Merge branch 'kvm-updates/3.1' of git://git.kernel.org/pub/scm/virt/kvm/kvm

* 'kvm-updates/3.1' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (143 commits)
  KVM: IOMMU: Disable device assignment without interrupt remapping
  KVM: MMU: trace mmio page fault
  KVM: MMU: mmio page fault support
  KVM: MMU: reorganize struct kvm_shadow_walk_iterator
  KVM: MMU: lockless walking shadow page table
  KVM: MMU: do not need atomicly to set/clear spte
  KVM: MMU: introduce the rules to modify shadow page table
  KVM: MMU: abstract some functions to handle fault pfn
  KVM: MMU: filter out the mmio pfn from the fault pfn
  KVM: MMU: remove bypass_guest_pf
  KVM: MMU: split kvm_mmu_free_page
  KVM: MMU: count used shadow pages on prepareing path
  KVM: MMU: rename 'pt_write' to 'emulate'
  KVM: MMU: cleanup for FNAME(fetch)
  KVM: MMU: optimize to handle dirty bit
  KVM: MMU: cache mmio info on page fault path
  KVM: x86: introduce vcpu_mmio_gva_to_gpa to cleanup the code
  KVM: MMU: do not update slot bitmap if spte is nonpresent
  KVM: MMU: fix walking shadow page table
  KVM guest: KVM Steal time registration
  ...

4 files changed, 85 insertions, 12 deletions

diff --git a/kernel/compat.c b/kernel/compat.c
index fc9eb093acd5..18197ae2d465 100644
--- a/kernel/compat.c
+++ b/kernel/compat.c
@@ -890,6 +890,7 @@ sigset_from_compat (sigset_t *set, compat_sigset_t *compat)
 	case 1: set->sig[0] = compat->sig[0] | (((long)compat->sig[1]) << 32 );
 	}
 }
+EXPORT_SYMBOL_GPL(sigset_from_compat);
 
 asmlinkage long
 compat_sys_rt_sigtimedwait (compat_sigset_t __user *uthese,
diff --git a/kernel/delayacct.c b/kernel/delayacct.c
index ead9b610aa71..418b3f7053aa 100644
--- a/kernel/delayacct.c
+++ b/kernel/delayacct.c
@@ -19,8 +19,10 @@
 #include <linux/time.h>
 #include <linux/sysctl.h>
 #include <linux/delayacct.h>
+#include <linux/module.h>
 
 int delayacct_on __read_mostly = 1;	/* Delay accounting turned on/off */
+EXPORT_SYMBOL_GPL(delayacct_on);
 struct kmem_cache *delayacct_cache;
 
 static int __init delayacct_setup_disable(char *str)
diff --git a/kernel/sched.c b/kernel/sched.c
index 9aaf567c5da5..751a7cc6a5cd 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -75,6 +75,9 @@
 #include <asm/tlb.h>
 #include <asm/irq_regs.h>
 #include <asm/mutex.h>
+#ifdef CONFIG_PARAVIRT
+#include <asm/paravirt.h>
+#endif
 
 #include "sched_cpupri.h"
 #include "workqueue_sched.h"
@@ -528,6 +531,12 @@ struct rq {
 #ifdef CONFIG_IRQ_TIME_ACCOUNTING
 	u64 prev_irq_time;
 #endif
+#ifdef CONFIG_PARAVIRT
+	u64 prev_steal_time;
+#endif
+#ifdef CONFIG_PARAVIRT_TIME_ACCOUNTING
+	u64 prev_steal_time_rq;
+#endif
 
 	/* calc_load related fields */
 	unsigned long calc_load_update;
@@ -1921,10 +1930,28 @@ void account_system_vtime(struct task_struct *curr)
 }
 EXPORT_SYMBOL_GPL(account_system_vtime);
 
-static void update_rq_clock_task(struct rq *rq, s64 delta)
+#endif /* CONFIG_IRQ_TIME_ACCOUNTING */
+
+#ifdef CONFIG_PARAVIRT
+static inline u64 steal_ticks(u64 steal)
 {
-	s64 irq_delta;
+	if (unlikely(steal > NSEC_PER_SEC))
+		return div_u64(steal, TICK_NSEC);
 
+	return __iter_div_u64_rem(steal, TICK_NSEC, &steal);
+}
+#endif
+
+static void update_rq_clock_task(struct rq *rq, s64 delta)
+{
+/*
+ * In theory, the compile should just see 0 here, and optimize out the call
+ * to sched_rt_avg_update. But I don't trust it...
+ */
+#if defined(CONFIG_IRQ_TIME_ACCOUNTING) || defined(CONFIG_PARAVIRT_TIME_ACCOUNTING)
+	s64 steal = 0, irq_delta = 0;
+#endif
+#ifdef CONFIG_IRQ_TIME_ACCOUNTING
 	irq_delta = irq_time_read(cpu_of(rq)) - rq->prev_irq_time;
 
 	/*
@@ -1947,12 +1974,35 @@ static void update_rq_clock_task(struct rq *rq, s64 delta)
 
 	rq->prev_irq_time += irq_delta;
 	delta -= irq_delta;
+#endif
+#ifdef CONFIG_PARAVIRT_TIME_ACCOUNTING
+	if (static_branch((&paravirt_steal_rq_enabled))) {
+		u64 st;
+
+		steal = paravirt_steal_clock(cpu_of(rq));
+		steal -= rq->prev_steal_time_rq;
+
+		if (unlikely(steal > delta))
+			steal = delta;
+
+		st = steal_ticks(steal);
+		steal = st * TICK_NSEC;
+
+		rq->prev_steal_time_rq += steal;
+
+		delta -= steal;
+	}
+#endif
+
 	rq->clock_task += delta;
 
-	if (irq_delta && sched_feat(NONIRQ_POWER))
-		sched_rt_avg_update(rq, irq_delta);
+#if defined(CONFIG_IRQ_TIME_ACCOUNTING) || defined(CONFIG_PARAVIRT_TIME_ACCOUNTING)
+	if ((irq_delta + steal) && sched_feat(NONTASK_POWER))
+		sched_rt_avg_update(rq, irq_delta + steal);
+#endif
 }
 
+#ifdef CONFIG_IRQ_TIME_ACCOUNTING
 static int irqtime_account_hi_update(void)
 {
 	struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat;
@@ -1987,12 +2037,7 @@ static int irqtime_account_si_update(void)
 
 #define sched_clock_irqtime	(0)
 
-static void update_rq_clock_task(struct rq *rq, s64 delta)
-{
-	rq->clock_task += delta;
-}
-
-#endif /* CONFIG_IRQ_TIME_ACCOUNTING */
+#endif
 
 #include "sched_idletask.c"
 #include "sched_fair.c"
@@ -3845,6 +3890,25 @@ void account_idle_time(cputime_t cputime)
 		cpustat->idle = cputime64_add(cpustat->idle, cputime64);
 }
 
+static __always_inline bool steal_account_process_tick(void)
+{
+#ifdef CONFIG_PARAVIRT
+	if (static_branch(&paravirt_steal_enabled)) {
+		u64 steal, st = 0;
+
+		steal = paravirt_steal_clock(smp_processor_id());
+		steal -= this_rq()->prev_steal_time;
+
+		st = steal_ticks(steal);
+		this_rq()->prev_steal_time += st * TICK_NSEC;
+
+		account_steal_time(st);
+		return st;
+	}
+#endif
+	return false;
+}
+
 #ifndef CONFIG_VIRT_CPU_ACCOUNTING
 
 #ifdef CONFIG_IRQ_TIME_ACCOUNTING
@@ -3876,6 +3940,9 @@ static void irqtime_account_process_tick(struct task_struct *p, int user_tick,
 	cputime64_t tmp = cputime_to_cputime64(cputime_one_jiffy);
 	struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat;
 
+	if (steal_account_process_tick())
+		return;
+
 	if (irqtime_account_hi_update()) {
 		cpustat->irq = cputime64_add(cpustat->irq, tmp);
 	} else if (irqtime_account_si_update()) {
@@ -3929,6 +3996,9 @@ void account_process_tick(struct task_struct *p, int user_tick)
 		return;
 	}
 
+	if (steal_account_process_tick())
+		return;
+
 	if (user_tick)
 		account_user_time(p, cputime_one_jiffy, one_jiffy_scaled);
 	else if ((p != rq->idle) || (irq_count() != HARDIRQ_OFFSET))
diff --git a/kernel/sched_features.h b/kernel/sched_features.h
index 1e7066d76c26..2e74677cb040 100644
--- a/kernel/sched_features.h
+++ b/kernel/sched_features.h
@@ -61,9 +61,9 @@ SCHED_FEAT(LB_BIAS, 1)
 SCHED_FEAT(OWNER_SPIN, 1)
 
 /*
- * Decrement CPU power based on irq activity
+ * Decrement CPU power based on time not spent running tasks
  */
-SCHED_FEAT(NONIRQ_POWER, 1)
+SCHED_FEAT(NONTASK_POWER, 1)
 
 /*
  * Queue remote wakeups on the target CPU and process them