[PATCH] x86/cpufeatures: Add enumeration for serialize instruction

[PATCH] x86/cpufeatures: Add enumeration for serialize instruction

[Ricardo Neri]

The serialize instruction ensures that before the next instruction is
fetched and executed, all the modifications to flags, registers, and memory
made by previous instructions are completed, draining all buffered writes
to memory.

Importantly, the serialize instruction does not modify registers,
arithmetic flags or memory.

Hence, the serialize instructions provides a better way for software
to serialize execution than using instructions such as cpuid, which does
modify registers and, in virtual machines, causes a VM exit.

This instruction is supported by the CPU if CPUID.7H.EDX[bit 14] is
set.

Cc: x86@kernel.org
Cc: "Ravi V. Shankar" <ravi.v.shankar@intel.com>
Signed-off-by: Ricardo Neri <ricardo.neri-calderon@linux.intel.com>
---
This new instruction is documented in the latest version of the Intel
Architecture Instruction Set Extensions and Future Features Programming
Reference Chapter 2.1 located at
https://software.intel.com/sites/default/files/managed/c5/15/architecture-instruction-set-extensions-programming-reference.pdf
---
 arch/x86/include/asm/cpufeatures.h | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index db189945e9b0..cd9b1ec022ec 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -364,6 +364,7 @@
 #define X86_FEATURE_AVX512_VP2INTERSECT (18*32+ 8) /* AVX-512 Intersect for D/Q */
 #define X86_FEATURE_MD_CLEAR		(18*32+10) /* VERW clears CPU buffers */
 #define X86_FEATURE_TSX_FORCE_ABORT	(18*32+13) /* "" TSX_FORCE_ABORT */
+#define X86_FEATURE_SERIALIZE		(18*32+14) /* SERIALIZE instruction */
 #define X86_FEATURE_PCONFIG		(18*32+18) /* Intel PCONFIG */
 #define X86_FEATURE_SPEC_CTRL		(18*32+26) /* "" Speculation Control (IBRS + IBPB) */
 #define X86_FEATURE_INTEL_STIBP		(18*32+27) /* "" Single Thread Indirect Branch Predictors */
-- 
2.17.1

Re: [PATCH] x86/cpufeatures: Add enumeration for serialize instruction

[Borislav Petkov]

On Thu, Apr 02, 2020 at 06:40:26PM -0700, Ricardo Neri wrote:
> The serialize instruction ensures that before the next instruction is
> fetched and executed, all the modifications to flags, registers, and memory
> made by previous instructions are completed, draining all buffered writes
> to memory.
> 
> Importantly, the serialize instruction does not modify registers,
> arithmetic flags or memory.
> 
> Hence, the serialize instructions provides a better way for software
> to serialize execution than using instructions such as cpuid, which does
> modify registers and, in virtual machines, causes a VM exit.
> 
> This instruction is supported by the CPU if CPUID.7H.EDX[bit 14] is
> set.
> 
> Cc: x86@kernel.org
> Cc: "Ravi V. Shankar" <ravi.v.shankar@intel.com>
> Signed-off-by: Ricardo Neri <ricardo.neri-calderon@linux.intel.com>
> ---
> This new instruction is documented in the latest version of the Intel
> Architecture Instruction Set Extensions and Future Features Programming
> Reference Chapter 2.1 located at
> https://software.intel.com/sites/default/files/managed/c5/15/architecture-instruction-set-extensions-programming-reference.pdf
> ---
>  arch/x86/include/asm/cpufeatures.h | 1 +
>  1 file changed, 1 insertion(+)
> 
> diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
> index db189945e9b0..cd9b1ec022ec 100644
> --- a/arch/x86/include/asm/cpufeatures.h
> +++ b/arch/x86/include/asm/cpufeatures.h
> @@ -364,6 +364,7 @@
>  #define X86_FEATURE_AVX512_VP2INTERSECT (18*32+ 8) /* AVX-512 Intersect for D/Q */
>  #define X86_FEATURE_MD_CLEAR		(18*32+10) /* VERW clears CPU buffers */
>  #define X86_FEATURE_TSX_FORCE_ABORT	(18*32+13) /* "" TSX_FORCE_ABORT */
> +#define X86_FEATURE_SERIALIZE		(18*32+14) /* SERIALIZE instruction */
>  #define X86_FEATURE_PCONFIG		(18*32+18) /* Intel PCONFIG */
>  #define X86_FEATURE_SPEC_CTRL		(18*32+26) /* "" Speculation Control (IBRS + IBPB) */
>  #define X86_FEATURE_INTEL_STIBP		(18*32+27) /* "" Single Thread Indirect Branch Predictors */
> -- 

Send this together with code which is using it, pls.

Thx.

-- 
Regards/Gruss,
    Boris.

https://people.kernel.org/tglx/notes-about-netiquette

Re: [PATCH] x86/cpufeatures: Add enumeration for serialize instruction

[Ricardo Neri]

On Fri, Apr 03, 2020 at 10:12:17AM +0200, Borislav Petkov wrote:
> On Thu, Apr 02, 2020 at 06:40:26PM -0700, Ricardo Neri wrote:
> > The serialize instruction ensures that before the next instruction is
> > fetched and executed, all the modifications to flags, registers, and memory
> > made by previous instructions are completed, draining all buffered writes
> > to memory.
> > 
> > Importantly, the serialize instruction does not modify registers,
> > arithmetic flags or memory.
> > 
> > Hence, the serialize instructions provides a better way for software
> > to serialize execution than using instructions such as cpuid, which does
> > modify registers and, in virtual machines, causes a VM exit.
> > 
> > This instruction is supported by the CPU if CPUID.7H.EDX[bit 14] is
> > set.
> > 
> > Cc: x86@kernel.org
> > Cc: "Ravi V. Shankar" <ravi.v.shankar@intel.com>
> > Signed-off-by: Ricardo Neri <ricardo.neri-calderon@linux.intel.com>
> > ---
> > This new instruction is documented in the latest version of the Intel
> > Architecture Instruction Set Extensions and Future Features Programming
> > Reference Chapter 2.1 located at
> > https://software.intel.com/sites/default/files/managed/c5/15/architecture-instruction-set-extensions-programming-reference.pdf
> > ---
> >  arch/x86/include/asm/cpufeatures.h | 1 +
> >  1 file changed, 1 insertion(+)
> > 
> > diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
> > index db189945e9b0..cd9b1ec022ec 100644
> > --- a/arch/x86/include/asm/cpufeatures.h
> > +++ b/arch/x86/include/asm/cpufeatures.h
> > @@ -364,6 +364,7 @@
> >  #define X86_FEATURE_AVX512_VP2INTERSECT (18*32+ 8) /* AVX-512 Intersect for D/Q */
> >  #define X86_FEATURE_MD_CLEAR		(18*32+10) /* VERW clears CPU buffers */
> >  #define X86_FEATURE_TSX_FORCE_ABORT	(18*32+13) /* "" TSX_FORCE_ABORT */
> > +#define X86_FEATURE_SERIALIZE		(18*32+14) /* SERIALIZE instruction */
> >  #define X86_FEATURE_PCONFIG		(18*32+18) /* Intel PCONFIG */
> >  #define X86_FEATURE_SPEC_CTRL		(18*32+26) /* "" Speculation Control (IBRS + IBPB) */
> >  #define X86_FEATURE_INTEL_STIBP		(18*32+27) /* "" Single Thread Indirect Branch Predictors */
> > -- 
> 
> Send this together with code which is using it, pls.

Do you mean code in the kernel using this instructions. Thus far, I
don't have any kernel use cases for this instruction. My intention is to expose
this instruction to user space via /proc/cpuinfo. Is that not
acceptable?

Thanks and BR,
Ricardo

Re: [PATCH] x86/cpufeatures: Add enumeration for serialize instruction

[Borislav Petkov]

On Fri, Apr 03, 2020 at 10:20:39PM -0700, Ricardo Neri wrote:
> Do you mean code in the kernel using this instructions. Thus far, I
> don't have any kernel use cases for this instruction.

I'm sure you can find at least a couple of places in the kernel
which use CPUID to serialize and could switch to this new insn with
alternatives, for example. Or all those memory barrier uses. Would it be
better to switch to SERIALIZE there? Dunno, but would be good to know.
And so on.

> My intention is to expose this instruction to user space via
> /proc/cpuinfo. Is that not acceptable?

I know what your intention is. What good is the string "serialize" in
/proc/cpuinfo if nothing uses it?

-- 
Regards/Gruss,
    Boris.

https://people.kernel.org/tglx/notes-about-netiquette

Re: [PATCH] x86/cpufeatures: Add enumeration for serialize instruction

[Ricardo Neri]

On Sat, Apr 04, 2020 at 10:28:09AM +0200, Borislav Petkov wrote:
> On Fri, Apr 03, 2020 at 10:20:39PM -0700, Ricardo Neri wrote:
> > Do you mean code in the kernel using this instructions. Thus far, I
> > don't have any kernel use cases for this instruction.
> 
> I'm sure you can find at least a couple of places in the kernel
> which use CPUID to serialize and could switch to this new insn with
> alternatives, for example. Or all those memory barrier uses. Would it be
> better to switch to SERIALIZE there? Dunno, but would be good to know.
> And so on.

Yes, I lookede for uses of CPUID for serialization but I didn't find
any. I will look again. I will also look at the memory barrier cases.

Thanks and BR,
Ricardo

> 
> > My intention is to expose this instruction to user space via
> > /proc/cpuinfo. Is that not acceptable?
> 
> I know what your intention is. What good is the string "serialize" in
> /proc/cpuinfo if nothing uses it?

Wouldn't it be useful for userspace tools to see? Admittedly, the would
be looking at CPUID directly, I think.

Thanks and BR,
Ricardo

Re: [PATCH] x86/cpufeatures: Add enumeration for serialize instruction

[Andy Lutomirski]

On Fri, Apr 3, 2020 at 10:19 PM Ricardo Neri
<ricardo.neri-calderon@linux.intel.com> wrote:
>
> On Fri, Apr 03, 2020 at 10:12:17AM +0200, Borislav Petkov wrote:
> > On Thu, Apr 02, 2020 at 06:40:26PM -0700, Ricardo Neri wrote:
> > > The serialize instruction ensures that before the next instruction is
> > > fetched and executed, all the modifications to flags, registers, and memory
> > > made by previous instructions are completed, draining all buffered writes
> > > to memory.
> > >
> > > Importantly, the serialize instruction does not modify registers,
> > > arithmetic flags or memory.
> > >
> > > Hence, the serialize instructions provides a better way for software
> > > to serialize execution than using instructions such as cpuid, which does
> > > modify registers and, in virtual machines, causes a VM exit.
> > >
> > > This instruction is supported by the CPU if CPUID.7H.EDX[bit 14] is
> > > set.
> > >
> > > Cc: x86@kernel.org
> > > Cc: "Ravi V. Shankar" <ravi.v.shankar@intel.com>
> > > Signed-off-by: Ricardo Neri <ricardo.neri-calderon@linux.intel.com>
> > > ---
> > > This new instruction is documented in the latest version of the Intel
> > > Architecture Instruction Set Extensions and Future Features Programming
> > > Reference Chapter 2.1 located at
> > > https://software.intel.com/sites/default/files/managed/c5/15/architecture-instruction-set-extensions-programming-reference.pdf
> > > ---
> > >  arch/x86/include/asm/cpufeatures.h | 1 +
> > >  1 file changed, 1 insertion(+)
> > >
> > > diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
> > > index db189945e9b0..cd9b1ec022ec 100644
> > > --- a/arch/x86/include/asm/cpufeatures.h
> > > +++ b/arch/x86/include/asm/cpufeatures.h
> > > @@ -364,6 +364,7 @@
> > >  #define X86_FEATURE_AVX512_VP2INTERSECT (18*32+ 8) /* AVX-512 Intersect for D/Q */
> > >  #define X86_FEATURE_MD_CLEAR               (18*32+10) /* VERW clears CPU buffers */
> > >  #define X86_FEATURE_TSX_FORCE_ABORT        (18*32+13) /* "" TSX_FORCE_ABORT */
> > > +#define X86_FEATURE_SERIALIZE              (18*32+14) /* SERIALIZE instruction */
> > >  #define X86_FEATURE_PCONFIG                (18*32+18) /* Intel PCONFIG */
> > >  #define X86_FEATURE_SPEC_CTRL              (18*32+26) /* "" Speculation Control (IBRS + IBPB) */
> > >  #define X86_FEATURE_INTEL_STIBP            (18*32+27) /* "" Single Thread Indirect Branch Predictors */
> > > --
> >
> > Send this together with code which is using it, pls.
>
> Do you mean code in the kernel using this instructions. Thus far, I
> don't have any kernel use cases for this instruction. My intention is to expose
> this instruction to user space via /proc/cpuinfo. Is that not
> acceptable?

Presumably sync_core() should do, roughly:

if (static_cpu_has(X86_FEATURE_SERIALIZE)) {
  asm volatile("serialize");
  return;
}

but with the appropriate magic to build it on older binutils.  And you
should make sure that the in-kernel instruction decoder doesn't
explode when it sees serialize, presumably.

Re: [PATCH] x86/cpufeatures: Add enumeration for serialize instruction

[Ricardo Neri]

On Sat, Apr 04, 2020 at 02:15:57PM -0700, Andy Lutomirski wrote:
> On Fri, Apr 3, 2020 at 10:19 PM Ricardo Neri
> <ricardo.neri-calderon@linux.intel.com> wrote:
> >
> > On Fri, Apr 03, 2020 at 10:12:17AM +0200, Borislav Petkov wrote:
> > > On Thu, Apr 02, 2020 at 06:40:26PM -0700, Ricardo Neri wrote:
> > > > The serialize instruction ensures that before the next instruction is
> > > > fetched and executed, all the modifications to flags, registers, and memory
> > > > made by previous instructions are completed, draining all buffered writes
> > > > to memory.
> > > >
> > > > Importantly, the serialize instruction does not modify registers,
> > > > arithmetic flags or memory.
> > > >
> > > > Hence, the serialize instructions provides a better way for software
> > > > to serialize execution than using instructions such as cpuid, which does
> > > > modify registers and, in virtual machines, causes a VM exit.
> > > >
> > > > This instruction is supported by the CPU if CPUID.7H.EDX[bit 14] is
> > > > set.
> > > >
> > > > Cc: x86@kernel.org
> > > > Cc: "Ravi V. Shankar" <ravi.v.shankar@intel.com>
> > > > Signed-off-by: Ricardo Neri <ricardo.neri-calderon@linux.intel.com>
> > > > ---
> > > > This new instruction is documented in the latest version of the Intel
> > > > Architecture Instruction Set Extensions and Future Features Programming
> > > > Reference Chapter 2.1 located at
> > > > https://software.intel.com/sites/default/files/managed/c5/15/architecture-instruction-set-extensions-programming-reference.pdf
> > > > ---
> > > >  arch/x86/include/asm/cpufeatures.h | 1 +
> > > >  1 file changed, 1 insertion(+)
> > > >
> > > > diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
> > > > index db189945e9b0..cd9b1ec022ec 100644
> > > > --- a/arch/x86/include/asm/cpufeatures.h
> > > > +++ b/arch/x86/include/asm/cpufeatures.h
> > > > @@ -364,6 +364,7 @@
> > > >  #define X86_FEATURE_AVX512_VP2INTERSECT (18*32+ 8) /* AVX-512 Intersect for D/Q */
> > > >  #define X86_FEATURE_MD_CLEAR               (18*32+10) /* VERW clears CPU buffers */
> > > >  #define X86_FEATURE_TSX_FORCE_ABORT        (18*32+13) /* "" TSX_FORCE_ABORT */
> > > > +#define X86_FEATURE_SERIALIZE              (18*32+14) /* SERIALIZE instruction */
> > > >  #define X86_FEATURE_PCONFIG                (18*32+18) /* Intel PCONFIG */
> > > >  #define X86_FEATURE_SPEC_CTRL              (18*32+26) /* "" Speculation Control (IBRS + IBPB) */
> > > >  #define X86_FEATURE_INTEL_STIBP            (18*32+27) /* "" Single Thread Indirect Branch Predictors */
> > > > --
> > >
> > > Send this together with code which is using it, pls.
> >
> > Do you mean code in the kernel using this instructions. Thus far, I
> > don't have any kernel use cases for this instruction. My intention is to expose
> > this instruction to user space via /proc/cpuinfo. Is that not
> > acceptable?
> 
> Presumably sync_core() should do, roughly:
> 
> if (static_cpu_has(X86_FEATURE_SERIALIZE)) {
>   asm volatile("serialize");
>   return;
> }

Sure Andy, I will look at implementing something as you propose.

> 
> but with the appropriate magic to build it on older binutils.  

But old binutils will not be aware of this new instruction, right? How
could they be impacted?

> should make sure that the in-kernel instruction decoder doesn't
> explode when it sees serialize, presumably.

Sure Andy. I will also test for this.

Thanks and BR,
Ricardo

Re: [PATCH] x86/cpufeatures: Add enumeration for serialize instruction

[Andy Lutomirski]

> On Apr 6, 2020, at 6:37 PM, Ricardo Neri <ricardo.neri-calderon@linux.intel.com> wrote:
> 
> On Sat, Apr 04, 2020 at 02:15:57PM -0700, Andy Lutomirski wrote:
>>> On Fri, Apr 3, 2020 at 10:19 PM Ricardo Neri
>>> <ricardo.neri-calderon@linux.intel.com> wrote:
>>> 
>>> On Fri, Apr 03, 2020 at 10:12:17AM +0200, Borislav Petkov wrote:
>>>> On Thu, Apr 02, 2020 at 06:40:26PM -0700, Ricardo Neri wrote:
>>>>> The serialize instruction ensures that before the next instruction is
>>>>> fetched and executed, all the modifications to flags, registers, and memory
>>>>> made by previous instructions are completed, draining all buffered writes
>>>>> to memory.
>>>>> 
>>>>> Importantly, the serialize instruction does not modify registers,
>>>>> arithmetic flags or memory.
>>>>> 
>>>>> Hence, the serialize instructions provides a better way for software
>>>>> to serialize execution than using instructions such as cpuid, which does
>>>>> modify registers and, in virtual machines, causes a VM exit.
>>>>> 
>>>>> This instruction is supported by the CPU if CPUID.7H.EDX[bit 14] is
>>>>> set.
>>>>> 
>>>>> Cc: x86@kernel.org
>>>>> Cc: "Ravi V. Shankar" <ravi.v.shankar@intel.com>
>>>>> Signed-off-by: Ricardo Neri <ricardo.neri-calderon@linux.intel.com>
>>>>> ---
>>>>> This new instruction is documented in the latest version of the Intel
>>>>> Architecture Instruction Set Extensions and Future Features Programming
>>>>> Reference Chapter 2.1 located at
>>>>> https://software.intel.com/sites/default/files/managed/c5/15/architecture-instruction-set-extensions-programming-reference.pdf
>>>>> ---
>>>>> arch/x86/include/asm/cpufeatures.h | 1 +
>>>>> 1 file changed, 1 insertion(+)
>>>>> 
>>>>> diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
>>>>> index db189945e9b0..cd9b1ec022ec 100644
>>>>> --- a/arch/x86/include/asm/cpufeatures.h
>>>>> +++ b/arch/x86/include/asm/cpufeatures.h
>>>>> @@ -364,6 +364,7 @@
>>>>> #define X86_FEATURE_AVX512_VP2INTERSECT (18*32+ 8) /* AVX-512 Intersect for D/Q */
>>>>> #define X86_FEATURE_MD_CLEAR               (18*32+10) /* VERW clears CPU buffers */
>>>>> #define X86_FEATURE_TSX_FORCE_ABORT        (18*32+13) /* "" TSX_FORCE_ABORT */
>>>>> +#define X86_FEATURE_SERIALIZE              (18*32+14) /* SERIALIZE instruction */
>>>>> #define X86_FEATURE_PCONFIG                (18*32+18) /* Intel PCONFIG */
>>>>> #define X86_FEATURE_SPEC_CTRL              (18*32+26) /* "" Speculation Control (IBRS + IBPB) */
>>>>> #define X86_FEATURE_INTEL_STIBP            (18*32+27) /* "" Single Thread Indirect Branch Predictors */
>>>>> --
>>>> 
>>>> Send this together with code which is using it, pls.
>>> 
>>> Do you mean code in the kernel using this instructions. Thus far, I
>>> don't have any kernel use cases for this instruction. My intention is to expose
>>> this instruction to user space via /proc/cpuinfo. Is that not
>>> acceptable?
>> 
>> Presumably sync_core() should do, roughly:
>> 
>> if (static_cpu_has(X86_FEATURE_SERIALIZE)) {
>>  asm volatile("serialize");
>>  return;
>> }
> 
> Sure Andy, I will look at implementing something as you propose.
> 
>> 
>> but with the appropriate magic to build it on older binutils.  
> 
> But old binutils will not be aware of this new instruction, right? How
> could they be impacted?

Because old binutils will fail to assemble serialize :). You’re need a macro that turns it into .byte, or, if there’s just one user, you could open-code the .byte.

> 
>> should make sure that the in-kernel instruction decoder doesn't
>> explode when it sees serialize, presumably.
> 
> Sure Andy. I will also test for this.
> 
> Thanks and BR,
> Ricardo