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)")
Testing on a Xeon Gold 6142 2.6GHz 2 sockets, 32 cores, 64 threads,
so 64 pCPUs, and each VM is 64 vCPUs.
ebizzy -M
vanilla optimized boost
1VM 46799 48670 4%
2VM 23962 42691 78%
3VM 16152 37539 132%
Note: The patchset is not rebased against "locking/qspinlock/x86: Avoid
test-and-set when PV_DEDICATED is set" v3 since I can still observe a
little improvement for 64 vCPUs on 64 pCPUs, it is due to the system
is not completely isolated, there are many housekeeping tasks work
sporadically, and vCPUs are preemted some times, I also confirm this
when adding some print to the kvm_flush_tlb_others. After PV_DEDICATED
is merged, we can disable pv tlb flush when not overcommiting if it
is needed.
v5 -> v6:
* fix the percpu mask
* rebase against latest kvm/queue
v4 -> v5:
* flushmask instead of cpumask
v3 -> v4:
* use READ_ONCE()
* use try_cmpxchg instead of cmpxchg
* add {} to if
* no FLUSH flags to preserve during set_preempted
* "KVM: X86" prefix to patch subject
v2 -> v3:
* percpu cpumask
v1 -> v2:
* a new CPUID feature bit
* fix cmpxchg check
* use kvm_vcpu_flush_tlb() to get the statistics right
* just OR the KVM_VCPU_PREEMPTED in kvm_steal_time_set_preempted
* add a new bool argument to kvm_x86_ops->tlb_flush
* __cpumask_clear_cpu() instead of cpumask_clear_cpu()
* not put cpumask_t on stack
* rebase the patchset against "locking/qspinlock/x86: Avoid
test-and-set when PV_DEDICATED is set" v3
Wanpeng Li (4):
KVM: X86: Add vCPU running/preempted state
KVM: X86: Add Paravirt TLB Shootdown
KVM: X86: introduce invalidate_gpa argument to tlb flush
KVM: X86: Add flush_on_enter before guest enter
Documentation/virtual/kvm/cpuid.txt | 4 ++++
arch/x86/include/asm/kvm_host.h | 2 +-
arch/x86/include/uapi/asm/kvm_para.h | 5 +++++
arch/x86/kernel/kvm.c | 36 +++++++++++++++++++++++++++++++++++-
arch/x86/kvm/cpuid.c | 3 ++-
arch/x86/kvm/svm.c | 14 +++++++-------
arch/x86/kvm/vmx.c | 21 +++++++++++----------
arch/x86/kvm/x86.c | 25 ++++++++++++++++---------
8 files changed, 81 insertions(+), 29 deletions(-)
--
2.7.4
From 1585497865341280799@xxx Thu Nov 30 13:29:52 +0000 2017
X-GM-THRID: 1584579468645715159
X-Gmail-Labels: Inbox,Category Forums,HistoricalUnread
From: Wanpeng Li <[email protected]>
Introduce a new bool invalidate_gpa argument to kvm_x86_ops->tlb_flush,
it will be used by later patches to just flush guest tlb.
Cc: Paolo Bonzini <[email protected]>
Cc: Radim Krčmář <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Signed-off-by: Wanpeng Li <[email protected]>
---
arch/x86/include/asm/kvm_host.h | 2 +-
arch/x86/kvm/svm.c | 14 +++++++-------
arch/x86/kvm/vmx.c | 21 +++++++++++----------
arch/x86/kvm/x86.c | 6 +++---
4 files changed, 22 insertions(+), 21 deletions(-)
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index b97726e..63d34bc 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -952,7 +952,7 @@ struct kvm_x86_ops {
unsigned long (*get_rflags)(struct kvm_vcpu *vcpu);
void (*set_rflags)(struct kvm_vcpu *vcpu, unsigned long rflags);
- void (*tlb_flush)(struct kvm_vcpu *vcpu);
+ void (*tlb_flush)(struct kvm_vcpu *vcpu, bool invalidate_gpa);
void (*run)(struct kvm_vcpu *vcpu);
int (*handle_exit)(struct kvm_vcpu *vcpu);
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index 1f3e7f2..14cca8c 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -285,7 +285,7 @@ static int vgif = true;
module_param(vgif, int, 0444);
static void svm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0);
-static void svm_flush_tlb(struct kvm_vcpu *vcpu);
+static void svm_flush_tlb(struct kvm_vcpu *vcpu, bool invalidate_gpa);
static void svm_complete_interrupts(struct vcpu_svm *svm);
static int nested_svm_exit_handled(struct vcpu_svm *svm);
@@ -2035,7 +2035,7 @@ static int svm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
return 1;
if (npt_enabled && ((old_cr4 ^ cr4) & X86_CR4_PGE))
- svm_flush_tlb(vcpu);
+ svm_flush_tlb(vcpu, true);
vcpu->arch.cr4 = cr4;
if (!npt_enabled)
@@ -2385,7 +2385,7 @@ static void nested_svm_set_tdp_cr3(struct kvm_vcpu *vcpu,
svm->vmcb->control.nested_cr3 = __sme_set(root);
mark_dirty(svm->vmcb, VMCB_NPT);
- svm_flush_tlb(vcpu);
+ svm_flush_tlb(vcpu, true);
}
static void nested_svm_inject_npf_exit(struct kvm_vcpu *vcpu,
@@ -2989,7 +2989,7 @@ static void enter_svm_guest_mode(struct vcpu_svm *svm, u64 vmcb_gpa,
svm->nested.intercept_exceptions = nested_vmcb->control.intercept_exceptions;
svm->nested.intercept = nested_vmcb->control.intercept;
- svm_flush_tlb(&svm->vcpu);
+ svm_flush_tlb(&svm->vcpu, true);
svm->vmcb->control.int_ctl = nested_vmcb->control.int_ctl | V_INTR_MASKING_MASK;
if (nested_vmcb->control.int_ctl & V_INTR_MASKING_MASK)
svm->vcpu.arch.hflags |= HF_VINTR_MASK;
@@ -4785,7 +4785,7 @@ static int svm_set_tss_addr(struct kvm *kvm, unsigned int addr)
return 0;
}
-static void svm_flush_tlb(struct kvm_vcpu *vcpu)
+static void svm_flush_tlb(struct kvm_vcpu *vcpu, bool invalidate_gpa)
{
struct vcpu_svm *svm = to_svm(vcpu);
@@ -5076,7 +5076,7 @@ static void svm_set_cr3(struct kvm_vcpu *vcpu, unsigned long root)
svm->vmcb->save.cr3 = __sme_set(root);
mark_dirty(svm->vmcb, VMCB_CR);
- svm_flush_tlb(vcpu);
+ svm_flush_tlb(vcpu, true);
}
static void set_tdp_cr3(struct kvm_vcpu *vcpu, unsigned long root)
@@ -5090,7 +5090,7 @@ static void set_tdp_cr3(struct kvm_vcpu *vcpu, unsigned long root)
svm->vmcb->save.cr3 = kvm_read_cr3(vcpu);
mark_dirty(svm->vmcb, VMCB_CR);
- svm_flush_tlb(vcpu);
+ svm_flush_tlb(vcpu, true);
}
static int is_disabled(void)
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index b10d203..8c7e816 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -4136,9 +4136,10 @@ static void exit_lmode(struct kvm_vcpu *vcpu)
#endif
-static inline void __vmx_flush_tlb(struct kvm_vcpu *vcpu, int vpid)
+static inline void __vmx_flush_tlb(struct kvm_vcpu *vcpu, int vpid,
+ bool invalidate_gpa)
{
- if (enable_ept) {
+ if (enable_ept && (invalidate_gpa || !enable_vpid)) {
if (!VALID_PAGE(vcpu->arch.mmu.root_hpa))
return;
ept_sync_context(construct_eptp(vcpu, vcpu->arch.mmu.root_hpa));
@@ -4147,15 +4148,15 @@ static inline void __vmx_flush_tlb(struct kvm_vcpu *vcpu, int vpid)
}
}
-static void vmx_flush_tlb(struct kvm_vcpu *vcpu)
+static void vmx_flush_tlb(struct kvm_vcpu *vcpu, bool invalidate_gpa)
{
- __vmx_flush_tlb(vcpu, to_vmx(vcpu)->vpid);
+ __vmx_flush_tlb(vcpu, to_vmx(vcpu)->vpid, invalidate_gpa);
}
static void vmx_flush_tlb_ept_only(struct kvm_vcpu *vcpu)
{
if (enable_ept)
- vmx_flush_tlb(vcpu);
+ vmx_flush_tlb(vcpu, true);
}
static void vmx_decache_cr0_guest_bits(struct kvm_vcpu *vcpu)
@@ -4353,7 +4354,7 @@ static void vmx_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3)
ept_load_pdptrs(vcpu);
}
- vmx_flush_tlb(vcpu);
+ vmx_flush_tlb(vcpu, true);
vmcs_writel(GUEST_CR3, guest_cr3);
}
@@ -8026,7 +8027,7 @@ static int handle_invvpid(struct kvm_vcpu *vcpu)
return kvm_skip_emulated_instruction(vcpu);
}
- __vmx_flush_tlb(vcpu, vmx->nested.vpid02);
+ __vmx_flush_tlb(vcpu, vmx->nested.vpid02, true);
nested_vmx_succeed(vcpu);
return kvm_skip_emulated_instruction(vcpu);
@@ -10710,11 +10711,11 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
vmcs_write16(VIRTUAL_PROCESSOR_ID, vmx->nested.vpid02);
if (vmcs12->virtual_processor_id != vmx->nested.last_vpid) {
vmx->nested.last_vpid = vmcs12->virtual_processor_id;
- __vmx_flush_tlb(vcpu, to_vmx(vcpu)->nested.vpid02);
+ __vmx_flush_tlb(vcpu, to_vmx(vcpu)->nested.vpid02, true);
}
} else {
vmcs_write16(VIRTUAL_PROCESSOR_ID, vmx->vpid);
- vmx_flush_tlb(vcpu);
+ vmx_flush_tlb(vcpu, true);
}
}
@@ -11424,7 +11425,7 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu,
* L1's vpid. TODO: move to a more elaborate solution, giving
* each L2 its own vpid and exposing the vpid feature to L1.
*/
- vmx_flush_tlb(vcpu);
+ vmx_flush_tlb(vcpu, true);
}
/* Restore posted intr vector. */
if (nested_cpu_has_posted_intr(vmcs12))
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index bc501aa..c279530 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -6775,10 +6775,10 @@ static void vcpu_scan_ioapic(struct kvm_vcpu *vcpu)
kvm_x86_ops->load_eoi_exitmap(vcpu, eoi_exit_bitmap);
}
-static void kvm_vcpu_flush_tlb(struct kvm_vcpu *vcpu)
+static void kvm_vcpu_flush_tlb(struct kvm_vcpu *vcpu, bool invalidate_gpa)
{
++vcpu->stat.tlb_flush;
- kvm_x86_ops->tlb_flush(vcpu);
+ kvm_x86_ops->tlb_flush(vcpu, invalidate_gpa);
}
void kvm_vcpu_reload_apic_access_page(struct kvm_vcpu *vcpu)
@@ -6835,7 +6835,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
if (kvm_check_request(KVM_REQ_MMU_SYNC, vcpu))
kvm_mmu_sync_roots(vcpu);
if (kvm_check_request(KVM_REQ_TLB_FLUSH, vcpu))
- kvm_vcpu_flush_tlb(vcpu);
+ kvm_vcpu_flush_tlb(vcpu, true);
if (kvm_check_request(KVM_REQ_REPORT_TPR_ACCESS, vcpu)) {
vcpu->run->exit_reason = KVM_EXIT_TPR_ACCESS;
r = 0;
--
2.7.4
From 1585368487287926986@xxx Wed Nov 29 03:13:28 +0000 2017
X-GM-THRID: 1584613258350362224
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 the guest.
Cc: Paolo Bonzini <[email protected]>
Cc: Radim Krčmář <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Signed-off-by: Wanpeng Li <[email protected]>
---
arch/x86/kvm/cpuid.c | 3 ++-
arch/x86/kvm/x86.c | 21 ++++++++++++++-------
2 files changed, 16 insertions(+), 8 deletions(-)
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index b943711..8834898 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -601,7 +601,8 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
(1 << KVM_FEATURE_ASYNC_PF) |
(1 << KVM_FEATURE_PV_EOI) |
(1 << KVM_FEATURE_CLOCKSOURCE_STABLE_BIT) |
- (1 << KVM_FEATURE_PV_UNHALT);
+ (1 << KVM_FEATURE_PV_UNHALT) |
+ (1 << KVM_FEATURE_PV_TLB_FLUSH);
if (sched_info_on())
entry->eax |= (1 << KVM_FEATURE_STEAL_TIME);
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index c279530..94c23ae 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -2121,6 +2121,12 @@ static void kvmclock_reset(struct kvm_vcpu *vcpu)
vcpu->arch.pv_time_enabled = false;
}
+static void kvm_vcpu_flush_tlb(struct kvm_vcpu *vcpu, bool invalidate_gpa)
+{
+ ++vcpu->stat.tlb_flush;
+ kvm_x86_ops->tlb_flush(vcpu, invalidate_gpa);
+}
+
static void record_steal_time(struct kvm_vcpu *vcpu)
{
if (!(vcpu->arch.st.msr_val & KVM_MSR_ENABLED))
@@ -2130,7 +2136,14 @@ 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_vcpu_flush_tlb(vcpu, false);
+ }
if (vcpu->arch.st.steal.version & 1)
vcpu->arch.st.steal.version += 1; /* first time write, random junk */
@@ -6775,12 +6788,6 @@ static void vcpu_scan_ioapic(struct kvm_vcpu *vcpu)
kvm_x86_ops->load_eoi_exitmap(vcpu, eoi_exit_bitmap);
}
-static void kvm_vcpu_flush_tlb(struct kvm_vcpu *vcpu, bool invalidate_gpa)
-{
- ++vcpu->stat.tlb_flush;
- kvm_x86_ops->tlb_flush(vcpu, invalidate_gpa);
-}
-
void kvm_vcpu_reload_apic_access_page(struct kvm_vcpu *vcpu)
{
struct page *page = NULL;
--
2.7.4
From 1585290999167532022@xxx Tue Nov 28 06:41:49 +0000 2017
X-GM-THRID: 1582223927417446326
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]>
Cc: Peter Zijlstra <[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 09cc064..763b692 100644
--- a/arch/x86/include/uapi/asm/kvm_para.h
+++ b/arch/x86/include/uapi/asm/kvm_para.h
@@ -51,6 +51,9 @@ 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 b40ffbf..6610b92 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -643,7 +643,7 @@ __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 990df39..bc501aa 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -2130,7 +2130,7 @@ 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 */
@@ -2907,7 +2907,7 @@ 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 1584956591921415184@xxx Fri Nov 24 14:06:34 +0000 2017
X-GM-THRID: 1584956591921415184
X-Gmail-Labels: Inbox,Category Updates,HistoricalUnread