KVM: VMX: enable IPI virtualization

mainline inclusion
from mainline-v6.0-rc1
commit d588bb9b
category: feature
feature: IPI Virtualization
bugzilla: https://gitee.com/openeuler/intel-kernel/issues/I5ODSC
CVE: N/A
Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=d588bb9be1da6aa750aa64875fe57369db983d8b

Intel-SIG: commit d588bb9b ("KVM: VMX: enable IPI virtualization")

-------------------------------------

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: NChao Gao <chao.gao@intel.com>
Signed-off-by: NZeng Guang <guang.zeng@intel.com>
Message-Id: <20220419154510.11938-1-guang.zeng@intel.com>
Signed-off-by: NPaolo Bonzini <pbonzini@redhat.com>
Signed-off-by: NJason Zeng <jason.zeng@intel.com>

arch/x86/include/asm/kvm_host.h

@@ -1127,6 +1127,7 @@ struct kvm_x86_ops {
 	void (*vm_destroy)(struct kvm *kvm);
 
 	/* Create, but do not attach this VCPU */
+	int (*vcpu_precreate)(struct kvm *kvm);
 	int (*vcpu_create)(struct kvm_vcpu *vcpu);
 	void (*vcpu_free)(struct kvm_vcpu *vcpu);
 	void (*vcpu_reset)(struct kvm_vcpu *vcpu, bool init_event);

arch/x86/include/asm/vmx.h

@@ -75,6 +75,11 @@
 #define SECONDARY_EXEC_TSC_SCALING              VMCS_CONTROL_BIT(TSC_SCALING)
 #define SECONDARY_EXEC_ENABLE_USR_WAIT_PAUSE	VMCS_CONTROL_BIT(USR_WAIT_PAUSE)
 
+/*
+ * Definitions of Tertiary Processor-Based VM-Execution Controls.
+ */
+#define TERTIARY_EXEC_IPI_VIRT			VMCS_CONTROL_BIT(IPI_VIRT)
+
 #define PIN_BASED_EXT_INTR_MASK                 VMCS_CONTROL_BIT(INTR_EXITING)
 #define PIN_BASED_NMI_EXITING                   VMCS_CONTROL_BIT(NMI_EXITING)
 #define PIN_BASED_VIRTUAL_NMIS                  VMCS_CONTROL_BIT(VIRTUAL_NMIS)
@@ -157,6 +162,7 @@ static inline int vmx_misc_mseg_revid(u64 vmx_misc)
 enum vmcs_field {
 	VIRTUAL_PROCESSOR_ID            = 0x00000000,
 	POSTED_INTR_NV                  = 0x00000002,
+	LAST_PID_POINTER_INDEX		= 0x00000008,
 	GUEST_ES_SELECTOR               = 0x00000800,
 	GUEST_CS_SELECTOR               = 0x00000802,
 	GUEST_SS_SELECTOR               = 0x00000804,
@@ -222,6 +228,8 @@ enum vmcs_field {
 	TSC_MULTIPLIER_HIGH             = 0x00002033,
 	TERTIARY_VM_EXEC_CONTROL	= 0x00002034,
 	TERTIARY_VM_EXEC_CONTROL_HIGH	= 0x00002035,
+	PID_POINTER_TABLE		= 0x00002042,
+	PID_POINTER_TABLE_HIGH		= 0x00002043,
 	GUEST_PHYSICAL_ADDRESS          = 0x00002400,
 	GUEST_PHYSICAL_ADDRESS_HIGH     = 0x00002401,
 	VMCS_LINK_POINTER               = 0x00002800,

arch/x86/include/asm/vmxfeatures.h

@@ -85,4 +85,6 @@
 #define VMX_FEATURE_USR_WAIT_PAUSE	( 2*32+ 26) /* Enable TPAUSE, UMONITOR, UMWAIT in guest */
 #define VMX_FEATURE_ENCLV_EXITING	( 2*32+ 28) /* "" VM-Exit on ENCLV (leaf dependent) */
 
+/* Tertiary Processor-Based VM-Execution Controls, word 3 */
+#define VMX_FEATURE_IPI_VIRT		( 3*32+  4) /* Enable IPI virtualization */
 #endif /* _ASM_X86_VMXFEATURES_H */

arch/x86/kvm/vmx/capabilities.h

@@ -13,6 +13,7 @@ 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_apicv;
+extern bool __read_mostly enable_ipiv;
 extern int __read_mostly pt_mode;
 
 #define PT_MODE_SYSTEM		0
@@ -279,6 +280,11 @@ 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() &&

arch/x86/kvm/vmx/posted_intr.c

@@ -89,7 +89,7 @@ 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_can_use_ipiv(vcpu) || vmx_can_use_vtd_pi(vcpu->kvm)))
 		return;
 
 	/* Set SN when the vCPU is preempted */
@@ -147,7 +147,7 @@ int pi_pre_block(struct kvm_vcpu *vcpu)
 	struct pi_desc old, new;
 	struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu);
 
-	if (!vmx_can_use_vtd_pi(vcpu->kvm))
+	if (!(vmx_can_use_ipiv(vcpu) || vmx_can_use_vtd_pi(vcpu->kvm)))
 		return 0;
 
 	WARN_ON(irqs_disabled());

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 */

arch/x86/kvm/vmx/vmx.c

@@ -104,6 +104,9 @@ module_param(fasteoi, bool, S_IRUGO);
 bool __read_mostly enable_apicv = 1;
 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
@@ -2682,7 +2685,7 @@ 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);
@@ -4060,6 +4063,8 @@ static void vmx_update_msr_bitmap_x2apic(struct kvm_vcpu *vcpu, u8 mode)
 		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);
 	}
 }
 
@@ -4327,14 +4332,19 @@ 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);
+	}
 
 	if (cpu_has_vmx_msr_bitmap())
 		vmx_update_msr_bitmap(vcpu);
@@ -4368,7 +4378,16 @@ 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;
 }
 
 /*
@@ -4511,6 +4530,35 @@ static void ept_set_mmio_spte_mask(void)
 	kvm_mmu_set_mmio_spte_mask(VMX_EPT_MISCONFIG_WX_VALUE, 0);
 }
 
+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
 
 /*
@@ -4519,6 +4567,9 @@ static void ept_set_mmio_spte_mask(void)
  */
 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();
 
@@ -4552,7 +4603,12 @@ 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;
@@ -7249,6 +7305,10 @@ static int vmx_create_vcpu(struct kvm_vcpu *vcpu)
 
 	vmx->ept_pointer = INVALID_PAGE;
 
+	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:
@@ -7912,6 +7972,13 @@ static bool vmx_check_apicv_inhibit_reasons(ulong bit)
 	return supported & BIT(bit);
 }
 
+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 = {
 	.hardware_unsetup = hardware_unsetup,
 
@@ -7922,7 +7989,9 @@ 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_create_vcpu,
 	.vcpu_free = vmx_free_vcpu,
 	.vcpu_reset = vmx_vcpu_reset,
@@ -8124,6 +8193,9 @@ static __init int hardware_setup(void)
 		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;
 		kvm_max_tsc_scaling_ratio = KVM_VMX_TSC_MULTIPLIER_MAX;

arch/x86/kvm/vmx/vmx.h

@@ -358,6 +358,8 @@ struct kvm_vmx {
 
 	enum ept_pointers_status ept_pointers_match;
 	spinlock_t ept_pointer_lock;
+	/* Posted Interrupt Descriptor (PID) table for IPI virtualization */
+	u64 *pid_table;
 };
 
 bool nested_vmx_allowed(struct kvm_vcpu *vcpu);
@@ -558,4 +560,9 @@ static inline bool vmx_guest_state_valid(struct kvm_vcpu *vcpu)
 
 void dump_vmcs(void);
 
+static inline bool vmx_can_use_ipiv(struct kvm_vcpu *vcpu)
+{
+	return  lapic_in_kernel(vcpu) && enable_ipiv;
+}
+
 #endif /* __KVM_X86_VMX_H */

arch/x86/kvm/x86.c

@@ -10126,7 +10126,7 @@ int kvm_arch_vcpu_precreate(struct kvm *kvm, unsigned int id)
 	if (id >= kvm->arch.max_vcpu_ids)
 		return -EINVAL;
 
-	return 0;
+	return kvm_x86_ops.vcpu_precreate ? kvm_x86_ops.vcpu_precreate(kvm) : 0;
 }
 
 int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu)