KVM: X86: Implement PV IPIs in linux guest

Implement paravirtual apic hooks to enable PV IPIs for KVM if the "send IPI"
hypercall is available.  The hypercall lets a guest send IPIs, with
at most 128 destinations per hypercall in 64-bit mode and 64 vCPUs per
hypercall in 32-bit mode.

Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Radim Krčmář <rkrcmar@redhat.com>
Cc: Vitaly Kuznetsov <vkuznets@redhat.com>
Signed-off-by: Wanpeng Li <wanpengli@tencent.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

3 files changed, 98 insertions, 0 deletions

diff --git a/arch/x86/include/uapi/asm/kvm_para.h b/arch/x86/include/uapi/asm/kvm_para.h
index 0ede697c3961..19980ec1a316 100644
--- a/arch/x86/include/uapi/asm/kvm_para.h
+++ b/arch/x86/include/uapi/asm/kvm_para.h
@@ -28,6 +28,7 @@
 #define KVM_FEATURE_PV_UNHALT           7
 #define KVM_FEATURE_PV_TLB_FLUSH        9
 #define KVM_FEATURE_ASYNC_PF_VMEXIT     10
+#define KVM_FEATURE_PV_SEND_IPI 11
 
 #define KVM_HINTS_REALTIME      0
 
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index 39d79720380f..62cbd089f709 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -454,6 +454,98 @@ static void __init sev_map_percpu_data(void)
 }
 
 #ifdef CONFIG_SMP
+#define KVM_IPI_CLUSTER_SIZE    (2 * BITS_PER_LONG)
+
+static void __send_ipi_mask(const struct cpumask *mask, int vector)
+{
+        unsigned long flags;
+        int cpu, apic_id, icr;
+        int min = 0, max = 0;
+#ifdef CONFIG_X86_64
+        __uint128_t ipi_bitmap = 0;
+#else
+        u64 ipi_bitmap = 0;
+#endif
+
+        if (cpumask_empty(mask))
+                return;
+
+        local_irq_save(flags);
+
+        switch (vector) {
+        default:
+                icr = APIC_DM_FIXED | vector;
+                break;
+        case NMI_VECTOR:
+                icr = APIC_DM_NMI;
+                break;
+        }
+
+        for_each_cpu(cpu, mask) {
+                apic_id = per_cpu(x86_cpu_to_apicid, cpu);
+                if (!ipi_bitmap) {
+                        min = max = apic_id;
+                } else if (apic_id < min && max - apic_id < KVM_IPI_CLUSTER_SIZE) {
+                        ipi_bitmap <<= min - apic_id;
+                        min = apic_id;
+                } else if (apic_id < min + KVM_IPI_CLUSTER_SIZE) {
+                        max = apic_id < max ? max : apic_id;
+                } else {
+                        kvm_hypercall4(KVM_HC_SEND_IPI, (unsigned long)ipi_bitmap,
+                                (unsigned long)(ipi_bitmap >> BITS_PER_LONG), min, icr);
+                        min = max = apic_id;
+                        ipi_bitmap = 0;
+                }
+                __set_bit(apic_id - min, (unsigned long *)&ipi_bitmap);
+        }
+
+        if (ipi_bitmap) {
+                kvm_hypercall4(KVM_HC_SEND_IPI, (unsigned long)ipi_bitmap,
+                        (unsigned long)(ipi_bitmap >> BITS_PER_LONG), min, icr);
+        }
+
+        local_irq_restore(flags);
+}
+
+static void kvm_send_ipi_mask(const struct cpumask *mask, int vector)
+{
+        __send_ipi_mask(mask, vector);
+}
+
+static void kvm_send_ipi_mask_allbutself(const struct cpumask *mask, int vector)
+{
+        unsigned int this_cpu = smp_processor_id();
+        struct cpumask new_mask;
+        const struct cpumask *local_mask;
+
+        cpumask_copy(&new_mask, mask);
+        cpumask_clear_cpu(this_cpu, &new_mask);
+        local_mask = &new_mask;
+        __send_ipi_mask(local_mask, vector);
+}
+
+static void kvm_send_ipi_allbutself(int vector)
+{
+        kvm_send_ipi_mask_allbutself(cpu_online_mask, vector);
+}
+
+static void kvm_send_ipi_all(int vector)
+{
+        __send_ipi_mask(cpu_online_mask, vector);
+}
+
+/*
+ * Set the IPI entry points
+ */
+static void kvm_setup_pv_ipi(void)
+{
+        apic->send_IPI_mask = kvm_send_ipi_mask;
+        apic->send_IPI_mask_allbutself = kvm_send_ipi_mask_allbutself;
+        apic->send_IPI_allbutself = kvm_send_ipi_allbutself;
+        apic->send_IPI_all = kvm_send_ipi_all;
+        pr_info("KVM setup pv IPIs\n");
+}
+
 static void __init kvm_smp_prepare_cpus(unsigned int max_cpus)
 {
         native_smp_prepare_cpus(max_cpus);
@@ -626,6 +718,10 @@ static uint32_t __init kvm_detect(void)
 
 static void __init kvm_apic_init(void)
 {
+#if defined(CONFIG_SMP)
+        if (kvm_para_has_feature(KVM_FEATURE_PV_SEND_IPI))
+                kvm_setup_pv_ipi();
+#endif
 }
 
 static void __init kvm_init_platform(void)
diff --git a/include/uapi/linux/kvm_para.h b/include/uapi/linux/kvm_para.h
index f3893ef82b65..6c0ce49931e5 100644
--- a/include/uapi/linux/kvm_para.h
+++ b/include/uapi/linux/kvm_para.h
@@ -27,6 +27,7 @@
 #define KVM_HC_MIPS_EXIT_VM             7
 #define KVM_HC_MIPS_CONSOLE_OUTPUT      8
 #define KVM_HC_CLOCK_PAIRING            9
+#define KVM_HC_SEND_IPI         10
 
 /*
  * hypercalls use architecture specific