Commit 4df4cb9e authored by Michael Kelley's avatar Michael Kelley Committed by Thomas Gleixner

x86/hyperv: Initialize clockevents earlier in CPU onlining

Hyper-V has historically initialized stimer-based clockevents late in the
process of onlining a CPU because clockevents depend on stimer
interrupts. In the original Hyper-V design, stimer interrupts generate a
VMbus message, so the VMbus machinery must be running first, and VMbus
can't be initialized until relatively late. On x86/64, LAPIC timer based
clockevents are used during early initialization before VMbus and
stimer-based clockevents are ready, and again during CPU offlining after
the stimer clockevents have been shut down.

Unfortunately, this design creates problems when offlining CPUs for
hibernation or other purposes. stimer-based clockevents are shut down
relatively early in the offlining process, so clockevents_unbind_device()
must be used to fallback to the LAPIC-based clockevents for the remainder
of the offlining process.  Furthermore, the late initialization and early
shutdown of stimer-based clockevents doesn't work well on ARM64 since there
is no other timer like the LAPIC to fallback to. So CPU onlining and
offlining doesn't work properly.

Fix this by recognizing that stimer Direct Mode is the normal path for
newer versions of Hyper-V on x86/64, and the only path on other
architectures. With stimer Direct Mode, stimer interrupts don't require any
VMbus machinery. stimer clockevents can be initialized and shut down
consistent with how it is done for other clockevent devices. While the old
VMbus-based stimer interrupts must still be supported for backward
compatibility on x86, that mode of operation can be treated as legacy.

So add a new Hyper-V stimer entry in the CPU hotplug state list, and use
that new state when in Direct Mode. Update the Hyper-V clocksource driver
to allocate and initialize stimer clockevents earlier during boot. Update
Hyper-V initialization and the VMbus driver to use this new design. As a
result, the LAPIC timer is no longer used during boot or CPU
onlining/offlining and clockevents_unbind_device() is not called.  But
retain the old design as a legacy implementation for older versions of
Hyper-V that don't support Direct Mode.
Signed-off-by: default avatarMichael Kelley <mikelley@microsoft.com>
Signed-off-by: default avatarThomas Gleixner <tglx@linutronix.de>
Tested-by: default avatarDexuan Cui <decui@microsoft.com>
Reviewed-by: default avatarDexuan Cui <decui@microsoft.com>
Link: https://lkml.kernel.org/r/1573607467-9456-1-git-send-email-mikelley@microsoft.com
parent ac94be49
...@@ -311,6 +311,12 @@ void __init hyperv_init(void) ...@@ -311,6 +311,12 @@ void __init hyperv_init(void)
hypercall_msr.guest_physical_address = vmalloc_to_pfn(hv_hypercall_pg); hypercall_msr.guest_physical_address = vmalloc_to_pfn(hv_hypercall_pg);
wrmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64); 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(); hv_apic_init();
x86_init.pci.arch_init = hv_pci_init; x86_init.pci.arch_init = hv_pci_init;
......
...@@ -17,6 +17,7 @@ ...@@ -17,6 +17,7 @@
#include <linux/clocksource.h> #include <linux/clocksource.h>
#include <linux/sched_clock.h> #include <linux/sched_clock.h>
#include <linux/mm.h> #include <linux/mm.h>
#include <linux/cpuhotplug.h>
#include <clocksource/hyperv_timer.h> #include <clocksource/hyperv_timer.h>
#include <asm/hyperv-tlfs.h> #include <asm/hyperv-tlfs.h>
#include <asm/mshyperv.h> #include <asm/mshyperv.h>
...@@ -30,6 +31,15 @@ static u64 hv_sched_clock_offset __ro_after_init; ...@@ -30,6 +31,15 @@ static u64 hv_sched_clock_offset __ro_after_init;
* mechanism is used when running on older versions of Hyper-V * mechanism is used when running on older versions of Hyper-V
* that don't support Direct Mode. While Hyper-V provides * that don't support Direct Mode. While Hyper-V provides
* four stimer's per CPU, Linux uses only stimer0. * 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; static bool direct_mode_enabled;
...@@ -102,17 +112,12 @@ static int hv_ce_set_oneshot(struct clock_event_device *evt) ...@@ -102,17 +112,12 @@ static int hv_ce_set_oneshot(struct clock_event_device *evt)
/* /*
* hv_stimer_init - Per-cpu initialization of the clockevent * 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; struct clock_event_device *ce;
/* if (!hv_clock_event)
* Synthetic timers are always available except on old versions of return 0;
* 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;
ce = per_cpu_ptr(hv_clock_event, cpu); ce = per_cpu_ptr(hv_clock_event, cpu);
ce->name = "Hyper-V clockevent"; ce->name = "Hyper-V clockevent";
...@@ -127,28 +132,55 @@ void hv_stimer_init(unsigned int cpu) ...@@ -127,28 +132,55 @@ void hv_stimer_init(unsigned int cpu)
HV_CLOCK_HZ, HV_CLOCK_HZ,
HV_MIN_DELTA_TICKS, HV_MIN_DELTA_TICKS,
HV_MAX_MAX_DELTA_TICKS); HV_MAX_MAX_DELTA_TICKS);
return 0;
} }
EXPORT_SYMBOL_GPL(hv_stimer_init);
/* /*
* hv_stimer_cleanup - Per-cpu cleanup of the clockevent * 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; struct clock_event_device *ce;
/* Turn off clockevent device */ if (!hv_clock_event)
if (ms_hyperv.features & HV_MSR_SYNTIMER_AVAILABLE) { return 0;
ce = per_cpu_ptr(hv_clock_event, cpu);
/*
* 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); hv_ce_shutdown(ce);
} else
clockevents_unbind_device(ce, cpu);
return 0;
} }
EXPORT_SYMBOL_GPL(hv_stimer_cleanup); EXPORT_SYMBOL_GPL(hv_stimer_cleanup);
/* hv_stimer_alloc - Global initialization of the clockevent and stimer0 */ /* 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); hv_clock_event = alloc_percpu(struct clock_event_device);
if (!hv_clock_event) if (!hv_clock_event)
...@@ -159,22 +191,78 @@ int hv_stimer_alloc(int sint) ...@@ -159,22 +191,78 @@ int hv_stimer_alloc(int sint)
if (direct_mode_enabled) { if (direct_mode_enabled) {
ret = hv_setup_stimer0_irq(&stimer0_irq, &stimer0_vector, ret = hv_setup_stimer0_irq(&stimer0_irq, &stimer0_vector,
hv_stimer0_isr); hv_stimer0_isr);
if (ret) { if (ret)
free_percpu(hv_clock_event); goto free_percpu;
hv_clock_event = NULL;
return ret; /*
} * 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; free_stimer0_irq:
return 0; 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); 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() */ /* hv_stimer_free - Free global resources allocated by hv_stimer_alloc() */
void hv_stimer_free(void) 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); hv_remove_stimer0_irq(stimer0_irq);
stimer0_irq = 0; stimer0_irq = 0;
} }
...@@ -190,14 +278,20 @@ EXPORT_SYMBOL_GPL(hv_stimer_free); ...@@ -190,14 +278,20 @@ EXPORT_SYMBOL_GPL(hv_stimer_free);
void hv_stimer_global_cleanup(void) void hv_stimer_global_cleanup(void)
{ {
int cpu; int cpu;
struct clock_event_device *ce;
if (ms_hyperv.features & HV_MSR_SYNTIMER_AVAILABLE) { /*
for_each_present_cpu(cpu) { * hv_stime_legacy_cleanup() will stop the stimer if Direct
ce = per_cpu_ptr(hv_clock_event, cpu); * Mode is not enabled, and fallback to the LAPIC timer.
clockevents_unbind_device(ce, cpu); */
} 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(); hv_stimer_free();
} }
EXPORT_SYMBOL_GPL(hv_stimer_global_cleanup); EXPORT_SYMBOL_GPL(hv_stimer_global_cleanup);
......
...@@ -202,7 +202,7 @@ int hv_synic_init(unsigned int cpu) ...@@ -202,7 +202,7 @@ int hv_synic_init(unsigned int cpu)
{ {
hv_synic_enable_regs(cpu); hv_synic_enable_regs(cpu);
hv_stimer_init(cpu); hv_stimer_legacy_init(cpu, VMBUS_MESSAGE_SINT);
return 0; return 0;
} }
...@@ -277,7 +277,7 @@ int hv_synic_cleanup(unsigned int cpu) ...@@ -277,7 +277,7 @@ int hv_synic_cleanup(unsigned int cpu)
if (channel_found && vmbus_connection.conn_state == CONNECTED) if (channel_found && vmbus_connection.conn_state == CONNECTED)
return -EBUSY; return -EBUSY;
hv_stimer_cleanup(cpu); hv_stimer_legacy_cleanup(cpu);
hv_synic_disable_regs(cpu); hv_synic_disable_regs(cpu);
......
...@@ -1340,10 +1340,6 @@ static int vmbus_bus_init(void) ...@@ -1340,10 +1340,6 @@ static int vmbus_bus_init(void)
if (ret) if (ret)
goto err_alloc; 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. * Initialize the per-cpu interrupt state and stimer state.
* Then connect to the host. * Then connect to the host.
...@@ -1400,9 +1396,8 @@ static int vmbus_bus_init(void) ...@@ -1400,9 +1396,8 @@ static int vmbus_bus_init(void)
err_connect: err_connect:
cpuhp_remove_state(hyperv_cpuhp_online); cpuhp_remove_state(hyperv_cpuhp_online);
err_cpuhp: err_cpuhp:
hv_stimer_free();
err_alloc:
hv_synic_free(); hv_synic_free();
err_alloc:
hv_remove_vmbus_irq(); hv_remove_vmbus_irq();
bus_unregister(&hv_bus); bus_unregister(&hv_bus);
...@@ -2315,20 +2310,23 @@ static void hv_crash_handler(struct pt_regs *regs) ...@@ -2315,20 +2310,23 @@ static void hv_crash_handler(struct pt_regs *regs)
static int hv_synic_suspend(void) static int hv_synic_suspend(void)
{ {
/* /*
* When we reach here, all the non-boot CPUs have been offlined, and * When we reach here, all the non-boot CPUs have been offlined.
* the stimers on them have been unbound in hv_synic_cleanup() -> * 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_stimer_cleanup() -> clockevents_unbind_device().
* *
* hv_synic_suspend() only runs on CPU0 with interrupts disabled. Here * hv_synic_suspend() only runs on CPU0 with interrupts disabled.
* we do not unbind the stimer on CPU0 because: 1) it's unnecessary * Here we do not call hv_stimer_legacy_cleanup() on CPU0 because:
* because the interrupts remain disabled between syscore_suspend() * 1) it's unnecessary as interrupts remain disabled between
* and syscore_resume(): see create_image() and resume_target_kernel(); * syscore_suspend() and syscore_resume(): see create_image() and
* resume_target_kernel()
* 2) the stimer on CPU0 is automatically disabled later by * 2) the stimer on CPU0 is automatically disabled later by
* syscore_suspend() -> timekeeping_suspend() -> tick_suspend() -> ... * syscore_suspend() -> timekeeping_suspend() -> tick_suspend() -> ...
* -> clockevents_shutdown() -> ... -> hv_ce_shutdown(); 3) a warning * -> clockevents_shutdown() -> ... -> hv_ce_shutdown()
* would be triggered if we call clockevents_unbind_device(), which * 3) a warning would be triggered if we call
* may sleep, in an interrupts-disabled context. So, we intentionally * clockevents_unbind_device(), which may sleep, in an
* don't call hv_stimer_cleanup(0) here. * interrupts-disabled context.
*/ */
hv_synic_disable_regs(0); hv_synic_disable_regs(0);
......
...@@ -21,10 +21,11 @@ ...@@ -21,10 +21,11 @@
#define HV_MIN_DELTA_TICKS 1 #define HV_MIN_DELTA_TICKS 1
/* Routines called by the VMbus driver */ /* 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_free(void);
extern void hv_stimer_init(unsigned int cpu); extern int hv_stimer_cleanup(unsigned int cpu);
extern void 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_stimer_global_cleanup(void);
extern void hv_stimer0_isr(void); extern void hv_stimer0_isr(void);
......
...@@ -129,6 +129,7 @@ enum cpuhp_state { ...@@ -129,6 +129,7 @@ enum cpuhp_state {
CPUHP_AP_ARC_TIMER_STARTING, CPUHP_AP_ARC_TIMER_STARTING,
CPUHP_AP_RISCV_TIMER_STARTING, CPUHP_AP_RISCV_TIMER_STARTING,
CPUHP_AP_CSKY_TIMER_STARTING, CPUHP_AP_CSKY_TIMER_STARTING,
CPUHP_AP_HYPERV_TIMER_STARTING,
CPUHP_AP_KVM_STARTING, CPUHP_AP_KVM_STARTING,
CPUHP_AP_KVM_ARM_VGIC_INIT_STARTING, CPUHP_AP_KVM_ARM_VGIC_INIT_STARTING,
CPUHP_AP_KVM_ARM_VGIC_STARTING, CPUHP_AP_KVM_ARM_VGIC_STARTING,
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment