| Message ID | 1463664367-7675-1-git-send-email-jgross@suse.com (mailing list archive) |
|---|---|
| State | New, archived |
| Headers | show |
On 05/19/2016 09:26 AM, Juergen Gross wrote: > The pv_time_ops structure contains a function pointer for the > "steal_clock" functionality used only by KVM and Xen on ARM. Xen on x86 > uses its own mechanism to account for the "stolen" time a thread wasn't > able to run due to hypervisor scheduling. > > Add support in Xen arch independent time handling for this feature by > moving it out of the arm arch into drivers/xen and remove the x86 Xen > hack. > > Signed-off-by: Juergen Gross <jgross@suse.com> Reviewed-by: Boris Ostrovsky <boris.ostrovsky@oracle.com> I think this also needs to be acked by (or at least copied to) generic Linux maintainers. > --- > arch/arm/xen/enlighten.c | 17 ++--------------- > arch/x86/xen/time.c | 44 ++------------------------------------------ > drivers/xen/time.c | 20 ++++++++++++++++++++ > include/linux/kernel_stat.h | 1 - > include/xen/xen-ops.h | 1 + > kernel/sched/cputime.c | 10 ---------- > 6 files changed, 25 insertions(+), 68 deletions(-) ... > } > diff --git a/drivers/xen/time.c b/drivers/xen/time.c > index 7107842..2257b66 100644 > --- a/drivers/xen/time.c > +++ b/drivers/xen/time.c > @@ -6,6 +6,7 @@ > #include <linux/math64.h> > #include <linux/gfp.h> > > +#include <asm/paravirt.h> > #include <asm/xen/hypervisor.h> > #include <asm/xen/hypercall.h> > > @@ -75,6 +76,15 @@ bool xen_vcpu_stolen(int vcpu) > return per_cpu(xen_runstate, vcpu).state == RUNSTATE_runnable; > } (Unrelated to this patch.) Should this include RUNSTATE_offline as well? -boris
On 19/05/16 15:26, Juergen Gross wrote: > The pv_time_ops structure contains a function pointer for the > "steal_clock" functionality used only by KVM and Xen on ARM. Xen on x86 > uses its own mechanism to account for the "stolen" time a thread wasn't > able to run due to hypervisor scheduling. > > Add support in Xen arch independent time handling for this feature by > moving it out of the arm arch into drivers/xen and remove the x86 Xen > hack. > > Signed-off-by: Juergen Gross <jgross@suse.com> Sorry, forgot scheduling maintainer. Added. Juergen > --- > V3: add #include <asm/paravirt.h> to avoid build error on arm > V2: remove the x86 do_stolen_accounting() hack > --- > arch/arm/xen/enlighten.c | 17 ++--------------- > arch/x86/xen/time.c | 44 ++------------------------------------------ > drivers/xen/time.c | 20 ++++++++++++++++++++ > include/linux/kernel_stat.h | 1 - > include/xen/xen-ops.h | 1 + > kernel/sched/cputime.c | 10 ---------- > 6 files changed, 25 insertions(+), 68 deletions(-) > > diff --git a/arch/arm/xen/enlighten.c b/arch/arm/xen/enlighten.c > index 75cd734..9163b94 100644 > --- a/arch/arm/xen/enlighten.c > +++ b/arch/arm/xen/enlighten.c > @@ -84,19 +84,6 @@ int xen_unmap_domain_gfn_range(struct vm_area_struct *vma, > } > EXPORT_SYMBOL_GPL(xen_unmap_domain_gfn_range); > > -static unsigned long long xen_stolen_accounting(int cpu) > -{ > - struct vcpu_runstate_info state; > - > - BUG_ON(cpu != smp_processor_id()); > - > - xen_get_runstate_snapshot(&state); > - > - WARN_ON(state.state != RUNSTATE_running); > - > - return state.time[RUNSTATE_runnable] + state.time[RUNSTATE_offline]; > -} > - > static void xen_read_wallclock(struct timespec64 *ts) > { > u32 version; > @@ -355,8 +342,8 @@ static int __init xen_guest_init(void) > > register_cpu_notifier(&xen_cpu_notifier); > > - pv_time_ops.steal_clock = xen_stolen_accounting; > - static_key_slow_inc(¶virt_steal_enabled); > + xen_time_setup_guest(); > + > if (xen_initial_domain()) > pvclock_gtod_register_notifier(&xen_pvclock_gtod_notifier); > > diff --git a/arch/x86/xen/time.c b/arch/x86/xen/time.c > index a0a4e55..6be31df 100644 > --- a/arch/x86/xen/time.c > +++ b/arch/x86/xen/time.c > @@ -11,8 +11,6 @@ > #include <linux/interrupt.h> > #include <linux/clocksource.h> > #include <linux/clockchips.h> > -#include <linux/kernel_stat.h> > -#include <linux/math64.h> > #include <linux/gfp.h> > #include <linux/slab.h> > #include <linux/pvclock_gtod.h> > @@ -31,44 +29,6 @@ > > /* Xen may fire a timer up to this many ns early */ > #define TIMER_SLOP 100000 > -#define NS_PER_TICK (1000000000LL / HZ) > - > -/* snapshots of runstate info */ > -static DEFINE_PER_CPU(struct vcpu_runstate_info, xen_runstate_snapshot); > - > -/* unused ns of stolen time */ > -static DEFINE_PER_CPU(u64, xen_residual_stolen); > - > -static void do_stolen_accounting(void) > -{ > - struct vcpu_runstate_info state; > - struct vcpu_runstate_info *snap; > - s64 runnable, offline, stolen; > - cputime_t ticks; > - > - xen_get_runstate_snapshot(&state); > - > - WARN_ON(state.state != RUNSTATE_running); > - > - snap = this_cpu_ptr(&xen_runstate_snapshot); > - > - /* work out how much time the VCPU has not been runn*ing* */ > - runnable = state.time[RUNSTATE_runnable] - snap->time[RUNSTATE_runnable]; > - offline = state.time[RUNSTATE_offline] - snap->time[RUNSTATE_offline]; > - > - *snap = state; > - > - /* Add the appropriate number of ticks of stolen time, > - including any left-overs from last time. */ > - stolen = runnable + offline + __this_cpu_read(xen_residual_stolen); > - > - if (stolen < 0) > - stolen = 0; > - > - ticks = iter_div_u64_rem(stolen, NS_PER_TICK, &stolen); > - __this_cpu_write(xen_residual_stolen, stolen); > - account_steal_ticks(ticks); > -} > > /* Get the TSC speed from Xen */ > static unsigned long xen_tsc_khz(void) > @@ -335,8 +295,6 @@ static irqreturn_t xen_timer_interrupt(int irq, void *dev_id) > ret = IRQ_HANDLED; > } > > - do_stolen_accounting(); > - > return ret; > } > > @@ -431,6 +389,8 @@ static void __init xen_time_init(void) > xen_setup_timer(cpu); > xen_setup_cpu_clockevents(); > > + xen_time_setup_guest(); > + > if (xen_initial_domain()) > pvclock_gtod_register_notifier(&xen_pvclock_gtod_notifier); > } > diff --git a/drivers/xen/time.c b/drivers/xen/time.c > index 7107842..2257b66 100644 > --- a/drivers/xen/time.c > +++ b/drivers/xen/time.c > @@ -6,6 +6,7 @@ > #include <linux/math64.h> > #include <linux/gfp.h> > > +#include <asm/paravirt.h> > #include <asm/xen/hypervisor.h> > #include <asm/xen/hypercall.h> > > @@ -75,6 +76,15 @@ bool xen_vcpu_stolen(int vcpu) > return per_cpu(xen_runstate, vcpu).state == RUNSTATE_runnable; > } > > +static u64 xen_steal_clock(int cpu) > +{ > + struct vcpu_runstate_info state; > + > + BUG_ON(cpu != smp_processor_id()); > + xen_get_runstate_snapshot(&state); > + return state.time[RUNSTATE_runnable] + state.time[RUNSTATE_offline]; > +} > + > void xen_setup_runstate_info(int cpu) > { > struct vcpu_register_runstate_memory_area area; > @@ -86,3 +96,13 @@ void xen_setup_runstate_info(int cpu) > BUG(); > } > > +void __init xen_time_setup_guest(void) > +{ > + pv_time_ops.steal_clock = xen_steal_clock; > + > + static_key_slow_inc(¶virt_steal_enabled); > + /* > + * We can't set paravirt_steal_rq_enabled as this would require the > + * capability to read another cpu's runstate info. > + */ > +} > diff --git a/include/linux/kernel_stat.h b/include/linux/kernel_stat.h > index 25a822f..44fda64 100644 > --- a/include/linux/kernel_stat.h > +++ b/include/linux/kernel_stat.h > @@ -92,7 +92,6 @@ static inline void account_process_tick(struct task_struct *tsk, int user) > extern void account_process_tick(struct task_struct *, int user); > #endif > > -extern void account_steal_ticks(unsigned long ticks); > extern void account_idle_ticks(unsigned long ticks); > > #endif /* _LINUX_KERNEL_STAT_H */ > diff --git a/include/xen/xen-ops.h b/include/xen/xen-ops.h > index 86abe07..5ce51c2 100644 > --- a/include/xen/xen-ops.h > +++ b/include/xen/xen-ops.h > @@ -21,6 +21,7 @@ void xen_resume_notifier_unregister(struct notifier_block *nb); > > bool xen_vcpu_stolen(int vcpu); > void xen_setup_runstate_info(int cpu); > +void __init xen_time_setup_guest(void); > void xen_get_runstate_snapshot(struct vcpu_runstate_info *res); > > int xen_setup_shutdown_event(void); > diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c > index 75f98c5..8c4c6dc 100644 > --- a/kernel/sched/cputime.c > +++ b/kernel/sched/cputime.c > @@ -490,16 +490,6 @@ void account_process_tick(struct task_struct *p, int user_tick) > } > > /* > - * Account multiple ticks of steal time. > - * @p: the process from which the cpu time has been stolen > - * @ticks: number of stolen ticks > - */ > -void account_steal_ticks(unsigned long ticks) > -{ > - account_steal_time(jiffies_to_cputime(ticks)); > -} > - > -/* > * Account multiple ticks of idle time. > * @ticks: number of stolen ticks > */ >
On Thu, 19 May 2016, Juergen Gross wrote: > The pv_time_ops structure contains a function pointer for the > "steal_clock" functionality used only by KVM and Xen on ARM. Xen on x86 > uses its own mechanism to account for the "stolen" time a thread wasn't > able to run due to hypervisor scheduling. > > Add support in Xen arch independent time handling for this feature by > moving it out of the arm arch into drivers/xen and remove the x86 Xen > hack. > > Signed-off-by: Juergen Gross <jgross@suse.com> > --- > V3: add #include <asm/paravirt.h> to avoid build error on arm > V2: remove the x86 do_stolen_accounting() hack > --- > arch/arm/xen/enlighten.c | 17 ++--------------- > arch/x86/xen/time.c | 44 ++------------------------------------------ > drivers/xen/time.c | 20 ++++++++++++++++++++ > include/linux/kernel_stat.h | 1 - > include/xen/xen-ops.h | 1 + > kernel/sched/cputime.c | 10 ---------- > 6 files changed, 25 insertions(+), 68 deletions(-) > > diff --git a/arch/arm/xen/enlighten.c b/arch/arm/xen/enlighten.c > index 75cd734..9163b94 100644 > --- a/arch/arm/xen/enlighten.c > +++ b/arch/arm/xen/enlighten.c > @@ -84,19 +84,6 @@ int xen_unmap_domain_gfn_range(struct vm_area_struct *vma, > } > EXPORT_SYMBOL_GPL(xen_unmap_domain_gfn_range); > > -static unsigned long long xen_stolen_accounting(int cpu) > -{ > - struct vcpu_runstate_info state; > - > - BUG_ON(cpu != smp_processor_id()); > - > - xen_get_runstate_snapshot(&state); > - > - WARN_ON(state.state != RUNSTATE_running); > - > - return state.time[RUNSTATE_runnable] + state.time[RUNSTATE_offline]; > -} > - > static void xen_read_wallclock(struct timespec64 *ts) > { > u32 version; > @@ -355,8 +342,8 @@ static int __init xen_guest_init(void) > > register_cpu_notifier(&xen_cpu_notifier); > > - pv_time_ops.steal_clock = xen_stolen_accounting; > - static_key_slow_inc(¶virt_steal_enabled); > + xen_time_setup_guest(); You can remove #include <asm/paravirt.h> from headers now I believe > if (xen_initial_domain()) > pvclock_gtod_register_notifier(&xen_pvclock_gtod_notifier); > > diff --git a/arch/x86/xen/time.c b/arch/x86/xen/time.c > index a0a4e55..6be31df 100644 > --- a/arch/x86/xen/time.c > +++ b/arch/x86/xen/time.c > @@ -11,8 +11,6 @@ > #include <linux/interrupt.h> > #include <linux/clocksource.h> > #include <linux/clockchips.h> > -#include <linux/kernel_stat.h> > -#include <linux/math64.h> > #include <linux/gfp.h> > #include <linux/slab.h> > #include <linux/pvclock_gtod.h> > @@ -31,44 +29,6 @@ > > /* Xen may fire a timer up to this many ns early */ > #define TIMER_SLOP 100000 > -#define NS_PER_TICK (1000000000LL / HZ) > - > -/* snapshots of runstate info */ > -static DEFINE_PER_CPU(struct vcpu_runstate_info, xen_runstate_snapshot); > - > -/* unused ns of stolen time */ > -static DEFINE_PER_CPU(u64, xen_residual_stolen); > - > -static void do_stolen_accounting(void) > -{ > - struct vcpu_runstate_info state; > - struct vcpu_runstate_info *snap; > - s64 runnable, offline, stolen; > - cputime_t ticks; > - > - xen_get_runstate_snapshot(&state); > - > - WARN_ON(state.state != RUNSTATE_running); > - > - snap = this_cpu_ptr(&xen_runstate_snapshot); > - > - /* work out how much time the VCPU has not been runn*ing* */ > - runnable = state.time[RUNSTATE_runnable] - snap->time[RUNSTATE_runnable]; > - offline = state.time[RUNSTATE_offline] - snap->time[RUNSTATE_offline]; > - > - *snap = state; > - > - /* Add the appropriate number of ticks of stolen time, > - including any left-overs from last time. */ > - stolen = runnable + offline + __this_cpu_read(xen_residual_stolen); > - > - if (stolen < 0) > - stolen = 0; > - > - ticks = iter_div_u64_rem(stolen, NS_PER_TICK, &stolen); > - __this_cpu_write(xen_residual_stolen, stolen); > - account_steal_ticks(ticks); > -} > > /* Get the TSC speed from Xen */ > static unsigned long xen_tsc_khz(void) > @@ -335,8 +295,6 @@ static irqreturn_t xen_timer_interrupt(int irq, void *dev_id) > ret = IRQ_HANDLED; > } > > - do_stolen_accounting(); > - > return ret; > } > > @@ -431,6 +389,8 @@ static void __init xen_time_init(void) > xen_setup_timer(cpu); > xen_setup_cpu_clockevents(); > > + xen_time_setup_guest(); > + > if (xen_initial_domain()) > pvclock_gtod_register_notifier(&xen_pvclock_gtod_notifier); > } > diff --git a/drivers/xen/time.c b/drivers/xen/time.c > index 7107842..2257b66 100644 > --- a/drivers/xen/time.c > +++ b/drivers/xen/time.c > @@ -6,6 +6,7 @@ > #include <linux/math64.h> > #include <linux/gfp.h> > > +#include <asm/paravirt.h> > #include <asm/xen/hypervisor.h> > #include <asm/xen/hypercall.h> > > @@ -75,6 +76,15 @@ bool xen_vcpu_stolen(int vcpu) > return per_cpu(xen_runstate, vcpu).state == RUNSTATE_runnable; > } > > +static u64 xen_steal_clock(int cpu) > +{ > + struct vcpu_runstate_info state; > + > + BUG_ON(cpu != smp_processor_id()); > + xen_get_runstate_snapshot(&state); > + return state.time[RUNSTATE_runnable] + state.time[RUNSTATE_offline]; > +} > + > void xen_setup_runstate_info(int cpu) > { > struct vcpu_register_runstate_memory_area area; > @@ -86,3 +96,13 @@ void xen_setup_runstate_info(int cpu) > BUG(); > } > > +void __init xen_time_setup_guest(void) > +{ > + pv_time_ops.steal_clock = xen_steal_clock; > + > + static_key_slow_inc(¶virt_steal_enabled); > + /* > + * We can't set paravirt_steal_rq_enabled as this would require the > + * capability to read another cpu's runstate info. > + */ > +} > diff --git a/include/linux/kernel_stat.h b/include/linux/kernel_stat.h > index 25a822f..44fda64 100644 > --- a/include/linux/kernel_stat.h > +++ b/include/linux/kernel_stat.h > @@ -92,7 +92,6 @@ static inline void account_process_tick(struct task_struct *tsk, int user) > extern void account_process_tick(struct task_struct *, int user); > #endif > > -extern void account_steal_ticks(unsigned long ticks); > extern void account_idle_ticks(unsigned long ticks); > > #endif /* _LINUX_KERNEL_STAT_H */ > diff --git a/include/xen/xen-ops.h b/include/xen/xen-ops.h > index 86abe07..5ce51c2 100644 > --- a/include/xen/xen-ops.h > +++ b/include/xen/xen-ops.h > @@ -21,6 +21,7 @@ void xen_resume_notifier_unregister(struct notifier_block *nb); > > bool xen_vcpu_stolen(int vcpu); > void xen_setup_runstate_info(int cpu); > +void __init xen_time_setup_guest(void); please avoid __init in headers > void xen_get_runstate_snapshot(struct vcpu_runstate_info *res); > > int xen_setup_shutdown_event(void); > diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c > index 75f98c5..8c4c6dc 100644 > --- a/kernel/sched/cputime.c > +++ b/kernel/sched/cputime.c > @@ -490,16 +490,6 @@ void account_process_tick(struct task_struct *p, int user_tick) > } > > /* > - * Account multiple ticks of steal time. > - * @p: the process from which the cpu time has been stolen > - * @ticks: number of stolen ticks > - */ > -void account_steal_ticks(unsigned long ticks) > -{ > - account_steal_time(jiffies_to_cputime(ticks)); > -} > - > -/* > * Account multiple ticks of idle time. > * @ticks: number of stolen ticks > */ > -- > 2.6.6 >
On Thu, 19 May 2016, Stefano Stabellini wrote: > On Thu, 19 May 2016, Juergen Gross wrote: > > The pv_time_ops structure contains a function pointer for the > > "steal_clock" functionality used only by KVM and Xen on ARM. Xen on x86 > > uses its own mechanism to account for the "stolen" time a thread wasn't > > able to run due to hypervisor scheduling. > > > > Add support in Xen arch independent time handling for this feature by > > moving it out of the arm arch into drivers/xen and remove the x86 Xen > > hack. > > > > Signed-off-by: Juergen Gross <jgross@suse.com> > > --- > > V3: add #include <asm/paravirt.h> to avoid build error on arm > > V2: remove the x86 do_stolen_accounting() hack > > --- > > arch/arm/xen/enlighten.c | 17 ++--------------- > > arch/x86/xen/time.c | 44 ++------------------------------------------ > > drivers/xen/time.c | 20 ++++++++++++++++++++ > > include/linux/kernel_stat.h | 1 - > > include/xen/xen-ops.h | 1 + > > kernel/sched/cputime.c | 10 ---------- > > 6 files changed, 25 insertions(+), 68 deletions(-) > > > > diff --git a/arch/arm/xen/enlighten.c b/arch/arm/xen/enlighten.c > > index 75cd734..9163b94 100644 > > --- a/arch/arm/xen/enlighten.c > > +++ b/arch/arm/xen/enlighten.c > > @@ -84,19 +84,6 @@ int xen_unmap_domain_gfn_range(struct vm_area_struct *vma, > > } > > EXPORT_SYMBOL_GPL(xen_unmap_domain_gfn_range); > > > > -static unsigned long long xen_stolen_accounting(int cpu) > > -{ > > - struct vcpu_runstate_info state; > > - > > - BUG_ON(cpu != smp_processor_id()); > > - > > - xen_get_runstate_snapshot(&state); > > - > > - WARN_ON(state.state != RUNSTATE_running); > > - > > - return state.time[RUNSTATE_runnable] + state.time[RUNSTATE_offline]; > > -} > > - > > static void xen_read_wallclock(struct timespec64 *ts) > > { > > u32 version; > > @@ -355,8 +342,8 @@ static int __init xen_guest_init(void) > > > > register_cpu_notifier(&xen_cpu_notifier); > > > > - pv_time_ops.steal_clock = xen_stolen_accounting; > > - static_key_slow_inc(¶virt_steal_enabled); > > + xen_time_setup_guest(); > > You can remove > > #include <asm/paravirt.h> > > from headers now I believe Sorry for the broken English. I meant: you can remove #include <asm/paravirt.h> from the top of the file now I believe. > > > if (xen_initial_domain()) > > pvclock_gtod_register_notifier(&xen_pvclock_gtod_notifier); > > > > diff --git a/arch/x86/xen/time.c b/arch/x86/xen/time.c > > index a0a4e55..6be31df 100644 > > --- a/arch/x86/xen/time.c > > +++ b/arch/x86/xen/time.c > > @@ -11,8 +11,6 @@ > > #include <linux/interrupt.h> > > #include <linux/clocksource.h> > > #include <linux/clockchips.h> > > -#include <linux/kernel_stat.h> > > -#include <linux/math64.h> > > #include <linux/gfp.h> > > #include <linux/slab.h> > > #include <linux/pvclock_gtod.h> > > @@ -31,44 +29,6 @@ > > > > /* Xen may fire a timer up to this many ns early */ > > #define TIMER_SLOP 100000 > > -#define NS_PER_TICK (1000000000LL / HZ) > > - > > -/* snapshots of runstate info */ > > -static DEFINE_PER_CPU(struct vcpu_runstate_info, xen_runstate_snapshot); > > - > > -/* unused ns of stolen time */ > > -static DEFINE_PER_CPU(u64, xen_residual_stolen); > > - > > -static void do_stolen_accounting(void) > > -{ > > - struct vcpu_runstate_info state; > > - struct vcpu_runstate_info *snap; > > - s64 runnable, offline, stolen; > > - cputime_t ticks; > > - > > - xen_get_runstate_snapshot(&state); > > - > > - WARN_ON(state.state != RUNSTATE_running); > > - > > - snap = this_cpu_ptr(&xen_runstate_snapshot); > > - > > - /* work out how much time the VCPU has not been runn*ing* */ > > - runnable = state.time[RUNSTATE_runnable] - snap->time[RUNSTATE_runnable]; > > - offline = state.time[RUNSTATE_offline] - snap->time[RUNSTATE_offline]; > > - > > - *snap = state; > > - > > - /* Add the appropriate number of ticks of stolen time, > > - including any left-overs from last time. */ > > - stolen = runnable + offline + __this_cpu_read(xen_residual_stolen); > > - > > - if (stolen < 0) > > - stolen = 0; > > - > > - ticks = iter_div_u64_rem(stolen, NS_PER_TICK, &stolen); > > - __this_cpu_write(xen_residual_stolen, stolen); > > - account_steal_ticks(ticks); > > -} > > > > /* Get the TSC speed from Xen */ > > static unsigned long xen_tsc_khz(void) > > @@ -335,8 +295,6 @@ static irqreturn_t xen_timer_interrupt(int irq, void *dev_id) > > ret = IRQ_HANDLED; > > } > > > > - do_stolen_accounting(); > > - > > return ret; > > } > > > > @@ -431,6 +389,8 @@ static void __init xen_time_init(void) > > xen_setup_timer(cpu); > > xen_setup_cpu_clockevents(); > > > > + xen_time_setup_guest(); > > + > > if (xen_initial_domain()) > > pvclock_gtod_register_notifier(&xen_pvclock_gtod_notifier); > > } > > diff --git a/drivers/xen/time.c b/drivers/xen/time.c > > index 7107842..2257b66 100644 > > --- a/drivers/xen/time.c > > +++ b/drivers/xen/time.c > > @@ -6,6 +6,7 @@ > > #include <linux/math64.h> > > #include <linux/gfp.h> > > > > +#include <asm/paravirt.h> > > #include <asm/xen/hypervisor.h> > > #include <asm/xen/hypercall.h> > > > > @@ -75,6 +76,15 @@ bool xen_vcpu_stolen(int vcpu) > > return per_cpu(xen_runstate, vcpu).state == RUNSTATE_runnable; > > } > > > > +static u64 xen_steal_clock(int cpu) > > +{ > > + struct vcpu_runstate_info state; > > + > > + BUG_ON(cpu != smp_processor_id()); > > + xen_get_runstate_snapshot(&state); > > + return state.time[RUNSTATE_runnable] + state.time[RUNSTATE_offline]; > > +} > > + > > void xen_setup_runstate_info(int cpu) > > { > > struct vcpu_register_runstate_memory_area area; > > @@ -86,3 +96,13 @@ void xen_setup_runstate_info(int cpu) > > BUG(); > > } > > > > +void __init xen_time_setup_guest(void) > > +{ > > + pv_time_ops.steal_clock = xen_steal_clock; > > + > > + static_key_slow_inc(¶virt_steal_enabled); > > + /* > > + * We can't set paravirt_steal_rq_enabled as this would require the > > + * capability to read another cpu's runstate info. > > + */ > > +} > > diff --git a/include/linux/kernel_stat.h b/include/linux/kernel_stat.h > > index 25a822f..44fda64 100644 > > --- a/include/linux/kernel_stat.h > > +++ b/include/linux/kernel_stat.h > > @@ -92,7 +92,6 @@ static inline void account_process_tick(struct task_struct *tsk, int user) > > extern void account_process_tick(struct task_struct *, int user); > > #endif > > > > -extern void account_steal_ticks(unsigned long ticks); > > extern void account_idle_ticks(unsigned long ticks); > > > > #endif /* _LINUX_KERNEL_STAT_H */ > > diff --git a/include/xen/xen-ops.h b/include/xen/xen-ops.h > > index 86abe07..5ce51c2 100644 > > --- a/include/xen/xen-ops.h > > +++ b/include/xen/xen-ops.h > > @@ -21,6 +21,7 @@ void xen_resume_notifier_unregister(struct notifier_block *nb); > > > > bool xen_vcpu_stolen(int vcpu); > > void xen_setup_runstate_info(int cpu); > > +void __init xen_time_setup_guest(void); > > please avoid __init in headers > > > > void xen_get_runstate_snapshot(struct vcpu_runstate_info *res); > > > > int xen_setup_shutdown_event(void); > > diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c > > index 75f98c5..8c4c6dc 100644 > > --- a/kernel/sched/cputime.c > > +++ b/kernel/sched/cputime.c > > @@ -490,16 +490,6 @@ void account_process_tick(struct task_struct *p, int user_tick) > > } > > > > /* > > - * Account multiple ticks of steal time. > > - * @p: the process from which the cpu time has been stolen > > - * @ticks: number of stolen ticks > > - */ > > -void account_steal_ticks(unsigned long ticks) > > -{ > > - account_steal_time(jiffies_to_cputime(ticks)); > > -} > > - > > -/* > > * Account multiple ticks of idle time. > > * @ticks: number of stolen ticks > > */ > > -- > > 2.6.6 > > >
On 19/05/16 19:15, Stefano Stabellini wrote: > On Thu, 19 May 2016, Juergen Gross wrote: >> The pv_time_ops structure contains a function pointer for the >> "steal_clock" functionality used only by KVM and Xen on ARM. Xen on x86 >> uses its own mechanism to account for the "stolen" time a thread wasn't >> able to run due to hypervisor scheduling. >> >> Add support in Xen arch independent time handling for this feature by >> moving it out of the arm arch into drivers/xen and remove the x86 Xen >> hack. >> >> Signed-off-by: Juergen Gross <jgross@suse.com> >> --- >> V3: add #include <asm/paravirt.h> to avoid build error on arm >> V2: remove the x86 do_stolen_accounting() hack >> --- >> arch/arm/xen/enlighten.c | 17 ++--------------- >> arch/x86/xen/time.c | 44 ++------------------------------------------ >> drivers/xen/time.c | 20 ++++++++++++++++++++ >> include/linux/kernel_stat.h | 1 - >> include/xen/xen-ops.h | 1 + >> kernel/sched/cputime.c | 10 ---------- >> 6 files changed, 25 insertions(+), 68 deletions(-) >> >> diff --git a/arch/arm/xen/enlighten.c b/arch/arm/xen/enlighten.c >> index 75cd734..9163b94 100644 >> --- a/arch/arm/xen/enlighten.c >> +++ b/arch/arm/xen/enlighten.c >> @@ -84,19 +84,6 @@ int xen_unmap_domain_gfn_range(struct vm_area_struct *vma, >> } >> EXPORT_SYMBOL_GPL(xen_unmap_domain_gfn_range); >> >> -static unsigned long long xen_stolen_accounting(int cpu) >> -{ >> - struct vcpu_runstate_info state; >> - >> - BUG_ON(cpu != smp_processor_id()); >> - >> - xen_get_runstate_snapshot(&state); >> - >> - WARN_ON(state.state != RUNSTATE_running); >> - >> - return state.time[RUNSTATE_runnable] + state.time[RUNSTATE_offline]; >> -} >> - >> static void xen_read_wallclock(struct timespec64 *ts) >> { >> u32 version; >> @@ -355,8 +342,8 @@ static int __init xen_guest_init(void) >> >> register_cpu_notifier(&xen_cpu_notifier); >> >> - pv_time_ops.steal_clock = xen_stolen_accounting; >> - static_key_slow_inc(¶virt_steal_enabled); >> + xen_time_setup_guest(); > > You can remove > > #include <asm/paravirt.h> > > from headers now I believe Correct. Done. >> diff --git a/include/linux/kernel_stat.h b/include/linux/kernel_stat.h >> index 25a822f..44fda64 100644 >> --- a/include/linux/kernel_stat.h >> +++ b/include/linux/kernel_stat.h >> @@ -92,7 +92,6 @@ static inline void account_process_tick(struct task_struct *tsk, int user) >> extern void account_process_tick(struct task_struct *, int user); >> #endif >> >> -extern void account_steal_ticks(unsigned long ticks); >> extern void account_idle_ticks(unsigned long ticks); >> >> #endif /* _LINUX_KERNEL_STAT_H */ >> diff --git a/include/xen/xen-ops.h b/include/xen/xen-ops.h >> index 86abe07..5ce51c2 100644 >> --- a/include/xen/xen-ops.h >> +++ b/include/xen/xen-ops.h >> @@ -21,6 +21,7 @@ void xen_resume_notifier_unregister(struct notifier_block *nb); >> >> bool xen_vcpu_stolen(int vcpu); >> void xen_setup_runstate_info(int cpu); >> +void __init xen_time_setup_guest(void); > > please avoid __init in headers Okay. Juergen
diff --git a/arch/arm/xen/enlighten.c b/arch/arm/xen/enlighten.c index 75cd734..9163b94 100644 --- a/arch/arm/xen/enlighten.c +++ b/arch/arm/xen/enlighten.c @@ -84,19 +84,6 @@ int xen_unmap_domain_gfn_range(struct vm_area_struct *vma, } EXPORT_SYMBOL_GPL(xen_unmap_domain_gfn_range); -static unsigned long long xen_stolen_accounting(int cpu) -{ - struct vcpu_runstate_info state; - - BUG_ON(cpu != smp_processor_id()); - - xen_get_runstate_snapshot(&state); - - WARN_ON(state.state != RUNSTATE_running); - - return state.time[RUNSTATE_runnable] + state.time[RUNSTATE_offline]; -} - static void xen_read_wallclock(struct timespec64 *ts) { u32 version; @@ -355,8 +342,8 @@ static int __init xen_guest_init(void) register_cpu_notifier(&xen_cpu_notifier); - pv_time_ops.steal_clock = xen_stolen_accounting; - static_key_slow_inc(¶virt_steal_enabled); + xen_time_setup_guest(); + if (xen_initial_domain()) pvclock_gtod_register_notifier(&xen_pvclock_gtod_notifier); diff --git a/arch/x86/xen/time.c b/arch/x86/xen/time.c index a0a4e55..6be31df 100644 --- a/arch/x86/xen/time.c +++ b/arch/x86/xen/time.c @@ -11,8 +11,6 @@ #include <linux/interrupt.h> #include <linux/clocksource.h> #include <linux/clockchips.h> -#include <linux/kernel_stat.h> -#include <linux/math64.h> #include <linux/gfp.h> #include <linux/slab.h> #include <linux/pvclock_gtod.h> @@ -31,44 +29,6 @@ /* Xen may fire a timer up to this many ns early */ #define TIMER_SLOP 100000 -#define NS_PER_TICK (1000000000LL / HZ) - -/* snapshots of runstate info */ -static DEFINE_PER_CPU(struct vcpu_runstate_info, xen_runstate_snapshot); - -/* unused ns of stolen time */ -static DEFINE_PER_CPU(u64, xen_residual_stolen); - -static void do_stolen_accounting(void) -{ - struct vcpu_runstate_info state; - struct vcpu_runstate_info *snap; - s64 runnable, offline, stolen; - cputime_t ticks; - - xen_get_runstate_snapshot(&state); - - WARN_ON(state.state != RUNSTATE_running); - - snap = this_cpu_ptr(&xen_runstate_snapshot); - - /* work out how much time the VCPU has not been runn*ing* */ - runnable = state.time[RUNSTATE_runnable] - snap->time[RUNSTATE_runnable]; - offline = state.time[RUNSTATE_offline] - snap->time[RUNSTATE_offline]; - - *snap = state; - - /* Add the appropriate number of ticks of stolen time, - including any left-overs from last time. */ - stolen = runnable + offline + __this_cpu_read(xen_residual_stolen); - - if (stolen < 0) - stolen = 0; - - ticks = iter_div_u64_rem(stolen, NS_PER_TICK, &stolen); - __this_cpu_write(xen_residual_stolen, stolen); - account_steal_ticks(ticks); -} /* Get the TSC speed from Xen */ static unsigned long xen_tsc_khz(void) @@ -335,8 +295,6 @@ static irqreturn_t xen_timer_interrupt(int irq, void *dev_id) ret = IRQ_HANDLED; } - do_stolen_accounting(); - return ret; } @@ -431,6 +389,8 @@ static void __init xen_time_init(void) xen_setup_timer(cpu); xen_setup_cpu_clockevents(); + xen_time_setup_guest(); + if (xen_initial_domain()) pvclock_gtod_register_notifier(&xen_pvclock_gtod_notifier); } diff --git a/drivers/xen/time.c b/drivers/xen/time.c index 7107842..2257b66 100644 --- a/drivers/xen/time.c +++ b/drivers/xen/time.c @@ -6,6 +6,7 @@ #include <linux/math64.h> #include <linux/gfp.h> +#include <asm/paravirt.h> #include <asm/xen/hypervisor.h> #include <asm/xen/hypercall.h> @@ -75,6 +76,15 @@ bool xen_vcpu_stolen(int vcpu) return per_cpu(xen_runstate, vcpu).state == RUNSTATE_runnable; } +static u64 xen_steal_clock(int cpu) +{ + struct vcpu_runstate_info state; + + BUG_ON(cpu != smp_processor_id()); + xen_get_runstate_snapshot(&state); + return state.time[RUNSTATE_runnable] + state.time[RUNSTATE_offline]; +} + void xen_setup_runstate_info(int cpu) { struct vcpu_register_runstate_memory_area area; @@ -86,3 +96,13 @@ void xen_setup_runstate_info(int cpu) BUG(); } +void __init xen_time_setup_guest(void) +{ + pv_time_ops.steal_clock = xen_steal_clock; + + static_key_slow_inc(¶virt_steal_enabled); + /* + * We can't set paravirt_steal_rq_enabled as this would require the + * capability to read another cpu's runstate info. + */ +} diff --git a/include/linux/kernel_stat.h b/include/linux/kernel_stat.h index 25a822f..44fda64 100644 --- a/include/linux/kernel_stat.h +++ b/include/linux/kernel_stat.h @@ -92,7 +92,6 @@ static inline void account_process_tick(struct task_struct *tsk, int user) extern void account_process_tick(struct task_struct *, int user); #endif -extern void account_steal_ticks(unsigned long ticks); extern void account_idle_ticks(unsigned long ticks); #endif /* _LINUX_KERNEL_STAT_H */ diff --git a/include/xen/xen-ops.h b/include/xen/xen-ops.h index 86abe07..5ce51c2 100644 --- a/include/xen/xen-ops.h +++ b/include/xen/xen-ops.h @@ -21,6 +21,7 @@ void xen_resume_notifier_unregister(struct notifier_block *nb); bool xen_vcpu_stolen(int vcpu); void xen_setup_runstate_info(int cpu); +void __init xen_time_setup_guest(void); void xen_get_runstate_snapshot(struct vcpu_runstate_info *res); int xen_setup_shutdown_event(void); diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c index 75f98c5..8c4c6dc 100644 --- a/kernel/sched/cputime.c +++ b/kernel/sched/cputime.c @@ -490,16 +490,6 @@ void account_process_tick(struct task_struct *p, int user_tick) } /* - * Account multiple ticks of steal time. - * @p: the process from which the cpu time has been stolen - * @ticks: number of stolen ticks - */ -void account_steal_ticks(unsigned long ticks) -{ - account_steal_time(jiffies_to_cputime(ticks)); -} - -/* * Account multiple ticks of idle time. * @ticks: number of stolen ticks */
The pv_time_ops structure contains a function pointer for the "steal_clock" functionality used only by KVM and Xen on ARM. Xen on x86 uses its own mechanism to account for the "stolen" time a thread wasn't able to run due to hypervisor scheduling. Add support in Xen arch independent time handling for this feature by moving it out of the arm arch into drivers/xen and remove the x86 Xen hack. Signed-off-by: Juergen Gross <jgross@suse.com> --- V3: add #include <asm/paravirt.h> to avoid build error on arm V2: remove the x86 do_stolen_accounting() hack --- arch/arm/xen/enlighten.c | 17 ++--------------- arch/x86/xen/time.c | 44 ++------------------------------------------ drivers/xen/time.c | 20 ++++++++++++++++++++ include/linux/kernel_stat.h | 1 - include/xen/xen-ops.h | 1 + kernel/sched/cputime.c | 10 ---------- 6 files changed, 25 insertions(+), 68 deletions(-)