xen: add steal_clock support on x86

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>
Reviewed-by: Stefano Stabellini <sstabellini@kernel.org>
Signed-off-by: David Vrabel <david.vrabel@citrix.com>

arch/arm/xen/enlighten.c

@@ -12,7 +12,6 @@
 #include <xen/page.h>
 #include <xen/interface/sched.h>
 #include <xen/xen-ops.h>
-#include <asm/paravirt.h>
 #include <asm/xen/hypervisor.h>
 #include <asm/xen/hypercall.h>
 #include <asm/xen/xen-ops.h>
@@ -86,19 +85,6 @@ 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;
@@ -432,8 +418,8 @@ static int __init xen_guest_init(void)
 
 	register_cpu_notifier(&xen_cpu_notifier);
 
-	pv_time_ops.steal_clock = xen_stolen_accounting;
+	xen_time_setup_guest();
-	static_key_slow_inc(&paravirt_steal_enabled);
+
 	if (xen_initial_domain())
 		pvclock_gtod_register_notifier(&xen_pvclock_gtod_notifier);
 

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);
 }

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(&paravirt_steal_enabled);
+	/*
+	 * We can't set paravirt_steal_rq_enabled as this would require the
+	 * capability to read another cpu's runstate info.
+	 */
+}

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 */

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 xen_time_setup_guest(void);
 void xen_get_runstate_snapshot(struct vcpu_runstate_info *res);
 
 int xen_setup_shutdown_event(void);

kernel/sched/cputime.c

@@ -489,16 +489,6 @@ void account_process_tick(struct task_struct *p, int user_tick)
 		account_idle_time(cputime_one_jiffy);
 }
 
-/*
- * 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