Merge branch 'timers-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull timer updates from Ingo Molnar:
 "The main changes in the timer code in this cycle were:

   - Clockevent updates:

      - timer-of framework cleanups. (Geert Uytterhoeven)

      - Use timer-of for the renesas-ostm and the device name to prevent
        name collision in case of multiple timers. (Geert Uytterhoeven)

      - Check if there is an error after calling of_clk_get in asm9260
        (Chuhong Yuan)

   - ABI fix: Zero out high order bits of nanoseconds on compat
     syscalls. This got broken a year ago, with apparently no side
     effects so far.

     Since the kernel would use random data otherwise I don't think we'd
     have other options but to fix the bug, even if there was a side
     effect to applications (Dmitry Safonov)

   - Optimize ns_to_timespec64() on 32-bit systems: move away from
     div_s64_rem() which can be slow, to div_u64_rem() which is faster
     (Arnd Bergmann)

   - Annotate KCSAN-reported false positive data races in
     hrtimer_is_queued() users by moving timer->state handling over to
     the READ_ONCE()/WRITE_ONCE() APIs. This documents these accesses
     (Eric Dumazet)

   - Misc cleanups and small fixes"

[ I undid the "ABI fix" and updated the comments instead. The reason
  there were apparently no side effects is that the fix was a no-op.

  The updated comment is to say _why_ it was a no-op.    - Linus ]

* 'timers-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  time: Zero the upper 32-bits in __kernel_timespec on 32-bit
  time: Rename tsk->real_start_time to ->start_boottime
  hrtimer: Remove the comment about not used HRTIMER_SOFTIRQ
  time: Fix spelling mistake in comment
  time: Optimize ns_to_timespec64()
  hrtimer: Annotate lockless access to timer->state
  clocksource/drivers/asm9260: Add a check for of_clk_get
  clocksource/drivers/renesas-ostm: Use unique device name instead of ostm
  clocksource/drivers/renesas-ostm: Convert to timer_of
  clocksource/drivers/timer-of: Use unique device name instead of timer
  clocksource/drivers/timer-of: Convert last full_name to %pOF

drivers/clocksource/Kconfig

@@ -528,6 +528,7 @@ config SH_TIMER_MTU2
 config RENESAS_OSTM
 	bool "Renesas OSTM timer driver" if COMPILE_TEST
 	select CLKSRC_MMIO
+	select TIMER_OF
 	help
 	  Enables the support for the Renesas OSTM.
 

drivers/clocksource/asm9260_timer.c

@@ -194,6 +194,10 @@ static int __init asm9260_timer_init(struct device_node *np)
 	}
 
 	clk = of_clk_get(np, 0);
+	if (IS_ERR(clk)) {
+		pr_err("Failed to get clk!\n");
+		return PTR_ERR(clk);
+	}
 
 	ret = clk_prepare_enable(clk);
 	if (ret) {

drivers/clocksource/renesas-ostm.c

@@ -6,14 +6,14 @@
  * Copyright (C) 2017 Chris Brandt
  */
 
-#include <linux/of_address.h>
-#include <linux/of_irq.h>
 #include <linux/clk.h>
 #include <linux/clockchips.h>
 #include <linux/interrupt.h>
 #include <linux/sched_clock.h>
 #include <linux/slab.h>
 
+#include "timer-of.h"
+
 /*
  * The OSTM contains independent channels.
  * The first OSTM channel probed will be set up as a free running
@@ -24,12 +24,6 @@
  * driven clock event.
  */
 
-struct ostm_device {
-	void __iomem *base;
-	unsigned long ticks_per_jiffy;
-	struct clock_event_device ced;
-};
-
 static void __iomem *system_clock;	/* For sched_clock() */
 
 /* OSTM REGISTERS */
@@ -47,41 +41,32 @@ static void __iomem *system_clock;	/* For sched_clock() */
 #define	CTL_ONESHOT		0x02
 #define	CTL_FREERUN		0x02
 
-static struct ostm_device *ced_to_ostm(struct clock_event_device *ced)
+static void ostm_timer_stop(struct timer_of *to)
 {
-	return container_of(ced, struct ostm_device, ced);
-}
-
-static void ostm_timer_stop(struct ostm_device *ostm)
-{
-	if (readb(ostm->base + OSTM_TE) & TE) {
-		writeb(TT, ostm->base + OSTM_TT);
+	if (readb(timer_of_base(to) + OSTM_TE) & TE) {
+		writeb(TT, timer_of_base(to) + OSTM_TT);
 
 		/*
 		 * Read back the register simply to confirm the write operation
 		 * has completed since I/O writes can sometimes get queued by
 		 * the bus architecture.
 		 */
-		while (readb(ostm->base + OSTM_TE) & TE)
+		while (readb(timer_of_base(to) + OSTM_TE) & TE)
 			;
 	}
 }
 
-static int __init ostm_init_clksrc(struct ostm_device *ostm, unsigned long rate)
+static int __init ostm_init_clksrc(struct timer_of *to)
 {
-	/*
-	 * irq not used (clock sources don't use interrupts)
-	 */
+	ostm_timer_stop(to);
 
-	ostm_timer_stop(ostm);
+	writel(0, timer_of_base(to) + OSTM_CMP);
+	writeb(CTL_FREERUN, timer_of_base(to) + OSTM_CTL);
+	writeb(TS, timer_of_base(to) + OSTM_TS);
 
-	writel(0, ostm->base + OSTM_CMP);
-	writeb(CTL_FREERUN, ostm->base + OSTM_CTL);
-	writeb(TS, ostm->base + OSTM_TS);
-
-	return clocksource_mmio_init(ostm->base + OSTM_CNT,
-			"ostm", rate,
-			300, 32, clocksource_mmio_readl_up);
+	return clocksource_mmio_init(timer_of_base(to) + OSTM_CNT,
+				     to->np->full_name, timer_of_rate(to), 300,
+				     32, clocksource_mmio_readl_up);
 }
 
 static u64 notrace ostm_read_sched_clock(void)
@@ -89,87 +74,75 @@ static u64 notrace ostm_read_sched_clock(void)
 	return readl(system_clock);
 }
 
-static void __init ostm_init_sched_clock(struct ostm_device *ostm,
-			unsigned long rate)
+static void __init ostm_init_sched_clock(struct timer_of *to)
 {
-	system_clock = ostm->base + OSTM_CNT;
-	sched_clock_register(ostm_read_sched_clock, 32, rate);
+	system_clock = timer_of_base(to) + OSTM_CNT;
+	sched_clock_register(ostm_read_sched_clock, 32, timer_of_rate(to));
 }
 
 static int ostm_clock_event_next(unsigned long delta,
 				 struct clock_event_device *ced)
 {
-	struct ostm_device *ostm = ced_to_ostm(ced);
+	struct timer_of *to = to_timer_of(ced);
 
-	ostm_timer_stop(ostm);
+	ostm_timer_stop(to);
 
-	writel(delta, ostm->base + OSTM_CMP);
-	writeb(CTL_ONESHOT, ostm->base + OSTM_CTL);
-	writeb(TS, ostm->base + OSTM_TS);
+	writel(delta, timer_of_base(to) + OSTM_CMP);
+	writeb(CTL_ONESHOT, timer_of_base(to) + OSTM_CTL);
+	writeb(TS, timer_of_base(to) + OSTM_TS);
 
 	return 0;
 }
 
 static int ostm_shutdown(struct clock_event_device *ced)
 {
-	struct ostm_device *ostm = ced_to_ostm(ced);
+	struct timer_of *to = to_timer_of(ced);
 
-	ostm_timer_stop(ostm);
+	ostm_timer_stop(to);
 
 	return 0;
 }
 static int ostm_set_periodic(struct clock_event_device *ced)
 {
-	struct ostm_device *ostm = ced_to_ostm(ced);
+	struct timer_of *to = to_timer_of(ced);
 
 	if (clockevent_state_oneshot(ced) || clockevent_state_periodic(ced))
-		ostm_timer_stop(ostm);
+		ostm_timer_stop(to);
 
-	writel(ostm->ticks_per_jiffy - 1, ostm->base + OSTM_CMP);
-	writeb(CTL_PERIODIC, ostm->base + OSTM_CTL);
-	writeb(TS, ostm->base + OSTM_TS);
+	writel(timer_of_period(to) - 1, timer_of_base(to) + OSTM_CMP);
+	writeb(CTL_PERIODIC, timer_of_base(to) + OSTM_CTL);
+	writeb(TS, timer_of_base(to) + OSTM_TS);
 
 	return 0;
 }
 
 static int ostm_set_oneshot(struct clock_event_device *ced)
 {
-	struct ostm_device *ostm = ced_to_ostm(ced);
+	struct timer_of *to = to_timer_of(ced);
 
-	ostm_timer_stop(ostm);
+	ostm_timer_stop(to);
 
 	return 0;
 }
 
 static irqreturn_t ostm_timer_interrupt(int irq, void *dev_id)
 {
-	struct ostm_device *ostm = dev_id;
+	struct clock_event_device *ced = dev_id;
 
-	if (clockevent_state_oneshot(&ostm->ced))
-		ostm_timer_stop(ostm);
+	if (clockevent_state_oneshot(ced))
+		ostm_timer_stop(to_timer_of(ced));
 
 	/* notify clockevent layer */
-	if (ostm->ced.event_handler)
-		ostm->ced.event_handler(&ostm->ced);
+	if (ced->event_handler)
+		ced->event_handler(ced);
 
 	return IRQ_HANDLED;
 }
 
-static int __init ostm_init_clkevt(struct ostm_device *ostm, int irq,
-			unsigned long rate)
+static int __init ostm_init_clkevt(struct timer_of *to)
 {
-	struct clock_event_device *ced = &ostm->ced;
-	int ret = -ENXIO;
-
-	ret = request_irq(irq, ostm_timer_interrupt,
-			  IRQF_TIMER | IRQF_IRQPOLL,
-			  "ostm", ostm);
-	if (ret) {
-		pr_err("ostm: failed to request irq\n");
-		return ret;
-	}
+	struct clock_event_device *ced = &to->clkevt;
 
-	ced->name = "ostm";
 	ced->features = CLOCK_EVT_FEAT_ONESHOT | CLOCK_EVT_FEAT_PERIODIC;
 	ced->set_state_shutdown = ostm_shutdown;
 	ced->set_state_periodic = ostm_set_periodic;
@@ -178,79 +151,61 @@ static int __init ostm_init_clkevt(struct ostm_device *ostm, int irq,
 	ced->shift = 32;
 	ced->rating = 300;
 	ced->cpumask = cpumask_of(0);
-	clockevents_config_and_register(ced, rate, 0xf, 0xffffffff);
+	clockevents_config_and_register(ced, timer_of_rate(to), 0xf,
+					0xffffffff);
 
 	return 0;
 }
 
 static int __init ostm_init(struct device_node *np)
 {
-	struct ostm_device *ostm;
-	int ret = -EFAULT;
-	struct clk *ostm_clk = NULL;
-	int irq;
-	unsigned long rate;
-
-	ostm = kzalloc(sizeof(*ostm), GFP_KERNEL);
-	if (!ostm)
-		return -ENOMEM;
-
-	ostm->base = of_iomap(np, 0);
-	if (!ostm->base) {
-		pr_err("ostm: failed to remap I/O memory\n");
-		goto err;
-	}
+	struct timer_of *to;
+	int ret;
 
-	irq = irq_of_parse_and_map(np, 0);
-	if (irq < 0) {
-		pr_err("ostm: Failed to get irq\n");
-		goto err;
-	}
-
-	ostm_clk = of_clk_get(np, 0);
-	if (IS_ERR(ostm_clk)) {
-		pr_err("ostm: Failed to get clock\n");
-		ostm_clk = NULL;
-		goto err;
-	}
+	to = kzalloc(sizeof(*to), GFP_KERNEL);
+	if (!to)
+		return -ENOMEM;
 
-	ret = clk_prepare_enable(ostm_clk);
-	if (ret) {
-		pr_err("ostm: Failed to enable clock\n");
-		goto err;
+	to->flags = TIMER_OF_BASE | TIMER_OF_CLOCK;
+	if (system_clock) {
+		/*
+		 * clock sources don't use interrupts, clock events do
+		 */
+		to->flags |= TIMER_OF_IRQ;
+		to->of_irq.flags = IRQF_TIMER | IRQF_IRQPOLL;
+		to->of_irq.handler = ostm_timer_interrupt;
 	}
 
-	rate = clk_get_rate(ostm_clk);
-	ostm->ticks_per_jiffy = DIV_ROUND_CLOSEST(rate, HZ);
+	ret = timer_of_init(np, to);
+	if (ret)
+		goto err_free;
 
 	/*
 	 * First probed device will be used as system clocksource. Any
 	 * additional devices will be used as clock events.
 	 */
 	if (!system_clock) {
-		ret = ostm_init_clksrc(ostm, rate);
-
-		if (!ret) {
-			ostm_init_sched_clock(ostm, rate);
-			pr_info("ostm: used for clocksource\n");
-		}
+		ret = ostm_init_clksrc(to);
+		if (ret)
+			goto err_cleanup;
 
+		ostm_init_sched_clock(to);
+		pr_info("%pOF: used for clocksource\n", np);
 	} else {
-		ret = ostm_init_clkevt(ostm, irq, rate);
-
-		if (!ret)
-			pr_info("ostm: used for clock events\n");
-	}
+		ret = ostm_init_clkevt(to);
+		if (ret)
+			goto err_cleanup;
 
-err:
-	if (ret) {
-		clk_disable_unprepare(ostm_clk);
-		iounmap(ostm->base);
-		kfree(ostm);
-		return ret;
+		pr_info("%pOF: used for clock events\n", np);
 	}
 
 	return 0;
+
+err_cleanup:
+	timer_of_cleanup(to);
+err_free:
+	kfree(to);
+	return ret;
 }
 
 TIMER_OF_DECLARE(ostm, "renesas,ostm", ostm_init);

drivers/clocksource/timer-of.c

@@ -57,8 +57,8 @@ static __init int timer_of_irq_init(struct device_node *np,
 	if (of_irq->name) {
 		of_irq->irq = ret = of_irq_get_byname(np, of_irq->name);
 		if (ret < 0) {
-			pr_err("Failed to get interrupt %s for %s\n",
-			       of_irq->name, np->full_name);
+			pr_err("Failed to get interrupt %s for %pOF\n",
+			       of_irq->name, np);
 			return ret;
 		}
 	} else	{
@@ -192,7 +192,7 @@ int __init timer_of_init(struct device_node *np, struct timer_of *to)
 	}
 
 	if (!to->clkevt.name)
-		to->clkevt.name = np->name;
+		to->clkevt.name = np->full_name;
 
 	to->np = np;
 

fs/exec.c

@@ -1131,7 +1131,7 @@ static int de_thread(struct task_struct *tsk)
 		 * also take its birthdate (always earlier than our own).
 		 */
 		tsk->start_time = leader->start_time;
-		tsk->real_start_time = leader->real_start_time;
+		tsk->start_boottime = leader->start_boottime;
 
 		BUG_ON(!same_thread_group(leader, tsk));
 		BUG_ON(has_group_leader_pid(tsk));

fs/proc/array.c

@@ -533,7 +533,7 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns,
 	nice = task_nice(task);
 
 	/* convert nsec -> ticks */
-	start_time = nsec_to_clock_t(task->real_start_time);
+	start_time = nsec_to_clock_t(task->start_boottime);
 
 	seq_put_decimal_ull(m, "", pid_nr_ns(pid, ns));
 	seq_puts(m, " (");

include/linux/hrtimer.h

@@ -456,12 +456,18 @@ extern u64 hrtimer_next_event_without(const struct hrtimer *exclude);
 
 extern bool hrtimer_active(const struct hrtimer *timer);
 
-/*
- * Helper function to check, whether the timer is on one of the queues
+/**
+ * hrtimer_is_queued = check, whether the timer is on one of the queues
+ * @timer:	Timer to check
+ *
+ * Returns: True if the timer is queued, false otherwise
+ *
+ * The function can be used lockless, but it gives only a current snapshot.
  */
-static inline int hrtimer_is_queued(struct hrtimer *timer)
+static inline bool hrtimer_is_queued(struct hrtimer *timer)
 {
-	return timer->state & HRTIMER_STATE_ENQUEUED;
+	/* The READ_ONCE pairs with the update functions of timer->state */
+	return !!(READ_ONCE(timer->state) & HRTIMER_STATE_ENQUEUED);
 }
 
 /*

include/linux/interrupt.h

@@ -533,8 +533,7 @@ enum
 	IRQ_POLL_SOFTIRQ,
 	TASKLET_SOFTIRQ,
 	SCHED_SOFTIRQ,
-	HRTIMER_SOFTIRQ, /* Unused, but kept as tools rely on the
-			    numbering. Sigh! */
+	HRTIMER_SOFTIRQ,
 	RCU_SOFTIRQ,    /* Preferable RCU should always be the last softirq */
 
 	NR_SOFTIRQS

include/linux/sched.h

@@ -862,7 +862,7 @@ struct task_struct {
 	u64				start_time;
 
 	/* Boot based time in nsecs: */
-	u64				real_start_time;
+	u64				start_boottime;
 
 	/* MM fault and swap info: this can arguably be seen as either mm-specific or thread-specific: */
 	unsigned long			min_flt;

kernel/fork.c

@@ -2185,7 +2185,7 @@ static __latent_entropy struct task_struct *copy_process(
 	 */
 
 	p->start_time = ktime_get_ns();
-	p->real_start_time = ktime_get_boottime_ns();
+	p->start_boottime = ktime_get_boottime_ns();
 
 	/*
 	 * Make it visible to the rest of the system, but dont wake it up yet.

kernel/time/hrtimer.c

@@ -966,7 +966,8 @@ static int enqueue_hrtimer(struct hrtimer *timer,
 
 	base->cpu_base->active_bases |= 1 << base->index;
 
-	timer->state = HRTIMER_STATE_ENQUEUED;
+	/* Pairs with the lockless read in hrtimer_is_queued() */
+	WRITE_ONCE(timer->state, HRTIMER_STATE_ENQUEUED);
 
 	return timerqueue_add(&base->active, &timer->node);
 }
@@ -988,7 +989,8 @@ static void __remove_hrtimer(struct hrtimer *timer,
 	struct hrtimer_cpu_base *cpu_base = base->cpu_base;
 	u8 state = timer->state;
 
-	timer->state = newstate;
+	/* Pairs with the lockless read in hrtimer_is_queued() */
+	WRITE_ONCE(timer->state, newstate);
 	if (!(state & HRTIMER_STATE_ENQUEUED))
 		return;
 
@@ -1013,8 +1015,9 @@ static void __remove_hrtimer(struct hrtimer *timer,
 static inline int
 remove_hrtimer(struct hrtimer *timer, struct hrtimer_clock_base *base, bool restart)
 {
-	if (hrtimer_is_queued(timer)) {
 	u8 state = timer->state;
+
+	if (state & HRTIMER_STATE_ENQUEUED) {
 		int reprogram;
 
 		/*

kernel/time/time.c

@@ -179,7 +179,7 @@ int do_sys_settimeofday64(const struct timespec64 *tv, const struct timezone *tz
 		return error;
 
 	if (tz) {
-		/* Verify we're witin the +-15 hrs range */
+		/* Verify we're within the +-15 hrs range */
 		if (tz->tz_minuteswest > 15*60 || tz->tz_minuteswest < -15*60)
 			return -EINVAL;
 
@@ -548,18 +548,21 @@ EXPORT_SYMBOL(set_normalized_timespec64);
  */
 struct timespec64 ns_to_timespec64(const s64 nsec)
 {
-	struct timespec64 ts;
+	struct timespec64 ts = { 0, 0 };
 	s32 rem;
 
-	if (!nsec)
-		return (struct timespec64) {0, 0};
-
-	ts.tv_sec = div_s64_rem(nsec, NSEC_PER_SEC, &rem);
-	if (unlikely(rem < 0)) {
-		ts.tv_sec--;
-		rem += NSEC_PER_SEC;
-	}
+	if (likely(nsec > 0)) {
+		ts.tv_sec = div_u64_rem(nsec, NSEC_PER_SEC, &rem);
 		ts.tv_nsec = rem;
+	} else if (nsec < 0) {
+		/*
+		 * With negative times, tv_sec points to the earlier
+		 * second, and tv_nsec counts the nanoseconds since
+		 * then, so tv_nsec is always a positive number.
+		 */
+		ts.tv_sec = -div_u64_rem(-nsec - 1, NSEC_PER_SEC, &rem) - 1;
+		ts.tv_nsec = NSEC_PER_SEC - rem - 1;
+	}
 
 	return ts;
 }
@@ -878,10 +881,11 @@ int get_timespec64(struct timespec64 *ts,
 
 	ts->tv_sec = kts.tv_sec;
 
-	/* Zero out the padding for 32 bit systems or in compat mode */
+	/* Zero out the padding in compat mode */
 	if (in_compat_syscall())
 		kts.tv_nsec &= 0xFFFFFFFFUL;
 
+	/* In 32-bit mode, this drops the padding */
 	ts->tv_nsec = kts.tv_nsec;
 
 	return 0;