Remote flushing api's does a busy wait which is fine in bare-metal
scenario. But with-in the guest, the vcpus might have been pre-empted
or blocked. In this scenario, the initator vcpu would end up
busy-waiting for a long amount of time.
This patch set implements para-virt flush tlbs making sure that it
does not wait for vcpus that are sleeping. And all the sleeping vcpus
flush the tlb on guest enter. Idea was discussed here:
https://lkml.org/lkml/2012/2/20/157
The best result is achieved when we're overcommiting the host by running
multiple vCPUs on each pCPU. In this case PV tlb flush avoids touching
vCPUs which are not scheduled and avoid the wait on the main CPU.
In addition, thanks for commit 9e52fc2b50d ("x86/mm: Enable RCU based
page table freeing (CONFIG_HAVE_RCU_TABLE_FREE=y)")
Test on a Haswell i7 desktop 4 cores (2HT), so 8 pCPUs, running ebizzy in
one linux guest.
ebizzy -M
vanilla optimized boost
8 vCPUs 10152 10083 -0.68%
16 vCPUs 1224 4866 297.5%
24 vCPUs 1109 3871 249%
32 vCPUs 1025 3375 229.3%
Wanpeng Li (3):
KVM: Add vCPU running/preempted state
KVM: Add paravirt remote TLB flush
KVM: Add flush_on_enter before guest enter
arch/x86/include/uapi/asm/kvm_para.h | 4 ++++
arch/x86/kernel/kvm.c | 31 ++++++++++++++++++++++++++++++-
arch/x86/kvm/x86.c | 12 ++++++++++--
3 files changed, 44 insertions(+), 3 deletions(-)
--
2.7.4
From 1583551491008068872@xxx Thu Nov 09 01:53:05 +0000 2017
X-GM-THRID: 1583551491008068872
X-Gmail-Labels: Inbox,Category Forums,HistoricalUnread
From: Wanpeng Li <[email protected]>
This patch reuses the preempted field in kvm_steal_time, and will export
the vcpu running/pre-empted information to the guest from host. This will
enable guest to intelligently send ipi to running vcpus and set flag for
pre-empted vcpus. This will prevent waiting for vcpus that are not running.
Cc: Paolo Bonzini <[email protected]>
Cc: Radim Krčmář <[email protected]>
Signed-off-by: Wanpeng Li <[email protected]>
---
arch/x86/include/uapi/asm/kvm_para.h | 3 +++
arch/x86/kernel/kvm.c | 2 +-
arch/x86/kvm/x86.c | 4 ++--
3 files changed, 6 insertions(+), 3 deletions(-)
diff --git a/arch/x86/include/uapi/asm/kvm_para.h b/arch/x86/include/uapi/asm/kvm_para.h
index a965e5b0..ff23ce9 100644
--- a/arch/x86/include/uapi/asm/kvm_para.h
+++ b/arch/x86/include/uapi/asm/kvm_para.h
@@ -50,6 +50,9 @@ struct kvm_steal_time {
__u32 pad[11];
};
+#define KVM_VCPU_NOT_PREEMPTED (0 << 0)
+#define KVM_VCPU_PREEMPTED (1 << 0)
+
#define KVM_CLOCK_PAIRING_WALLCLOCK 0
struct kvm_clock_pairing {
__s64 sec;
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index 8bb9594..1b1b641 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -608,7 +608,7 @@ __visible bool __kvm_vcpu_is_preempted(long cpu)
{
struct kvm_steal_time *src = &per_cpu(steal_time, cpu);
- return !!src->preempted;
+ return !!(src->preempted & KVM_VCPU_PREEMPTED);
}
PV_CALLEE_SAVE_REGS_THUNK(__kvm_vcpu_is_preempted);
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index d2507c6..1ea28a2 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -2116,7 +2116,7 @@ static void record_steal_time(struct kvm_vcpu *vcpu)
&vcpu->arch.st.steal, sizeof(struct kvm_steal_time))))
return;
- vcpu->arch.st.steal.preempted = 0;
+ vcpu->arch.st.steal.preempted = KVM_VCPU_NOT_PREEMPTED;
if (vcpu->arch.st.steal.version & 1)
vcpu->arch.st.steal.version += 1; /* first time write, random junk */
@@ -2887,7 +2887,7 @@ static void kvm_steal_time_set_preempted(struct kvm_vcpu *vcpu)
if (!(vcpu->arch.st.msr_val & KVM_MSR_ENABLED))
return;
- vcpu->arch.st.steal.preempted = 1;
+ vcpu->arch.st.steal.preempted = KVM_VCPU_PREEMPTED;
kvm_write_guest_offset_cached(vcpu->kvm, &vcpu->arch.st.stime,
&vcpu->arch.st.steal.preempted,
--
2.7.4
From 1583551606621367367@xxx Thu Nov 09 01:54:55 +0000 2017
X-GM-THRID: 1583551606621367367
X-Gmail-Labels: Inbox,Category Forums,HistoricalUnread
From: Wanpeng Li <[email protected]>
PV-Flush guest would indicate to flush on enter, flush the TLB before
entering and exiting the guest.
Cc: Paolo Bonzini <[email protected]>
Cc: Radim Krčmář <[email protected]>
Signed-off-by: Wanpeng Li <[email protected]>
---
arch/x86/kvm/x86.c | 12 ++++++++++--
1 file changed, 10 insertions(+), 2 deletions(-)
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 1ea28a2..f295360 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -2116,7 +2116,13 @@ static void record_steal_time(struct kvm_vcpu *vcpu)
&vcpu->arch.st.steal, sizeof(struct kvm_steal_time))))
return;
- vcpu->arch.st.steal.preempted = KVM_VCPU_NOT_PREEMPTED;
+ if (xchg(&vcpu->arch.st.steal.preempted, KVM_VCPU_NOT_PREEMPTED) ==
+ (KVM_VCPU_SHOULD_FLUSH | KVM_VCPU_PREEMPTED))
+ /*
+ * Do TLB_FLUSH before entering the guest, its passed
+ * the stage of request checking
+ */
+ kvm_x86_ops->tlb_flush(vcpu);
if (vcpu->arch.st.steal.version & 1)
vcpu->arch.st.steal.version += 1; /* first time write, random junk */
@@ -2887,7 +2893,9 @@ static void kvm_steal_time_set_preempted(struct kvm_vcpu *vcpu)
if (!(vcpu->arch.st.msr_val & KVM_MSR_ENABLED))
return;
- vcpu->arch.st.steal.preempted = KVM_VCPU_PREEMPTED;
+ if (xchg(&vcpu->arch.st.steal.preempted, KVM_VCPU_PREEMPTED) ==
+ KVM_VCPU_SHOULD_FLUSH)
+ kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu);
kvm_write_guest_offset_cached(vcpu->kvm, &vcpu->arch.st.stime,
&vcpu->arch.st.steal.preempted,
--
2.7.4
From 1583551507097428689@xxx Thu Nov 09 01:53:21 +0000 2017
X-GM-THRID: 1583551507097428689
X-Gmail-Labels: Inbox,Category Forums,HistoricalUnread