1 files changed, 97 insertions, 42 deletions

diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 2d3be7f3ad67..fbabb2f06273 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -26,6 +26,7 @@
 #include "cpuid.h"
 #include "pmu.h"
 #include "hyperv.h"
+#include "lapic.h"
 
 #include <linux/clocksource.h>
 #include <linux/interrupt.h>
@@ -897,6 +898,8 @@ EXPORT_SYMBOL_GPL(kvm_set_xcr);
 		__reserved_bits |= X86_CR4_PKE;		\
 	if (!__cpu_has(__c, X86_FEATURE_LA57))		\
 		__reserved_bits |= X86_CR4_LA57;	\
+	if (!__cpu_has(__c, X86_FEATURE_UMIP))		\
+		__reserved_bits |= X86_CR4_UMIP;	\
 	__reserved_bits;				\
 })
 
@@ -1609,6 +1612,8 @@ struct pvclock_clock {
 	u64 mask;
 	u32 mult;
 	u32 shift;
+	u64 base_cycles;
+	u64 offset;
 };
 
 struct pvclock_gtod_data {
@@ -1617,11 +1622,8 @@ struct pvclock_gtod_data {
 	struct pvclock_clock clock; /* extract of a clocksource struct */
 	struct pvclock_clock raw_clock; /* extract of a clocksource struct */
 
-	u64		boot_ns_raw;
-	u64		boot_ns;
-	u64		nsec_base;
+	ktime_t		offs_boot;
 	u64		wall_time_sec;
-	u64		monotonic_raw_nsec;
 };
 
 static struct pvclock_gtod_data pvclock_gtod_data;
@@ -1629,10 +1631,6 @@ static struct pvclock_gtod_data pvclock_gtod_data;
 static void update_pvclock_gtod(struct timekeeper *tk)
 {
 	struct pvclock_gtod_data *vdata = &pvclock_gtod_data;
-	u64 boot_ns, boot_ns_raw;
-
-	boot_ns = ktime_to_ns(ktime_add(tk->tkr_mono.base, tk->offs_boot));
-	boot_ns_raw = ktime_to_ns(ktime_add(tk->tkr_raw.base, tk->offs_boot));
 
 	write_seqcount_begin(&vdata->seq);
 
@@ -1642,23 +1640,35 @@ static void update_pvclock_gtod(struct timekeeper *tk)
 	vdata->clock.mask		= tk->tkr_mono.mask;
 	vdata->clock.mult		= tk->tkr_mono.mult;
 	vdata->clock.shift		= tk->tkr_mono.shift;
+	vdata->clock.base_cycles	= tk->tkr_mono.xtime_nsec;
+	vdata->clock.offset		= tk->tkr_mono.base;
 
 	vdata->raw_clock.vclock_mode	= tk->tkr_raw.clock->archdata.vclock_mode;
 	vdata->raw_clock.cycle_last	= tk->tkr_raw.cycle_last;
 	vdata->raw_clock.mask		= tk->tkr_raw.mask;
 	vdata->raw_clock.mult		= tk->tkr_raw.mult;
 	vdata->raw_clock.shift		= tk->tkr_raw.shift;
-
-	vdata->boot_ns			= boot_ns;
-	vdata->nsec_base		= tk->tkr_mono.xtime_nsec;
+	vdata->raw_clock.base_cycles	= tk->tkr_raw.xtime_nsec;
+	vdata->raw_clock.offset		= tk->tkr_raw.base;
 
 	vdata->wall_time_sec            = tk->xtime_sec;
 
-	vdata->boot_ns_raw		= boot_ns_raw;
-	vdata->monotonic_raw_nsec	= tk->tkr_raw.xtime_nsec;
+	vdata->offs_boot		= tk->offs_boot;
 
 	write_seqcount_end(&vdata->seq);
 }
+
+static s64 get_kvmclock_base_ns(void)
+{
+	/* Count up from boot time, but with the frequency of the raw clock.  */
+	return ktime_to_ns(ktime_add(ktime_get_raw(), pvclock_gtod_data.offs_boot));
+}
+#else
+static s64 get_kvmclock_base_ns(void)
+{
+	/* Master clock not used, so we can just use CLOCK_BOOTTIME.  */
+	return ktime_get_boottime_ns();
+}
 #endif
 
 void kvm_set_pending_timer(struct kvm_vcpu *vcpu)
@@ -1672,7 +1682,7 @@ static void kvm_write_wall_clock(struct kvm *kvm, gpa_t wall_clock)
 	int version;
 	int r;
 	struct pvclock_wall_clock wc;
-	struct timespec64 boot;
+	u64 wall_nsec;
 
 	if (!wall_clock)
 		return;
@@ -1692,17 +1702,12 @@ static void kvm_write_wall_clock(struct kvm *kvm, gpa_t wall_clock)
 	/*
 	 * The guest calculates current wall clock time by adding
 	 * system time (updated by kvm_guest_time_update below) to the
-	 * wall clock specified here.  guest system time equals host
-	 * system time for us, thus we must fill in host boot time here.
+	 * wall clock specified here.  We do the reverse here.
 	 */
-	getboottime64(&boot);
+	wall_nsec = ktime_get_real_ns() - get_kvmclock_ns(kvm);
 
-	if (kvm->arch.kvmclock_offset) {
-		struct timespec64 ts = ns_to_timespec64(kvm->arch.kvmclock_offset);
-		boot = timespec64_sub(boot, ts);
-	}
-	wc.sec = (u32)boot.tv_sec; /* overflow in 2106 guest time */
-	wc.nsec = boot.tv_nsec;
+	wc.nsec = do_div(wall_nsec, 1000000000);
+	wc.sec = (u32)wall_nsec; /* overflow in 2106 guest time */
 	wc.version = version;
 
 	kvm_write_guest(kvm, wall_clock, &wc, sizeof(wc));
@@ -1950,7 +1955,7 @@ void kvm_write_tsc(struct kvm_vcpu *vcpu, struct msr_data *msr)
 
 	raw_spin_lock_irqsave(&kvm->arch.tsc_write_lock, flags);
 	offset = kvm_compute_tsc_offset(vcpu, data);
-	ns = ktime_get_boottime_ns();
+	ns = get_kvmclock_base_ns();
 	elapsed = ns - kvm->arch.last_tsc_nsec;
 
 	if (vcpu->arch.virtual_tsc_khz) {
@@ -2125,10 +2130,10 @@ static int do_monotonic_raw(s64 *t, u64 *tsc_timestamp)
 
 	do {
 		seq = read_seqcount_begin(&gtod->seq);
-		ns = gtod->monotonic_raw_nsec;
+		ns = gtod->raw_clock.base_cycles;
 		ns += vgettsc(&gtod->raw_clock, tsc_timestamp, &mode);
-		ns >>= gtod->clock.shift;
-		ns += gtod->boot_ns_raw;
+		ns >>= gtod->raw_clock.shift;
+		ns += ktime_to_ns(ktime_add(gtod->raw_clock.offset, gtod->offs_boot));
 	} while (unlikely(read_seqcount_retry(&gtod->seq, seq)));
 	*t = ns;
 
@@ -2145,7 +2150,7 @@ static int do_realtime(struct timespec64 *ts, u64 *tsc_timestamp)
 	do {
 		seq = read_seqcount_begin(&gtod->seq);
 		ts->tv_sec = gtod->wall_time_sec;
-		ns = gtod->nsec_base;
+		ns = gtod->clock.base_cycles;
 		ns += vgettsc(&gtod->clock, tsc_timestamp, &mode);
 		ns >>= gtod->clock.shift;
 	} while (unlikely(read_seqcount_retry(&gtod->seq, seq)));
@@ -2288,7 +2293,7 @@ u64 get_kvmclock_ns(struct kvm *kvm)
 	spin_lock(&ka->pvclock_gtod_sync_lock);
 	if (!ka->use_master_clock) {
 		spin_unlock(&ka->pvclock_gtod_sync_lock);
-		return ktime_get_boottime_ns() + ka->kvmclock_offset;
+		return get_kvmclock_base_ns() + ka->kvmclock_offset;
 	}
 
 	hv_clock.tsc_timestamp = ka->master_cycle_now;
@@ -2304,7 +2309,7 @@ u64 get_kvmclock_ns(struct kvm *kvm)
 				   &hv_clock.tsc_to_system_mul);
 		ret = __pvclock_read_cycles(&hv_clock, rdtsc());
 	} else
-		ret = ktime_get_boottime_ns() + ka->kvmclock_offset;
+		ret = get_kvmclock_base_ns() + ka->kvmclock_offset;
 
 	put_cpu();
 
@@ -2403,7 +2408,7 @@ static int kvm_guest_time_update(struct kvm_vcpu *v)
 	}
 	if (!use_master_clock) {
 		host_tsc = rdtsc();
-		kernel_ns = ktime_get_boottime_ns();
+		kernel_ns = get_kvmclock_base_ns();
 	}
 
 	tsc_timestamp = kvm_read_l1_tsc(v, host_tsc);
@@ -2443,6 +2448,7 @@ static int kvm_guest_time_update(struct kvm_vcpu *v)
 	vcpu->hv_clock.tsc_timestamp = tsc_timestamp;
 	vcpu->hv_clock.system_time = kernel_ns + v->kvm->arch.kvmclock_offset;
 	vcpu->last_guest_tsc = tsc_timestamp;
+	WARN_ON(vcpu->hv_clock.system_time < 0);
 
 	/* If the host uses TSC clocksource, then it is stable */
 	pvclock_flags = 0;
@@ -7456,18 +7462,22 @@ static void kvm_pv_kick_cpu_op(struct kvm *kvm, unsigned long flags, int apicid)
 	kvm_irq_delivery_to_apic(kvm, NULL, &lapic_irq, NULL);
 }
 
-void kvm_vcpu_deactivate_apicv(struct kvm_vcpu *vcpu)
+bool kvm_apicv_activated(struct kvm *kvm)
 {
-	if (!lapic_in_kernel(vcpu)) {
-		WARN_ON_ONCE(vcpu->arch.apicv_active);
-		return;
-	}
-	if (!vcpu->arch.apicv_active)
-		return;
+	return (READ_ONCE(kvm->arch.apicv_inhibit_reasons) == 0);
+}
+EXPORT_SYMBOL_GPL(kvm_apicv_activated);
 
-	vcpu->arch.apicv_active = false;
-	kvm_x86_ops->refresh_apicv_exec_ctrl(vcpu);
+void kvm_apicv_init(struct kvm *kvm, bool enable)
+{
+	if (enable)
+		clear_bit(APICV_INHIBIT_REASON_DISABLE,
+			  &kvm->arch.apicv_inhibit_reasons);
+	else
+		set_bit(APICV_INHIBIT_REASON_DISABLE,
+			&kvm->arch.apicv_inhibit_reasons);
 }
+EXPORT_SYMBOL_GPL(kvm_apicv_init);
 
 static void kvm_sched_yield(struct kvm *kvm, unsigned long dest_id)
 {
@@ -7996,6 +8006,47 @@ void kvm_make_scan_ioapic_request(struct kvm *kvm)
 	kvm_make_all_cpus_request(kvm, KVM_REQ_SCAN_IOAPIC);
 }
 
+void kvm_vcpu_update_apicv(struct kvm_vcpu *vcpu)
+{
+	if (!lapic_in_kernel(vcpu))
+		return;
+
+	vcpu->arch.apicv_active = kvm_apicv_activated(vcpu->kvm);
+	kvm_apic_update_apicv(vcpu);
+	kvm_x86_ops->refresh_apicv_exec_ctrl(vcpu);
+}
+EXPORT_SYMBOL_GPL(kvm_vcpu_update_apicv);
+
+/*
+ * NOTE: Do not hold any lock prior to calling this.
+ *
+ * In particular, kvm_request_apicv_update() expects kvm->srcu not to be
+ * locked, because it calls __x86_set_memory_region() which does
+ * synchronize_srcu(&kvm->srcu).
+ */
+void kvm_request_apicv_update(struct kvm *kvm, bool activate, ulong bit)
+{
+	if (!kvm_x86_ops->check_apicv_inhibit_reasons ||
+	    !kvm_x86_ops->check_apicv_inhibit_reasons(bit))
+		return;
+
+	if (activate) {
+		if (!test_and_clear_bit(bit, &kvm->arch.apicv_inhibit_reasons) ||
+		    !kvm_apicv_activated(kvm))
+			return;
+	} else {
+		if (test_and_set_bit(bit, &kvm->arch.apicv_inhibit_reasons) ||
+		    kvm_apicv_activated(kvm))
+			return;
+	}
+
+	trace_kvm_apicv_update_request(activate, bit);
+	if (kvm_x86_ops->pre_update_apicv_exec_ctrl)
+		kvm_x86_ops->pre_update_apicv_exec_ctrl(kvm, activate);
+	kvm_make_all_cpus_request(kvm, KVM_REQ_APICV_UPDATE);
+}
+EXPORT_SYMBOL_GPL(kvm_request_apicv_update);
+
 static void vcpu_scan_ioapic(struct kvm_vcpu *vcpu)
 {
 	if (!kvm_apic_present(vcpu))
@@ -8186,6 +8237,8 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 		 */
 		if (kvm_check_request(KVM_REQ_HV_STIMER, vcpu))
 			kvm_hv_process_stimers(vcpu);
+		if (kvm_check_request(KVM_REQ_APICV_UPDATE, vcpu))
+			kvm_vcpu_update_apicv(vcpu);
 	}
 
 	if (kvm_check_request(KVM_REQ_EVENT, vcpu) || req_int_win) {
@@ -9219,10 +9272,11 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu)
 		return r;
 
 	if (irqchip_in_kernel(vcpu->kvm)) {
-		vcpu->arch.apicv_active = kvm_x86_ops->get_enable_apicv(vcpu->kvm);
 		r = kvm_create_lapic(vcpu, lapic_timer_advance_ns);
 		if (r < 0)
 			goto fail_mmu_destroy;
+		if (kvm_apicv_activated(vcpu->kvm))
+			vcpu->arch.apicv_active = true;
 	} else
 		static_key_slow_inc(&kvm_no_apic_vcpu);
 
@@ -9633,7 +9687,7 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 	mutex_init(&kvm->arch.apic_map_lock);
 	spin_lock_init(&kvm->arch.pvclock_gtod_sync_lock);
 
-	kvm->arch.kvmclock_offset = -ktime_get_boottime_ns();
+	kvm->arch.kvmclock_offset = -get_kvmclock_base_ns();
 	pvclock_update_vm_gtod_copy(kvm);
 
 	kvm->arch.guest_can_read_msr_platform_info = true;
@@ -10448,3 +10502,4 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_pml_full);
 EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_pi_irte_update);
 EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_avic_unaccelerated_access);
 EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_avic_incomplete_ipi);
+EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_apicv_update_request);