Merge branch 'perf/urgent' into perf/core, to pick up dependency

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

kernel/events/uprobes.c

@@ -172,8 +172,10 @@ static int __replace_page(struct vm_area_struct *vma, unsigned long addr,
 	mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end);
 	err = -EAGAIN;
 	ptep = page_check_address(page, mm, addr, &ptl, 0);
-	if (!ptep)
+	if (!ptep) {
+		mem_cgroup_cancel_charge(kpage, memcg, false);
 		goto unlock;
+	}
 
 	get_page(kpage);
 	page_add_new_anon_rmap(kpage, vma, addr, false);
@@ -200,7 +202,6 @@ static int __replace_page(struct vm_area_struct *vma, unsigned long addr,
 
 	err = 0;
  unlock:
-	mem_cgroup_cancel_charge(kpage, memcg, false);
 	mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end);
 	unlock_page(page);
 	return err;

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);

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;

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);

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);
 		}

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;
 

kernel/printk/internal.h

@@ -16,11 +16,9 @@
  */
 #include <linux/percpu.h>
 
-typedef __printf(2, 0) int (*printk_func_t)(int level, const char *fmt,
-					    va_list args);
+typedef __printf(1, 0) int (*printk_func_t)(const char *fmt, va_list args);
 
-__printf(2, 0)
-int vprintk_default(int level, const char *fmt, va_list args);
+int __printf(1, 0) vprintk_default(const char *fmt, va_list args);
 
 #ifdef CONFIG_PRINTK_NMI
 
@@ -33,10 +31,9 @@ extern raw_spinlock_t logbuf_lock;
  * via per-CPU variable.
  */
 DECLARE_PER_CPU(printk_func_t, printk_func);
-__printf(2, 0)
-static inline int vprintk_func(int level, const char *fmt, va_list args)
+static inline __printf(1, 0) int vprintk_func(const char *fmt, va_list args)
 {
-	return this_cpu_read(printk_func)(level, fmt, args);
+	return this_cpu_read(printk_func)(fmt, args);
 }
 
 extern atomic_t nmi_message_lost;
@@ -47,10 +44,9 @@ static inline int get_nmi_message_lost(void)
 
 #else /* CONFIG_PRINTK_NMI */
 
-__printf(2, 0)
-static inline int vprintk_func(int level, const char *fmt, va_list args)
+static inline __printf(1, 0) int vprintk_func(const char *fmt, va_list args)
 {
-	return vprintk_default(level, fmt, args);
+	return vprintk_default(fmt, args);
 }
 
 static inline int get_nmi_message_lost(void)

kernel/printk/nmi.c

@@ -58,7 +58,7 @@ static DEFINE_PER_CPU(struct nmi_seq_buf, nmi_print_seq);
  * one writer running. But the buffer might get flushed from another
  * CPU, so we need to be careful.
  */
-static int vprintk_nmi(int level, const char *fmt, va_list args)
+static int vprintk_nmi(const char *fmt, va_list args)
 {
 	struct nmi_seq_buf *s = this_cpu_ptr(&nmi_print_seq);
 	int add = 0;
@@ -79,16 +79,7 @@ again:
 	if (!len)
 		smp_rmb();
 
-	if (level != LOGLEVEL_DEFAULT) {
-		add = snprintf(s->buffer + len, sizeof(s->buffer) - len,
-				KERN_SOH "%c", '0' + level);
-		add += vsnprintf(s->buffer + len + add,
-				 sizeof(s->buffer) - len - add,
-				 fmt, args);
-	} else {
-		add = vsnprintf(s->buffer + len, sizeof(s->buffer) - len,
-				fmt, args);
-	}
+	add = vsnprintf(s->buffer + len, sizeof(s->buffer) - len, fmt, args);
 
 	/*
 	 * Do it once again if the buffer has been flushed in the meantime.

kernel/printk/printk.c

@@ -1930,26 +1930,7 @@ asmlinkage int printk_emit(int facility, int level,
 }
 EXPORT_SYMBOL(printk_emit);
 
-#define define_pr_level(func, loglevel)				\
-asmlinkage __visible void func(const char *fmt, ...)		\
-{								\
-	va_list args;						\
-								\
-	va_start(args, fmt);					\
-	vprintk_default(loglevel, fmt, args);			\
-	va_end(args);						\
-}								\
-EXPORT_SYMBOL(func)
-
-define_pr_level(__pr_emerg, LOGLEVEL_EMERG);
-define_pr_level(__pr_alert, LOGLEVEL_ALERT);
-define_pr_level(__pr_crit, LOGLEVEL_CRIT);
-define_pr_level(__pr_err, LOGLEVEL_ERR);
-define_pr_level(__pr_warn, LOGLEVEL_WARNING);
-define_pr_level(__pr_notice, LOGLEVEL_NOTICE);
-define_pr_level(__pr_info, LOGLEVEL_INFO);
-
-int vprintk_default(int level, const char *fmt, va_list args)
+int vprintk_default(const char *fmt, va_list args)
 {
 	int r;
 
@@ -1959,7 +1940,7 @@ int vprintk_default(int level, const char *fmt, va_list args)
 		return r;
 	}
 #endif
-	r = vprintk_emit(0, level, NULL, 0, fmt, args);
+	r = vprintk_emit(0, LOGLEVEL_DEFAULT, NULL, 0, fmt, args);
 
 	return r;
 }
@@ -1992,7 +1973,7 @@ asmlinkage __visible int printk(const char *fmt, ...)
 	int r;
 
 	va_start(args, fmt);
-	r = vprintk_func(LOGLEVEL_DEFAULT, fmt, args);
+	r = vprintk_func(fmt, args);
 	va_end(args);
 
 	return r;

kernel/sched/core.c

@@ -74,6 +74,7 @@
 #include <linux/context_tracking.h>
 #include <linux/compiler.h>
 #include <linux/frame.h>
+#include <linux/prefetch.h>
 
 #include <asm/switch_to.h>
 #include <asm/tlb.h>
@@ -2971,6 +2972,23 @@ DEFINE_PER_CPU(struct kernel_cpustat, kernel_cpustat);
 EXPORT_PER_CPU_SYMBOL(kstat);
 EXPORT_PER_CPU_SYMBOL(kernel_cpustat);
 
+/*
+ * The function fair_sched_class.update_curr accesses the struct curr
+ * and its field curr->exec_start; when called from task_sched_runtime(),
+ * we observe a high rate of cache misses in practice.
+ * Prefetching this data results in improved performance.
+ */
+static inline void prefetch_curr_exec_start(struct task_struct *p)
+{
+#ifdef CONFIG_FAIR_GROUP_SCHED
+	struct sched_entity *curr = (&p->se)->cfs_rq->curr;
+#else
+	struct sched_entity *curr = (&task_rq(p)->cfs)->curr;
+#endif
+	prefetch(curr);
+	prefetch(&curr->exec_start);
+}
+
 /*
  * Return accounted runtime for the task.
  * In case the task is currently running, return the runtime plus current's
@@ -3005,6 +3023,7 @@ unsigned long long task_sched_runtime(struct task_struct *p)
 	 * thread, breaking clock_gettime().
 	 */
 	if (task_current(rq, p) && task_on_rq_queued(p)) {
+		prefetch_curr_exec_start(p);
 		update_rq_clock(rq);
 		p->sched_class->update_curr(rq);
 	}

kernel/sched/cpudeadline.c

@@ -168,7 +168,7 @@ void cpudl_set(struct cpudl *cp, int cpu, u64 dl, int is_valid)
 
 	if (old_idx == IDX_INVALID) {
 		cp->size++;
-		cp->elements[cp->size - 1].dl = 0;
+		cp->elements[cp->size - 1].dl = dl;
 		cp->elements[cp->size - 1].cpu = cpu;
 		cp->elements[cpu].idx = cp->size - 1;
 		cpudl_change_key(cp, cp->size - 1, dl);

kernel/sched/cputime.c

@@ -508,13 +508,21 @@ 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(cputime);
+
+	if (steal >= cputime)
+		return;
+
+	cputime -= steal;
+	account_idle_time(cputime);
 }
 
 /*

kernel/sched/deadline.c

@@ -658,8 +658,11 @@ static enum hrtimer_restart dl_task_timer(struct hrtimer *timer)
 	 *
 	 * XXX figure out if select_task_rq_dl() deals with offline cpus.
 	 */
-	if (unlikely(!rq->online))
+	if (unlikely(!rq->online)) {
+		lockdep_unpin_lock(&rq->lock, rf.cookie);
 		rq = dl_task_offline_migration(rq, p);
+		rf.cookie = lockdep_pin_lock(&rq->lock);
+	}
 
 	/*
 	 * Queueing this task back might have overloaded rq, check if we need

kernel/sched/fair.c

@@ -4269,7 +4269,7 @@ static void sync_throttle(struct task_group *tg, int cpu)
 	pcfs_rq = tg->parent->cfs_rq[cpu];
 
 	cfs_rq->throttle_count = pcfs_rq->throttle_count;
-	pcfs_rq->throttled_clock_task = rq_clock_task(cpu_rq(cpu));
+	cfs_rq->throttled_clock_task = rq_clock_task(cpu_rq(cpu));
 }
 
 /* conditionally throttle active cfs_rq's from put_prev_entity() */

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:
 		 */