Merge branch 'sched/urgent' into sched/core, to pick up dependencies

Signed-off-by: Ingo Molnar <mingo@kernel.org>

8 files changed, 127 insertions, 37 deletions

diff --git a/kernel/events/core.c b/kernel/events/core.c
index a19550d..1903b8f 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -843,6 +843,32 @@ perf_cgroup_mark_enabled(struct perf_event *event,
 		}
 	}
 }
+
+/*
+ * Update cpuctx->cgrp so that it is set when first cgroup event is added and
+ * cleared when last cgroup event is removed.
+ */
+static inline void
+list_update_cgroup_event(struct perf_event *event,
+			 struct perf_event_context *ctx, bool add)
+{
+	struct perf_cpu_context *cpuctx;
+
+	if (!is_cgroup_event(event))
+		return;
+
+	if (add && ctx->nr_cgroups++)
+		return;
+	else if (!add && --ctx->nr_cgroups)
+		return;
+	/*
+	 * Because cgroup events are always per-cpu events,
+	 * this will always be called from the right CPU.
+	 */
+	cpuctx = __get_cpu_context(ctx);
+	cpuctx->cgrp = add ? event->cgrp : NULL;
+}
+
 #else /* !CONFIG_CGROUP_PERF */
 
 static inline bool
@@ -920,6 +946,13 @@ perf_cgroup_mark_enabled(struct perf_event *event,
 			 struct perf_event_context *ctx)
 {
 }
+
+static inline void
+list_update_cgroup_event(struct perf_event *event,
+			 struct perf_event_context *ctx, bool add)
+{
+}
+
 #endif
 
 /*
@@ -1392,6 +1425,7 @@ ctx_group_list(struct perf_event *event, struct perf_event_context *ctx)
 static void
 list_add_event(struct perf_event *event, struct perf_event_context *ctx)
 {
+
 	lockdep_assert_held(&ctx->lock);
 
 	WARN_ON_ONCE(event->attach_state & PERF_ATTACH_CONTEXT);
@@ -1412,8 +1446,7 @@ list_add_event(struct perf_event *event, struct perf_event_context *ctx)
 		list_add_tail(&event->group_entry, list);
 	}
 
-	if (is_cgroup_event(event))
-		ctx->nr_cgroups++;
+	list_update_cgroup_event(event, ctx, true);
 
 	list_add_rcu(&event->event_entry, &ctx->event_list);
 	ctx->nr_events++;
@@ -1581,8 +1614,6 @@ static void perf_group_attach(struct perf_event *event)
 static void
 list_del_event(struct perf_event *event, struct perf_event_context *ctx)
 {
-	struct perf_cpu_context *cpuctx;
-
 	WARN_ON_ONCE(event->ctx != ctx);
 	lockdep_assert_held(&ctx->lock);
 
@@ -1594,20 +1625,7 @@ list_del_event(struct perf_event *event, struct perf_event_context *ctx)
 
 	event->attach_state &= ~PERF_ATTACH_CONTEXT;
 
-	if (is_cgroup_event(event)) {
-		ctx->nr_cgroups--;
-		/*
-		 * Because cgroup events are always per-cpu events, this will
-		 * always be called from the right CPU.
-		 */
-		cpuctx = __get_cpu_context(ctx);
-		/*
-		 * If there are no more cgroup events then clear cgrp to avoid
-		 * stale pointer in update_cgrp_time_from_cpuctx().
-		 */
-		if (!ctx->nr_cgroups)
-			cpuctx->cgrp = NULL;
-	}
+	list_update_cgroup_event(event, ctx, false);
 
 	ctx->nr_events--;
 	if (event->attr.inherit_stat)
@@ -1716,8 +1734,8 @@ static inline int pmu_filter_match(struct perf_event *event)
 static inline int
 event_filter_match(struct perf_event *event)
 {
-	return (event->cpu == -1 || event->cpu == smp_processor_id())
-	    && perf_cgroup_match(event) && pmu_filter_match(event);
+	return (event->cpu == -1 || event->cpu == smp_processor_id()) &&
+	       perf_cgroup_match(event) && pmu_filter_match(event);
 }
 
 static void
@@ -1737,8 +1755,8 @@ event_sched_out(struct perf_event *event,
 	 * maintained, otherwise bogus information is return
 	 * via read() for time_enabled, time_running:
 	 */
-	if (event->state == PERF_EVENT_STATE_INACTIVE
-	    && !event_filter_match(event)) {
+	if (event->state == PERF_EVENT_STATE_INACTIVE &&
+	    !event_filter_match(event)) {
 		delta = tstamp - event->tstamp_stopped;
 		event->tstamp_running += delta;
 		event->tstamp_stopped = tstamp;
@@ -2236,10 +2254,15 @@ perf_install_in_context(struct perf_event_context *ctx,
 
 	lockdep_assert_held(&ctx->mutex);
 
-	event->ctx = ctx;
 	if (event->cpu != -1)
 		event->cpu = cpu;
 
+	/*
+	 * Ensures that if we can observe event->ctx, both the event and ctx
+	 * will be 'complete'. See perf_iterate_sb_cpu().
+	 */
+	smp_store_release(&event->ctx, ctx);
+
 	if (!task) {
 		cpu_function_call(cpu, __perf_install_in_context, event);
 		return;
@@ -5969,6 +5992,14 @@ static void perf_iterate_sb_cpu(perf_iterate_f output, void *data)
 	struct perf_event *event;
 
 	list_for_each_entry_rcu(event, &pel->list, sb_list) {
+		/*
+		 * Skip events that are not fully formed yet; ensure that
+		 * if we observe event->ctx, both event and ctx will be
+		 * complete enough. See perf_install_in_context().
+		 */
+		if (!smp_load_acquire(&event->ctx))
+			continue;
+
 		if (event->state < PERF_EVENT_STATE_INACTIVE)
 			continue;
 		if (!event_filter_match(event))
diff --git a/kernel/futex.c b/kernel/futex.c
index 33664f7..46cb3a3 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -179,7 +179,15 @@ int __read_mostly futex_cmpxchg_enabled;
  * Futex flags used to encode options to functions and preserve them across
  * restarts.
  */
-#define FLAGS_SHARED		0x01
+#ifdef CONFIG_MMU
+# define FLAGS_SHARED		0x01
+#else
+/*
+ * NOMMU does not have per process address space. Let the compiler optimize
+ * code away.
+ */
+# define FLAGS_SHARED		0x00
+#endif
 #define FLAGS_CLOCKRT		0x02
 #define FLAGS_HAS_TIMEOUT	0x04
 
@@ -405,6 +413,16 @@ static void get_futex_key_refs(union futex_key *key)
 	if (!key->both.ptr)
 		return;
 
+	/*
+	 * On MMU less systems futexes are always "private" as there is no per
+	 * process address space. We need the smp wmb nevertheless - yes,
+	 * arch/blackfin has MMU less SMP ...
+	 */
+	if (!IS_ENABLED(CONFIG_MMU)) {
+		smp_mb(); /* explicit smp_mb(); (B) */
+		return;
+	}
+
 	switch (key->both.offset & (FUT_OFF_INODE|FUT_OFF_MMSHARED)) {
 	case FUT_OFF_INODE:
 		ihold(key->shared.inode); /* implies smp_mb(); (B) */
@@ -436,6 +454,9 @@ static void drop_futex_key_refs(union futex_key *key)
 		return;
 	}
 
+	if (!IS_ENABLED(CONFIG_MMU))
+		return;
+
 	switch (key->both.offset & (FUT_OFF_INODE|FUT_OFF_MMSHARED)) {
 	case FUT_OFF_INODE:
 		iput(key->shared.inode);
diff --git a/kernel/irq/msi.c b/kernel/irq/msi.c
index 5499935..19e9dfb 100644
--- a/kernel/irq/msi.c
+++ b/kernel/irq/msi.c
@@ -359,6 +359,17 @@ int msi_domain_alloc_irqs(struct irq_domain *domain, struct device *dev,
 		else
 			dev_dbg(dev, "irq [%d-%d] for MSI\n",
 				virq, virq + desc->nvec_used - 1);
+		/*
+		 * This flag is set by the PCI layer as we need to activate
+		 * the MSI entries before the PCI layer enables MSI in the
+		 * card. Otherwise the card latches a random msi message.
+		 */
+		if (info->flags & MSI_FLAG_ACTIVATE_EARLY) {
+			struct irq_data *irq_data;
+
+			irq_data = irq_domain_get_irq_data(domain, desc->irq);
+			irq_domain_activate_irq(irq_data);
+		}
 	}
 
 	return 0;
diff --git a/kernel/locking/qspinlock_paravirt.h b/kernel/locking/qspinlock_paravirt.h
index 37649e6..8a99abf 100644
--- a/kernel/locking/qspinlock_paravirt.h
+++ b/kernel/locking/qspinlock_paravirt.h
@@ -450,7 +450,7 @@ pv_wait_head_or_lock(struct qspinlock *lock, struct mcs_spinlock *node)
 				goto gotlock;
 			}
 		}
-		WRITE_ONCE(pn->state, vcpu_halted);
+		WRITE_ONCE(pn->state, vcpu_hashed);
 		qstat_inc(qstat_pv_wait_head, true);
 		qstat_inc(qstat_pv_wait_again, waitcnt);
 		pv_wait(&l->locked, _Q_SLOW_VAL);
diff --git a/kernel/locking/qspinlock_stat.h b/kernel/locking/qspinlock_stat.h
index 22e0253..b9d0315 100644
--- a/kernel/locking/qspinlock_stat.h
+++ b/kernel/locking/qspinlock_stat.h
@@ -153,7 +153,6 @@ static ssize_t qstat_read(struct file *file, char __user *user_buf,
 		 */
 		if ((counter == qstat_pv_latency_kick) ||
 		    (counter == qstat_pv_latency_wake)) {
-			stat = 0;
 			if (kicks)
 				stat = DIV_ROUND_CLOSEST_ULL(stat, kicks);
 		}
diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c
index a881c6a..33c79b6 100644
--- a/kernel/power/hibernate.c
+++ b/kernel/power/hibernate.c
@@ -300,12 +300,12 @@ static int create_image(int platform_mode)
 	save_processor_state();
 	trace_suspend_resume(TPS("machine_suspend"), PM_EVENT_HIBERNATE, true);
 	error = swsusp_arch_suspend();
+	/* Restore control flow magically appears here */
+	restore_processor_state();
 	trace_suspend_resume(TPS("machine_suspend"), PM_EVENT_HIBERNATE, false);
 	if (error)
 		printk(KERN_ERR "PM: Error %d creating hibernation image\n",
 			error);
-	/* Restore control flow magically appears here */
-	restore_processor_state();
 	if (!in_suspend)
 		events_check_enabled = false;
 
diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c
index 1934f65..a846cf8 100644
--- a/kernel/sched/cputime.c
+++ b/kernel/sched/cputime.c
@@ -263,6 +263,11 @@ void account_idle_time(cputime_t cputime)
 		cpustat[CPUTIME_IDLE] += (__force u64) cputime;
 }
 
+/*
+ * When a guest is interrupted for a longer amount of time, missed clock
+ * ticks are not redelivered later. Due to that, this function may on
+ * occasion account more time than the calling functions think elapsed.
+ */
 static __always_inline cputime_t steal_account_process_time(cputime_t maxtime)
 {
 #ifdef CONFIG_PARAVIRT
@@ -371,7 +376,7 @@ static void irqtime_account_process_tick(struct task_struct *p, int user_tick,
 	 * idle, or potentially user or system time. Due to rounding,
 	 * other time can exceed ticks occasionally.
 	 */
-	other = account_other_time(cputime);
+	other = account_other_time(ULONG_MAX);
 	if (other >= cputime)
 		return;
 	cputime -= other;
@@ -486,7 +491,7 @@ void account_process_tick(struct task_struct *p, int user_tick)
 	}
 
 	cputime = cputime_one_jiffy;
-	steal = steal_account_process_time(cputime);
+	steal = steal_account_process_time(ULONG_MAX);
 
 	if (steal >= cputime)
 		return;
@@ -508,13 +513,21 @@ void account_process_tick(struct task_struct *p, int user_tick)
  */
 void account_idle_ticks(unsigned long ticks)
 {
+	cputime_t cputime, steal;
 
 	if (sched_clock_irqtime) {
 		irqtime_account_idle_ticks(ticks);
 		return;
 	}
 
-	account_idle_time(jiffies_to_cputime(ticks));
+	cputime = jiffies_to_cputime(ticks);
+	steal = steal_account_process_time(ULONG_MAX);
+
+	if (steal >= cputime)
+		return;
+
+	cputime -= steal;
+	account_idle_time(cputime);
 }
 
 /*
@@ -606,19 +619,25 @@ static void cputime_adjust(struct task_cputime *curr,
 	stime = curr->stime;
 	utime = curr->utime;
 
-	if (utime == 0) {
-		stime = rtime;
+	/*
+	 * If either stime or both stime and utime are 0, assume all runtime is
+	 * userspace. Once a task gets some ticks, the monotonicy code at
+	 * 'update' will ensure things converge to the observed ratio.
+	 */
+	if (stime == 0) {
+		utime = rtime;
 		goto update;
 	}
 
-	if (stime == 0) {
-		utime = rtime;
+	if (utime == 0) {
+		stime = rtime;
 		goto update;
 	}
 
 	stime = scale_stime((__force u64)stime, (__force u64)rtime,
 			    (__force u64)(stime + utime));
 
+update:
 	/*
 	 * Make sure stime doesn't go backwards; this preserves monotonicity
 	 * for utime because rtime is monotonic.
@@ -641,7 +660,6 @@ static void cputime_adjust(struct task_cputime *curr,
 		stime = rtime - utime;
 	}
 
-update:
 	prev->stime = stime;
 	prev->utime = utime;
 out:
@@ -686,6 +704,13 @@ static cputime_t get_vtime_delta(struct task_struct *tsk)
 	unsigned long now = READ_ONCE(jiffies);
 	cputime_t delta, other;
 
+	/*
+	 * Unlike tick based timing, vtime based timing never has lost
+	 * ticks, and no need for steal time accounting to make up for
+	 * lost ticks. Vtime accounts a rounded version of actual
+	 * elapsed time. Limit account_other_time to prevent rounding
+	 * errors from causing elapsed vtime to go negative.
+	 */
 	delta = jiffies_to_cputime(now - tsk->vtime_snap);
 	other = account_other_time(delta);
 	WARN_ON_ONCE(tsk->vtime_snap_whence == VTIME_INACTIVE);
diff --git a/kernel/time/timer.c b/kernel/time/timer.c
index 555670a..32bf6f7 100644
--- a/kernel/time/timer.c
+++ b/kernel/time/timer.c
@@ -1496,6 +1496,7 @@ u64 get_next_timer_interrupt(unsigned long basej, u64 basem)
 	struct timer_base *base = this_cpu_ptr(&timer_bases[BASE_STD]);
 	u64 expires = KTIME_MAX;
 	unsigned long nextevt;
+	bool is_max_delta;
 
 	/*
 	 * Pretend that there is no timer pending if the cpu is offline.
@@ -1506,6 +1507,7 @@ u64 get_next_timer_interrupt(unsigned long basej, u64 basem)
 
 	spin_lock(&base->lock);
 	nextevt = __next_timer_interrupt(base);
+	is_max_delta = (nextevt == base->clk + NEXT_TIMER_MAX_DELTA);
 	base->next_expiry = nextevt;
 	/*
 	 * We have a fresh next event. Check whether we can forward the base:
@@ -1519,7 +1521,8 @@ u64 get_next_timer_interrupt(unsigned long basej, u64 basem)
 		expires = basem;
 		base->is_idle = false;
 	} else {
-		expires = basem + (nextevt - basej) * TICK_NSEC;
+		if (!is_max_delta)
+			expires = basem + (nextevt - basej) * TICK_NSEC;
 		/*
 		 * If we expect to sleep more than a tick, mark the base idle:
 		 */