diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 1b08ba66c088fa79a6a6615ba19f5c3133e2311b..b8ce51554cc244b5558c78d8933bb39699975df2 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -1122,6 +1122,7 @@ 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); diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h index 4c9c4df1c74d81eef43c8bd6e65fce6d1e85e5b7..aaf3812063bbf3e061e69de20058f32431ad07ae 100644 --- a/arch/x86/include/asm/vmx.h +++ b/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, diff --git a/arch/x86/include/asm/vmxfeatures.h b/arch/x86/include/asm/vmxfeatures.h index 0d43a41310afddef197bd327f2397826daad59d0..af446ba041db0425edf89237452d291d1d47dc19 100644 --- a/arch/x86/include/asm/vmxfeatures.h +++ b/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 */ diff --git a/arch/x86/kvm/vmx/capabilities.h b/arch/x86/kvm/vmx/capabilities.h index e52e355b99ab253d54821d13c235c9a9d675e583..1fc2d141588907c2e710ecac2a9ca7d5dd3238f1 100644 --- a/arch/x86/kvm/vmx/capabilities.h +++ b/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() && diff --git a/arch/x86/kvm/vmx/posted_intr.c b/arch/x86/kvm/vmx/posted_intr.c index 5f8acd2faa7c1ea4848b257a5564e54376fe25ec..9689541fa02768a63dd6c09f4cc2f43517122857 100644 --- a/arch/x86/kvm/vmx/posted_intr.c +++ b/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()); diff --git a/arch/x86/kvm/vmx/posted_intr.h b/arch/x86/kvm/vmx/posted_intr.h index 0bdc41391c5b8fae1d0f581944a6b21ee9156d26..39d92d52caa90341ae254c5c87ce354c3a591f20 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 60526737578652761ec973d41b906e37a173021c..1cce20417d96b3104ca01f0ffde7d52ebf8c3f96 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/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 @@ -2664,7 +2667,7 @@ 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); @@ -4042,6 +4045,8 @@ 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); } } @@ -4309,14 +4314,19 @@ 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); @@ -4350,7 +4360,16 @@ 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; } /* @@ -4493,6 +4512,35 @@ 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 /* @@ -4501,6 +4549,9 @@ 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(); @@ -4534,7 +4585,12 @@ 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; @@ -7226,6 +7282,10 @@ 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: @@ -7889,6 +7949,13 @@ 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, @@ -7899,7 +7966,9 @@ 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, @@ -8101,6 +8170,9 @@ 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; diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h index f3ac7929c99a958f28dd6501f80507f445eba589..31c7b8f489f62ed509928c2cfc4c0428856ea656 100644 --- a/arch/x86/kvm/vmx/vmx.h +++ b/arch/x86/kvm/vmx/vmx.h @@ -357,6 +357,8 @@ 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); @@ -553,4 +555,9 @@ 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 */ diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index bee4c895276ef072796223c9a569484dcdf16491..ccc9d019637adf060a847ff518e23eb1e76312c3 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -9949,7 +9949,7 @@ 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)