powerpc/time: add API for KVM to re-arm the host timer/decrementer

Rather than have KVM look up the host timer and fiddle with the
irq-work internal details, have the powerpc/time.c code provide a
function for KVM to re-arm the Linux timer code when exiting a
guest.

This is implementation has an improvement over existing code of
marking a decrementer interrupt as soft-pending if a timer has
expired, rather than setting DEC to a -ve value, which tended to
cause host timers to take two interrupts (first hdec to exit the
guest, then the immediate dec).

Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20211123095231.1036501-8-npiggin@gmail.com
This commit is contained in:
Nicholas Piggin 2021-11-23 19:51:45 +10:00 committed by Michael Ellerman
parent 34bf08a207
commit 25aa145856
3 changed files with 49 additions and 26 deletions

View file

@ -99,18 +99,6 @@ extern void div128_by_32(u64 dividend_high, u64 dividend_low,
extern void secondary_cpu_time_init(void);
extern void __init time_init(void);
#ifdef CONFIG_PPC64
static inline unsigned long test_irq_work_pending(void)
{
unsigned long x;
asm volatile("lbz %0,%1(13)"
: "=r" (x)
: "i" (offsetof(struct paca_struct, irq_work_pending)));
return x;
}
#endif
DECLARE_PER_CPU(u64, decrementers_next_tb);
static inline u64 timer_get_next_tb(void)
@ -118,6 +106,10 @@ static inline u64 timer_get_next_tb(void)
return __this_cpu_read(decrementers_next_tb);
}
#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
void timer_rearm_host_dec(u64 now);
#endif
/* Convert timebase ticks to nanoseconds */
unsigned long long tb_to_ns(unsigned long long tb_ticks);

View file

@ -498,6 +498,16 @@ EXPORT_SYMBOL(profile_pc);
* 64-bit uses a byte in the PACA, 32-bit uses a per-cpu variable...
*/
#ifdef CONFIG_PPC64
static inline unsigned long test_irq_work_pending(void)
{
unsigned long x;
asm volatile("lbz %0,%1(13)"
: "=r" (x)
: "i" (offsetof(struct paca_struct, irq_work_pending)));
return x;
}
static inline void set_irq_work_pending_flag(void)
{
asm volatile("stb %0,%1(13)" : :
@ -541,13 +551,44 @@ void arch_irq_work_raise(void)
preempt_enable();
}
static void set_dec_or_work(u64 val)
{
set_dec(val);
/* We may have raced with new irq work */
if (unlikely(test_irq_work_pending()))
set_dec(1);
}
#else /* CONFIG_IRQ_WORK */
#define test_irq_work_pending() 0
#define clear_irq_work_pending()
static void set_dec_or_work(u64 val)
{
set_dec(val);
}
#endif /* CONFIG_IRQ_WORK */
#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
void timer_rearm_host_dec(u64 now)
{
u64 *next_tb = this_cpu_ptr(&decrementers_next_tb);
WARN_ON_ONCE(!arch_irqs_disabled());
WARN_ON_ONCE(mfmsr() & MSR_EE);
if (now >= *next_tb) {
local_paca->irq_happened |= PACA_IRQ_DEC;
} else {
now = *next_tb - now;
if (now <= decrementer_max)
set_dec_or_work(now);
}
}
EXPORT_SYMBOL_GPL(timer_rearm_host_dec);
#endif
/*
* timer_interrupt - gets called when the decrementer overflows,
* with interrupts disabled.
@ -608,10 +649,7 @@ DEFINE_INTERRUPT_HANDLER_ASYNC(timer_interrupt)
} else {
now = *next_tb - now;
if (now <= decrementer_max)
set_dec(now);
/* We may have raced with new irq work */
if (test_irq_work_pending())
set_dec(1);
set_dec_or_work(now);
__this_cpu_inc(irq_stat.timer_irqs_others);
}
@ -845,11 +883,7 @@ static int decrementer_set_next_event(unsigned long evt,
struct clock_event_device *dev)
{
__this_cpu_write(decrementers_next_tb, get_tb() + evt);
set_dec(evt);
/* We may have raced with new irq work */
if (test_irq_work_pending())
set_dec(1);
set_dec_or_work(evt);
return 0;
}

View file

@ -4062,11 +4062,8 @@ static int kvmhv_p9_guest_entry(struct kvm_vcpu *vcpu, u64 time_limit,
vc->entry_exit_map = 0x101;
vc->in_guest = 0;
next_timer = timer_get_next_tb();
set_dec(next_timer - tb);
/* We may have raced with new irq work */
if (test_irq_work_pending())
set_dec(1);
timer_rearm_host_dec(tb);
mtspr(SPRN_SPRG_VDSO_WRITE, local_paca->sprg_vdso);
kvmhv_load_host_pmu();