Commit f9d1b541 authored by Paolo Bonzini's avatar Paolo Bonzini
Browse files

Merge branch 'kvm-fixes-6.10-1' into HEAD 

* Fixes and debugging help for the #VE sanity check.  Also disable
  it by default, even for CONFIG_DEBUG_KERNEL, because it was found
  to trigger spuriously (most likely a processor erratum as the
  exact symptoms vary by generation).

* Avoid WARN() when two NMIs arrive simultaneously during an NMI-disabled
  situation (GIF=0 or interrupt shadow) when the processor supports
  virtual NMI.  While generally KVM will not request an NMI window
  when virtual NMIs are supported, in this case it *does* have to
  single-step over the interrupt shadow or enable the STGI intercept,
  in order to deliver the latched second NMI.

* Drop support for hand tuning APIC timer advancement from userspace.
  Since we have adaptive tuning, and it has proved to work well,
  drop the module parameter for manual configuration and with it a
  few stupid bugs that it had.
parents c3f38fa6 89a58812

arch/x86/include/asm/kvm_host.h

+1 −0
Original line number Diff line number Diff line
@@ -2154,6 +2154,7 @@ int kvm_emulate_hypercall(struct kvm_vcpu *vcpu); 


int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, u64 error_code,

		       void *insn, int insn_len);

void kvm_mmu_print_sptes(struct kvm_vcpu *vcpu, gpa_t gpa, const char *msg);

void kvm_mmu_invlpg(struct kvm_vcpu *vcpu, gva_t gva);

void kvm_mmu_invalidate_addr(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,

			     u64 addr, unsigned long roots);

arch/x86/include/asm/vmxfeatures.h

+1 −1
Original line number Diff line number Diff line
@@ -77,7 +77,7 @@ 
#define VMX_FEATURE_ENCLS_EXITING	( 2*32+ 15) /* "" VM-Exit on ENCLS (leaf dependent) */

#define VMX_FEATURE_RDSEED_EXITING	( 2*32+ 16) /* "" VM-Exit on RDSEED */

#define VMX_FEATURE_PAGE_MOD_LOGGING	( 2*32+ 17) /* "pml" Log dirty pages into buffer */

#define VMX_FEATURE_EPT_VIOLATION_VE	( 2*32+ 18) /* "" Conditionally reflect EPT violations as #VE exceptions */

#define VMX_FEATURE_EPT_VIOLATION_VE	( 2*32+ 18) /* Conditionally reflect EPT violations as #VE exceptions */

#define VMX_FEATURE_PT_CONCEAL_VMX	( 2*32+ 19) /* "" Suppress VMX indicators in Processor Trace */

#define VMX_FEATURE_XSAVES		( 2*32+ 20) /* "" Enable XSAVES and XRSTORS in guest */

#define VMX_FEATURE_MODE_BASED_EPT_EXEC	( 2*32+ 22) /* "ept_mode_based_exec" Enable separate EPT EXEC bits for supervisor vs. user */

arch/x86/kvm/Kconfig

+7 −4
Original line number Diff line number Diff line
@@ -44,6 +44,7 @@ config KVM 
	select KVM_VFIO

	select HAVE_KVM_PM_NOTIFIER if PM

	select KVM_GENERIC_HARDWARE_ENABLING

	select KVM_WERROR if WERROR

	help

	  Support hosting fully virtualized guest machines using hardware

	  virtualization extensions.  You will need a fairly recent
@@ -66,7 +67,7 @@ config KVM_WERROR 
	# FRAME_WARN, i.e. KVM_WERROR=y with KASAN=y requires special tuning.

	# Building KVM with -Werror and KASAN is still doable via enabling

	# the kernel-wide WERROR=y.

	depends on KVM && EXPERT && !KASAN

	depends on KVM && ((EXPERT && !KASAN) || WERROR)

	help

	  Add -Werror to the build flags for KVM.
@@ -97,15 +98,17 @@ config KVM_INTEL 


config KVM_INTEL_PROVE_VE

        bool "Check that guests do not receive #VE exceptions"

        default KVM_PROVE_MMU || DEBUG_KERNEL

        depends on KVM_INTEL

        depends on KVM_INTEL && EXPERT

        help



          Checks that KVM's page table management code will not incorrectly

          let guests receive a virtualization exception.  Virtualization

          exceptions will be trapped by the hypervisor rather than injected

          in the guest.



          Note: some CPUs appear to generate spurious EPT Violations #VEs

          that trigger KVM's WARN, in particular with eptad=0 and/or nested

          virtualization.



          If unsure, say N.



config X86_SGX_KVM

arch/x86/kvm/lapic.c

+21 −18
Original line number Diff line number Diff line
@@ -59,7 +59,17 @@ 
#define MAX_APIC_VECTOR			256

#define APIC_VECTORS_PER_REG		32



static bool lapic_timer_advance_dynamic __read_mostly;

/*

 * Enable local APIC timer advancement (tscdeadline mode only) with adaptive

 * tuning.  When enabled, KVM programs the host timer event to fire early, i.e.

 * before the deadline expires, to account for the delay between taking the

 * VM-Exit (to inject the guest event) and the subsequent VM-Enter to resume

 * the guest, i.e. so that the interrupt arrives in the guest with minimal

 * latency relative to the deadline programmed by the guest.

 */

static bool lapic_timer_advance __read_mostly = true;

module_param(lapic_timer_advance, bool, 0444);



#define LAPIC_TIMER_ADVANCE_ADJUST_MIN	100	/* clock cycles */

#define LAPIC_TIMER_ADVANCE_ADJUST_MAX	10000	/* clock cycles */

#define LAPIC_TIMER_ADVANCE_NS_INIT	1000
@@ -1854,16 +1864,14 @@ static void __kvm_wait_lapic_expire(struct kvm_vcpu *vcpu) 
	guest_tsc = kvm_read_l1_tsc(vcpu, rdtsc());

	trace_kvm_wait_lapic_expire(vcpu->vcpu_id, guest_tsc - tsc_deadline);



	if (lapic_timer_advance_dynamic) {

	adjust_lapic_timer_advance(vcpu, guest_tsc - tsc_deadline);



	/*

		 * If the timer fired early, reread the TSC to account for the

		 * overhead of the above adjustment to avoid waiting longer

		 * than is necessary.

	 * If the timer fired early, reread the TSC to account for the overhead

	 * of the above adjustment to avoid waiting longer than is necessary.

	 */

	if (guest_tsc < tsc_deadline)

		guest_tsc = kvm_read_l1_tsc(vcpu, rdtsc());

	}



	if (guest_tsc < tsc_deadline)

		__wait_lapic_expire(vcpu, tsc_deadline - guest_tsc);
@@ -2812,7 +2820,7 @@ static enum hrtimer_restart apic_timer_fn(struct hrtimer *data) 
		return HRTIMER_NORESTART;

}



int kvm_create_lapic(struct kvm_vcpu *vcpu, int timer_advance_ns)

int kvm_create_lapic(struct kvm_vcpu *vcpu)

{

	struct kvm_lapic *apic;
@@ -2845,13 +2853,8 @@ int kvm_create_lapic(struct kvm_vcpu *vcpu, int timer_advance_ns) 
	hrtimer_init(&apic->lapic_timer.timer, CLOCK_MONOTONIC,

		     HRTIMER_MODE_ABS_HARD);

	apic->lapic_timer.timer.function = apic_timer_fn;

	if (timer_advance_ns == -1) {

	if (lapic_timer_advance)

		apic->lapic_timer.timer_advance_ns = LAPIC_TIMER_ADVANCE_NS_INIT;

		lapic_timer_advance_dynamic = true;

	} else {

		apic->lapic_timer.timer_advance_ns = timer_advance_ns;

		lapic_timer_advance_dynamic = false;

	}



	/*

	 * Stuff the APIC ENABLE bit in lieu of temporarily incrementing

arch/x86/kvm/lapic.h

+1 −1
Original line number Diff line number Diff line
@@ -85,7 +85,7 @@ struct kvm_lapic { 


struct dest_map;



int kvm_create_lapic(struct kvm_vcpu *vcpu, int timer_advance_ns);

int kvm_create_lapic(struct kvm_vcpu *vcpu);

void kvm_free_lapic(struct kvm_vcpu *vcpu);



int kvm_apic_has_interrupt(struct kvm_vcpu *vcpu);