencyManagerPerPort {
public:
     CCPortLatency          m_port;   << crash is on the function reset of this
object 
     CPortLatencyHWBase  *  m_io;
     uint32_t               m_flag;
};


**Workaround**: 

Adding no-sse to this function solves the issue 

__attribute__((noinline,target("no-sse2"))) 
void CCPortLatency::reset(){





void CCPortLatency::reset(){


warning: bad breakpoint number at or near '0x585763'
(gdb) disassemble 0x585763 
Dump of assembler code for function CCPortLatency::Create(unsigned char,
unsigned short, unsigned short, unsigned short, CCPortLatency*,
CLatencyPktMode*, CNatRxManager*):
   0x00000000005856a0 <+0>:     push   %rbp
   0x00000000005856a1 <+1>:     mov    %rsp,%rbp
   0x00000000005856a4 <+4>:     push   %r12
   0x00000000005856a6 <+6>:     push   %r10
   0x00000000005856a8 <+8>:     lea    0x10(%rbp),%r10
   0x00000000005856ac <+12>:    push   %rbx
   0x00000000005856ad <+13>:    mov    %rdi,%rbx
   0x00000000005856b0 <+16>:    sub    $0x8,%rsp
   0x00000000005856b4 <+20>:    mov    (%r10),%rax
   0x00000000005856b7 <+23>:    movb   $0x0,0x3f(%rbx)
   0x00000000005856bb <+27>:    mov    0x8(%r10),%rdi
   0x00000000005856bf <+31>:    mov    %rax,(%rbx)
   0x00000000005856c2 <+34>:    test   %rax,%rax
   0x00000000005856c5 <+37>:    je     0x585795 <CCPortLatency::Create(unsigned
char, unsigned short, unsigned short, unsigned short, CCPortLatency*,
CLatencyPktMode*, CNatRxManager*)+245>
   0x00000000005856cb <+43>:    mov    %esi,%eax
   0x00000000005856cd <+45>:    mov    %sil,0x31(%rbx)
   0x00000000005856d1 <+49>:    movzbl %sil,%esi
   0x00000000005856d5 <+53>:    not    %eax
   0x00000000005856d7 <+55>:    mov    %rdi,0x8(%rbx)
   0x00000000005856db <+59>:    and    $0x1,%eax
   0x00000000005856de <+62>:    movb   $0x1,0x3e(%rbx)
   0x00000000005856e2 <+66>:    movl   $0x12345678,0x28(%rbx)
   0x00000000005856e9 <+73>:    movl   $0x1,0x38(%rbx)
   0x00000000005856f0 <+80>:    mov    %cx,0x34(%rbx)
   0x00000000005856f4 <+84>:    mov    %dx,0x32(%rbx)
   0x00000000005856f8 <+88>:    mov    %r8w,0x36(%rbx)
   0x00000000005856fd <+93>:    mov    %r9,0x10(%rbx)
   0x0000000000585701 <+97>:    mov    %al,0x19(%rbx)
   0x0000000000585704 <+100>:   mov    %al,0x18(%rbx)
   0x0000000000585707 <+103>:   movq   $0x0,0x1c(%rbx)
   0x000000000058570f <+111>:   cmpb   $0x0,0xc2e938(%rsi)
   0x0000000000585716 <+118>:   je     0x585721 <CCPortLatency::Create(unsigned
char, unsigned short, unsigned short, unsigned short, CCPortLatency*,
CLatencyPktMode*, CNatRxManager*)+129>
   0x0000000000585718 <+120>:   movb   $0x1,0x24(%rbx)
   0x000000000058571c <+124>:   movb   $0x1,0x24(%r9)
   0x0000000000585721 <+129>:   lea    0x100(%rbx),%r12
---Type <return> to continue, or q <return> to quit---
   0x0000000000585728 <+136>:   mov    %r12,%rdi
   0x000000000058572b <+139>:   callq  0x590320 <CTimeHistogram::Create()>
   0x0000000000585730 <+144>:   mov    0x6a8449(%rip),%rdi        # 0xc2db80
<stdout@@GLIBC_2.2.5>
   0x0000000000585737 <+151>:   callq  0x4c5be0 <fflush@plt>
   0x000000000058573c <+156>:   mov    0x28(%rbx),%eax
   0x000000000058573f <+159>:   mov    %r12,%rdi
   0x0000000000585742 <+162>:   vpxor  %xmm0,%xmm0,%xmm0
   0x0000000000585746 <+166>:   movb   $0x0,0x30(%rbx)
   0x000000000058574a <+170>:   movq   $0x0,0xc0(%rbx)
   0x0000000000585755 <+181>:   movq   $0x0,0xc8(%rbx)
   0x0000000000585760 <+192>:   mov    %eax,0x2c(%rbx)
=> 0x0000000000585763 <+195>:   vmovdqa %ymm0,0x40(%rbx) << crash here
   0x0000000000585768 <+200>:   vmovdqa %ymm0,0x60(%rbx)
   0x000000000058576d <+205>:   vmovdqa %ymm0,0x80(%rbx)
   0x0000000000585775 <+213>:   vmovdqa %ymm0,0xa0(%rbx)