KVM: VMX: enable IPI virtualization

With IPI virtualization enabled, the processor emulates writes to
APIC registers that would send IPIs. The processor sets the bit
corresponding to the vector in target vCPU's PIR and may send a
notification (IPI) specified by NDST and NV fields in target vCPU's
Posted-Interrupt Descriptor (PID). It is similar to what IOMMU
engine does when dealing with posted interrupt from devices.

A PID-pointer table is used by the processor to locate the PID of a
vCPU with the vCPU's APIC ID. The table size depends on maximum APIC
ID assigned for current VM session from userspace. Allocating memory
for PID-pointer table is deferred to vCPU creation, because irqchip
mode and VM-scope maximum APIC ID is settled at that point. KVM can
skip PID-pointer table allocation if !irqchip_in_kernel().

Like VT-d PI, if a vCPU goes to blocked state, VMM needs to switch its
notification vector to wakeup vector. This can ensure that when an IPI
for blocked vCPUs arrives, VMM can get control and wake up blocked
vCPUs. And if a VCPU is preempted, its posted interrupt notification
is suppressed.

Note that IPI virtualization can only virualize physical-addressing,
flat mode, unicast IPIs. Sending other IPIs would still cause a
trap-like APIC-write VM-exit and need to be handled by VMM.

Signed-off-by: Chao Gao <chao.gao@intel.com>
Signed-off-by: Zeng Guang <guang.zeng@intel.com>
Message-Id: <20220419154510.11938-1-guang.zeng@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

5 files changed, 106 insertions, 6 deletions

diff --git a/arch/x86/kvm/vmx/capabilities.h b/arch/x86/kvm/vmx/capabilities.h
index 31f3d88b3e4d..5f656c9e33be 100644
--- a/arch/x86/kvm/vmx/capabilities.h
+++ b/arch/x86/kvm/vmx/capabilities.h
@@ -13,6 +13,7 @@ extern bool __read_mostly enable_ept;
 extern bool __read_mostly enable_unrestricted_guest;
 extern bool __read_mostly enable_ept_ad_bits;
 extern bool __read_mostly enable_pml;
+extern bool __read_mostly enable_ipiv;
 extern int __read_mostly pt_mode;
 
 #define PT_MODE_SYSTEM		0
@@ -283,6 +284,11 @@ static inline bool cpu_has_vmx_apicv(void)
 		cpu_has_vmx_posted_intr();
 }
 
+static inline bool cpu_has_vmx_ipiv(void)
+{
+	return vmcs_config.cpu_based_3rd_exec_ctrl & TERTIARY_EXEC_IPI_VIRT;
+}
+
 static inline bool cpu_has_vmx_flexpriority(void)
 {
 	return cpu_has_vmx_tpr_shadow() &&
diff --git a/arch/x86/kvm/vmx/posted_intr.c b/arch/x86/kvm/vmx/posted_intr.c
index 07e5fcf5a5aa..237a1f40f939 100644
--- a/arch/x86/kvm/vmx/posted_intr.c
+++ b/arch/x86/kvm/vmx/posted_intr.c
@@ -177,11 +177,24 @@ static void pi_enable_wakeup_handler(struct kvm_vcpu *vcpu)
 	local_irq_restore(flags);
 }
 
+static bool vmx_needs_pi_wakeup(struct kvm_vcpu *vcpu)
+{
+	/*
+	 * The default posted interrupt vector does nothing when
+	 * invoked outside guest mode.   Return whether a blocked vCPU
+	 * can be the target of posted interrupts, as is the case when
+	 * using either IPI virtualization or VT-d PI, so that the
+	 * notification vector is switched to the one that calls
+	 * back to the pi_wakeup_handler() function.
+	 */
+	return vmx_can_use_ipiv(vcpu) || vmx_can_use_vtd_pi(vcpu->kvm);
+}
+
 void vmx_vcpu_pi_put(struct kvm_vcpu *vcpu)
 {
 	struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu);
 
-	if (!vmx_can_use_vtd_pi(vcpu->kvm))
+	if (!vmx_needs_pi_wakeup(vcpu))
 		return;
 
 	if (kvm_vcpu_is_blocking(vcpu) && !vmx_interrupt_blocked(vcpu))
diff --git a/arch/x86/kvm/vmx/posted_intr.h b/arch/x86/kvm/vmx/posted_intr.h
index 9a45d5c9f116..26992076552e 100644
--- a/arch/x86/kvm/vmx/posted_intr.h
+++ b/arch/x86/kvm/vmx/posted_intr.h
@@ -5,6 +5,8 @@
 #define POSTED_INTR_ON  0
 #define POSTED_INTR_SN  1
 
+#define PID_TABLE_ENTRY_VALID 1
+
 /* Posted-Interrupt Descriptor */
 struct pi_desc {
 	u32 pir[8];     /* Posted interrupt requested */
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 3cbe3a38b356..f3175dae25aa 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -105,6 +105,9 @@ module_param(fasteoi, bool, S_IRUGO);
 
 module_param(enable_apicv, bool, S_IRUGO);
 
+bool __read_mostly enable_ipiv = true;
+module_param(enable_ipiv, bool, 0444);
+
 /*
  * If nested=1, nested virtualization is supported, i.e., guests may use
  * VMX and be a hypervisor for its own guests. If nested=0, guests may not
@@ -2527,7 +2530,7 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf,
 	}
 
 	if (_cpu_based_exec_control & CPU_BASED_ACTIVATE_TERTIARY_CONTROLS) {
-		u64 opt3 = 0;
+		u64 opt3 = TERTIARY_EXEC_IPI_VIRT;
 
 		_cpu_based_3rd_exec_control = adjust_vmx_controls64(opt3,
 					      MSR_IA32_VMX_PROCBASED_CTLS3);
@@ -3874,6 +3877,8 @@ static void vmx_update_msr_bitmap_x2apic(struct kvm_vcpu *vcpu)
 		vmx_enable_intercept_for_msr(vcpu, X2APIC_MSR(APIC_TMCCT), MSR_TYPE_RW);
 		vmx_disable_intercept_for_msr(vcpu, X2APIC_MSR(APIC_EOI), MSR_TYPE_W);
 		vmx_disable_intercept_for_msr(vcpu, X2APIC_MSR(APIC_SELF_IPI), MSR_TYPE_W);
+		if (enable_ipiv)
+			vmx_disable_intercept_for_msr(vcpu, X2APIC_MSR(APIC_ICR), MSR_TYPE_RW);
 	}
 }
 
@@ -4202,14 +4207,19 @@ static void vmx_refresh_apicv_exec_ctrl(struct kvm_vcpu *vcpu)
 
 	pin_controls_set(vmx, vmx_pin_based_exec_ctrl(vmx));
 
-	if (kvm_vcpu_apicv_active(vcpu))
+	if (kvm_vcpu_apicv_active(vcpu)) {
 		secondary_exec_controls_setbit(vmx,
 					       SECONDARY_EXEC_APIC_REGISTER_VIRT |
 					       SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY);
-	else
+		if (enable_ipiv)
+			tertiary_exec_controls_setbit(vmx, TERTIARY_EXEC_IPI_VIRT);
+	} else {
 		secondary_exec_controls_clearbit(vmx,
 						 SECONDARY_EXEC_APIC_REGISTER_VIRT |
 						 SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY);
+		if (enable_ipiv)
+			tertiary_exec_controls_clearbit(vmx, TERTIARY_EXEC_IPI_VIRT);
+	}
 
 	vmx_update_msr_bitmap_x2apic(vcpu);
 }
@@ -4242,7 +4252,16 @@ static u32 vmx_exec_control(struct vcpu_vmx *vmx)
 
 static u64 vmx_tertiary_exec_control(struct vcpu_vmx *vmx)
 {
-	return vmcs_config.cpu_based_3rd_exec_ctrl;
+	u64 exec_control = vmcs_config.cpu_based_3rd_exec_ctrl;
+
+	/*
+	 * IPI virtualization relies on APICv. Disable IPI virtualization if
+	 * APICv is inhibited.
+	 */
+	if (!enable_ipiv || !kvm_vcpu_apicv_active(&vmx->vcpu))
+		exec_control &= ~TERTIARY_EXEC_IPI_VIRT;
+
+	return exec_control;
 }
 
 /*
@@ -4390,10 +4409,42 @@ static u32 vmx_secondary_exec_control(struct vcpu_vmx *vmx)
 	return exec_control;
 }
 
+static inline int vmx_get_pid_table_order(struct kvm *kvm)
+{
+	return get_order(kvm->arch.max_vcpu_ids * sizeof(*to_kvm_vmx(kvm)->pid_table));
+}
+
+static int vmx_alloc_ipiv_pid_table(struct kvm *kvm)
+{
+	struct page *pages;
+	struct kvm_vmx *kvm_vmx = to_kvm_vmx(kvm);
+
+	if (!irqchip_in_kernel(kvm) || !enable_ipiv)
+		return 0;
+
+	if (kvm_vmx->pid_table)
+		return 0;
+
+	pages = alloc_pages(GFP_KERNEL | __GFP_ZERO, vmx_get_pid_table_order(kvm));
+	if (!pages)
+		return -ENOMEM;
+
+	kvm_vmx->pid_table = (void *)page_address(pages);
+	return 0;
+}
+
+static int vmx_vcpu_precreate(struct kvm *kvm)
+{
+	return vmx_alloc_ipiv_pid_table(kvm);
+}
+
 #define VMX_XSS_EXIT_BITMAP 0
 
 static void init_vmcs(struct vcpu_vmx *vmx)
 {
+	struct kvm *kvm = vmx->vcpu.kvm;
+	struct kvm_vmx *kvm_vmx = to_kvm_vmx(kvm);
+
 	if (nested)
 		nested_vmx_set_vmcs_shadowing_bitmap();
 
@@ -4425,7 +4476,12 @@ static void init_vmcs(struct vcpu_vmx *vmx)
 		vmcs_write64(POSTED_INTR_DESC_ADDR, __pa((&vmx->pi_desc)));
 	}
 
-	if (!kvm_pause_in_guest(vmx->vcpu.kvm)) {
+	if (vmx_can_use_ipiv(&vmx->vcpu)) {
+		vmcs_write64(PID_POINTER_TABLE, __pa(kvm_vmx->pid_table));
+		vmcs_write16(LAST_PID_POINTER_INDEX, kvm->arch.max_vcpu_ids - 1);
+	}
+
+	if (!kvm_pause_in_guest(kvm)) {
 		vmcs_write32(PLE_GAP, ple_gap);
 		vmx->ple_window = ple_window;
 		vmx->ple_window_dirty = true;
@@ -7116,6 +7172,10 @@ static int vmx_vcpu_create(struct kvm_vcpu *vcpu)
 			goto free_vmcs;
 	}
 
+	if (vmx_can_use_ipiv(vcpu))
+		WRITE_ONCE(to_kvm_vmx(vcpu->kvm)->pid_table[vcpu->vcpu_id],
+			   __pa(&vmx->pi_desc) | PID_TABLE_ENTRY_VALID);
+
 	return 0;
 
 free_vmcs:
@@ -7750,6 +7810,13 @@ static bool vmx_check_apicv_inhibit_reasons(enum kvm_apicv_inhibit reason)
 	return supported & BIT(reason);
 }
 
+static void vmx_vm_destroy(struct kvm *kvm)
+{
+	struct kvm_vmx *kvm_vmx = to_kvm_vmx(kvm);
+
+	free_pages((unsigned long)kvm_vmx->pid_table, vmx_get_pid_table_order(kvm));
+}
+
 static struct kvm_x86_ops vmx_x86_ops __initdata = {
 	.name = "kvm_intel",
 
@@ -7761,7 +7828,9 @@ static struct kvm_x86_ops vmx_x86_ops __initdata = {
 
 	.vm_size = sizeof(struct kvm_vmx),
 	.vm_init = vmx_vm_init,
+	.vm_destroy = vmx_vm_destroy,
 
+	.vcpu_precreate = vmx_vcpu_precreate,
 	.vcpu_create = vmx_vcpu_create,
 	.vcpu_free = vmx_vcpu_free,
 	.vcpu_reset = vmx_vcpu_reset,
@@ -8039,6 +8108,9 @@ static __init int hardware_setup(void)
 	if (!enable_apicv)
 		vmx_x86_ops.sync_pir_to_irr = NULL;
 
+	if (!enable_apicv || !cpu_has_vmx_ipiv())
+		enable_ipiv = false;
+
 	if (cpu_has_vmx_tsc_scaling())
 		kvm_has_tsc_control = true;
 
diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h
index c37befcea2c0..d7baedda79e5 100644
--- a/arch/x86/kvm/vmx/vmx.h
+++ b/arch/x86/kvm/vmx/vmx.h
@@ -366,6 +366,8 @@ struct kvm_vmx {
 	unsigned int tss_addr;
 	bool ept_identity_pagetable_done;
 	gpa_t ept_identity_map_addr;
+	/* Posted Interrupt Descriptor (PID) table for IPI virtualization */
+	u64 *pid_table;
 };
 
 bool nested_vmx_allowed(struct kvm_vcpu *vcpu);
@@ -581,4 +583,9 @@ static inline int vmx_get_instr_info_reg2(u32 vmx_instr_info)
 	return (vmx_instr_info >> 28) & 0xf;
 }
 
+static inline bool vmx_can_use_ipiv(struct kvm_vcpu *vcpu)
+{
+	return  lapic_in_kernel(vcpu) && enable_ipiv;
+}
+
 #endif /* __KVM_X86_VMX_H */