linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
* [PATCH] KVM: VMX: invalidate vpid for invlpg instruction
@ 2012-08-31 16:10 Davidlohr Bueso
  2012-08-31 17:37 ` Marcelo Tosatti
  0 siblings, 1 reply; 6+ messages in thread
From: Davidlohr Bueso @ 2012-08-31 16:10 UTC (permalink / raw)
  To: Avi Kivity, Marcelo Tosatti; +Cc: KVM, lkml

For processors that support VPIDs we should invalidate the page table entry
specified by the lineal address. For this purpose add support for individual
address invalidations.

Signed-off-by: Davidlohr Bueso <dave@gnu.org>
---
 arch/x86/include/asm/vmx.h |    6 ++++--
 arch/x86/kvm/vmx.c         |   15 +++++++++++++++
 2 files changed, 19 insertions(+), 2 deletions(-)

diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h
index 74fcb96..20abb18 100644
--- a/arch/x86/include/asm/vmx.h
+++ b/arch/x86/include/asm/vmx.h
@@ -393,6 +393,7 @@ enum vmcs_field {
 #define IDENTITY_PAGETABLE_PRIVATE_MEMSLOT	(KVM_MEMORY_SLOTS + 2)
 
 #define VMX_NR_VPIDS				(1 << 16)
+#define VMX_VPID_EXTENT_INDIVIDUAL_ADDR         0
 #define VMX_VPID_EXTENT_SINGLE_CONTEXT		1
 #define VMX_VPID_EXTENT_ALL_CONTEXT		2
 
@@ -406,12 +407,13 @@ enum vmcs_field {
 #define VMX_EPTP_WB_BIT				(1ull << 14)
 #define VMX_EPT_2MB_PAGE_BIT			(1ull << 16)
 #define VMX_EPT_1GB_PAGE_BIT			(1ull << 17)
-#define VMX_EPT_AD_BIT					(1ull << 21)
+#define VMX_EPT_AD_BIT				(1ull << 21)
 #define VMX_EPT_EXTENT_INDIVIDUAL_BIT		(1ull << 24)
 #define VMX_EPT_EXTENT_CONTEXT_BIT		(1ull << 25)
 #define VMX_EPT_EXTENT_GLOBAL_BIT		(1ull << 26)
 
-#define VMX_VPID_EXTENT_SINGLE_CONTEXT_BIT      (1ull << 9) /* (41 - 32) */
+#define VMX_VPID_EXTENT_INDIVIDUAL_ADDR_BIT     (1ull << 8)  /* (40 - 32) */
+#define VMX_VPID_EXTENT_SINGLE_CONTEXT_BIT      (1ull << 9)  /* (41 - 32) */
 #define VMX_VPID_EXTENT_GLOBAL_CONTEXT_BIT      (1ull << 10) /* (42 - 32) */
 
 #define VMX_EPT_DEFAULT_GAW			3
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index c00f03d..d87b22c 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -816,6 +816,11 @@ static inline bool cpu_has_vmx_invept_global(void)
 	return vmx_capability.ept & VMX_EPT_EXTENT_GLOBAL_BIT;
 }
 
+static inline bool cpu_has_vmx_invvpid_individual_addr(void)
+{
+	return vmx_capability.vpid & VMX_VPID_EXTENT_INDIVIDUAL_ADDR_BIT;
+}
+
 static inline bool cpu_has_vmx_invvpid_single(void)
 {
 	return vmx_capability.vpid & VMX_VPID_EXTENT_SINGLE_CONTEXT_BIT;
@@ -1011,6 +1016,15 @@ static void loaded_vmcs_clear(struct loaded_vmcs *loaded_vmcs)
 			loaded_vmcs->cpu, __loaded_vmcs_clear, loaded_vmcs, 1);
 }
 
+static inline void vpid_sync_vcpu_individual_addr(struct vcpu_vmx *vmx, gpa_t gpa)
+{
+	if (vmx->vpid == 0)
+		return;
+
+	if (cpu_has_vmx_invvpid_individual_addr())
+		__invvpid(VMX_VPID_EXTENT_INDIVIDUAL_ADDR, vmx->vpid, gpa);
+}
+
 static inline void vpid_sync_vcpu_single(struct vcpu_vmx *vmx)
 {
 	if (vmx->vpid == 0)
@@ -4719,6 +4733,7 @@ static int handle_invlpg(struct kvm_vcpu *vcpu)
 	unsigned long exit_qualification = vmcs_readl(EXIT_QUALIFICATION);
 
 	kvm_mmu_invlpg(vcpu, exit_qualification);
+	vpid_sync_vcpu_individual_addr(to_vmx(vcpu), exit_qualification);
 	skip_emulated_instruction(vcpu);
 	return 1;
 }
-- 
1.7.4.1




^ permalink raw reply related	[flat|nested] 6+ messages in thread

* Re: [PATCH] KVM: VMX: invalidate vpid for invlpg instruction
  2012-08-31 16:10 [PATCH] KVM: VMX: invalidate vpid for invlpg instruction Davidlohr Bueso
@ 2012-08-31 17:37 ` Marcelo Tosatti
  2012-09-02 23:27   ` Davidlohr Bueso
  0 siblings, 1 reply; 6+ messages in thread
From: Marcelo Tosatti @ 2012-08-31 17:37 UTC (permalink / raw)
  To: Davidlohr Bueso; +Cc: Avi Kivity, KVM, lkml

On Fri, Aug 31, 2012 at 06:10:48PM +0200, Davidlohr Bueso wrote:
> For processors that support VPIDs we should invalidate the page table entry
> specified by the lineal address. For this purpose add support for individual
> address invalidations.

Not necessary - a single context invalidation is performed through
KVM_REQ_TLB_FLUSH.

Single-context. If the INVVPID type is 1, the logical processor
invalidates all
linear mappings and combined mappings associated with the VPID specified
in the INVVPID descriptor.


^ permalink raw reply	[flat|nested] 6+ messages in thread

* Re: [PATCH] KVM: VMX: invalidate vpid for invlpg instruction
  2012-08-31 17:37 ` Marcelo Tosatti
@ 2012-09-02 23:27   ` Davidlohr Bueso
  2012-09-03  9:11     ` Avi Kivity
  0 siblings, 1 reply; 6+ messages in thread
From: Davidlohr Bueso @ 2012-09-02 23:27 UTC (permalink / raw)
  To: Marcelo Tosatti; +Cc: Avi Kivity, KVM, lkml

On Fri, 2012-08-31 at 14:37 -0300, Marcelo Tosatti wrote:
> On Fri, Aug 31, 2012 at 06:10:48PM +0200, Davidlohr Bueso wrote:
> > For processors that support VPIDs we should invalidate the page table entry
> > specified by the lineal address. For this purpose add support for individual
> > address invalidations.
> 
> Not necessary - a single context invalidation is performed through
> KVM_REQ_TLB_FLUSH.

Since vpid_sync_context() supports both single and all-context vpid
invalidations, wouldn't it make sense to also add individual address
ones as well, supporting further granularity?

> 
> Single-context. If the INVVPID type is 1, the logical processor
> invalidates all
> linear mappings and combined mappings associated with the VPID specified
> in the INVVPID descriptor.
> 
> 



^ permalink raw reply	[flat|nested] 6+ messages in thread

* Re: [PATCH] KVM: VMX: invalidate vpid for invlpg instruction
  2012-09-02 23:27   ` Davidlohr Bueso
@ 2012-09-03  9:11     ` Avi Kivity
  2012-09-05 21:54       ` Davidlohr Bueso
  0 siblings, 1 reply; 6+ messages in thread
From: Avi Kivity @ 2012-09-03  9:11 UTC (permalink / raw)
  To: dave; +Cc: Marcelo Tosatti, KVM, lkml

On 09/03/2012 02:27 AM, Davidlohr Bueso wrote:
> On Fri, 2012-08-31 at 14:37 -0300, Marcelo Tosatti wrote:
>> On Fri, Aug 31, 2012 at 06:10:48PM +0200, Davidlohr Bueso wrote:
>> > For processors that support VPIDs we should invalidate the page table entry
>> > specified by the lineal address. For this purpose add support for individual
>> > address invalidations.
>> 
>> Not necessary - a single context invalidation is performed through
>> KVM_REQ_TLB_FLUSH.
> 
> Since vpid_sync_context() supports both single and all-context vpid
> invalidations, wouldn't it make sense to also add individual address
> ones as well, supporting further granularity?

It might.  Do you have benchmarks supporting this?

-- 
error compiling committee.c: too many arguments to function

^ permalink raw reply	[flat|nested] 6+ messages in thread

* Re: [PATCH] KVM: VMX: invalidate vpid for invlpg instruction
  2012-09-03  9:11     ` Avi Kivity
@ 2012-09-05 21:54       ` Davidlohr Bueso
  2012-09-06  8:05         ` Avi Kivity
  0 siblings, 1 reply; 6+ messages in thread
From: Davidlohr Bueso @ 2012-09-05 21:54 UTC (permalink / raw)
  To: Avi Kivity; +Cc: Marcelo Tosatti, KVM, lkml

On Mon, 2012-09-03 at 12:11 +0300, Avi Kivity wrote:
> On 09/03/2012 02:27 AM, Davidlohr Bueso wrote:
> > On Fri, 2012-08-31 at 14:37 -0300, Marcelo Tosatti wrote:
> >> On Fri, Aug 31, 2012 at 06:10:48PM +0200, Davidlohr Bueso wrote:
> >> > For processors that support VPIDs we should invalidate the page table entry
> >> > specified by the lineal address. For this purpose add support for individual
> >> > address invalidations.
> >> 
> >> Not necessary - a single context invalidation is performed through
> >> KVM_REQ_TLB_FLUSH.
> > 
> > Since vpid_sync_context() supports both single and all-context vpid
> > invalidations, wouldn't it make sense to also add individual address
> > ones as well, supporting further granularity?
> 
> It might.  Do you have benchmarks supporting this?
> 

I ran two benchmarks: Java Dacapo[1] Sunflow (renders a set of images
using ray tracing) and a vanilla 3.2 kernel build (with 1 job and -j8).

The host configuration is an Intel i7-2635QM (4 cores + HT) with 4Gb RAM
running Linus's latest and only running standard system daemons. For KVM
I disabled EPT.
The guest configuration is a 64bit 4 core 4Gb RAM, running Linux 3.2
(debian) and only running the benchmark.

All results represent the mean of 5 runs, with time(1).

Dacapo without individual addr invvpid:
real   1m25.406s
user   4m59.315s
sys    1m25.406s

Dacapo with individual addr invvpid:
real   1m4.421s
user   3m47.150s
sys    0m1.592s

--

vanilla kernel build without individual addr invvpid:
real   16m42.571s
user   13m28.975s
sys    2m54.487s

vanilla kernel build with individual addr invvpid:
real   15m45.789s
user   12m25.691s
sys    2m44.806s

--

vanilla kernel build (-j8) without individual addr invvpid:
real   10m32.276s
user   33m47.687s
sys    5m37.725s

vanilla kernel build (-j8) with individual addr invvpid:
real   8m29.789s
user   28m12.850s
sys    4m34.353s


In all cases using individual address invalidation outperforms single
context ones regarding wall time. Comments?

[1] http://dacapobench.org/


Thanks,
Davidlohr


^ permalink raw reply	[flat|nested] 6+ messages in thread

* Re: [PATCH] KVM: VMX: invalidate vpid for invlpg instruction
  2012-09-05 21:54       ` Davidlohr Bueso
@ 2012-09-06  8:05         ` Avi Kivity
  0 siblings, 0 replies; 6+ messages in thread
From: Avi Kivity @ 2012-09-06  8:05 UTC (permalink / raw)
  To: dave; +Cc: Marcelo Tosatti, KVM, lkml

On 09/06/2012 12:54 AM, Davidlohr Bueso wrote:
> On Mon, 2012-09-03 at 12:11 +0300, Avi Kivity wrote:
>> On 09/03/2012 02:27 AM, Davidlohr Bueso wrote:
>> > On Fri, 2012-08-31 at 14:37 -0300, Marcelo Tosatti wrote:
>> >> On Fri, Aug 31, 2012 at 06:10:48PM +0200, Davidlohr Bueso wrote:
>> >> > For processors that support VPIDs we should invalidate the page table entry
>> >> > specified by the lineal address. For this purpose add support for individual
>> >> > address invalidations.
>> >> 
>> >> Not necessary - a single context invalidation is performed through
>> >> KVM_REQ_TLB_FLUSH.
>> > 
>> > Since vpid_sync_context() supports both single and all-context vpid
>> > invalidations, wouldn't it make sense to also add individual address
>> > ones as well, supporting further granularity?
>> 
>> It might.  Do you have benchmarks supporting this?
>> 
> 
> I ran two benchmarks: Java Dacapo[1] Sunflow (renders a set of images
> using ray tracing) and a vanilla 3.2 kernel build (with 1 job and -j8).
> 
> The host configuration is an Intel i7-2635QM (4 cores + HT) with 4Gb RAM
> running Linus's latest and only running standard system daemons. For KVM
> I disabled EPT.

That's not very interesting.  In all real machines, if you have VPID you
also have EPT.  Intel are unlikely to produce a processor without EPT.

> The guest configuration is a 64bit 4 core 4Gb RAM, running Linux 3.2
> (debian) and only running the benchmark.
> 
> All results represent the mean of 5 runs, with time(1).

The results are impressive, but lack real-world relevance.
Individual-address invalidation isn't very useful with EPT, since we let
the guest issue INVLPG itself and otherwise don't bother with guest page
tables.

Individual-address INVEPT would probably be more useful, but there is no
such instruction variant.

-- 
error compiling committee.c: too many arguments to function

^ permalink raw reply	[flat|nested] 6+ messages in thread

end of thread, other threads:[~2012-09-06  8:05 UTC | newest]

Thread overview: 6+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2012-08-31 16:10 [PATCH] KVM: VMX: invalidate vpid for invlpg instruction Davidlohr Bueso
2012-08-31 17:37 ` Marcelo Tosatti
2012-09-02 23:27   ` Davidlohr Bueso
2012-09-03  9:11     ` Avi Kivity
2012-09-05 21:54       ` Davidlohr Bueso
2012-09-06  8:05         ` Avi Kivity

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).