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 */
return -ENOIOCTLCMD;
}
+/*
+ * 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_mips_vcpu_enter_exit(struct kvm_vcpu *vcpu)
+{
+ int ret;
+
+ guest_state_enter_irqoff();
+ ret = kvm_mips_callbacks->vcpu_run(vcpu);
+ guest_state_exit_irqoff();
+
+ return ret;
+}
+
int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
{
int r = -EINTR;
lose_fpu(1);
local_irq_disable();
- guest_enter_irqoff();
+ guest_timing_enter_irqoff();
trace_kvm_enter(vcpu);
/*
*/
smp_store_mb(vcpu->mode, IN_GUEST_MODE);
- r = kvm_mips_callbacks->vcpu_run(vcpu);
+ r = kvm_mips_vcpu_enter_exit(vcpu);
+
+ /*
+ * 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.
+ *
+ * TODO: is there a barrier which ensures that pending interrupts are
+ * recognised? Currently this just hopes that the CPU takes any pending
+ * interrupts between the enable and disable.
+ */
+ local_irq_enable();
+ local_irq_disable();
trace_kvm_out(vcpu);
- guest_exit_irqoff();
+ guest_timing_exit_irqoff();
local_irq_enable();
out:
/*
* Return value is in the form (errcode<<2 | RESUME_FLAG_HOST | RESUME_FLAG_NV)
*/
-int kvm_mips_handle_exit(struct kvm_vcpu *vcpu)
+static int __kvm_mips_handle_exit(struct kvm_vcpu *vcpu)
{
struct kvm_run *run = vcpu->run;
u32 cause = vcpu->arch.host_cp0_cause;
return ret;
}
+int noinstr kvm_mips_handle_exit(struct kvm_vcpu *vcpu)
+{
+ int ret;
+
+ guest_state_exit_irqoff();
+ ret = __kvm_mips_handle_exit(vcpu);
+ guest_state_enter_irqoff();
+
+ return ret;
+}
+
/* Enable FPU for guest and restore context */
void kvm_own_fpu(struct kvm_vcpu *vcpu)
{
int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu)
{
struct kvm_cpu_context *cntx;
+ struct kvm_vcpu_csr *reset_csr = &vcpu->arch.guest_reset_csr;
/* Mark this VCPU never ran */
vcpu->arch.ran_atleast_once = false;
cntx->hstatus |= HSTATUS_SPVP;
cntx->hstatus |= HSTATUS_SPV;
+ /* By default, make CY, TM, and IR counters accessible in VU mode */
+ reset_csr->scounteren = 0x7;
+
/* Setup VCPU timer */
kvm_riscv_vcpu_timer_init(vcpu);
csr_write(CSR_HVIP, csr->hvip);
}
+/*
+ * 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 void noinstr kvm_riscv_vcpu_enter_exit(struct kvm_vcpu *vcpu)
+{
+ guest_state_enter_irqoff();
+ __kvm_riscv_switch_to(&vcpu->arch);
+ guest_state_exit_irqoff();
+}
+
int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
{
int ret;
continue;
}
- guest_enter_irqoff();
+ guest_timing_enter_irqoff();
- __kvm_riscv_switch_to(&vcpu->arch);
+ kvm_riscv_vcpu_enter_exit(vcpu);
vcpu->mode = OUTSIDE_GUEST_MODE;
vcpu->stat.exits++;
kvm_riscv_vcpu_sync_interrupts(vcpu);
/*
- * We may have taken a host interrupt in VS/VU-mode (i.e.
- * 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 HS-mode with interrupts disabled
- * so enabling the interrupts now will have the effect
- * of taking the interrupt again, in HS-mode this time.
+ * There's no barrier which ensures that pending interrupts are
+ * recognised, so we just hope that the CPU takes any pending
+ * interrupts between the enable and disable.
*/
local_irq_enable();
+ local_irq_disable();
- /*
- * 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();
+ guest_timing_exit_irqoff();
+
+ local_irq_enable();
preempt_enable();
#include <linux/errno.h>
#include <linux/err.h>
#include <linux/kvm_host.h>
+#include <linux/version.h>
#include <asm/csr.h>
#include <asm/sbi.h>
#include <asm/kvm_vcpu_timer.h>
*out_val = KVM_SBI_IMPID;
break;
case SBI_EXT_BASE_GET_IMP_VERSION:
- *out_val = 0;
+ *out_val = LINUX_VERSION_CODE;
break;
case SBI_EXT_BASE_PROBE_EXT:
if ((cp->a0 >= SBI_EXT_EXPERIMENTAL_START &&
KVM_X86_OP(load_eoi_exitmap)
KVM_X86_OP(set_virtual_apic_mode)
KVM_X86_OP_NULL(set_apic_access_page_addr)
-KVM_X86_OP(deliver_posted_interrupt)
+KVM_X86_OP(deliver_interrupt)
KVM_X86_OP_NULL(sync_pir_to_irr)
KVM_X86_OP(set_tss_addr)
KVM_X86_OP(set_identity_map_addr)
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);
);
kvm_cpu_cap_mask(CPUID_7_0_EBX,
- F(FSGSBASE) | F(SGX) | F(BMI1) | F(HLE) | F(AVX2) | F(SMEP) |
- F(BMI2) | F(ERMS) | F(INVPCID) | F(RTM) | 0 /*MPX*/ | F(RDSEED) |
- F(ADX) | F(SMAP) | F(AVX512IFMA) | F(AVX512F) | F(AVX512PF) |
- F(AVX512ER) | F(AVX512CD) | F(CLFLUSHOPT) | F(CLWB) | F(AVX512DQ) |
- F(SHA_NI) | F(AVX512BW) | F(AVX512VL) | 0 /*INTEL_PT*/
- );
+ F(FSGSBASE) | F(SGX) | F(BMI1) | F(HLE) | F(AVX2) |
+ F(FDP_EXCPTN_ONLY) | F(SMEP) | F(BMI2) | F(ERMS) | F(INVPCID) |
+ F(RTM) | F(ZERO_FCS_FDS) | 0 /*MPX*/ | F(AVX512F) |
+ F(AVX512DQ) | F(RDSEED) | F(ADX) | F(SMAP) | F(AVX512IFMA) |
+ F(CLFLUSHOPT) | F(CLWB) | 0 /*INTEL_PT*/ | F(AVX512PF) |
+ F(AVX512ER) | F(AVX512CD) | F(SHA_NI) | F(AVX512BW) |
+ F(AVX512VL));
kvm_cpu_cap_mask(CPUID_7_ECX,
F(AVX512VBMI) | F(LA57) | F(PKU) | 0 /*OSPKE*/ | F(RDPID) |
apic->regs + APIC_TMR);
}
- if (static_call(kvm_x86_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);
- }
+ static_call(kvm_x86_deliver_interrupt)(apic, delivery_mode,
+ trig_mode, vector);
break;
case APIC_DM_REMRD:
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)
.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 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,
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;
}
set_debugreg(0, 7);
}
+ guest_timing_enter_irqoff();
+
for (;;) {
/*
* Assert that vCPU vs. VM APICv state is consistent. An APICv
* 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;
kvm_free_pit(kvm);
}
-#define ERR_PTR_USR(e) ((void __user *)ERR_PTR(e))
-
/**
* __x86_set_memory_region: Setup KVM internal memory slot
*
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); \
#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)
{
/*
#define KVM_S390_NORMAL_RESET _IO(KVMIO, 0xc3)
#define KVM_S390_CLEAR_RESET _IO(KVMIO, 0xc4)
-/* Available with KVM_CAP_XSAVE2 */
-#define KVM_GET_XSAVE2 _IOR(KVMIO, 0xcf, struct kvm_xsave)
-
struct kvm_s390_pv_sec_parm {
__u64 origin;
__u64 length;
#define KVM_GET_STATS_FD _IO(KVMIO, 0xce)
+/* Available with KVM_CAP_XSAVE2 */
+#define KVM_GET_XSAVE2 _IOR(KVMIO, 0xcf, struct kvm_xsave)
+
#endif /* __LINUX_KVM_H */