Ping: [PATCH v2] x86-64: fix ZMM register state tracking

["Jan Beulich" <JBeulich@suse.com>]

>>> On 10.10.18 at 17:12,  wrote:
> The three AVX512 state components are entirely independent - one being
> in its "init state" has no implication whatsoever on either of the other
> two. Fully separate X86_XSTATE_ZMM_H and X86_XSTATE_ZMM handling, to
> prevent upper halves of the upper 16 ZMM registers to display as if they
> were zero (when they aren't) after e.g. VZEROALL/VZEROUPPER.
> 
> gdb/
> 2018-10-10  Jan Beulich  <jbeulich@suse.com>
> 
> 	* i387-tdep.c (i387_supply_xsave): Split handling of
> 	X86_XSTATE_ZMM_H and X86_XSTATE_ZMM.
> 	(i387_collect_xsave): Likewise.
> 
> gdb/testsuite/
> 2018-10-10  Simon Marchi <simon.marchi@polymtl.ca>
> 
> 	* testsuite/gdb.arch/i386-avx512.c,
> 	testsuite/gdb.arch/i386-avx512.exp: Add 7th test.
> 
> ---
> v2: Attach comments to zmm_endlo_regnum declarations. Add testcase
>     provided by Simon.
> 
> --- a/gdb/i387-tdep.c
> +++ b/gdb/i387-tdep.c
> @@ -924,6 +924,12 @@ i387_supply_xsave (struct regcache *regc
>    struct gdbarch_tdep *tdep = gdbarch_tdep (gdbarch);
>    const gdb_byte *regs = (const gdb_byte *) xsave;
>    int i;
> +  /* In 64-bit mode the split between "low" and "high" ZMM registers is at
> +     ZMM16.  Outside of 64-bit mode there are no "high" ZMM registers at 
> all.
> +     Precalculate the number to be used for the split point, with the all
> +     registers in the "low" portion outside of 64-bit mode.  */
> +  unsigned int zmm_endlo_regnum = I387_ZMM0H_REGNUM (tdep)
> +				  + std::min (tdep->num_zmm_regs, 16);
>    ULONGEST clear_bv;
>    static const gdb_byte zero[I386_MAX_REGISTER_SIZE] = { 0 };
>    enum
> @@ -1002,7 +1008,8 @@ i387_supply_xsave (struct regcache *regc
>        return;
>  
>      case avx512_zmm_h:
> -      if ((clear_bv & (X86_XSTATE_ZMM_H | X86_XSTATE_ZMM)))
> +      if ((clear_bv & (regnum < zmm_endlo_regnum ? X86_XSTATE_ZMM_H
> +						 : X86_XSTATE_ZMM)))
>  	regcache->raw_supply (regnum, zero);
>        else
>  	regcache->raw_supply (regnum,
> @@ -1080,21 +1087,17 @@ i387_supply_xsave (struct regcache *regc
>  	    }
>  	}
>  
> -      /* Handle the upper ZMM registers.  */
> -      if ((tdep->xcr0 & (X86_XSTATE_ZMM_H | X86_XSTATE_ZMM)))
> +      /* Handle the upper halves of the low 8/16 ZMM registers.  */
> +      if ((tdep->xcr0 & X86_XSTATE_ZMM_H))
>  	{
> -	  if ((clear_bv & (X86_XSTATE_ZMM_H | X86_XSTATE_ZMM)))
> +	  if ((clear_bv & X86_XSTATE_ZMM_H))
>  	    {
> -	      for (i = I387_ZMM0H_REGNUM (tdep);
> -		   i < I387_ZMMENDH_REGNUM (tdep);
> -		   i++)
> +	      for (i = I387_ZMM0H_REGNUM (tdep); i < zmm_endlo_regnum; i++)
>  		regcache->raw_supply (i, zero);
>  	    }
>  	  else
>  	    {
> -	      for (i = I387_ZMM0H_REGNUM (tdep);
> -		   i < I387_ZMMENDH_REGNUM (tdep);
> -		   i++)
> +	      for (i = I387_ZMM0H_REGNUM (tdep); i < zmm_endlo_regnum; i++)
>  		regcache->raw_supply (i,
>  				      XSAVE_AVX512_ZMM_H_ADDR (tdep, regs, i));
>  	    }
> @@ -1119,11 +1122,13 @@ i387_supply_xsave (struct regcache *regc
>  	    }
>  	}
>  
> -      /* Handle the YMM_AVX512 registers.  */
> +      /* Handle the upper 16 ZMM/YMM/XMM registers (if any).  */
>        if ((tdep->xcr0 & X86_XSTATE_ZMM))
>  	{
>  	  if ((clear_bv & X86_XSTATE_ZMM))
>  	    {
> +	      for (i = zmm_endlo_regnum; i < I387_ZMMENDH_REGNUM (tdep); i++)
> +		regcache->raw_supply (i, zero);
>  	      for (i = I387_YMM16H_REGNUM (tdep);
>  		   i < I387_YMMH_AVX512_END_REGNUM (tdep);
>  		   i++)
> @@ -1135,6 +1140,9 @@ i387_supply_xsave (struct regcache *regc
>  	    }
>  	  else
>  	    {
> +	      for (i = zmm_endlo_regnum; i < I387_ZMMENDH_REGNUM (tdep); i++)
> +		regcache->raw_supply (i,
> +				      XSAVE_AVX512_ZMM_H_ADDR (tdep, regs, i));
>  	      for (i = I387_YMM16H_REGNUM (tdep);
>  		   i < I387_YMMH_AVX512_END_REGNUM (tdep);
>  		   i++)
> @@ -1341,6 +1349,9 @@ i387_collect_xsave (const struct regcach
>    gdb_byte raw[I386_MAX_REGISTER_SIZE];
>    ULONGEST initial_xstate_bv, clear_bv, xstate_bv = 0;
>    unsigned int i;
> +  /* See the comment in i387_supply_xsave().  */
> +  unsigned int zmm_endlo_regnum = I387_ZMM0H_REGNUM (tdep)
> +				  + std::min (tdep->num_zmm_regs, 16);
>    enum
>      {
>        x87_ctrl_or_mxcsr = 0x1,
> @@ -1441,9 +1452,8 @@ i387_collect_xsave (const struct regcach
>  	     i < I387_MPXEND_REGNUM (tdep); i++)
>  	  memset (XSAVE_MPX_ADDR (tdep, regs, i), 0, 8);
>  
> -      if ((clear_bv & (X86_XSTATE_ZMM_H | X86_XSTATE_ZMM)))
> -	for (i = I387_ZMM0H_REGNUM (tdep);
> -	     i < I387_ZMMENDH_REGNUM (tdep); i++)
> +      if ((clear_bv & X86_XSTATE_ZMM_H))
> +	for (i = I387_ZMM0H_REGNUM (tdep); i < zmm_endlo_regnum; i++)
>  	  memset (XSAVE_AVX512_ZMM_H_ADDR (tdep, regs, i), 0, 32);
>  
>        if ((clear_bv & X86_XSTATE_K))
> @@ -1453,6 +1463,8 @@ i387_collect_xsave (const struct regcach
>  
>        if ((clear_bv & X86_XSTATE_ZMM))
>  	{
> +	  for (i = zmm_endlo_regnum; i < I387_ZMMENDH_REGNUM (tdep); i++)
> +	    memset (XSAVE_AVX512_ZMM_H_ADDR (tdep, regs, i), 0, 32);
>  	  for (i = I387_YMM16H_REGNUM (tdep);
>  	       i < I387_YMMH_AVX512_END_REGNUM (tdep); i++)
>  	    memset (XSAVE_YMM_AVX512_ADDR (tdep, regs, i), 0, 16);
> --- a/gdb/testsuite/gdb.arch/i386-avx512.c
> +++ b/gdb/testsuite/gdb.arch/i386-avx512.c
> @@ -249,6 +249,13 @@ main (int argc, char **argv)
>  	 move back to array and check values.  */
>        move_zmm_data_to_memory ();
>        asm ("nop"); /* sixth breakpoint here  */
> +
> +      asm ("vpternlogd $0xff, %zmm0, %zmm0, %zmm0");
> +#ifdef __x86_64__
> +      asm ("vpternlogd $0xff, %zmm0, %zmm0, %zmm16");
> +#endif
> +      asm ("vzeroupper");
> +      asm ("nop"); /* seventh breakpoint here  */
>      }
>  
>    return 0;
> --- a/gdb/testsuite/gdb.arch/i386-avx512.exp
> +++ b/gdb/testsuite/gdb.arch/i386-avx512.exp
> @@ -174,3 +174,13 @@ for { set r 0 } { $r < $nr_regs } { incr
>          ".. = \\{f = \\{[expr $r + 30], [expr $r.125 + 30], [expr $r.25 + 
> 20], [expr $r.375 + 20], [expr $r.5 + 10], [expr $r.625 + 10], [expr $r.75 + 
> 10], [expr $r.875 + 10]\\}\\}.*" \
>          "check contents of zmm_data\[$r\] after writing XMM regs"
>  }
> +
> +gdb_test "break [gdb_get_line_number "seventh breakpoint here"]" \
> +    "Breakpoint .* at .*i386-avx512.c.*" \
> +    "set seventh breakpoint in main"
> +gdb_continue_to_breakpoint "continue to seventh breakpoint in main"
> +gdb_test "print \$zmm0.v16_int32" "= {-1, -1, -1, -1, 0 <repeats 12 
> times>}"
> +
> +if { $nr_regs >= 16 } {
> +    gdb_test "print \$zmm16.v16_int32" "= {-1 <repeats 16 times>}"
> +}
> 
> 
> 
>