[PATCH v8 2/4] KVM: X86: Add Paravirt TLB Shootdown

[Wanpeng Li]

From: Wanpeng Li <wanpeng.li@xxxxxxxxxxx>

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.

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.

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%

Cc: Paolo Bonzini <pbonzini@xxxxxxxxxx>
Cc: Radim KrÄmÃÅ <rkrcmar@xxxxxxxxxx>
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Signed-off-by: Wanpeng Li <wanpeng.li@xxxxxxxxxxx>
---
 Documentation/virtual/kvm/cpuid.txt  |  4 +++
 arch/x86/include/uapi/asm/kvm_para.h |  2 ++
 arch/x86/kernel/kvm.c                | 47 ++++++++++++++++++++++++++++++++++++
 3 files changed, 53 insertions(+)

diff --git a/Documentation/virtual/kvm/cpuid.txt b/Documentation/virtual/kvm/cpuid.txt
index 3c65feb..dcab6dc 100644
--- a/Documentation/virtual/kvm/cpuid.txt
+++ b/Documentation/virtual/kvm/cpuid.txt
@@ -54,6 +54,10 @@ KVM_FEATURE_PV_UNHALT              ||     7 || guest checks this feature bit
                                    ||       || before enabling paravirtualized
                                    ||       || spinlock support.
 ------------------------------------------------------------------------------
+KVM_FEATURE_PV_TLB_FLUSH           ||     9 || guest checks this feature bit
+                                   ||       || before enabling paravirtualized
+                                   ||       || tlb flush.
+------------------------------------------------------------------------------
 KVM_FEATURE_CLOCKSOURCE_STABLE_BIT ||    24 || host will warn if no guest-side
                                    ||       || per-cpu warps are expected in
                                    ||       || kvmclock.
diff --git a/arch/x86/include/uapi/asm/kvm_para.h b/arch/x86/include/uapi/asm/kvm_para.h
index 763b692..8fbcc16 100644
--- a/arch/x86/include/uapi/asm/kvm_para.h
+++ b/arch/x86/include/uapi/asm/kvm_para.h
@@ -25,6 +25,7 @@
 #define KVM_FEATURE_STEAL_TIME		5
 #define KVM_FEATURE_PV_EOI		6
 #define KVM_FEATURE_PV_UNHALT		7
+#define KVM_FEATURE_PV_TLB_FLUSH	9
 
 /* The last 8 bits are used to indicate how to interpret the flags field
  * in pvclock structure. If no bits are set, all flags are ignored.
@@ -53,6 +54,7 @@ struct kvm_steal_time {
 
 #define KVM_VCPU_NOT_PREEMPTED      (0 << 0)
 #define KVM_VCPU_PREEMPTED          (1 << 0)
+#define KVM_VCPU_SHOULD_FLUSH       (1 << 1)
 
 #define KVM_CLOCK_PAIRING_WALLCLOCK 0
 struct kvm_clock_pairing {
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index 6610b92..73e00c4 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -498,6 +498,34 @@ static void __init kvm_apf_trap_init(void)
 	update_intr_gate(X86_TRAP_PF, async_page_fault);
 }
 
+static DEFINE_PER_CPU(cpumask_var_t, __pv_tlb_mask);
+
+static void kvm_flush_tlb_others(const struct cpumask *cpumask,
+			const struct flush_tlb_info *info)
+{
+	u8 state;
+	int cpu;
+	struct kvm_steal_time *src;
+	struct cpumask *flushmask = this_cpu_cpumask_var_ptr(__pv_tlb_mask);
+
+	cpumask_copy(flushmask, cpumask);
+	/*
+	 * We have to call flush only on online vCPUs. And
+	 * queue flush_on_enter for pre-empted vCPUs
+	 */
+	for_each_cpu(cpu, flushmask) {
+		src = &per_cpu(steal_time, cpu);
+		state = READ_ONCE(src->preempted);
+		if ((state & KVM_VCPU_PREEMPTED)) {
+			if (try_cmpxchg(&src->preempted, &state,
+				state | KVM_VCPU_SHOULD_FLUSH))
+				__cpumask_clear_cpu(cpu, flushmask);
+		}
+	}
+
+	native_flush_tlb_others(flushmask, info);
+}
+
 static void __init kvm_guest_init(void)
 {
 	int i;
@@ -517,6 +545,9 @@ static void __init kvm_guest_init(void)
 		pv_time_ops.steal_clock = kvm_steal_clock;
 	}
 
+	if (kvm_para_has_feature(KVM_FEATURE_PV_TLB_FLUSH))
+		pv_mmu_ops.flush_tlb_others = kvm_flush_tlb_others;
+
 	if (kvm_para_has_feature(KVM_FEATURE_PV_EOI))
 		apic_set_eoi_write(kvm_guest_apic_eoi_write);
 
@@ -598,6 +629,22 @@ static __init int activate_jump_labels(void)
 }
 arch_initcall(activate_jump_labels);
 
+static __init int kvm_setup_pv_tlb_flush(void)
+{
+	int cpu;
+
+	if (kvm_para_has_feature(KVM_FEATURE_PV_TLB_FLUSH)) {
+		for_each_possible_cpu(cpu) {
+			zalloc_cpumask_var_node(per_cpu_ptr(&__pv_tlb_mask, cpu),
+				GFP_KERNEL, cpu_to_node(cpu));
+		}
+		pr_info("KVM setup pv remote TLB flush\n");
+	}
+
+	return 0;
+}
+arch_initcall(kvm_setup_pv_tlb_flush);
+
 #ifdef CONFIG_PARAVIRT_SPINLOCKS
 
 /* Kick a cpu by its apicid. Used to wake up a halted vcpu */
-- 
2.7.4