return vcpu_mode_priv(vcpu);
}
+ #ifdef CONFIG_GUEST_PERF_EVENTS
+ unsigned long kvm_arch_vcpu_get_ip(struct kvm_vcpu *vcpu)
+ {
+ return *vcpu_pc(vcpu);
+ }
+ #endif
+
/* Just ensure a guest exit from a particular CPU */
static void exit_vm_noop(void *info)
{
xfer_to_guest_mode_work_pending();
}
+/*
+ * Actually run the vCPU, entering an RCU extended quiescent state (EQS) while
+ * the vCPU is running.
+ *
+ * This must be noinstr as instrumentation may make use of RCU, and this is not
+ * safe during the EQS.
+ */
+static int noinstr kvm_arm_vcpu_enter_exit(struct kvm_vcpu *vcpu)
+{
+ int ret;
+
+ guest_state_enter_irqoff();
+ ret = kvm_call_hyp_ret(__kvm_vcpu_run, vcpu);
+ guest_state_exit_irqoff();
+
+ return ret;
+}
+
/**
* kvm_arch_vcpu_ioctl_run - the main VCPU run function to execute guest code
* @vcpu: The VCPU pointer
* Enter the guest
*/
trace_kvm_entry(*vcpu_pc(vcpu));
- guest_enter_irqoff();
+ guest_timing_enter_irqoff();
- ret = kvm_call_hyp_ret(__kvm_vcpu_run, vcpu);
+ ret = kvm_arm_vcpu_enter_exit(vcpu);
vcpu->mode = OUTSIDE_GUEST_MODE;
vcpu->stat.exits++;
kvm_arch_vcpu_ctxsync_fp(vcpu);
/*
- * We may have taken a host interrupt in HYP mode (ie
- * while executing the guest). This interrupt is still
- * pending, as we haven't serviced it yet!
+ * We must ensure that any pending interrupts are taken before
+ * we exit guest timing so that timer ticks are accounted as
+ * guest time. Transiently unmask interrupts so that any
+ * pending interrupts are taken.
*
- * We're now back in SVC mode, with interrupts
- * disabled. Enabling the interrupts now will have
- * the effect of taking the interrupt again, in SVC
- * mode this time.
+ * Per ARM DDI 0487G.b section D1.13.4, an ISB (or other
+ * context synchronization event) is necessary to ensure that
+ * pending interrupts are taken.
*/
local_irq_enable();
+ isb();
+ local_irq_disable();
+
+ guest_timing_exit_irqoff();
+
+ local_irq_enable();
- /*
- * We do local_irq_enable() before calling guest_exit() so
- * that if a timer interrupt hits while running the guest we
- * account that tick as being spent in the guest. We enable
- * preemption after calling guest_exit() so that if we get
- * preempted we make sure ticks after that is not counted as
- * guest time.
- */
- guest_exit();
trace_kvm_exit(ret, kvm_vcpu_trap_get_class(vcpu), *vcpu_pc(vcpu));
/* Exit types that need handling before we can be preempted */
if (err)
goto out;
- kvm_perf_init();
+ kvm_register_perf_callbacks(NULL);
+
kvm_sys_reg_table_init();
out:
/* NOP: Compiling as a module not supported */
void kvm_arch_exit(void)
{
- kvm_perf_teardown();
+ kvm_unregister_perf_callbacks();
}
static int __init early_kvm_mode_cfg(char *arg)
unsigned nmi_pending; /* NMI queued after currently running handler */
bool nmi_injected; /* Trying to inject an NMI this entry */
bool smi_pending; /* SMI queued after currently running handler */
+ u8 handling_intr_from_guest;
struct kvm_mtrr mtrr_state;
u64 pat;
void (*load_eoi_exitmap)(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap);
void (*set_virtual_apic_mode)(struct kvm_vcpu *vcpu);
void (*set_apic_access_page_addr)(struct kvm_vcpu *vcpu);
- int (*deliver_posted_interrupt)(struct kvm_vcpu *vcpu, int vector);
+ void (*deliver_interrupt)(struct kvm_lapic *apic, int delivery_mode,
+ int trig_mode, int vector);
int (*sync_pir_to_irr)(struct kvm_vcpu *vcpu);
int (*set_tss_addr)(struct kvm *kvm, unsigned int addr);
int (*set_identity_map_addr)(struct kvm *kvm, u64 ident_addr);
int (*disabled_by_bios)(void);
int (*check_processor_compatibility)(void);
int (*hardware_setup)(void);
+ unsigned int (*handle_intel_pt_intr)(void);
struct kvm_x86_ops *runtime_ops;
};
return -ENOTSUPP;
}
+ #define kvm_arch_pmi_in_guest(vcpu) \
+ ((vcpu) && (vcpu)->arch.handling_intr_from_guest)
+
int kvm_mmu_module_init(void);
void kvm_mmu_module_exit(void);
int kvm_complete_insn_gp(struct kvm_vcpu *vcpu, int err);
void __kvm_request_immediate_exit(struct kvm_vcpu *vcpu);
- int kvm_is_in_guest(void);
-
void __user *__x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa,
u32 size);
bool kvm_vcpu_is_reset_bsp(struct kvm_vcpu *vcpu);
SVM_EVTINJ_VALID | SVM_EVTINJ_TYPE_INTR;
}
+static void svm_deliver_interrupt(struct kvm_lapic *apic, int delivery_mode,
+ int trig_mode, int vector)
+{
+ struct kvm_vcpu *vcpu = apic->vcpu;
+
+ if (svm_deliver_avic_intr(vcpu, vector)) {
+ kvm_lapic_set_irr(vector, apic);
+ kvm_make_request(KVM_REQ_EVENT, vcpu);
+ kvm_vcpu_kick(vcpu);
+ } else {
+ trace_kvm_apicv_accept_irq(vcpu->vcpu_id, delivery_mode,
+ trig_mode, vector);
+ }
+}
+
static void svm_update_cr8_intercept(struct kvm_vcpu *vcpu, int tpr, int irr)
{
struct vcpu_svm *svm = to_svm(vcpu);
struct vcpu_svm *svm = to_svm(vcpu);
unsigned long vmcb_pa = svm->current_vmcb->pa;
- kvm_guest_enter_irqoff();
+ guest_state_enter_irqoff();
if (sev_es_guest(vcpu->kvm)) {
__svm_sev_es_vcpu_run(vmcb_pa);
vmload(__sme_page_pa(sd->save_area));
}
- kvm_guest_exit_irqoff();
+ guest_state_exit_irqoff();
}
static __no_kcsan fastpath_t svm_vcpu_run(struct kvm_vcpu *vcpu)
vcpu->arch.regs_dirty = 0;
if (unlikely(svm->vmcb->control.exit_code == SVM_EXIT_NMI))
- kvm_before_interrupt(vcpu);
+ kvm_before_interrupt(vcpu, KVM_HANDLING_NMI);
kvm_load_host_xsave_state(vcpu);
stgi();
.pmu_ops = &amd_pmu_ops,
.nested_ops = &svm_nested_ops,
- .deliver_posted_interrupt = svm_deliver_avic_intr,
+ .deliver_interrupt = svm_deliver_interrupt,
.dy_apicv_has_pending_interrupt = svm_dy_apicv_has_pending_interrupt,
.update_pi_irte = svm_update_pi_irte,
.setup_mce = svm_setup_mce,
return 0;
}
+static void vmx_deliver_interrupt(struct kvm_lapic *apic, int delivery_mode,
+ int trig_mode, int vector)
+{
+ struct kvm_vcpu *vcpu = apic->vcpu;
+
+ if (vmx_deliver_posted_interrupt(vcpu, vector)) {
+ kvm_lapic_set_irr(vector, apic);
+ kvm_make_request(KVM_REQ_EVENT, vcpu);
+ kvm_vcpu_kick(vcpu);
+ } else {
+ trace_kvm_apicv_accept_irq(vcpu->vcpu_id, delivery_mode,
+ trig_mode, vector);
+ }
+}
+
/*
* Set up the vmcs's constant host-state fields, i.e., host-state fields that
* will not change in the lifetime of the guest.
static void handle_interrupt_nmi_irqoff(struct kvm_vcpu *vcpu,
unsigned long entry)
{
- kvm_before_interrupt(vcpu);
+ bool is_nmi = entry == (unsigned long)asm_exc_nmi_noist;
+
+ kvm_before_interrupt(vcpu, is_nmi ? KVM_HANDLING_NMI : KVM_HANDLING_IRQ);
vmx_do_interrupt_nmi_irqoff(entry);
kvm_after_interrupt(vcpu);
}
static noinstr void vmx_vcpu_enter_exit(struct kvm_vcpu *vcpu,
struct vcpu_vmx *vmx)
{
- kvm_guest_enter_irqoff();
+ guest_state_enter_irqoff();
/* L1D Flush includes CPU buffer clear to mitigate MDS */
if (static_branch_unlikely(&vmx_l1d_should_flush))
vcpu->arch.cr2 = native_read_cr2();
- kvm_guest_exit_irqoff();
+ guest_state_exit_irqoff();
}
static fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu)
.hwapic_isr_update = vmx_hwapic_isr_update,
.guest_apic_has_interrupt = vmx_guest_apic_has_interrupt,
.sync_pir_to_irr = vmx_sync_pir_to_irr,
- .deliver_posted_interrupt = vmx_deliver_posted_interrupt,
+ .deliver_interrupt = vmx_deliver_interrupt,
.dy_apicv_has_pending_interrupt = pi_has_pending_interrupt,
.set_tss_addr = vmx_set_tss_addr,
.vcpu_deliver_sipi_vector = kvm_vcpu_deliver_sipi_vector,
};
+ static unsigned int vmx_handle_intel_pt_intr(void)
+ {
+ struct kvm_vcpu *vcpu = kvm_get_running_vcpu();
+
+ /* '0' on failure so that the !PT case can use a RET0 static call. */
+ if (!kvm_arch_pmi_in_guest(vcpu))
+ return 0;
+
+ kvm_make_request(KVM_REQ_PMI, vcpu);
+ __set_bit(MSR_CORE_PERF_GLOBAL_OVF_CTRL_TRACE_TOPA_PMI_BIT,
+ (unsigned long *)&vcpu->arch.pmu.global_status);
+ return 1;
+ }
+
static __init void vmx_setup_user_return_msrs(void)
{
kvm_add_user_return_msr(vmx_uret_msrs_list[i]);
}
+ static struct kvm_x86_init_ops vmx_init_ops __initdata;
+
static __init int hardware_setup(void)
{
unsigned long host_bndcfgs;
return -EINVAL;
if (!enable_ept || !cpu_has_vmx_intel_pt())
pt_mode = PT_MODE_SYSTEM;
+ if (pt_mode == PT_MODE_HOST_GUEST)
+ vmx_init_ops.handle_intel_pt_intr = vmx_handle_intel_pt_intr;
+ else
+ vmx_init_ops.handle_intel_pt_intr = NULL;
setup_default_sgx_lepubkeyhash();
.disabled_by_bios = vmx_disabled_by_bios,
.check_processor_compatibility = vmx_check_processor_compat,
.hardware_setup = hardware_setup,
+ .handle_intel_pt_intr = NULL,
.runtime_ops = &vmx_x86_ops,
};
u64 __read_mostly kvm_mce_cap_supported = MCG_CTL_P | MCG_SER_P;
EXPORT_SYMBOL_GPL(kvm_mce_cap_supported);
+#define ERR_PTR_USR(e) ((void __user *)ERR_PTR(e))
+
#define emul_to_vcpu(ctxt) \
((struct kvm_vcpu *)(ctxt)->vcpu)
void __user *uaddr = (void __user*)(unsigned long)attr->addr;
if ((u64)(unsigned long)uaddr != attr->addr)
- return ERR_PTR(-EFAULT);
+ return ERR_PTR_USR(-EFAULT);
return uaddr;
}
kvmclock_cpu_online, kvmclock_cpu_down_prep);
}
- DEFINE_PER_CPU(struct kvm_vcpu *, current_vcpu);
- EXPORT_PER_CPU_SYMBOL_GPL(current_vcpu);
-
- int kvm_is_in_guest(void)
- {
- return __this_cpu_read(current_vcpu) != NULL;
- }
-
- static int kvm_is_user_mode(void)
- {
- int user_mode = 3;
-
- if (__this_cpu_read(current_vcpu))
- user_mode = static_call(kvm_x86_get_cpl)(__this_cpu_read(current_vcpu));
-
- return user_mode != 0;
- }
-
- static unsigned long kvm_get_guest_ip(void)
- {
- unsigned long ip = 0;
-
- if (__this_cpu_read(current_vcpu))
- ip = kvm_rip_read(__this_cpu_read(current_vcpu));
-
- return ip;
- }
-
- static void kvm_handle_intel_pt_intr(void)
- {
- struct kvm_vcpu *vcpu = __this_cpu_read(current_vcpu);
-
- kvm_make_request(KVM_REQ_PMI, vcpu);
- __set_bit(MSR_CORE_PERF_GLOBAL_OVF_CTRL_TRACE_TOPA_PMI_BIT,
- (unsigned long *)&vcpu->arch.pmu.global_status);
- }
-
- static struct perf_guest_info_callbacks kvm_guest_cbs = {
- .is_in_guest = kvm_is_in_guest,
- .is_user_mode = kvm_is_user_mode,
- .get_guest_ip = kvm_get_guest_ip,
- .handle_intel_pt_intr = kvm_handle_intel_pt_intr,
- };
-
#ifdef CONFIG_X86_64
static void pvclock_gtod_update_fn(struct work_struct *work)
{
kvm_timer_init();
- perf_register_guest_info_callbacks(&kvm_guest_cbs);
-
if (boot_cpu_has(X86_FEATURE_XSAVE)) {
host_xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK);
supported_xcr0 = host_xcr0 & KVM_SUPPORTED_XCR0;
clear_hv_tscchange_cb();
#endif
kvm_lapic_exit();
- perf_unregister_guest_info_callbacks(&kvm_guest_cbs);
if (!boot_cpu_has(X86_FEATURE_CONSTANT_TSC))
cpufreq_unregister_notifier(&kvmclock_cpufreq_notifier_block,
set_debugreg(0, 7);
}
+ guest_timing_enter_irqoff();
+
for (;;) {
/*
* Assert that vCPU vs. VM APICv state is consistent. An APICv
* interrupts on processors that implement an interrupt shadow, the
* stat.exits increment will do nicely.
*/
- kvm_before_interrupt(vcpu);
+ kvm_before_interrupt(vcpu, KVM_HANDLING_IRQ);
local_irq_enable();
++vcpu->stat.exits;
local_irq_disable();
* of accounting via context tracking, but the loss of accuracy is
* acceptable for all known use cases.
*/
- vtime_account_guest_exit();
+ guest_timing_exit_irqoff();
if (lapic_in_kernel(vcpu)) {
s64 delta = vcpu->arch.apic->lapic_timer.advance_expire_delta;
memcpy(&kvm_x86_ops, ops->runtime_ops, sizeof(kvm_x86_ops));
kvm_ops_static_call_update();
+ kvm_register_perf_callbacks(ops->handle_intel_pt_intr);
+
if (!kvm_cpu_cap_has(X86_FEATURE_XSAVES))
supported_xss = 0;
void kvm_arch_hardware_unsetup(void)
{
+ kvm_unregister_perf_callbacks();
+
static_call(kvm_x86_hardware_unsetup)();
}
kvm_free_pit(kvm);
}
-#define ERR_PTR_USR(e) ((void __user *)ERR_PTR(e))
-
/**
* __x86_set_memory_region: Setup KVM internal memory slot
*
return vcpu->arch.preempted_in_kernel;
}
+ unsigned long kvm_arch_vcpu_get_ip(struct kvm_vcpu *vcpu)
+ {
+ return kvm_rip_read(vcpu);
+ }
+
int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu)
{
return kvm_vcpu_exiting_guest_mode(vcpu) == IN_GUEST_MODE;
void kvm_spurious_fault(void);
-static __always_inline void kvm_guest_enter_irqoff(void)
-{
- /*
- * VMENTER enables interrupts (host state), but the kernel state is
- * interrupts disabled when this is invoked. Also tell RCU about
- * it. This is the same logic as for exit_to_user_mode().
- *
- * This ensures that e.g. latency analysis on the host observes
- * guest mode as interrupt enabled.
- *
- * guest_enter_irqoff() informs context tracking about the
- * transition to guest mode and if enabled adjusts RCU state
- * accordingly.
- */
- instrumentation_begin();
- trace_hardirqs_on_prepare();
- lockdep_hardirqs_on_prepare(CALLER_ADDR0);
- instrumentation_end();
-
- guest_enter_irqoff();
- lockdep_hardirqs_on(CALLER_ADDR0);
-}
-
-static __always_inline void kvm_guest_exit_irqoff(void)
-{
- /*
- * VMEXIT disables interrupts (host state), but tracing and lockdep
- * have them in state 'on' as recorded before entering guest mode.
- * Same as enter_from_user_mode().
- *
- * context_tracking_guest_exit() restores host context and reinstates
- * RCU if enabled and required.
- *
- * This needs to be done immediately after VM-Exit, before any code
- * that might contain tracepoints or call out to the greater world,
- * e.g. before x86_spec_ctrl_restore_host().
- */
- lockdep_hardirqs_off(CALLER_ADDR0);
- context_tracking_guest_exit();
-
- instrumentation_begin();
- trace_hardirqs_off_finish();
- instrumentation_end();
-}
-
#define KVM_NESTED_VMENTER_CONSISTENCY_CHECK(consistency_check) \
({ \
bool failed = (consistency_check); \
return kvm->arch.cstate_in_guest;
}
- DECLARE_PER_CPU(struct kvm_vcpu *, current_vcpu);
+ enum kvm_intr_type {
+ /* Values are arbitrary, but must be non-zero. */
+ KVM_HANDLING_IRQ = 1,
+ KVM_HANDLING_NMI,
+ };
- static inline void kvm_before_interrupt(struct kvm_vcpu *vcpu)
+ static inline void kvm_before_interrupt(struct kvm_vcpu *vcpu,
+ enum kvm_intr_type intr)
{
- __this_cpu_write(current_vcpu, vcpu);
+ WRITE_ONCE(vcpu->arch.handling_intr_from_guest, (u8)intr);
}
static inline void kvm_after_interrupt(struct kvm_vcpu *vcpu)
{
- __this_cpu_write(current_vcpu, NULL);
+ WRITE_ONCE(vcpu->arch.handling_intr_from_guest, 0);
}
+ static inline bool kvm_handling_nmi_from_guest(struct kvm_vcpu *vcpu)
+ {
+ return vcpu->arch.handling_intr_from_guest == KVM_HANDLING_NMI;
+ }
static inline bool kvm_pat_valid(u64 data)
{
#include <linux/refcount.h>
#include <linux/nospec.h>
#include <linux/notifier.h>
+#include <linux/ftrace.h>
#include <linux/hashtable.h>
+#include <linux/instrumentation.h>
#include <linux/interval_tree.h>
#include <linux/rbtree.h>
#include <linux/xarray.h>
u64 last_used_slot_gen;
};
-/* must be called with irqs disabled */
-static __always_inline void guest_enter_irqoff(void)
+/*
+ * Start accounting time towards a guest.
+ * Must be called before entering guest context.
+ */
+static __always_inline void guest_timing_enter_irqoff(void)
{
/*
* This is running in ioctl context so its safe to assume that it's the
instrumentation_begin();
vtime_account_guest_enter();
instrumentation_end();
+}
+/*
+ * Enter guest context and enter an RCU extended quiescent state.
+ *
+ * Between guest_context_enter_irqoff() and guest_context_exit_irqoff() it is
+ * unsafe to use any code which may directly or indirectly use RCU, tracing
+ * (including IRQ flag tracing), or lockdep. All code in this period must be
+ * non-instrumentable.
+ */
+static __always_inline void guest_context_enter_irqoff(void)
+{
/*
* KVM does not hold any references to rcu protected data when it
* switches CPU into a guest mode. In fact switching to a guest mode
}
}
-static __always_inline void guest_exit_irqoff(void)
+/*
+ * Deprecated. Architectures should move to guest_timing_enter_irqoff() and
+ * guest_state_enter_irqoff().
+ */
+static __always_inline void guest_enter_irqoff(void)
+{
+ guest_timing_enter_irqoff();
+ guest_context_enter_irqoff();
+}
+
+/**
+ * guest_state_enter_irqoff - Fixup state when entering a guest
+ *
+ * Entry to a guest will enable interrupts, but the kernel state is interrupts
+ * disabled when this is invoked. Also tell RCU about it.
+ *
+ * 1) Trace interrupts on state
+ * 2) Invoke context tracking if enabled to adjust RCU state
+ * 3) Tell lockdep that interrupts are enabled
+ *
+ * Invoked from architecture specific code before entering a guest.
+ * Must be called with interrupts disabled and the caller must be
+ * non-instrumentable.
+ * The caller has to invoke guest_timing_enter_irqoff() before this.
+ *
+ * Note: this is analogous to exit_to_user_mode().
+ */
+static __always_inline void guest_state_enter_irqoff(void)
+{
+ instrumentation_begin();
+ trace_hardirqs_on_prepare();
+ lockdep_hardirqs_on_prepare(CALLER_ADDR0);
+ instrumentation_end();
+
+ guest_context_enter_irqoff();
+ lockdep_hardirqs_on(CALLER_ADDR0);
+}
+
+/*
+ * Exit guest context and exit an RCU extended quiescent state.
+ *
+ * Between guest_context_enter_irqoff() and guest_context_exit_irqoff() it is
+ * unsafe to use any code which may directly or indirectly use RCU, tracing
+ * (including IRQ flag tracing), or lockdep. All code in this period must be
+ * non-instrumentable.
+ */
+static __always_inline void guest_context_exit_irqoff(void)
{
context_tracking_guest_exit();
+}
+/*
+ * Stop accounting time towards a guest.
+ * Must be called after exiting guest context.
+ */
+static __always_inline void guest_timing_exit_irqoff(void)
+{
instrumentation_begin();
/* Flush the guest cputime we spent on the guest */
vtime_account_guest_exit();
instrumentation_end();
}
+/*
+ * Deprecated. Architectures should move to guest_state_exit_irqoff() and
+ * guest_timing_exit_irqoff().
+ */
+static __always_inline void guest_exit_irqoff(void)
+{
+ guest_context_exit_irqoff();
+ guest_timing_exit_irqoff();
+}
+
static inline void guest_exit(void)
{
unsigned long flags;
local_irq_restore(flags);
}
+/**
+ * guest_state_exit_irqoff - Establish state when returning from guest mode
+ *
+ * Entry from a guest disables interrupts, but guest mode is traced as
+ * interrupts enabled. Also with NO_HZ_FULL RCU might be idle.
+ *
+ * 1) Tell lockdep that interrupts are disabled
+ * 2) Invoke context tracking if enabled to reactivate RCU
+ * 3) Trace interrupts off state
+ *
+ * Invoked from architecture specific code after exiting a guest.
+ * Must be invoked with interrupts disabled and the caller must be
+ * non-instrumentable.
+ * The caller has to invoke guest_timing_exit_irqoff() after this.
+ *
+ * Note: this is analogous to enter_from_user_mode().
+ */
+static __always_inline void guest_state_exit_irqoff(void)
+{
+ lockdep_hardirqs_off(CALLER_ADDR0);
+ guest_context_exit_irqoff();
+
+ instrumentation_begin();
+ trace_hardirqs_off_finish();
+ instrumentation_end();
+}
+
static inline int kvm_vcpu_exiting_guest_mode(struct kvm_vcpu *vcpu)
{
/*
}
#endif
+ #ifdef CONFIG_GUEST_PERF_EVENTS
+ unsigned long kvm_arch_vcpu_get_ip(struct kvm_vcpu *vcpu);
+
+ void kvm_register_perf_callbacks(unsigned int (*pt_intr_handler)(void));
+ void kvm_unregister_perf_callbacks(void);
+ #else
+ static inline void kvm_register_perf_callbacks(void *ign) {}
+ static inline void kvm_unregister_perf_callbacks(void) {}
+ #endif /* CONFIG_GUEST_PERF_EVENTS */
+
int kvm_arch_init_vm(struct kvm *kvm, unsigned long type);
void kvm_arch_destroy_vm(struct kvm *kvm);
void kvm_arch_sync_events(struct kvm *kvm);