KVM: VMX: enable IPI virtualization
PATCH v9 9/9 KVM: VMX: enable IPI virtualization
From: Chao Gao <[email protected]>
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.
--- arch/x86/include/asm/kvm-x86-ops.h | 1 + arch/x86/include/asm/kvm_host.h | 1 + arch/x86/include/asm/vmx.h | 8 +++ arch/x86/include/asm/vmxfeatures.h | 2 + arch/x86/kvm/vmx/capabilities.h | 6 +++ arch/x86/kvm/vmx/posted_intr.c | 15 +++++- arch/x86/kvm/vmx/posted_intr.h | 2 + arch/x86/kvm/vmx/vmx.c | 82 ++++++++++++++++++++++++++++-- arch/x86/kvm/vmx/vmx.h | 7 +++ arch/x86/kvm/x86.c | 2 +- 10 files changed, 119 insertions(+), 7 deletions(-)
arch/x86/include/asm/kvm-x86-ops.h +1 -0
@@ -21,6 +21,7 @@ KVM_X86_OP(has_emulated_msr) KVM_X86_OP(vcpu_after_set_cpuid) KVM_X86_OP(vm_init) KVM_X86_OP_OPTIONAL(vm_destroy) +KVM_X86_OP_OPTIONAL_RET0(vcpu_precreate) KVM_X86_OP(vcpu_create) KVM_X86_OP(vcpu_free) KVM_X86_OP(vcpu_reset)
arch/x86/include/asm/kvm_host.h +1 -0
@@ -1337,6 +1337,7 @@ 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 +8 -0
@@ -76,6 +76,11 @@#define SECONDARY_EXEC_ENABLE_USR_WAIT_PAUSE VMCS_CONTROL_BIT(USR_WAIT_PAUSE)#define SECONDARY_EXEC_BUS_LOCK_DETECTION VMCS_CONTROL_BIT(BUS_LOCK_DETECTION) +/* +* 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)
@@ -159,6 +164,7 @@ 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 ,
@@ -224,6 +230,8 @@ 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 +2 -0
@@ -86,4 +86,6 @@#define VMX_FEATURE_ENCLV_EXITING ( 2*32+ 28)/* "" VM-Exit on ENCLV (leaf dependent) */ #define VMX_FEATURE_BUS_LOCK_DETECTION ( 2*32+ 30)/* "" VM-Exit when bus lock caused */ +/* 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 +6 -0
@@ -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() &&
arch/x86/kvm/vmx/posted_intr.c +14 -1
@@ -177,11 +177,24 @@ static void pi_enable_wakeup_handler(struct kvm_vcpu *vcpu)local_irq_restore (flags); } +static bool vmx_can_use_pi_wakeup (struct kvm_vcpu *vcpu) +{ +/* +* If a blocked vCPU can be the target of posted interrupts, +* switching notification vector is needed so that kernel can +* be informed when an interrupt is posted and get the chance +* to wake up the blocked vCPU. For now, using posted interrupt +* for vCPU wakeup when IPI virtualization or VT-d PI can be +* enabled. +*/ +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_can_use_pi_wakeup (vcpu))return ;if (kvm_vcpu_is_blocking (vcpu) && !vmx_interrupt_blocked (vcpu))
arch/x86/kvm/vmx/posted_intr.h +2 -0
@@ -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 +77 -5
159 lines not on this page · raw message
arch/x86/kvm/vmx/vmx.h +7 -0
@@ -365,6 +365,8 @@ 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);
@@ -580,4 +582,9 @@ 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 */
arch/x86/kvm/x86.c +1 -1
@@ -11195,7 +11195,7 @@ int kvm_arch_vcpu_precreate(struct kvm *kvm, unsigned int id)if (id >= kvm->arch.max_vcpu_ids)return -EINVAL ; -return 0 ; +return static_call (kvm_x86_vcpu_precreate)(kvm); }int kvm_arch_vcpu_create (struct kvm_vcpu *vcpu)
Signature · 1 line
2.27.0
Paolo Bonzini
maintainerarch/x86/kvm/vmx/posted_intr.c static void pi_enable_wakeup_handler(struct kvm_vcpu *vcpu) · line 191
Quoted 12 lines · Zeng Guang
arch/x86/kvm/vmx/posted_intr.c +12
-0+static bool vmx_can_use_pi_wakeup (struct kvm_vcpu *vcpu) +{ +/* +* If a blocked vCPU can be the target of posted interrupts, +* switching notification vector is needed so that kernel can +* be informed when an interrupt is posted and get the chance +* to wake up the blocked vCPU. For now, using posted interrupt +* for vCPU wakeup when IPI virtualization or VT-d PI can be +* enabled. +*/ +return vmx_can_use_ipiv (vcpu) ||vmx_can_use_vtd_pi (vcpu->kvm); +}
Slightly more accurate name and comment:
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);
}
Paolo
Quoted 29 lines · Paolo Bonzini
arch/x86/kvm/vmx/posted_intr.c static void pi_enable_wakeup_handler(struct kvm_vcpu *vcpu) · line 191
Quoted 12 lines · Zeng Guang
arch/x86/kvm/vmx/posted_intr.c +12
-0+static bool vmx_can_use_pi_wakeup (struct kvm_vcpu *vcpu) +{ +/* +* If a blocked vCPU can be the target of posted interrupts, +* switching notification vector is needed so that kernel can +* be informed when an interrupt is posted and get the chance +* to wake up the blocked vCPU. For now, using posted interrupt +* for vCPU wakeup when IPI virtualization or VT-d PI can be +* enabled. +*/ +return vmx_can_use_ipiv (vcpu) ||vmx_can_use_vtd_pi (vcpu->kvm); +}Slightly more accurate name and comment:
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 thepi_wakeup_handler()function.
*/
returnvmx_can_use_ipiv(vcpu)||vmx_can_use_vtd_pi(vcpu->kvm);
}
Quoted 1 line
Paolo
Thanks. It's much accurate and better to describe the functionality of this API. I will change it.
Quoted 9 lines · Zeng Guang
From: Chao Gao <[email protected]>
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.
...
Quoted 21 lines
arch/x86/kvm/vmx/vmx.c +5
-2@@ -3872,6 +3875,8 @@ 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 ); } }@@ -4195,14 +4200,19 @@ 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 );
arch/x86/kvm/vmx/vmx.c static void vmx_refresh_apicv_exec_ctrl(struct kvm_vcpu *vcpu) · line 4218
Quoted 10 lines
arch/x86/kvm/vmx/vmx.c +4
-0+ }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); }
Hi, just a small question here:
It seems that we clear the TERTIARY_EXEC_IPI_VIRT bit before enabling interception for APIC_ICR when deactivating APICv on some reason. Is there any problem with this sequence?
Thanks,
shenming
Quoted 11 lines · Shenming Lu
arch/x86/kvm/vmx/vmx.c static void vmx_refresh_apicv_exec_ctrl(struct kvm_vcpu *vcpu) · line 4218
Quoted 5 lines
arch/x86/kvm/vmx/vmx.c +3
-0+if (enable_ipiv) +tertiary_exec_controls_clearbit (vmx,TERTIARY_EXEC_IPI_VIRT ); + }vmx_update_msr_bitmap_x2apic (vcpu); }Hi, just a small question here:
It seems that we clear the
TERTIARY_EXEC_IPI_VIRTbit before enabling interception forAPIC_ICRwhen deactivating APICv on some reason. Is there any problem with this sequence?
Both are done before the next vCPU entry. As long as no guest code can run between them (APICv setting takes effect in guest), this sequence shouldn't have any problem.
Quoted 9 lines · Chao Gao
Quoted 8 lines · Shenming Lu
arch/x86/kvm/vmx/vmx.c static void vmx_refresh_apicv_exec_ctrl(struct kvm_vcpu *vcpu) · line 4218
Quoted 5 lines
arch/x86/kvm/vmx/vmx.c +3
-0+if (enable_ipiv) +tertiary_exec_controls_clearbit (vmx,TERTIARY_EXEC_IPI_VIRT ); + }vmx_update_msr_bitmap_x2apic (vcpu); }Hi, just a small question here:
Quoted 7 lines
Quoted 3 lines
It seems that we clear the
TERTIARY_EXEC_IPI_VIRTbit before enabling interception forAPIC_ICRwhen deactivating APICv on some reason. Is there any problem with this sequence?Both are done before the next vCPU entry. As long as no guest code can run between them (APICv setting takes effect in guest), this sequence shouldn't have any problem.
OK. Thanks for reply,
Shenmimg