* [PATCH 0/2] KVM: nVMX: Skip IPBP on nested VMCS switch
@ 2020-05-06 23:58 Sean Christopherson
2020-05-06 23:58 ` [PATCH 1/2] KVM: nVMX: Refactor IBPB handling on VMCS switch to genericize code Sean Christopherson
` (2 more replies)
0 siblings, 3 replies; 4+ messages in thread
From: Sean Christopherson @ 2020-05-06 23:58 UTC (permalink / raw)
To: Paolo Bonzini
Cc: Sean Christopherson, Vitaly Kuznetsov, Wanpeng Li, Jim Mattson,
Joerg Roedel, kvm, linux-kernel
Or as Jim would say, "Really skip IPBP on nested VMCS switch" :-D
Patch 1 is the delta between kvm/queue and v3 of the original patch[*],
i.e. I just cherry-picked v3 and fixed the conflicts.
Patch 2 applies the "no IPBP" logic to copy_vmcs02_to_vmcs12_rare().
Feel free to sqaush both of these to commit 7407a52f23732 ("KVM: nVMX:
Skip IBPB when switching between vmcs01 and vmcs02") if you so desire.
[*] https://lkml.kernel.org/r/20200505044644.16563-1-sean.j.christopherson@intel.com
Sean Christopherson (2):
KVM: nVMX: Refactor IBPB handling on VMCS switch to genericize code
KVM: nVMX: Skip IPBP when switching between vmcs01 and vmcs02, redux
arch/x86/kvm/vmx/nested.c | 13 +++----------
arch/x86/kvm/vmx/vmx.c | 19 ++++++++++++++-----
arch/x86/kvm/vmx/vmx.h | 4 ++--
3 files changed, 19 insertions(+), 17 deletions(-)
--
2.26.0
^ permalink raw reply [flat|nested] 4+ messages in thread
* [PATCH 1/2] KVM: nVMX: Refactor IBPB handling on VMCS switch to genericize code
2020-05-06 23:58 [PATCH 0/2] KVM: nVMX: Skip IPBP on nested VMCS switch Sean Christopherson
@ 2020-05-06 23:58 ` Sean Christopherson
2020-05-06 23:58 ` [PATCH 2/2] KVM: nVMX: Skip IPBP when switching between vmcs01 and vmcs02, redux Sean Christopherson
2020-05-07 11:58 ` [PATCH 0/2] KVM: nVMX: Skip IPBP on nested VMCS switch Paolo Bonzini
2 siblings, 0 replies; 4+ messages in thread
From: Sean Christopherson @ 2020-05-06 23:58 UTC (permalink / raw)
To: Paolo Bonzini
Cc: Sean Christopherson, Vitaly Kuznetsov, Wanpeng Li, Jim Mattson,
Joerg Roedel, kvm, linux-kernel
Refactor the IPBP handling to effectively move the WARN and comment in
vmx_switch_vmcs() to vmx_vcpu_load_vmcs(). A future patch will give
copy_vmcs02_to_vmcs12_rare() the same treatment.
Signed-off-by: Sean Christopherson <sean.j.christopherson@intel.com>
---
arch/x86/kvm/vmx/nested.c | 9 +--------
arch/x86/kvm/vmx/vmx.c | 17 +++++++++++++----
arch/x86/kvm/vmx/vmx.h | 3 ++-
3 files changed, 16 insertions(+), 13 deletions(-)
diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index 20a9edca51fa5..7d1e19149ef46 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -302,15 +302,8 @@ static void vmx_switch_vmcs(struct kvm_vcpu *vcpu, struct loaded_vmcs *vmcs)
cpu = get_cpu();
prev = vmx->loaded_vmcs;
- WARN_ON_ONCE(prev->cpu != cpu || prev->vmcs != per_cpu(current_vmcs, cpu));
vmx->loaded_vmcs = vmcs;
-
- /*
- * This is the same guest from our point of view, so no
- * indirect branch prediction barrier is needed. The L1
- * guest can protect itself with retpolines, IBPB or IBRS.
- */
- vmx_vcpu_load_vmcs(vcpu, cpu, false);
+ vmx_vcpu_load_vmcs(vcpu, cpu, prev);
vmx_sync_vmcs_host_state(vmx, prev);
put_cpu();
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 94f49c5ae89aa..ddbd8fae24927 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -1311,10 +1311,12 @@ static void vmx_vcpu_pi_load(struct kvm_vcpu *vcpu, int cpu)
pi_set_on(pi_desc);
}
-void vmx_vcpu_load_vmcs(struct kvm_vcpu *vcpu, int cpu, bool need_ibpb)
+void vmx_vcpu_load_vmcs(struct kvm_vcpu *vcpu, int cpu,
+ struct loaded_vmcs *buddy)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
bool already_loaded = vmx->loaded_vmcs->cpu == cpu;
+ struct vmcs *prev;
if (!already_loaded) {
loaded_vmcs_clear(vmx->loaded_vmcs);
@@ -1333,10 +1335,17 @@ void vmx_vcpu_load_vmcs(struct kvm_vcpu *vcpu, int cpu, bool need_ibpb)
local_irq_enable();
}
- if (per_cpu(current_vmcs, cpu) != vmx->loaded_vmcs->vmcs) {
+ prev = per_cpu(current_vmcs, cpu);
+ if (prev != vmx->loaded_vmcs->vmcs) {
per_cpu(current_vmcs, cpu) = vmx->loaded_vmcs->vmcs;
vmcs_load(vmx->loaded_vmcs->vmcs);
- if (need_ibpb)
+
+ /*
+ * No indirect branch prediction barrier needed when switching
+ * the active VMCS within a guest, e.g. on nested VM-Enter.
+ * The L1 VMM can protect itself with retpolines, IBPB or IBRS.
+ */
+ if (!buddy || WARN_ON_ONCE(buddy->vmcs != prev))
indirect_branch_prediction_barrier();
}
@@ -1378,7 +1387,7 @@ void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
- vmx_vcpu_load_vmcs(vcpu, cpu, true);
+ vmx_vcpu_load_vmcs(vcpu, cpu, NULL);
vmx_vcpu_pi_load(vcpu, cpu);
diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h
index c6f940ba5d79c..4a6f382b05b49 100644
--- a/arch/x86/kvm/vmx/vmx.h
+++ b/arch/x86/kvm/vmx/vmx.h
@@ -320,7 +320,8 @@ struct kvm_vmx {
};
bool nested_vmx_allowed(struct kvm_vcpu *vcpu);
-void vmx_vcpu_load_vmcs(struct kvm_vcpu *vcpu, int cpu, bool need_ibpb);
+void vmx_vcpu_load_vmcs(struct kvm_vcpu *vcpu, int cpu,
+ struct loaded_vmcs *buddy);
void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu);
int allocate_vpid(void);
void free_vpid(int vpid);
--
2.26.0
^ permalink raw reply related [flat|nested] 4+ messages in thread
* [PATCH 2/2] KVM: nVMX: Skip IPBP when switching between vmcs01 and vmcs02, redux
2020-05-06 23:58 [PATCH 0/2] KVM: nVMX: Skip IPBP on nested VMCS switch Sean Christopherson
2020-05-06 23:58 ` [PATCH 1/2] KVM: nVMX: Refactor IBPB handling on VMCS switch to genericize code Sean Christopherson
@ 2020-05-06 23:58 ` Sean Christopherson
2020-05-07 11:58 ` [PATCH 0/2] KVM: nVMX: Skip IPBP on nested VMCS switch Paolo Bonzini
2 siblings, 0 replies; 4+ messages in thread
From: Sean Christopherson @ 2020-05-06 23:58 UTC (permalink / raw)
To: Paolo Bonzini
Cc: Sean Christopherson, Vitaly Kuznetsov, Wanpeng Li, Jim Mattson,
Joerg Roedel, kvm, linux-kernel
Skip the Indirect Branch Prediction Barrier that is triggered on a VMCS
switch when temporarily loading vmcs02 to synchronize it to vmcs12, i.e.
give copy_vmcs02_to_vmcs12_rare() the same treatment as
vmx_switch_vmcs().
Make vmx_vcpu_load() static now that it's only referenced within vmx.c.
Signed-off-by: Sean Christopherson <sean.j.christopherson@intel.com>
---
arch/x86/kvm/vmx/nested.c | 4 ++--
arch/x86/kvm/vmx/vmx.c | 2 +-
arch/x86/kvm/vmx/vmx.h | 1 -
3 files changed, 3 insertions(+), 4 deletions(-)
diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index 7d1e19149ef46..4f770eed66cc9 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -3915,12 +3915,12 @@ static void copy_vmcs02_to_vmcs12_rare(struct kvm_vcpu *vcpu,
cpu = get_cpu();
vmx->loaded_vmcs = &vmx->nested.vmcs02;
- vmx_vcpu_load(&vmx->vcpu, cpu);
+ vmx_vcpu_load_vmcs(vcpu, cpu, &vmx->vmcs01);
sync_vmcs02_to_vmcs12_rare(vcpu, vmcs12);
vmx->loaded_vmcs = &vmx->vmcs01;
- vmx_vcpu_load(&vmx->vcpu, cpu);
+ vmx_vcpu_load_vmcs(vcpu, cpu, &vmx->nested.vmcs02);
put_cpu();
}
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index ddbd8fae24927..bc5e5cf1d4cc8 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -1383,7 +1383,7 @@ void vmx_vcpu_load_vmcs(struct kvm_vcpu *vcpu, int cpu,
* Switches to specified vcpu, until a matching vcpu_put(), but assumes
* vcpu mutex is already taken.
*/
-void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
+static void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h
index 4a6f382b05b49..298ddef79d009 100644
--- a/arch/x86/kvm/vmx/vmx.h
+++ b/arch/x86/kvm/vmx/vmx.h
@@ -322,7 +322,6 @@ struct kvm_vmx {
bool nested_vmx_allowed(struct kvm_vcpu *vcpu);
void vmx_vcpu_load_vmcs(struct kvm_vcpu *vcpu, int cpu,
struct loaded_vmcs *buddy);
-void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu);
int allocate_vpid(void);
void free_vpid(int vpid);
void vmx_set_constant_host_state(struct vcpu_vmx *vmx);
--
2.26.0
^ permalink raw reply related [flat|nested] 4+ messages in thread
* Re: [PATCH 0/2] KVM: nVMX: Skip IPBP on nested VMCS switch
2020-05-06 23:58 [PATCH 0/2] KVM: nVMX: Skip IPBP on nested VMCS switch Sean Christopherson
2020-05-06 23:58 ` [PATCH 1/2] KVM: nVMX: Refactor IBPB handling on VMCS switch to genericize code Sean Christopherson
2020-05-06 23:58 ` [PATCH 2/2] KVM: nVMX: Skip IPBP when switching between vmcs01 and vmcs02, redux Sean Christopherson
@ 2020-05-07 11:58 ` Paolo Bonzini
2 siblings, 0 replies; 4+ messages in thread
From: Paolo Bonzini @ 2020-05-07 11:58 UTC (permalink / raw)
To: Sean Christopherson
Cc: Vitaly Kuznetsov, Wanpeng Li, Jim Mattson, Joerg Roedel, kvm,
linux-kernel
On 07/05/20 01:58, Sean Christopherson wrote:
> Or as Jim would say, "Really skip IPBP on nested VMCS switch" :-D
>
> Patch 1 is the delta between kvm/queue and v3 of the original patch[*],
> i.e. I just cherry-picked v3 and fixed the conflicts.
>
> Patch 2 applies the "no IPBP" logic to copy_vmcs02_to_vmcs12_rare().
>
> Feel free to sqaush both of these to commit 7407a52f23732 ("KVM: nVMX:
> Skip IBPB when switching between vmcs01 and vmcs02") if you so desire.
I squashed patch 1 and applied patch 2 separately. Thanks!
Paolo
> [*] https://lkml.kernel.org/r/20200505044644.16563-1-sean.j.christopherson@intel.com
>
> Sean Christopherson (2):
> KVM: nVMX: Refactor IBPB handling on VMCS switch to genericize code
> KVM: nVMX: Skip IPBP when switching between vmcs01 and vmcs02, redux
>
> arch/x86/kvm/vmx/nested.c | 13 +++----------
> arch/x86/kvm/vmx/vmx.c | 19 ++++++++++++++-----
> arch/x86/kvm/vmx/vmx.h | 4 ++--
> 3 files changed, 19 insertions(+), 17 deletions(-)
>
^ permalink raw reply [flat|nested] 4+ messages in thread
end of thread, other threads:[~2020-05-07 11:58 UTC | newest]
Thread overview: 4+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2020-05-06 23:58 [PATCH 0/2] KVM: nVMX: Skip IPBP on nested VMCS switch Sean Christopherson
2020-05-06 23:58 ` [PATCH 1/2] KVM: nVMX: Refactor IBPB handling on VMCS switch to genericize code Sean Christopherson
2020-05-06 23:58 ` [PATCH 2/2] KVM: nVMX: Skip IPBP when switching between vmcs01 and vmcs02, redux Sean Christopherson
2020-05-07 11:58 ` [PATCH 0/2] KVM: nVMX: Skip IPBP on nested VMCS switch Paolo Bonzini
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).