x86/kvm/hyperv: stable clocksource for L2 guests when running nested KVM on Hyper-V

index 189a398290db..21f9d53d9f00 100644
@@ -110,12 +110,19 @@ static int hv_cpu_init(unsigned int cpu)
  */
 void hyperv_init(void)
 {
-	u64 guest_id;
+	u64 guest_id, required_msrs;
 	union hv_x64_msr_hypercall_contents hypercall_msr;
 
 	if (x86_hyper_type != X86_HYPER_MS_HYPERV)
 		return;
 
+	/* Absolutely required MSRs */
+	required_msrs = HV_X64_MSR_HYPERCALL_AVAILABLE |
+		HV_X64_MSR_VP_INDEX_AVAILABLE;
+
+	if ((ms_hyperv.features & required_msrs) != required_msrs)
+		return;
+
 	/* Allocate percpu VP index */
 	hv_vp_index = kmalloc_array(num_possible_cpus(), sizeof(*hv_vp_index),
 				    GFP_KERNEL);

index 21f9d53d9f00..1a6c63f721bc 100644
@@ -37,6 +37,7 @@ struct ms_hyperv_tsc_page *hv_get_tsc_page(void)
 {
 	return tsc_pg;
 }
+EXPORT_SYMBOL_GPL(hv_get_tsc_page);
 
 static u64 read_hv_clock_tsc(struct clocksource *arg)
 {

index 8bf450b13d9f..6b1d4ea78270 100644
@@ -325,9 +325,10 @@ static inline void hyperv_setup_mmu_ops(void) {}
 
 #ifdef CONFIG_HYPERV_TSCPAGE
 struct ms_hyperv_tsc_page *hv_get_tsc_page(void);
-static inline u64 hv_read_tsc_page(const struct ms_hyperv_tsc_page *tsc_pg)
+static inline u64 hv_read_tsc_page_tsc(const struct ms_hyperv_tsc_page *tsc_pg,
+				       u64 *cur_tsc)
 {
-	u64 scale, offset, cur_tsc;
+	u64 scale, offset;
 	u32 sequence;
 
 	/*

@@ -358,7 +359,7 @@ static inline u64 hv_read_tsc_page(const struct ms_hyperv_tsc_page *tsc_pg)
 
 		scale = READ_ONCE(tsc_pg->tsc_scale);
 		offset = READ_ONCE(tsc_pg->tsc_offset);
-		cur_tsc = rdtsc_ordered();
+		*cur_tsc = rdtsc_ordered();
 
 		/*
 		 * Make sure we read sequence after we read all other values

@@ -368,7 +369,14 @@ static inline u64 hv_read_tsc_page(const struct ms_hyperv_tsc_page *tsc_pg)
 
 	} while (READ_ONCE(tsc_pg->tsc_sequence) != sequence);
 
-	return mul_u64_u64_shr(cur_tsc, scale, 64) + offset;
+	return mul_u64_u64_shr(*cur_tsc, scale, 64) + offset;
+}
+
+static inline u64 hv_read_tsc_page(const struct ms_hyperv_tsc_page *tsc_pg)
+{
+	u64 cur_tsc;
+
+	return hv_read_tsc_page_tsc(tsc_pg, &cur_tsc);
 }
 
 #else

@@ -376,5 +384,12 @@ static inline struct ms_hyperv_tsc_page *hv_get_tsc_page(void)
 {
 	return NULL;
 }
+
+static inline u64 hv_read_tsc_page_tsc(const struct ms_hyperv_tsc_page *tsc_pg,
+				       u64 *cur_tsc)
+{
+	BUG();
+	return U64_MAX;
+}
 #endif
 #endif

101 lines not on this page · raw message

index 67421f649cfa..e71c1120426b 100644
@@ -103,7 +103,12 @@
 #endif
 
 #define MANAGED_IRQ_SHUTDOWN_VECTOR	0xef
-#define LOCAL_TIMER_VECTOR		0xee
+
+#if IS_ENABLED(CONFIG_HYPERV)
+#define HYPERV_REENLIGHTENMENT_VECTOR	0xee
+#endif
+
+#define LOCAL_TIMER_VECTOR		0xed
 
 #define NR_VECTORS			 256
 

index 6b1d4ea78270..1790002a2052 100644
@@ -160,6 +160,7 @@ static inline void vmbus_signal_eom(struct hv_message *msg, u32 old_msg_type)
 #define hv_set_synint_state(int_num, val) wrmsrl(int_num, val)
 
 void hyperv_callback_vector(void);
+void hyperv_reenlightenment_vector(void);
 #ifdef CONFIG_TRACING
 #define trace_hyperv_callback_vector hyperv_callback_vector
 #endif

@@ -316,11 +317,19 @@ void hyper_alloc_mmu(void);
 void hyperv_report_panic(struct pt_regs *regs, long err);
 bool hv_is_hypercall_page_setup(void);
 void hyperv_cleanup(void);
+
+void hyperv_reenlightenment_intr(struct pt_regs *regs);
+void set_hv_tscchange_cb(void (*cb)(void));
+void clear_hv_tscchange_cb(void);
+void hyperv_stop_tsc_emulation(void);
 #else /* CONFIG_HYPERV */
 static inline void hyperv_init(void) {}
 static inline bool hv_is_hypercall_page_setup(void) { return false; }
 static inline void hyperv_cleanup(void) {}
 static inline void hyperv_setup_mmu_ops(void) {}
+static inline void set_hv_tscchange_cb(void (*cb)(void)) {}
+static inline void clear_hv_tscchange_cb(void) {}
+static inline void hyperv_stop_tsc_emulation(void) {};
 #endif /* CONFIG_HYPERV */
 
 #ifdef CONFIG_HYPERV_TSCPAGE

index 1a5bfead93b4..197c2e6c7376 100644
@@ -40,6 +40,9 @@
  */
 #define HV_X64_ACCESS_FREQUENCY_MSRS		(1 << 11)
 
+/* AccessReenlightenmentControls privilege */
+#define HV_X64_ACCESS_REENLIGHTENMENT		BIT(13)
+
 /*
  * Basic SynIC MSRs (HV_X64_MSR_SCONTROL through HV_X64_MSR_EOM
  * and HV_X64_MSR_SINT0 through HV_X64_MSR_SINT15) available

@@ -234,6 +237,30 @@
 #define HV_X64_MSR_CRASH_PARAMS		\
 		(1 + (HV_X64_MSR_CRASH_P4 - HV_X64_MSR_CRASH_P0))
 
+/* TSC emulation after migration */
+#define HV_X64_MSR_REENLIGHTENMENT_CONTROL	0x40000106
+
+struct hv_reenlightenment_control {
+	u64 vector:8;
+	u64 reserved1:8;
+	u64 enabled:1;
+	u64 reserved2:15;
+	u64 target_vp:32;
+};
+
+#define HV_X64_MSR_TSC_EMULATION_CONTROL	0x40000107
+#define HV_X64_MSR_TSC_EMULATION_STATUS		0x40000108
+
+struct hv_tsc_emulation_control {
+	u64 enabled:1;
+	u64 reserved:63;
+};
+
+struct hv_tsc_emulation_status {
+	u64 inprogress:1;
+	u64 reserved:63;
+};
+
 #define HV_X64_MSR_HYPERCALL_ENABLE		0x00000001
 #define HV_X64_MSR_HYPERCALL_PAGE_ADDRESS_SHIFT	12
 #define HV_X64_MSR_HYPERCALL_PAGE_ADDRESS_MASK	\

index 85eb5fc180c8..9340f41ce8d3 100644
@@ -251,6 +251,12 @@ static void __init ms_hyperv_init_platform(void)
 	hyperv_setup_mmu_ops();
 	/* Setup the IDT for hypervisor callback */
 	alloc_intr_gate(HYPERVISOR_CALLBACK_VECTOR, hyperv_callback_vector);
+
+	/* Setup the IDT for reenlightenment notifications */
+	if (ms_hyperv.features & HV_X64_ACCESS_REENLIGHTENMENT)
+		alloc_intr_gate(HYPERV_REENLIGHTENMENT_VECTOR,
+				hyperv_reenlightenment_vector);
+
 #endif
 }
 

index 712ac40081f7..e4377e2f2a10 100644
@@ -191,6 +191,26 @@ void clear_hv_tscchange_cb(void)
 }
 EXPORT_SYMBOL_GPL(clear_hv_tscchange_cb);
 
+static int hv_cpu_die(unsigned int cpu)
+{
+	struct hv_reenlightenment_control re_ctrl;
+	unsigned int new_cpu;
+
+	if (hv_reenlightenment_cb == NULL)
+		return 0;
+
+	rdmsrl(HV_X64_MSR_REENLIGHTENMENT_CONTROL, *((u64 *)&re_ctrl));
+	if (re_ctrl.target_vp == hv_vp_index[cpu]) {
+		/* Reassign to some other online CPU */
+		new_cpu = cpumask_any_but(cpu_online_mask, cpu);
+
+		re_ctrl.target_vp = hv_vp_index[new_cpu];
+		wrmsrl(HV_X64_MSR_REENLIGHTENMENT_CONTROL, *((u64 *)&re_ctrl));
+	}
+
+	return 0;
+}
+
 /*
  * This function is to be invoked early in the boot sequence after the
  * hypervisor has been detected.

@@ -220,7 +240,7 @@ void hyperv_init(void)
 		return;
 
 	if (cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "x86/hyperv_init:online",
-			      hv_cpu_init, NULL) < 0)
+			      hv_cpu_init, hv_cpu_die) < 0)
 		goto free_vp_index;
 
 	/*

index e4377e2f2a10..a3adece392f1 100644
@@ -147,6 +147,8 @@ __visible void __irq_entry hyperv_reenlightenment_intr(struct pt_regs *regs)
 {
 	entering_ack_irq();
 
+	inc_irq_stat(irq_hv_reenlightenment_count);
+
 	schedule_delayed_work(&hv_reenlightenment_work, HZ/10);
 
 	exiting_irq();

index 51cc979dd364..7c341a74ec8c 100644
@@ -38,6 +38,9 @@ typedef struct {
 #if IS_ENABLED(CONFIG_HYPERV) || defined(CONFIG_XEN)
 	unsigned int irq_hv_callback_count;
 #endif
+#if IS_ENABLED(CONFIG_HYPERV)
+	unsigned int irq_hv_reenlightenment_count;
+#endif
 } ____cacheline_aligned irq_cpustat_t;
 
 DECLARE_PER_CPU_SHARED_ALIGNED(irq_cpustat_t, irq_stat);

index 68e1867cca80..45fb4d2565f8 100644
@@ -141,6 +141,15 @@ int arch_show_interrupts(struct seq_file *p, int prec)
 				   irq_stats(j)->irq_hv_callback_count);
 		seq_puts(p, "  Hypervisor callback interrupts\n");
 	}
+#endif
+#if IS_ENABLED(CONFIG_HYPERV)
+	if (test_bit(HYPERV_REENLIGHTENMENT_VECTOR, system_vectors)) {
+		seq_printf(p, "%*s: ", prec, "HRE");
+		for_each_online_cpu(j)
+			seq_printf(p, "%10u ",
+				   irq_stats(j)->irq_hv_reenlightenment_count);
+		seq_puts(p, "  Hyper-V reenlightenment interrupts\n");
+	}
 #endif
 	seq_printf(p, "%*s: %10u\n", prec, "ERR", atomic_read(&irq_err_count));
 #if defined(CONFIG_X86_IO_APIC)

index c53298dfbf50..b1ce368a07af 100644
@@ -67,6 +67,7 @@
 #include <asm/pvclock.h>
 #include <asm/div64.h>
 #include <asm/irq_remapping.h>
+#include <asm/mshyperv.h>
 
 #define CREATE_TRACE_POINTS
 #include "trace.h"

@@ -1377,6 +1378,11 @@ static u64 compute_guest_tsc(struct kvm_vcpu *vcpu, s64 kernel_ns)
 	return tsc;
 }
 
+static inline int gtod_is_based_on_tsc(int mode)
+{
+	return mode == VCLOCK_TSC || mode == VCLOCK_HVCLOCK;
+}
+
 static void kvm_track_tsc_matching(struct kvm_vcpu *vcpu)
 {
 #ifdef CONFIG_X86_64

@@ -1396,7 +1402,7 @@ static void kvm_track_tsc_matching(struct kvm_vcpu *vcpu)
 	 * perform request to enable masterclock.
 	 */
 	if (ka->use_master_clock ||
-	    (gtod->clock.vclock_mode == VCLOCK_TSC && vcpus_matched))
+	    (gtod_is_based_on_tsc(gtod->clock.vclock_mode) && vcpus_matched))
 		kvm_make_request(KVM_REQ_MASTERCLOCK_UPDATE, vcpu);
 
 	trace_kvm_track_tsc(vcpu->vcpu_id, ka->nr_vcpus_matched_tsc,

@@ -1459,6 +1465,19 @@ static void kvm_vcpu_write_tsc_offset(struct kvm_vcpu *vcpu, u64 offset)
 	vcpu->arch.tsc_offset = offset;
 }
 
+static inline bool kvm_check_tsc_unstable(void)
+{
+#ifdef CONFIG_X86_64
+	/*
+	 * TSC is marked unstable when we're running on Hyper-V,
+	 * 'TSC page' clocksource is good.
+	 */
+	if (pvclock_gtod_data.clock.vclock_mode == VCLOCK_HVCLOCK)
+		return false;
+#endif
+	return check_tsc_unstable();
+}
+
 void kvm_write_tsc(struct kvm_vcpu *vcpu, struct msr_data *msr)
 {
 	struct kvm *kvm = vcpu->kvm;

@@ -1504,7 +1523,7 @@ void kvm_write_tsc(struct kvm_vcpu *vcpu, struct msr_data *msr)
          */
 	if (synchronizing &&
 	    vcpu->arch.virtual_tsc_khz == kvm->arch.last_tsc_khz) {
-		if (!check_tsc_unstable()) {
+		if (!kvm_check_tsc_unstable()) {
 			offset = kvm->arch.cur_tsc_offset;
 			pr_debug("kvm: matched tsc offset for %llu\n", data);
 		} else {

@@ -1604,18 +1623,43 @@ static u64 read_tsc(void)
 	return last;
 }
 
-static inline u64 vgettsc(u64 *cycle_now)
+static inline u64 vgettsc(u64 *tsc_timestamp, int *mode)
 {
 	long v;
 	struct pvclock_gtod_data *gtod = &pvclock_gtod_data;
+	u64 tsc_pg_val;
+
+	switch (gtod->clock.vclock_mode) {
+	case VCLOCK_HVCLOCK:
+		tsc_pg_val = hv_read_tsc_page_tsc(hv_get_tsc_page(),
+						  tsc_timestamp);
+		if (tsc_pg_val != U64_MAX) {
+			/* TSC page valid */
+			*mode = VCLOCK_HVCLOCK;
+			v = (tsc_pg_val - gtod->clock.cycle_last) &
+				gtod->clock.mask;
+		} else {
+			/* TSC page invalid */
+			*mode = VCLOCK_NONE;
+		}
+		break;
+	case VCLOCK_TSC:
+		*mode = VCLOCK_TSC;
+		*tsc_timestamp = read_tsc();
+		v = (*tsc_timestamp - gtod->clock.cycle_last) &
+			gtod->clock.mask;
+		break;
+	default:
+		*mode = VCLOCK_NONE;
+	}
 
-	*cycle_now = read_tsc();
+	if (*mode == VCLOCK_NONE)
+		*tsc_timestamp = v = 0;
 
-	v = (*cycle_now - gtod->clock.cycle_last) & gtod->clock.mask;
 	return v * gtod->clock.mult;
 }
 
-static int do_monotonic_boot(s64 *t, u64 *cycle_now)
+static int do_monotonic_boot(s64 *t, u64 *tsc_timestamp)
 {
 	struct pvclock_gtod_data *gtod = &pvclock_gtod_data;
 	unsigned long seq;

@@ -1624,9 +1668,8 @@ static int do_monotonic_boot(s64 *t, u64 *cycle_now)
 
 	do {
 		seq = read_seqcount_begin(&gtod->seq);
-		mode = gtod->clock.vclock_mode;
 		ns = gtod->nsec_base;
-		ns += vgettsc(cycle_now);
+		ns += vgettsc(tsc_timestamp, &mode);
 		ns >>= gtod->clock.shift;
 		ns += gtod->boot_ns;
 	} while (unlikely(read_seqcount_retry(&gtod->seq, seq)));

@@ -1635,7 +1678,7 @@ static int do_monotonic_boot(s64 *t, u64 *cycle_now)
 	return mode;
 }
 
-static int do_realtime(struct timespec *ts, u64 *cycle_now)
+static int do_realtime(struct timespec *ts, u64 *tsc_timestamp)
 {
 	struct pvclock_gtod_data *gtod = &pvclock_gtod_data;
 	unsigned long seq;

@@ -1644,10 +1687,9 @@ static int do_realtime(struct timespec *ts, u64 *cycle_now)
 
 	do {
 		seq = read_seqcount_begin(&gtod->seq);
-		mode = gtod->clock.vclock_mode;
 		ts->tv_sec = gtod->wall_time_sec;
 		ns = gtod->nsec_base;
-		ns += vgettsc(cycle_now);
+		ns += vgettsc(tsc_timestamp, &mode);
 		ns >>= gtod->clock.shift;
 	} while (unlikely(read_seqcount_retry(&gtod->seq, seq)));
 

@@ -1657,25 +1699,26 @@ static int do_realtime(struct timespec *ts, u64 *cycle_now)
 	return mode;
 }
 
-/* returns true if host is using tsc clocksource */
-static bool kvm_get_time_and_clockread(s64 *kernel_ns, u64 *cycle_now)
+/* returns true if host is using TSC based clocksource */
+static bool kvm_get_time_and_clockread(s64 *kernel_ns, u64 *tsc_timestamp)
 {
 	/* checked again under seqlock below */
-	if (pvclock_gtod_data.clock.vclock_mode != VCLOCK_TSC)
+	if (!gtod_is_based_on_tsc(pvclock_gtod_data.clock.vclock_mode))
 		return false;
 
-	return do_monotonic_boot(kernel_ns, cycle_now) == VCLOCK_TSC;
+	return gtod_is_based_on_tsc(do_monotonic_boot(kernel_ns,
+						      tsc_timestamp));
 }
 
-/* returns true if host is using tsc clocksource */
+/* returns true if host is using TSC based clocksource */
 static bool kvm_get_walltime_and_clockread(struct timespec *ts,
-					   u64 *cycle_now)
+					   u64 *tsc_timestamp)
 {
 	/* checked again under seqlock below */
-	if (pvclock_gtod_data.clock.vclock_mode != VCLOCK_TSC)
+	if (!gtod_is_based_on_tsc(pvclock_gtod_data.clock.vclock_mode))
 		return false;
 
-	return do_realtime(ts, cycle_now) == VCLOCK_TSC;
+	return gtod_is_based_on_tsc(do_realtime(ts, tsc_timestamp));
 }
 #endif
 

@@ -2869,13 +2912,13 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 		kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu);
 	}
 
-	if (unlikely(vcpu->cpu != cpu) || check_tsc_unstable()) {
+	if (unlikely(vcpu->cpu != cpu) || kvm_check_tsc_unstable()) {
 		s64 tsc_delta = !vcpu->arch.last_host_tsc ? 0 :
 				rdtsc() - vcpu->arch.last_host_tsc;
 		if (tsc_delta < 0)
 			mark_tsc_unstable("KVM discovered backwards TSC");
 
-		if (check_tsc_unstable()) {
+		if (kvm_check_tsc_unstable()) {
 			u64 offset = kvm_compute_tsc_offset(vcpu,
 						vcpu->arch.last_guest_tsc);
 			kvm_vcpu_write_tsc_offset(vcpu, offset);

@@ -6110,9 +6153,9 @@ static int pvclock_gtod_notify(struct notifier_block *nb, unsigned long unused,
 	update_pvclock_gtod(tk);
 
 	/* disable master clock if host does not trust, or does not
-	 * use, TSC clocksource
+	 * use, TSC based clocksource.
 	 */
-	if (gtod->clock.vclock_mode != VCLOCK_TSC &&
+	if (!gtod_is_based_on_tsc(gtod->clock.vclock_mode) &&
 	    atomic_read(&kvm_guest_has_master_clock) != 0)
 		queue_work(system_long_wq, &pvclock_gtod_work);
 

@@ -7767,7 +7810,7 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm,
 {
 	struct kvm_vcpu *vcpu;
 
-	if (check_tsc_unstable() && atomic_read(&kvm->online_vcpus) != 0)
+	if (kvm_check_tsc_unstable() && atomic_read(&kvm->online_vcpus) != 0)
 		printk_once(KERN_WARNING
 		"kvm: SMP vm created on host with unstable TSC; "
 		"guest TSC will not be reliable\n");

@@ -7924,7 +7967,7 @@ int kvm_arch_hardware_enable(void)
 		return ret;
 
 	local_tsc = rdtsc();
-	stable = !check_tsc_unstable();
+	stable = !kvm_check_tsc_unstable();
 	list_for_each_entry(kvm, &vm_list, vm_list) {
 		kvm_for_each_vcpu(i, vcpu, kvm) {
 			if (!stable && vcpu->cpu == smp_processor_id())

index b1ce368a07af..879a99987401 100644
@@ -68,6 +68,7 @@
 #include <asm/div64.h>
 #include <asm/irq_remapping.h>
 #include <asm/mshyperv.h>
+#include <asm/hypervisor.h>
 
 #define CREATE_TRACE_POINTS
 #include "trace.h"

@@ -5932,6 +5933,43 @@ static void tsc_khz_changed(void *data)
 	__this_cpu_write(cpu_tsc_khz, khz);
 }
 
+static void kvm_hyperv_tsc_notifier(void)
+{
+#ifdef CONFIG_X86_64
+	struct kvm *kvm;
+	struct kvm_vcpu *vcpu;
+	int cpu;
+
+	spin_lock(&kvm_lock);
+	list_for_each_entry(kvm, &vm_list, vm_list)
+		kvm_make_mclock_inprogress_request(kvm);
+
+	hyperv_stop_tsc_emulation();
+
+	/* TSC frequency always matches when on Hyper-V */
+	for_each_present_cpu(cpu)
+		per_cpu(cpu_tsc_khz, cpu) = tsc_khz;
+	kvm_max_guest_tsc_khz = tsc_khz;
+
+	list_for_each_entry(kvm, &vm_list, vm_list) {
+		struct kvm_arch *ka = &kvm->arch;
+
+		spin_lock(&ka->pvclock_gtod_sync_lock);
+
+		pvclock_update_vm_gtod_copy(kvm);
+
+		kvm_for_each_vcpu(cpu, vcpu, kvm)
+			kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu);
+
+		kvm_for_each_vcpu(cpu, vcpu, kvm)
+			kvm_clear_request(KVM_REQ_MCLOCK_INPROGRESS, vcpu);
+
+		spin_unlock(&ka->pvclock_gtod_sync_lock);
+	}
+	spin_unlock(&kvm_lock);
+#endif
+}
+
 static int kvmclock_cpufreq_notifier(struct notifier_block *nb, unsigned long val,
 				     void *data)
 {

@@ -6217,6 +6255,9 @@ int kvm_arch_init(void *opaque)
 	kvm_lapic_init();
 #ifdef CONFIG_X86_64
 	pvclock_gtod_register_notifier(&pvclock_gtod_notifier);
+
+	if (x86_hyper_type == X86_HYPER_MS_HYPERV)
+		set_hv_tscchange_cb(kvm_hyperv_tsc_notifier);
 #endif
 
 	return 0;

@@ -6229,6 +6270,10 @@ int kvm_arch_init(void *opaque)
 
 void kvm_arch_exit(void)
 {
+#ifdef CONFIG_X86_64
+	if (x86_hyper_type == X86_HYPER_MS_HYPERV)
+		clear_hv_tscchange_cb();
+#endif
 	kvm_lapic_exit();
 	perf_unregister_guest_info_callbacks(&kvm_guest_cbs);