KVM: X86: Yield to IPI target if necessary

When sending a call-function IPI-many to vCPUs, yield if any of
the IPI target vCPUs was preempted, we just select the first
preempted target vCPU which we found since the state of target
vCPUs can change underneath and to avoid race conditions.

Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Radim Krčmář <rkrcmar@redhat.com>
Cc: Liran Alon <liran.alon@oracle.com>
Signed-off-by: Wanpeng Li <wanpengli@tencent.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

diff --git a/Documentation/virtual/kvm/hypercalls.txt b/Documentation/virtual/kvm/hypercalls.txt
index da24c13..da21065 100644 (file)
--- a/Documentation/virtual/kvm/hypercalls.txt
+++ b/Documentation/virtual/kvm/hypercalls.txt
@@ -141,3 +141,14 @@ a0 corresponds to the APIC ID in the third argument (a2), bit 1
 corresponds to the APIC ID a2+1, and so on.
 
 Returns the number of CPUs to which the IPIs were delivered successfully.
+
+7. KVM_HC_SCHED_YIELD
+------------------------
+Architecture: x86
+Status: active
+Purpose: Hypercall used to yield if the IPI target vCPU is preempted
+
+a0: destination APIC ID
+
+Usage example: When sending a call-function IPI-many to vCPUs, yield if
+any of the IPI target vCPUs was preempted.

diff --git a/arch/x86/include/uapi/asm/kvm_para.h b/arch/x86/include/uapi/asm/kvm_para.h
index 21d5f02..2a8e0b6 100644 (file)
--- a/arch/x86/include/uapi/asm/kvm_para.h
+++ b/arch/x86/include/uapi/asm/kvm_para.h
@@ -30,6 +30,7 @@
 #define KVM_FEATURE_ASYNC_PF_VMEXIT    10
 #define KVM_FEATURE_PV_SEND_IPI        11
 #define KVM_FEATURE_POLL_CONTROL       12
+#define KVM_FEATURE_PV_SCHED_YIELD     13
 
 #define KVM_HINTS_REALTIME      0
 

diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index 5169b8c..82caf01 100644 (file)
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -527,6 +527,21 @@ static void kvm_setup_pv_ipi(void)
        pr_info("KVM setup pv IPIs\n");
 }
 
+static void kvm_smp_send_call_func_ipi(const struct cpumask *mask)
+{
+       int cpu;
+
+       native_send_call_func_ipi(mask);
+
+       /* Make sure other vCPUs get a chance to run if they need to. */
+       for_each_cpu(cpu, mask) {
+               if (vcpu_is_preempted(cpu)) {
+                       kvm_hypercall1(KVM_HC_SCHED_YIELD, per_cpu(x86_cpu_to_apicid, cpu));
+                       break;
+               }
+       }
+}
+
 static void __init kvm_smp_prepare_cpus(unsigned int max_cpus)
 {
        native_smp_prepare_cpus(max_cpus);
@@ -638,6 +653,12 @@ static void __init kvm_guest_init(void)
 #ifdef CONFIG_SMP
        smp_ops.smp_prepare_cpus = kvm_smp_prepare_cpus;
        smp_ops.smp_prepare_boot_cpu = kvm_smp_prepare_boot_cpu;
+       if (kvm_para_has_feature(KVM_FEATURE_PV_SCHED_YIELD) &&
+           !kvm_para_has_hint(KVM_HINTS_REALTIME) &&
+           kvm_para_has_feature(KVM_FEATURE_STEAL_TIME)) {
+               smp_ops.send_call_func_ipi = kvm_smp_send_call_func_ipi;
+               pr_info("KVM setup pv sched yield\n");
+       }
        if (cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN, "x86/kvm:online",
                                      kvm_cpu_online, kvm_cpu_down_prepare) < 0)
                pr_err("kvm_guest: Failed to install cpu hotplug callbacks\n");

diff --git a/include/uapi/linux/kvm_para.h b/include/uapi/linux/kvm_para.h
index 6c0ce49..8b86609 100644 (file)
--- a/include/uapi/linux/kvm_para.h
+++ b/include/uapi/linux/kvm_para.h
@@ -28,6 +28,7 @@
 #define KVM_HC_MIPS_CONSOLE_OUTPUT     8
 #define KVM_HC_CLOCK_PAIRING           9
 #define KVM_HC_SEND_IPI                10
+#define KVM_HC_SCHED_YIELD             11
 
 /*
  * hypercalls use architecture specific