[PATCH v2 7/7] kvm/x86: rework guest entry logic

[Mark Rutland]

For consistency and clarity, migrate x86 over to the generic helpers for
guest timing and lockdep/RCU/tracing management, and remove the
x86-specific helpers.

Prior to this patch, the guest timing was entered in
kvm_guest_enter_irqoff() (called by svm_vcpu_enter_exit() and
svm_vcpu_enter_exit()), and was exited by the call to
vtime_account_guest_exit() within vcpu_enter_guest().

To minimize duplication and to more clearly balance entry and exit, both
entry and exit of guest timing are placed in vcpu_enter_guest(), using
the new guest_timing_{enter,exit}_irqoff() helpers. When context
tracking is used a small amount of additional time will be accounted
towards guests; tick-based accounting is unnaffected as IRQs are
disabled at this point and not enabled until after the return from the
guest.

This also corrects (benign) mis-balanced context tracking accounting
introduced in commits:

  ae95f566b3d22ade ("KVM: X86: TSCDEADLINE MSR emulation fastpath")
  26efe2fd92e50822 ("KVM: VMX: Handle preemption timer fastpath")

Where KVM can enter a guest multiple times, calling vtime_guest_enter()
without a corresponding call to vtime_account_guest_exit(), and with
vtime_account_system() called when vtime_account_guest() should be used.
As account_system_time() checks PF_VCPU and calls account_guest_time(),
this doesn't result in any functional problem, but is unnecessarily
confusing.

Signed-off-by: Mark Rutland <mark.rutland@xxxxxxx>
Cc: Borislav Petkov <bp@xxxxxxxxx>
Cc: Dave Hansen <dave.hansen@xxxxxxxxxxxxxxx>
Cc: Ingo Molnar <mingo@xxxxxxxxxx>
Cc: Jim Mattson <jmattson@xxxxxxxxxx>
Cc: Joerg Roedel <joro@xxxxxxxxxx>
Cc: Paolo Bonzini <pbonzini@xxxxxxxxxx>
Cc: Sean Christopherson <seanjc@xxxxxxxxxx>
Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Cc: Vitaly Kuznetsov <vkuznets@xxxxxxxxxx>
Cc: Wanpeng Li <wanpengli@xxxxxxxxxxx>
---
 arch/x86/kvm/svm/svm.c |  4 ++--
 arch/x86/kvm/vmx/vmx.c |  4 ++--
 arch/x86/kvm/x86.c     |  4 +++-
 arch/x86/kvm/x86.h     | 45 ------------------------------------------
 4 files changed, 7 insertions(+), 50 deletions(-)

diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index 5151efa424acb..1253add2c1075 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -3814,7 +3814,7 @@ static noinstr void svm_vcpu_enter_exit(struct kvm_vcpu *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);
@@ -3834,7 +3834,7 @@ static noinstr void svm_vcpu_enter_exit(struct kvm_vcpu *vcpu)
 		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)
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 0dbf94eb954fd..f458026a85159 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -6593,7 +6593,7 @@ static fastpath_t vmx_exit_handlers_fastpath(struct kvm_vcpu *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))
@@ -6609,7 +6609,7 @@ static noinstr void vmx_vcpu_enter_exit(struct kvm_vcpu *vcpu,
 
 	vcpu->arch.cr2 = native_read_cr2();
 
-	kvm_guest_exit_irqoff();
+	guest_state_exit_irqoff();
 }
 
 static fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu)
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index e50e97ac44084..bd3873b90889d 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -9876,6 +9876,8 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 		set_debugreg(0, 7);
 	}
 
+	guest_timing_enter_irqoff();
+
 	for (;;) {
 		/*
 		 * Assert that vCPU vs. VM APICv state is consistent.  An APICv
@@ -9949,7 +9951,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 	 * 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;
diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h
index 4abcd8d9836dd..8e50645ac740e 100644
--- a/arch/x86/kvm/x86.h
+++ b/arch/x86/kvm/x86.h
@@ -10,51 +10,6 @@
 
 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);				\
-- 
2.30.2