Merge branch 'x86-hyperv-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 hyperv updates from Ingo Molnar:
 "Misc updates to the hyperv guest code:

   - Rework clockevents initialization to better support hibernation

   - Allow guests to enable InvariantTSC

   - Micro-optimize send_ipi_one"

* 'x86-hyperv-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/hyperv: Initialize clockevents earlier in CPU onlining
  x86/hyperv: Allow guests to enable InvariantTSC
  x86/hyperv: Micro-optimize send_ipi_one()

arch/x86/hyperv/hv_apic.c

@@ -194,10 +194,20 @@ static bool __send_ipi_mask(const struct cpumask *mask, int vector)
 
 static bool __send_ipi_one(int cpu, int vector)
 {
-	struct cpumask mask = CPU_MASK_NONE;
+	int vp = hv_cpu_number_to_vp_number(cpu);
 
-	cpumask_set_cpu(cpu, &mask);
-	return __send_ipi_mask(&mask, vector);
+	trace_hyperv_send_ipi_one(cpu, vector);
+
+	if (!hv_hypercall_pg || (vp == VP_INVAL))
+		return false;
+
+	if ((vector < HV_IPI_LOW_VECTOR) || (vector > HV_IPI_HIGH_VECTOR))
+		return false;
+
+	if (vp >= 64)
+		return __send_ipi_mask_ex(cpumask_of(cpu), vector);
+
+	return !hv_do_fast_hypercall16(HVCALL_SEND_IPI, vector, BIT_ULL(vp));
 }
 
 static void hv_send_ipi(int cpu, int vector)

arch/x86/hyperv/hv_init.c

@@ -311,6 +311,12 @@ void __init hyperv_init(void)
 	hypercall_msr.guest_physical_address = vmalloc_to_pfn(hv_hypercall_pg);
 	wrmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64);
 
+	/*
+	 * Ignore any errors in setting up stimer clockevents
+	 * as we can run with the LAPIC timer as a fallback.
+	 */
+	(void)hv_stimer_alloc();
+
 	hv_apic_init();
 
 	x86_init.pci.arch_init = hv_pci_init;

arch/x86/include/asm/hyperv-tlfs.h

@@ -86,6 +86,8 @@
 #define HV_X64_ACCESS_FREQUENCY_MSRS		BIT(11)
 /* AccessReenlightenmentControls privilege */
 #define HV_X64_ACCESS_REENLIGHTENMENT		BIT(13)
+/* AccessTscInvariantControls privilege */
+#define HV_X64_ACCESS_TSC_INVARIANT		BIT(15)
 
 /*
  * Feature identification: indicates which flags were specified at partition
@@ -278,6 +280,9 @@
 #define HV_X64_MSR_TSC_EMULATION_CONTROL	0x40000107
 #define HV_X64_MSR_TSC_EMULATION_STATUS		0x40000108
 
+/* TSC invariant control */
+#define HV_X64_MSR_TSC_INVARIANT_CONTROL	0x40000118
+
 /*
  * Declare the MSR used to setup pages used to communicate with the hypervisor.
  */

arch/x86/include/asm/trace/hyperv.h

@@ -71,6 +71,21 @@ TRACE_EVENT(hyperv_send_ipi_mask,
 		      __entry->ncpus, __entry->vector)
 	);
 
+TRACE_EVENT(hyperv_send_ipi_one,
+	    TP_PROTO(int cpu,
+		     int vector),
+	    TP_ARGS(cpu, vector),
+	    TP_STRUCT__entry(
+		    __field(int, cpu)
+		    __field(int, vector)
+		    ),
+	    TP_fast_assign(__entry->cpu = cpu;
+			   __entry->vector = vector;
+		    ),
+	    TP_printk("cpu %d vector %x",
+		      __entry->cpu, __entry->vector)
+	);
+
 #endif /* CONFIG_HYPERV */
 
 #undef TRACE_INCLUDE_PATH

arch/x86/kernel/cpu/mshyperv.c

@@ -290,7 +290,12 @@ static void __init ms_hyperv_init_platform(void)
 	machine_ops.shutdown = hv_machine_shutdown;
 	machine_ops.crash_shutdown = hv_machine_crash_shutdown;
 #endif
-	mark_tsc_unstable("running on Hyper-V");
+	if (ms_hyperv.features & HV_X64_ACCESS_TSC_INVARIANT) {
+		wrmsrl(HV_X64_MSR_TSC_INVARIANT_CONTROL, 0x1);
+		setup_force_cpu_cap(X86_FEATURE_TSC_RELIABLE);
+	} else {
+		mark_tsc_unstable("running on Hyper-V");
+	}
 
 	/*
 	 * Generation 2 instances don't support reading the NMI status from

drivers/clocksource/hyperv_timer.c

@@ -17,6 +17,7 @@
 #include <linux/clocksource.h>
 #include <linux/sched_clock.h>
 #include <linux/mm.h>
+#include <linux/cpuhotplug.h>
 #include <clocksource/hyperv_timer.h>
 #include <asm/hyperv-tlfs.h>
 #include <asm/mshyperv.h>
@@ -30,6 +31,15 @@ static u64 hv_sched_clock_offset __ro_after_init;
  * mechanism is used when running on older versions of Hyper-V
  * that don't support Direct Mode. While Hyper-V provides
  * four stimer's per CPU, Linux uses only stimer0.
+ *
+ * Because Direct Mode does not require processing a VMbus
+ * message, stimer interrupts can be enabled earlier in the
+ * process of booting a CPU, and consistent with when timer
+ * interrupts are enabled for other clocksource drivers.
+ * However, for legacy versions of Hyper-V when Direct Mode
+ * is not enabled, setting up stimer interrupts must be
+ * delayed until VMbus is initialized and can process the
+ * interrupt message.
  */
 static bool direct_mode_enabled;
 
@@ -102,17 +112,12 @@ static int hv_ce_set_oneshot(struct clock_event_device *evt)
 /*
  * hv_stimer_init - Per-cpu initialization of the clockevent
  */
-void hv_stimer_init(unsigned int cpu)
+static int hv_stimer_init(unsigned int cpu)
 {
 	struct clock_event_device *ce;
 
-	/*
-	 * Synthetic timers are always available except on old versions of
-	 * Hyper-V on x86.  In that case, just return as Linux will use a
-	 * clocksource based on emulated PIT or LAPIC timer hardware.
-	 */
-	if (!(ms_hyperv.features & HV_MSR_SYNTIMER_AVAILABLE))
-		return;
+	if (!hv_clock_event)
+		return 0;
 
 	ce = per_cpu_ptr(hv_clock_event, cpu);
 	ce->name = "Hyper-V clockevent";
@@ -127,28 +132,55 @@ void hv_stimer_init(unsigned int cpu)
 					HV_CLOCK_HZ,
 					HV_MIN_DELTA_TICKS,
 					HV_MAX_MAX_DELTA_TICKS);
+	return 0;
 }
-EXPORT_SYMBOL_GPL(hv_stimer_init);
 
 /*
  * hv_stimer_cleanup - Per-cpu cleanup of the clockevent
  */
-void hv_stimer_cleanup(unsigned int cpu)
+int hv_stimer_cleanup(unsigned int cpu)
 {
 	struct clock_event_device *ce;
 
-	/* Turn off clockevent device */
-	if (ms_hyperv.features & HV_MSR_SYNTIMER_AVAILABLE) {
-		ce = per_cpu_ptr(hv_clock_event, cpu);
+	if (!hv_clock_event)
+		return 0;
+
+	/*
+	 * In the legacy case where Direct Mode is not enabled
+	 * (which can only be on x86/64), stimer cleanup happens
+	 * relatively early in the CPU offlining process. We
+	 * must unbind the stimer-based clockevent device so
+	 * that the LAPIC timer can take over until clockevents
+	 * are no longer needed in the offlining process. Note
+	 * that clockevents_unbind_device() eventually calls
+	 * hv_ce_shutdown().
+	 *
+	 * The unbind should not be done when Direct Mode is
+	 * enabled because we may be on an architecture where
+	 * there are no other clockevent devices to fallback to.
+	 */
+	ce = per_cpu_ptr(hv_clock_event, cpu);
+	if (direct_mode_enabled)
 		hv_ce_shutdown(ce);
-	}
+	else
+		clockevents_unbind_device(ce, cpu);
+
+	return 0;
 }
 EXPORT_SYMBOL_GPL(hv_stimer_cleanup);
 
 /* hv_stimer_alloc - Global initialization of the clockevent and stimer0 */
-int hv_stimer_alloc(int sint)
+int hv_stimer_alloc(void)
 {
-	int ret;
+	int ret = 0;
+
+	/*
+	 * Synthetic timers are always available except on old versions of
+	 * Hyper-V on x86.  In that case, return as error as Linux will use a
+	 * clockevent based on emulated LAPIC timer hardware.
+	 */
+	if (!(ms_hyperv.features & HV_MSR_SYNTIMER_AVAILABLE))
+		return -EINVAL;
 
 	hv_clock_event = alloc_percpu(struct clock_event_device);
 	if (!hv_clock_event)
@@ -159,22 +191,78 @@ int hv_stimer_alloc(int sint)
 	if (direct_mode_enabled) {
 		ret = hv_setup_stimer0_irq(&stimer0_irq, &stimer0_vector,
 				hv_stimer0_isr);
-		if (ret) {
-			free_percpu(hv_clock_event);
-			hv_clock_event = NULL;
-			return ret;
-		}
+		if (ret)
+			goto free_percpu;
+
+		/*
+		 * Since we are in Direct Mode, stimer initialization
+		 * can be done now with a CPUHP value in the same range
+		 * as other clockevent devices.
+		 */
+		ret = cpuhp_setup_state(CPUHP_AP_HYPERV_TIMER_STARTING,
+				"clockevents/hyperv/stimer:starting",
+				hv_stimer_init, hv_stimer_cleanup);
+		if (ret < 0)
+			goto free_stimer0_irq;
 	}
+	return ret;
 
-	stimer0_message_sint = sint;
-	return 0;
+free_stimer0_irq:
+	hv_remove_stimer0_irq(stimer0_irq);
+	stimer0_irq = 0;
+free_percpu:
+	free_percpu(hv_clock_event);
+	hv_clock_event = NULL;
+	return ret;
 }
 EXPORT_SYMBOL_GPL(hv_stimer_alloc);
 
+/*
+ * hv_stimer_legacy_init -- Called from the VMbus driver to handle
+ * the case when Direct Mode is not enabled, and the stimer
+ * must be initialized late in the CPU onlining process.
+ *
+ */
+void hv_stimer_legacy_init(unsigned int cpu, int sint)
+{
+	if (direct_mode_enabled)
+		return;
+
+	/*
+	 * This function gets called by each vCPU, so setting the
+	 * global stimer_message_sint value each time is conceptually
+	 * not ideal, but the value passed in is always the same and
+	 * it avoids introducing yet another interface into this
+	 * clocksource driver just to set the sint in the legacy case.
+	 */
+	stimer0_message_sint = sint;
+	(void)hv_stimer_init(cpu);
+}
+EXPORT_SYMBOL_GPL(hv_stimer_legacy_init);
+
+/*
+ * hv_stimer_legacy_cleanup -- Called from the VMbus driver to
+ * handle the case when Direct Mode is not enabled, and the
+ * stimer must be cleaned up early in the CPU offlining
+ * process.
+ */
+void hv_stimer_legacy_cleanup(unsigned int cpu)
+{
+	if (direct_mode_enabled)
+		return;
+	(void)hv_stimer_cleanup(cpu);
+}
+EXPORT_SYMBOL_GPL(hv_stimer_legacy_cleanup);
+
+
 /* hv_stimer_free - Free global resources allocated by hv_stimer_alloc() */
 void hv_stimer_free(void)
 {
-	if (direct_mode_enabled && (stimer0_irq != 0)) {
+	if (!hv_clock_event)
+		return;
+
+	if (direct_mode_enabled) {
+		cpuhp_remove_state(CPUHP_AP_HYPERV_TIMER_STARTING);
 		hv_remove_stimer0_irq(stimer0_irq);
 		stimer0_irq = 0;
 	}
@@ -190,14 +278,20 @@ EXPORT_SYMBOL_GPL(hv_stimer_free);
 void hv_stimer_global_cleanup(void)
 {
 	int	cpu;
-	struct clock_event_device *ce;
 
-	if (ms_hyperv.features & HV_MSR_SYNTIMER_AVAILABLE) {
-		for_each_present_cpu(cpu) {
-			ce = per_cpu_ptr(hv_clock_event, cpu);
-			clockevents_unbind_device(ce, cpu);
-		}
+	/*
+	 * hv_stime_legacy_cleanup() will stop the stimer if Direct
+	 * Mode is not enabled, and fallback to the LAPIC timer.
+	 */
+	for_each_present_cpu(cpu) {
+		hv_stimer_legacy_cleanup(cpu);
 	}
+
+	/*
+	 * If Direct Mode is enabled, the cpuhp teardown callback
+	 * (hv_stimer_cleanup) will be run on all CPUs to stop the
+	 * stimers.
+	 */
 	hv_stimer_free();
 }
 EXPORT_SYMBOL_GPL(hv_stimer_global_cleanup);

drivers/hv/hv.c

@@ -202,7 +202,7 @@ int hv_synic_init(unsigned int cpu)
 {
 	hv_synic_enable_regs(cpu);
 
-	hv_stimer_init(cpu);
+	hv_stimer_legacy_init(cpu, VMBUS_MESSAGE_SINT);
 
 	return 0;
 }
@@ -277,7 +277,7 @@ int hv_synic_cleanup(unsigned int cpu)
 	if (channel_found && vmbus_connection.conn_state == CONNECTED)
 		return -EBUSY;
 
-	hv_stimer_cleanup(cpu);
+	hv_stimer_legacy_cleanup(cpu);
 
 	hv_synic_disable_regs(cpu);
 

drivers/hv/vmbus_drv.c

@@ -1340,10 +1340,6 @@ static int vmbus_bus_init(void)
 	if (ret)
 		goto err_alloc;
 
-	ret = hv_stimer_alloc(VMBUS_MESSAGE_SINT);
-	if (ret < 0)
-		goto err_alloc;
-
 	/*
 	 * Initialize the per-cpu interrupt state and stimer state.
 	 * Then connect to the host.
@@ -1400,9 +1396,8 @@ static int vmbus_bus_init(void)
 err_connect:
 	cpuhp_remove_state(hyperv_cpuhp_online);
 err_cpuhp:
-	hv_stimer_free();
-err_alloc:
 	hv_synic_free();
+err_alloc:
 	hv_remove_vmbus_irq();
 
 	bus_unregister(&hv_bus);
@@ -2315,20 +2310,23 @@ static void hv_crash_handler(struct pt_regs *regs)
 static int hv_synic_suspend(void)
 {
 	/*
-	 * When we reach here, all the non-boot CPUs have been offlined, and
-	 * the stimers on them have been unbound in hv_synic_cleanup() ->
+	 * When we reach here, all the non-boot CPUs have been offlined.
+	 * If we're in a legacy configuration where stimer Direct Mode is
+	 * not enabled, the stimers on the non-boot CPUs have been unbound
+	 * in hv_synic_cleanup() -> hv_stimer_legacy_cleanup() ->
 	 * hv_stimer_cleanup() -> clockevents_unbind_device().
 	 *
-	 * hv_synic_suspend() only runs on CPU0 with interrupts disabled. Here
-	 * we do not unbind the stimer on CPU0 because: 1) it's unnecessary
-	 * because the interrupts remain disabled between syscore_suspend()
-	 * and syscore_resume(): see create_image() and resume_target_kernel();
+	 * hv_synic_suspend() only runs on CPU0 with interrupts disabled.
+	 * Here we do not call hv_stimer_legacy_cleanup() on CPU0 because:
+	 * 1) it's unnecessary as interrupts remain disabled between
+	 * syscore_suspend() and syscore_resume(): see create_image() and
+	 * resume_target_kernel()
 	 * 2) the stimer on CPU0 is automatically disabled later by
 	 * syscore_suspend() -> timekeeping_suspend() -> tick_suspend() -> ...
-	 * -> clockevents_shutdown() -> ... -> hv_ce_shutdown(); 3) a warning
-	 * would be triggered if we call clockevents_unbind_device(), which
-	 * may sleep, in an interrupts-disabled context. So, we intentionally
-	 * don't call hv_stimer_cleanup(0) here.
+	 * -> clockevents_shutdown() -> ... -> hv_ce_shutdown()
+	 * 3) a warning would be triggered if we call
+	 * clockevents_unbind_device(), which may sleep, in an
+	 * interrupts-disabled context.
 	 */
 
 	hv_synic_disable_regs(0);

include/clocksource/hyperv_timer.h

@@ -21,10 +21,11 @@
 #define HV_MIN_DELTA_TICKS 1
 
 /* Routines called by the VMbus driver */
-extern int hv_stimer_alloc(int sint);
+extern int hv_stimer_alloc(void);
 extern void hv_stimer_free(void);
-extern void hv_stimer_init(unsigned int cpu);
-extern void hv_stimer_cleanup(unsigned int cpu);
+extern int hv_stimer_cleanup(unsigned int cpu);
+extern void hv_stimer_legacy_init(unsigned int cpu, int sint);
+extern void hv_stimer_legacy_cleanup(unsigned int cpu);
 extern void hv_stimer_global_cleanup(void);
 extern void hv_stimer0_isr(void);
 

include/linux/cpuhotplug.h

@@ -129,6 +129,7 @@ enum cpuhp_state {
 	CPUHP_AP_ARC_TIMER_STARTING,
 	CPUHP_AP_RISCV_TIMER_STARTING,
 	CPUHP_AP_CSKY_TIMER_STARTING,
+	CPUHP_AP_HYPERV_TIMER_STARTING,
 	CPUHP_AP_KVM_STARTING,
 	CPUHP_AP_KVM_ARM_VGIC_INIT_STARTING,
 	CPUHP_AP_KVM_ARM_VGIC_STARTING,