Commit fe6b6bc8 authored by Chenyi Qiang's avatar Chenyi Qiang Committed by Paolo Bonzini
Browse files

KVM: VMX: Enable bus lock VM exit

Virtual Machine can exploit bus locks to degrade the performance of
system. Bus lock can be caused by split locked access to writeback(WB)
memory or by using locks on uncacheable(UC) memory. The bus lock is
typically >1000 cycles slower than an atomic operation within a cache
line. It also disrupts performance on other cores (which must wait for
the bus lock to be released before their memory operations can
complete).

To address the threat, bus lock VM exit is introduced to notify the VMM
when a bus lock was acquired, allowing it to enforce throttling or other
policy based mitigations.

A VMM can enable VM exit due to bus locks by setting a new "Bus Lock
Detection" VM-execution control(bit 30 of Secondary Processor-based VM
execution controls). If delivery of this VM exit was preempted by a
higher priority VM exit (e.g. EPT misconfiguration, EPT violation, APIC
access VM exit, APIC write VM exit, exception bitmap exiting), bit 26 of
exit reason in vmcs field is set to 1.

In current implementation, the KVM exposes this capability through
KVM_CAP_X86_BUS_LOCK_EXIT. The user can get the supported mode bitmap
(i.e. off and exit) and enable it explicitly (disabled by default). If
bus locks in guest are detected by KVM, exit to user space even when
current exit reason is handled by KVM internally. Set a new field
KVM_RUN_BUS_LOCK in vcpu->run->flags to inform the user space that there
is a bus lock detected in guest.

Document for Bus Lock VM exit is now available at the latest "Intel
Architecture Instruction Set Extensions Programming Reference".

Document Link:
https://software.intel.com/content/www/us/en/develop/download/intel-architecture-instruction-set-extensions-programming-reference.html



Co-developed-by: default avatarXiaoyao Li <xiaoyao.li@intel.com>
Signed-off-by: default avatarXiaoyao Li <xiaoyao.li@intel.com>
Signed-off-by: default avatarChenyi Qiang <chenyi.qiang@intel.com>
Message-Id: <20201106090315.18606-4-chenyi.qiang@intel.com>
Signed-off-by: default avatarPaolo Bonzini <pbonzini@redhat.com>
parent 15aad3be
......@@ -52,6 +52,9 @@
#define KVM_DIRTY_LOG_MANUAL_CAPS (KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE | \
KVM_DIRTY_LOG_INITIALLY_SET)
#define KVM_BUS_LOCK_DETECTION_VALID_MODE (KVM_BUS_LOCK_DETECTION_OFF | \
KVM_BUS_LOCK_DETECTION_EXIT)
/* x86-specific vcpu->requests bit members */
#define KVM_REQ_MIGRATE_TIMER KVM_ARCH_REQ(0)
#define KVM_REQ_REPORT_TPR_ACCESS KVM_ARCH_REQ(1)
......@@ -996,6 +999,8 @@ struct kvm_arch {
struct msr_bitmap_range ranges[16];
} msr_filter;
bool bus_lock_detection_enabled;
struct kvm_pmu_event_filter *pmu_event_filter;
struct task_struct *nx_lpage_recovery_thread;
......@@ -1418,6 +1423,8 @@ extern u8 kvm_tsc_scaling_ratio_frac_bits;
extern u64 kvm_max_tsc_scaling_ratio;
/* 1ull << kvm_tsc_scaling_ratio_frac_bits */
extern u64 kvm_default_tsc_scaling_ratio;
/* bus lock detection supported? */
extern bool kvm_has_bus_lock_exit;
extern u64 kvm_mce_cap_supported;
......
......@@ -73,6 +73,7 @@
#define SECONDARY_EXEC_PT_USE_GPA VMCS_CONTROL_BIT(PT_USE_GPA)
#define SECONDARY_EXEC_TSC_SCALING VMCS_CONTROL_BIT(TSC_SCALING)
#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)
#define PIN_BASED_EXT_INTR_MASK VMCS_CONTROL_BIT(INTR_EXITING)
#define PIN_BASED_NMI_EXITING VMCS_CONTROL_BIT(NMI_EXITING)
......
......@@ -83,5 +83,6 @@
#define VMX_FEATURE_TSC_SCALING ( 2*32+ 25) /* Scale hardware TSC when read in guest */
#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) */
#define VMX_FEATURE_BUS_LOCK_DETECTION ( 2*32+ 30) /* "" VM-Exit when bus lock caused */
#endif /* _ASM_X86_VMXFEATURES_H */
......@@ -112,6 +112,7 @@ struct kvm_ioapic_state {
#define KVM_NR_IRQCHIPS 3
#define KVM_RUN_X86_SMM (1 << 0)
#define KVM_RUN_X86_BUS_LOCK (1 << 1)
/* for KVM_GET_REGS and KVM_SET_REGS */
struct kvm_regs {
......
......@@ -89,6 +89,7 @@
#define EXIT_REASON_XRSTORS 64
#define EXIT_REASON_UMWAIT 67
#define EXIT_REASON_TPAUSE 68
#define EXIT_REASON_BUS_LOCK 74
#define VMX_EXIT_REASONS \
{ EXIT_REASON_EXCEPTION_NMI, "EXCEPTION_NMI" }, \
......@@ -150,7 +151,8 @@
{ EXIT_REASON_XSAVES, "XSAVES" }, \
{ EXIT_REASON_XRSTORS, "XRSTORS" }, \
{ EXIT_REASON_UMWAIT, "UMWAIT" }, \
{ EXIT_REASON_TPAUSE, "TPAUSE" }
{ EXIT_REASON_TPAUSE, "TPAUSE" }, \
{ EXIT_REASON_BUS_LOCK, "BUS_LOCK" }
#define VMX_EXIT_REASON_FLAGS \
{ VMX_EXIT_REASONS_FAILED_VMENTRY, "FAILED_VMENTRY" }
......
......@@ -262,6 +262,12 @@ static inline bool cpu_has_vmx_tsc_scaling(void)
SECONDARY_EXEC_TSC_SCALING;
}
static inline bool cpu_has_vmx_bus_lock_detection(void)
{
return vmcs_config.cpu_based_2nd_exec_ctrl &
SECONDARY_EXEC_BUS_LOCK_DETECTION;
}
static inline bool cpu_has_vmx_apicv(void)
{
return cpu_has_vmx_apic_register_virt() &&
......
......@@ -2428,7 +2428,8 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf,
SECONDARY_EXEC_ENABLE_USR_WAIT_PAUSE |
SECONDARY_EXEC_PT_USE_GPA |
SECONDARY_EXEC_PT_CONCEAL_VMX |
SECONDARY_EXEC_ENABLE_VMFUNC;
SECONDARY_EXEC_ENABLE_VMFUNC |
SECONDARY_EXEC_BUS_LOCK_DETECTION;
if (cpu_has_sgx())
opt2 |= SECONDARY_EXEC_ENCLS_EXITING;
if (adjust_vmx_controls(min2, opt2,
......@@ -4269,6 +4270,9 @@ static void vmx_compute_secondary_exec_control(struct vcpu_vmx *vmx)
vmx_adjust_sec_exec_control(vmx, &exec_control, waitpkg, WAITPKG,
ENABLE_USR_WAIT_PAUSE, false);
if (!vcpu->kvm->arch.bus_lock_detection_enabled)
exec_control &= ~SECONDARY_EXEC_BUS_LOCK_DETECTION;
vmx->secondary_exec_control = exec_control;
}
......@@ -5600,6 +5604,13 @@ static int handle_encls(struct kvm_vcpu *vcpu)
return 1;
}
static int handle_bus_lock_vmexit(struct kvm_vcpu *vcpu)
{
vcpu->run->exit_reason = KVM_EXIT_X86_BUS_LOCK;
vcpu->run->flags |= KVM_RUN_X86_BUS_LOCK;
return 0;
}
/*
* The exit handlers return 1 if the exit was handled fully and guest execution
* may resume. Otherwise they set the kvm_run parameter to indicate what needs
......@@ -5656,6 +5667,7 @@ static int (*kvm_vmx_exit_handlers[])(struct kvm_vcpu *vcpu) = {
[EXIT_REASON_VMFUNC] = handle_vmx_instruction,
[EXIT_REASON_PREEMPTION_TIMER] = handle_preemption_timer,
[EXIT_REASON_ENCLS] = handle_encls,
[EXIT_REASON_BUS_LOCK] = handle_bus_lock_vmexit,
};
static const int kvm_vmx_max_exit_handlers =
......@@ -5908,7 +5920,7 @@ void dump_vmcs(void)
* The guest has exited. See if we can fix it or if we need userspace
* assistance.
*/
static int vmx_handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath)
static int __vmx_handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
union vmx_exit_reason exit_reason = vmx->exit_reason;
......@@ -6061,6 +6073,25 @@ static int vmx_handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath)
return 0;
}
static int vmx_handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath)
{
int ret = __vmx_handle_exit(vcpu, exit_fastpath);
/*
* Even when current exit reason is handled by KVM internally, we
* still need to exit to user space when bus lock detected to inform
* that there is a bus lock in guest.
*/
if (to_vmx(vcpu)->exit_reason.bus_lock_detected) {
if (ret > 0)
vcpu->run->exit_reason = KVM_EXIT_X86_BUS_LOCK;
vcpu->run->flags |= KVM_RUN_X86_BUS_LOCK;
return 0;
}
return ret;
}
/*
* Software based L1D cache flush which is used when microcode providing
* the cache control MSR is not loaded.
......@@ -7812,6 +7843,8 @@ static __init int hardware_setup(void)
kvm_tsc_scaling_ratio_frac_bits = 48;
}
kvm_has_bus_lock_exit = cpu_has_vmx_bus_lock_detection();
set_bit(0, vmx_vpid_bitmap); /* 0 is reserved for host */
if (enable_ept)
......
......@@ -83,7 +83,7 @@ union vmx_exit_reason {
u32 reserved23 : 1;
u32 reserved24 : 1;
u32 reserved25 : 1;
u32 reserved26 : 1;
u32 bus_lock_detected : 1;
u32 enclave_mode : 1;
u32 smi_pending_mtf : 1;
u32 smi_from_vmx_root : 1;
......
......@@ -136,6 +136,8 @@ u64 __read_mostly kvm_max_tsc_scaling_ratio;
EXPORT_SYMBOL_GPL(kvm_max_tsc_scaling_ratio);
u64 __read_mostly kvm_default_tsc_scaling_ratio;
EXPORT_SYMBOL_GPL(kvm_default_tsc_scaling_ratio);
bool __read_mostly kvm_has_bus_lock_exit;
EXPORT_SYMBOL_GPL(kvm_has_bus_lock_exit);
/* tsc tolerance in parts per million - default to 1/2 of the NTP threshold */
static u32 __read_mostly tsc_tolerance_ppm = 250;
......@@ -3843,6 +3845,13 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
case KVM_CAP_STEAL_TIME:
r = sched_info_on();
break;
case KVM_CAP_X86_BUS_LOCK_EXIT:
if (kvm_has_bus_lock_exit)
r = KVM_BUS_LOCK_DETECTION_OFF |
KVM_BUS_LOCK_DETECTION_EXIT;
else
r = 0;
break;
default:
break;
}
......@@ -5298,6 +5307,20 @@ int kvm_vm_ioctl_enable_cap(struct kvm *kvm,
kvm->arch.user_space_msr_mask = cap->args[0];
r = 0;
break;
case KVM_CAP_X86_BUS_LOCK_EXIT:
r = -EINVAL;
if (cap->args[0] & ~KVM_BUS_LOCK_DETECTION_VALID_MODE)
break;
if ((cap->args[0] & KVM_BUS_LOCK_DETECTION_OFF) &&
(cap->args[0] & KVM_BUS_LOCK_DETECTION_EXIT))
break;
if (kvm_has_bus_lock_exit &&
cap->args[0] & KVM_BUS_LOCK_DETECTION_EXIT)
kvm->arch.bus_lock_detection_enabled = true;
r = 0;
break;
default:
r = -EINVAL;
break;
......
......@@ -252,6 +252,7 @@ struct kvm_hyperv_exit {
#define KVM_EXIT_X86_WRMSR 30
#define KVM_EXIT_DIRTY_RING_FULL 31
#define KVM_EXIT_AP_RESET_HOLD 32
#define KVM_EXIT_X86_BUS_LOCK 33
/* For KVM_EXIT_INTERNAL_ERROR */
/* Emulate instruction failed. */
......@@ -1058,6 +1059,7 @@ struct kvm_ppc_resize_hpt {
#define KVM_CAP_ENFORCE_PV_FEATURE_CPUID 190
#define KVM_CAP_SYS_HYPERV_CPUID 191
#define KVM_CAP_DIRTY_LOG_RING 192
#define KVM_CAP_X86_BUS_LOCK_EXIT 193
#ifdef KVM_CAP_IRQ_ROUTING
......@@ -1774,4 +1776,7 @@ struct kvm_dirty_gfn {
__u64 offset;
};
#define KVM_BUS_LOCK_DETECTION_OFF (1 << 0)
#define KVM_BUS_LOCK_DETECTION_EXIT (1 << 1)
#endif /* __LINUX_KVM_H */
Supports Markdown
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment