Re: [PATCH] x86/math-emu: Add support for FCMOVcc and F[U]COMI[P] insns

[Denys Vlasenko]

On 08/22/2015 10:54 AM, Ingo Molnar wrote:
> 
> * Denys Vlasenko <dvlasenk@xxxxxxxxxx> wrote:
> 
>> +/* fcmovCC and f(u)comi(p) are enabled if CPUID(1).EDX(15) "cmov" is set */
>> +
>>  static FUNC const st_instr_table[64] = {
>> -	fadd__, fld_i_, __BAD__, __BAD__, fadd_i, ffree_, faddp_, _df_c0_,
>> -	fmul__, fxch_i, __BAD__, __BAD__, fmul_i, _dd_c8_, fmulp_, _df_c8_,
>> -	fcom_st, fp_nop, __BAD__, __BAD__, _dc_d0_, fst_i_, _de_d0_, _df_d0_,
>> -	fcompst, _d9_d8_, __BAD__, __BAD__, _dc_d8_, fstp_i, fcompp, _df_d8_,
>> +	fadd__,  fld_i_,  fcmovb,   fcmovnb,  fadd_i,  ffree_,  faddp_,  _df_c0_,
>> +	fmul__,  fxch_i,  fcmove,   fcmovne,  fmul_i,  _dd_c8_, fmulp_,  _df_c8_,
>> +	fcom_st, fp_nop,  fcmovbe,  fcmovnbe, _dc_d0_, fst_i_,  _de_d0_, _df_d0_,
>> +	fcompst, _d9_d8_, fcmovu,   fcmovnu,  _dc_d8_, fstp_i,  fcompp,  _df_d8_,
>>  	fsub__, FPU_etc, __BAD__, finit_, fsubri, fucom_, fsubrp, fstsw_,
>> -	fsubr_, fconst, fucompp, __BAD__, fsub_i, fucomp, fsubp_, __BAD__,
>> -	fdiv__, FPU_triga, __BAD__, __BAD__, fdivri, __BAD__, fdivrp, __BAD__,
>> +	fsubr_, fconst,   fucompp,  fucomi_,  fsub_i,  fucomp,  fsubp_,  fucomip,
>> +	fdiv__, FPU_triga, __BAD__, fcomi_,   fdivri,  __BAD__, fdivrp,  fcomip,
>>  	fdivr_, FPU_trigb, __BAD__, __BAD__, fdiv_i, __BAD__, fdivp_, __BAD__,
>>  };
> 
> So the problem is that you did not give an FPU register encoding type table entry 
> for the new opcodes:
> 
> static u_char const type_table[64] = {
> 	_REGI_, _NONE_, _null_, _null_, _REGIi, _REGi_, _REGIp, _REGi_,
> 	_REGI_, _REGIn, _null_, _null_, _REGIi, _REGI_, _REGIp, _REGI_,
> 	_REGIc, _NONE_, _null_, _null_, _REGIc, _REG0_, _REGIc, _REG0_,
> 	_REGIc, _REG0_, _null_, _null_, _REGIc, _REG0_, _REGIc, _REG0_,
> 	_REGI_, _NONE_, _null_, _NONE_, _REGIi, _REGIc, _REGIp, _NONE_,
> 	_REGI_, _NONE_, _REGIc, _null_, _REGIi, _REGIc, _REGIp, _null_,
> 	_REGI_, _NONE_, _null_, _null_, _REGIi, _null_, _REGIp, _null_,
> 	_REGI_, _NONE_, _null_, _null_, _REGIi, _null_, _REGIp, _null_
> };
> 
> Those _null_ entries must be filled in as well.
> 
> For FUCOMI[P] it's _REGIc I think, so I tried that - and the patch below on top of 
> yours made those instructions appear to work - only to be caught in an MMX op:
> 
> 0xb75eb3fb <bn_mul_add_words+59>:       movd   %ebp,%mm0                                                                                                                              
> 
> :-/
> 
> Arguably the way I tested it, user-space libraries see SSE and MMX capabilities:
> 
> flags           : vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat 
> pse36 clflush mmx sse2 ht syscall nx mmxext lm 3dnowext 3dnow rep_good pni lahf_lm 
> cmp_legacy 3dnowprl...
> 
> So I'll first turn those CPUID bits off, to (hopefully) not confuse user-space.
> 
> Thanks,
> 
> 	Ingo
> 
> ====================>
> 
>  arch/x86/math-emu/fpu_entry.c | 82 ++++++++++++++-----------------------------
>  1 file changed, 27 insertions(+), 55 deletions(-)
> 
> diff --git a/arch/x86/math-emu/fpu_entry.c b/arch/x86/math-emu/fpu_entry.c
> index d20c8f8420e2..4d91c0fc6bc3 100644
> --- a/arch/x86/math-emu/fpu_entry.c
> +++ b/arch/x86/math-emu/fpu_entry.c
> @@ -40,12 +40,10 @@
>  
>  #define __BAD__ FPU_illegal	/* Illegal on an 80486, causes SIGILL */
>  
> -#ifndef NO_UNDOC_CODE		/* Un-documented FPU op-codes supported by default. */
> -
> -/* WARNING: These codes are not documented by Intel in their 80486 manual
> +/* WARNING: These codes are not all documented by Intel in their 80486 manual
>     and may not work on FPU clones or later Intel FPUs. */
>  
> -/* Changes to support the un-doc codes provided by Linus Torvalds. */
> +/* Changes to support the un-documented instructions provided by Linus Torvalds. */
>  
>  #define _d9_d8_ fstp_i		/* unofficial code (19) */
>  #define _dc_d0_ fcom_st		/* unofficial code (14) */
> @@ -60,31 +58,24 @@
>  /* fcmovCC and f(u)comi(p) are enabled if CPUID(1).EDX(15) "cmov" is set */
>  
>  static FUNC const st_instr_table[64] = {
> -	fadd__,  fld_i_,  fcmovb,   fcmovnb,  fadd_i,  ffree_,  faddp_,  _df_c0_,
> -	fmul__,  fxch_i,  fcmove,   fcmovne,  fmul_i,  _dd_c8_, fmulp_,  _df_c8_,
> -	fcom_st, fp_nop,  fcmovbe,  fcmovnbe, _dc_d0_, fst_i_,  _de_d0_, _df_d0_,
> -	fcompst, _d9_d8_, fcmovu,   fcmovnu,  _dc_d8_, fstp_i,  fcompp,  _df_d8_,
> -	fsub__, FPU_etc, __BAD__, finit_, fsubri, fucom_, fsubrp, fstsw_,
> -	fsubr_, fconst,   fucompp,  fucomi_,  fsub_i,  fucomp,  fsubp_,  fucomip,
> -	fdiv__, FPU_triga, __BAD__, fcomi_,   fdivri,  __BAD__, fdivrp,  fcomip,
> -	fdivr_, FPU_trigb, __BAD__, __BAD__, fdiv_i, __BAD__, fdivp_, __BAD__,
> +/* 0x00 */	fadd__,		fld_i_,		fcmovb,		fcmovnb,
> +/* 0x04 */	fadd_i,		ffree_,		faddp_,		_df_c0_,
> +/* 0x08 */	fmul__,		fxch_i,		fcmove,		fcmovne,
> +/* 0x0c */	fmul_i,		_dd_c8_,	fmulp_,		_df_c8_,
> +/* 0x10 */	fcom_st,	fp_nop,		fcmovbe,	fcmovnbe,
> +/* 0x14 */	_dc_d0_,	fst_i_,		_de_d0_,	_df_d0_,
> +/* 0x18 */	fcompst,	_d9_d8_,	fcmovu,		fcmovnu,
> +/* 0x1c */	_dc_d8_,	fstp_i,		fcompp,		_df_d8_,
> +/* 0x20 */	fsub__,		FPU_etc,	__BAD__,	finit_,
> +/* 0x24 */	fsubri,		fucom_,		fsubrp,		fstsw_,
> +/* 0x28 */	fsubr_,		fconst,		fucompp,	fucomi_,
> +/* 0x2c */	fsub_i,		fucomp,		fsubp_,		fucomip,
> +/* 0x30 */	fdiv__,		FPU_triga,	__BAD__,	fcomi_,
> +/* 0x34 */	fdivri,		__BAD__,	fdivrp,		fcomip,
> +/* 0x38 */	fdivr_,		FPU_trigb,	__BAD__,	__BAD__,
> +/* 0x3c */	fdiv_i,		__BAD__,	fdivp_,		__BAD__,

The numeric comments added at the left don't look correct.
In this table, each _column_ corresponds to one 0xd? opcode.
Each row corresponds to a group of mod-reg-rm bytes
with only "rm" field chnaging. (These insns act on registers,
not memory, and "rm" value encodes register number, st(i).)

Something like this:

/*Opcode: d8      d9        da      db       dc      dd      de      df */
/*c0..7*/ fadd__, fld_i_,   fcmovb, fcmovnb, fadd_i, ffree_, faddp_, _df_c0_,
/*c8..f*/ fmul__, fxch_i,   fcmove, fcmovne, fmul_i, _dd_c8_,fmulp_, _df_c8_,
/*d0..7*/ fcom_st,fp_nop,   fcmovbe,fcmovnbe,_dc_d0_,fst_i_, _de_d0_,_df_d0_,
/*d8..f*/ fcompst,_d9_d8_,  fcmovu, fcmovnu, _dc_d8_,fstp_i, fcompp, _df_d8_,
/*e0..7*/ fsub__, FPU_etc,  __BAD__,finit_,  fsubri, fucom_, fsubrp, fstsw_,
/*e8..f*/ fsubr_, fconst,   fucompp,fucomi_, fsub_i, fucomp, fsubp_, fucomip,
/*f0..7*/ fdiv__, FPU_triga,__BAD__,fcomi_,  fdivri, __BAD__,fdivrp, fcomip,
/*f8..f*/ fdivr_, FPU_trigb,__BAD__,__BAD__, fdiv_i, __BAD__,fdivp_, __BAD__,


They should be:
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/