Merge branch 'timers/urgent' into timers/core

Pick up dependent changes.

17 files changed, 107 insertions, 109 deletions

diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index c3c9a0e1b3c9..8d4e85eae42c 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -4265,6 +4265,11 @@ static void kill_css(struct cgroup_subsys_state *css)
 {
 	lockdep_assert_held(&cgroup_mutex);
 
+	if (css->flags & CSS_DYING)
+		return;
+
+	css->flags |= CSS_DYING;
+
 	/*
 	 * This must happen before css is disassociated with its cgroup.
 	 * See seq_css() for details.
diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index f6501f4f6040..ae643412948a 100644
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -176,9 +176,9 @@ typedef enum {
 } cpuset_flagbits_t;
 
 /* convenient tests for these bits */
-static inline bool is_cpuset_online(const struct cpuset *cs)
+static inline bool is_cpuset_online(struct cpuset *cs)
 {
-	return test_bit(CS_ONLINE, &cs->flags);
+	return test_bit(CS_ONLINE, &cs->flags) && !css_is_dying(&cs->css);
 }
 
 static inline int is_cpu_exclusive(const struct cpuset *cs)
diff --git a/kernel/cpu.c b/kernel/cpu.c
index 9ae6fbe5b5cf..cb5103413bd8 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -1658,13 +1658,13 @@ static ssize_t write_cpuhp_target(struct device *dev,
 	ret = !sp->name || sp->cant_stop ? -EINVAL : 0;
 	mutex_unlock(&cpuhp_state_mutex);
 	if (ret)
-		return ret;
+		goto out;
 
 	if (st->state < target)
 		ret = do_cpu_up(dev->id, target);
 	else
 		ret = do_cpu_down(dev->id, target);
-
+out:
 	unlock_device_hotplug();
 	return ret ? ret : count;
 }
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 6e75a5c9412d..6c4e523dc1e2 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -7316,6 +7316,21 @@ int perf_event_account_interrupt(struct perf_event *event)
 	return __perf_event_account_interrupt(event, 1);
 }
 
+static bool sample_is_allowed(struct perf_event *event, struct pt_regs *regs)
+{
+	/*
+	 * Due to interrupt latency (AKA "skid"), we may enter the
+	 * kernel before taking an overflow, even if the PMU is only
+	 * counting user events.
+	 * To avoid leaking information to userspace, we must always
+	 * reject kernel samples when exclude_kernel is set.
+	 */
+	if (event->attr.exclude_kernel && !user_mode(regs))
+		return false;
+
+	return true;
+}
+
 /*
  * Generic event overflow handling, sampling.
  */
@@ -7337,6 +7352,12 @@ static int __perf_event_overflow(struct perf_event *event,
 	ret = __perf_event_account_interrupt(event, throttle);
 
 	/*
+	 * For security, drop the skid kernel samples if necessary.
+	 */
+	if (!sample_is_allowed(event, regs))
+		return ret;
+
+	/*
 	 * XXX event_limit might not quite work as expected on inherited
 	 * events
 	 */
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index 070be980c37a..425170d4439b 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -1312,8 +1312,10 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new)
 			ret = __irq_set_trigger(desc,
 						new->flags & IRQF_TRIGGER_MASK);
 
-			if (ret)
+			if (ret) {
+				irq_release_resources(desc);
 				goto out_mask;
+			}
 		}
 
 		desc->istate &= ~(IRQS_AUTODETECT | IRQS_SPURIOUS_DISABLED | \
diff --git a/kernel/power/process.c b/kernel/power/process.c
index 78672d324a6e..c7209f060eeb 100644
--- a/kernel/power/process.c
+++ b/kernel/power/process.c
@@ -132,7 +132,7 @@ int freeze_processes(void)
 	if (!pm_freezing)
 		atomic_inc(&system_freezing_cnt);
 
-	pm_wakeup_clear(true);
+	pm_wakeup_clear();
 	pr_info("Freezing user space processes ... ");
 	pm_freezing = true;
 	error = try_to_freeze_tasks(true);
diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c
index c0248c74d6d4..15e6baef5c73 100644
--- a/kernel/power/suspend.c
+++ b/kernel/power/suspend.c
@@ -72,8 +72,6 @@ static void freeze_begin(void)
 
 static void freeze_enter(void)
 {
-	trace_suspend_resume(TPS("machine_suspend"), PM_SUSPEND_FREEZE, true);
-
 	spin_lock_irq(&suspend_freeze_lock);
 	if (pm_wakeup_pending())
 		goto out;
@@ -100,27 +98,6 @@ static void freeze_enter(void)
  out:
 	suspend_freeze_state = FREEZE_STATE_NONE;
 	spin_unlock_irq(&suspend_freeze_lock);
-
-	trace_suspend_resume(TPS("machine_suspend"), PM_SUSPEND_FREEZE, false);
-}
-
-static void s2idle_loop(void)
-{
-	do {
-		freeze_enter();
-
-		if (freeze_ops && freeze_ops->wake)
-			freeze_ops->wake();
-
-		dpm_resume_noirq(PMSG_RESUME);
-		if (freeze_ops && freeze_ops->sync)
-			freeze_ops->sync();
-
-		if (pm_wakeup_pending())
-			break;
-
-		pm_wakeup_clear(false);
-	} while (!dpm_suspend_noirq(PMSG_SUSPEND));
 }
 
 void freeze_wake(void)
@@ -394,8 +371,10 @@ static int suspend_enter(suspend_state_t state, bool *wakeup)
 	 * all the devices are suspended.
 	 */
 	if (state == PM_SUSPEND_FREEZE) {
-		s2idle_loop();
-		goto Platform_early_resume;
+		trace_suspend_resume(TPS("machine_suspend"), state, true);
+		freeze_enter();
+		trace_suspend_resume(TPS("machine_suspend"), state, false);
+		goto Platform_wake;
 	}
 
 	error = disable_nonboot_cpus();
diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c
index a1aecf44ab07..a1db38abac5b 100644
--- a/kernel/printk/printk.c
+++ b/kernel/printk/printk.c
@@ -269,7 +269,6 @@ static struct console *exclusive_console;
 #define MAX_CMDLINECONSOLES 8
 
 static struct console_cmdline console_cmdline[MAX_CMDLINECONSOLES];
-static int console_cmdline_cnt;
 
 static int preferred_console = -1;
 int console_set_on_cmdline;
@@ -1906,25 +1905,12 @@ static int __add_preferred_console(char *name, int idx, char *options,
 	 *	See if this tty is not yet registered, and
 	 *	if we have a slot free.
 	 */
-	for (i = 0, c = console_cmdline; i < console_cmdline_cnt; i++, c++) {
+	for (i = 0, c = console_cmdline;
+	     i < MAX_CMDLINECONSOLES && c->name[0];
+	     i++, c++) {
 		if (strcmp(c->name, name) == 0 && c->index == idx) {
-			if (brl_options)
-				return 0;
-
-			/*
-			 * Maintain an invariant that will help to find if
-			 * the matching console is preferred, see
-			 * register_console():
-			 *
-			 * The last non-braille console is always
-			 * the preferred one.
-			 */
-			if (i != console_cmdline_cnt - 1)
-				swap(console_cmdline[i],
-				     console_cmdline[console_cmdline_cnt - 1]);
-
-			preferred_console = console_cmdline_cnt - 1;
-
+			if (!brl_options)
+				preferred_console = i;
 			return 0;
 		}
 	}
@@ -1937,7 +1923,6 @@ static int __add_preferred_console(char *name, int idx, char *options,
 	braille_set_options(c, brl_options);
 
 	c->index = idx;
-	console_cmdline_cnt++;
 	return 0;
 }
 /*
@@ -2477,23 +2462,12 @@ void register_console(struct console *newcon)
 	}
 
 	/*
-	 * See if this console matches one we selected on the command line.
-	 *
-	 * There may be several entries in the console_cmdline array matching
-	 * with the same console, one with newcon->match(), another by
-	 * name/index:
-	 *
-	 *	pl011,mmio,0x87e024000000,115200 -- added from SPCR
-	 *	ttyAMA0 -- added from command line
-	 *
-	 * Traverse the console_cmdline array in reverse order to be
-	 * sure that if this console is preferred then it will be the first
-	 * matching entry.  We use the invariant that is maintained in
-	 * __add_preferred_console().
+	 *	See if this console matches one we selected on
+	 *	the command line.
 	 */
-	for (i = console_cmdline_cnt - 1; i >= 0; i--) {
-		c = console_cmdline + i;
-
+	for (i = 0, c = console_cmdline;
+	     i < MAX_CMDLINECONSOLES && c->name[0];
+	     i++, c++) {
 		if (!newcon->match ||
 		    newcon->match(newcon, c->name, c->index, c->options) != 0) {
 			/* default matching */
diff --git a/kernel/rcu/srcu.c b/kernel/rcu/srcu.c
index 584d8a983883..dea03614263f 100644
--- a/kernel/rcu/srcu.c
+++ b/kernel/rcu/srcu.c
@@ -263,7 +263,7 @@ EXPORT_SYMBOL_GPL(cleanup_srcu_struct);
 
 /*
  * Counts the new reader in the appropriate per-CPU element of the
- * srcu_struct.  Must be called from process context.
+ * srcu_struct.
  * Returns an index that must be passed to the matching srcu_read_unlock().
  */
 int __srcu_read_lock(struct srcu_struct *sp)
@@ -271,7 +271,7 @@ int __srcu_read_lock(struct srcu_struct *sp)
 	int idx;
 
 	idx = READ_ONCE(sp->completed) & 0x1;
-	__this_cpu_inc(sp->per_cpu_ref->lock_count[idx]);
+	this_cpu_inc(sp->per_cpu_ref->lock_count[idx]);
 	smp_mb(); /* B */  /* Avoid leaking the critical section. */
 	return idx;
 }
@@ -281,7 +281,6 @@ EXPORT_SYMBOL_GPL(__srcu_read_lock);
  * Removes the count for the old reader from the appropriate per-CPU
  * element of the srcu_struct.  Note that this may well be a different
  * CPU than that which was incremented by the corresponding srcu_read_lock().
- * Must be called from process context.
  */
 void __srcu_read_unlock(struct srcu_struct *sp, int idx)
 {
diff --git a/kernel/rcu/srcutiny.c b/kernel/rcu/srcutiny.c
index 36e1f82faed1..32798eb14853 100644
--- a/kernel/rcu/srcutiny.c
+++ b/kernel/rcu/srcutiny.c
@@ -97,8 +97,9 @@ EXPORT_SYMBOL_GPL(cleanup_srcu_struct);
 
 /*
  * Counts the new reader in the appropriate per-CPU element of the
- * srcu_struct.  Must be called from process context.
- * Returns an index that must be passed to the matching srcu_read_unlock().
+ * srcu_struct.  Can be invoked from irq/bh handlers, but the matching
+ * __srcu_read_unlock() must be in the same handler instance.  Returns an
+ * index that must be passed to the matching srcu_read_unlock().
  */
 int __srcu_read_lock(struct srcu_struct *sp)
 {
@@ -112,7 +113,7 @@ EXPORT_SYMBOL_GPL(__srcu_read_lock);
 
 /*
  * Removes the count for the old reader from the appropriate element of
- * the srcu_struct.  Must be called from process context.
+ * the srcu_struct.
  */
 void __srcu_read_unlock(struct srcu_struct *sp, int idx)
 {
diff --git a/kernel/rcu/srcutree.c b/kernel/rcu/srcutree.c
index 3ae8474557df..157654fa436a 100644
--- a/kernel/rcu/srcutree.c
+++ b/kernel/rcu/srcutree.c
@@ -357,7 +357,7 @@ EXPORT_SYMBOL_GPL(cleanup_srcu_struct);
 
 /*
  * Counts the new reader in the appropriate per-CPU element of the
- * srcu_struct.  Must be called from process context.
+ * srcu_struct.
  * Returns an index that must be passed to the matching srcu_read_unlock().
  */
 int __srcu_read_lock(struct srcu_struct *sp)
@@ -365,7 +365,7 @@ int __srcu_read_lock(struct srcu_struct *sp)
 	int idx;
 
 	idx = READ_ONCE(sp->srcu_idx) & 0x1;
-	__this_cpu_inc(sp->sda->srcu_lock_count[idx]);
+	this_cpu_inc(sp->sda->srcu_lock_count[idx]);
 	smp_mb(); /* B */  /* Avoid leaking the critical section. */
 	return idx;
 }
@@ -375,7 +375,6 @@ EXPORT_SYMBOL_GPL(__srcu_read_lock);
  * Removes the count for the old reader from the appropriate per-CPU
  * element of the srcu_struct.  Note that this may well be a different
  * CPU than that which was incremented by the corresponding srcu_read_lock().
- * Must be called from process context.
  */
 void __srcu_read_unlock(struct srcu_struct *sp, int idx)
 {
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 803c3bc274c4..326d4f88e2b1 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -5605,7 +5605,7 @@ void idle_task_exit(void)
 	BUG_ON(cpu_online(smp_processor_id()));
 
 	if (mm != &init_mm) {
-		switch_mm_irqs_off(mm, &init_mm, current);
+		switch_mm(mm, &init_mm, current);
 		finish_arch_post_lock_switch();
 	}
 	mmdrop(mm);
diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
index 622eed1b7658..076a2e31951c 100644
--- a/kernel/sched/cpufreq_schedutil.c
+++ b/kernel/sched/cpufreq_schedutil.c
@@ -101,9 +101,6 @@ static void sugov_update_commit(struct sugov_policy *sg_policy, u64 time,
 	if (sg_policy->next_freq == next_freq)
 		return;
 
-	if (sg_policy->next_freq > next_freq)
-		next_freq = (sg_policy->next_freq + next_freq) >> 1;
-
 	sg_policy->next_freq = next_freq;
 	sg_policy->last_freq_update_time = time;
 
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index d71109321841..c77e4b1d51c0 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -3563,7 +3563,7 @@ static inline void check_schedstat_required(void)
 			trace_sched_stat_runtime_enabled())  {
 		printk_deferred_once("Scheduler tracepoints stat_sleep, stat_iowait, "
 			     "stat_blocked and stat_runtime require the "
-			     "kernel parameter schedstats=enabled or "
+			     "kernel parameter schedstats=enable or "
 			     "kernel.sched_schedstats=1\n");
 	}
 #endif
diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c
index 987e496bb51a..b398c2ea69b2 100644
--- a/kernel/time/tick-broadcast.c
+++ b/kernel/time/tick-broadcast.c
@@ -37,9 +37,11 @@ static int tick_broadcast_forced;
 static __cacheline_aligned_in_smp DEFINE_RAW_SPINLOCK(tick_broadcast_lock);
 
 #ifdef CONFIG_TICK_ONESHOT
+static void tick_broadcast_setup_oneshot(struct clock_event_device *bc);
 static void tick_broadcast_clear_oneshot(int cpu);
 static void tick_resume_broadcast_oneshot(struct clock_event_device *bc);
 #else
+static inline void tick_broadcast_setup_oneshot(struct clock_event_device *bc) { BUG(); }
 static inline void tick_broadcast_clear_oneshot(int cpu) { }
 static inline void tick_resume_broadcast_oneshot(struct clock_event_device *bc) { }
 #endif
@@ -867,7 +869,7 @@ static void tick_broadcast_init_next_event(struct cpumask *mask,
 /**
  * tick_broadcast_setup_oneshot - setup the broadcast device
  */
-void tick_broadcast_setup_oneshot(struct clock_event_device *bc)
+static void tick_broadcast_setup_oneshot(struct clock_event_device *bc)
 {
 	int cpu = smp_processor_id();
 
diff --git a/kernel/time/tick-internal.h b/kernel/time/tick-internal.h
index f738251000fe..be0ac01f2e12 100644
--- a/kernel/time/tick-internal.h
+++ b/kernel/time/tick-internal.h
@@ -126,7 +126,6 @@ static inline int tick_check_oneshot_change(int allow_nohz) { return 0; }
 
 /* Functions related to oneshot broadcasting */
 #if defined(CONFIG_GENERIC_CLOCKEVENTS_BROADCAST) && defined(CONFIG_TICK_ONESHOT)
-extern void tick_broadcast_setup_oneshot(struct clock_event_device *bc);
 extern void tick_broadcast_switch_to_oneshot(void);
 extern void tick_shutdown_broadcast_oneshot(unsigned int cpu);
 extern int tick_broadcast_oneshot_active(void);
@@ -134,7 +133,6 @@ extern void tick_check_oneshot_broadcast_this_cpu(void);
 bool tick_broadcast_oneshot_available(void);
 extern struct cpumask *tick_get_broadcast_oneshot_mask(void);
 #else /* !(BROADCAST && ONESHOT): */
-static inline void tick_broadcast_setup_oneshot(struct clock_event_device *bc) { BUG(); }
 static inline void tick_broadcast_switch_to_oneshot(void) { }
 static inline void tick_shutdown_broadcast_oneshot(unsigned int cpu) { }
 static inline int tick_broadcast_oneshot_active(void) { return 0; }
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index 9652bc57fd09..b602c48cb841 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -118,6 +118,26 @@ static inline void tk_update_sleep_time(struct timekeeper *tk, ktime_t delta)
 	tk->offs_boot = ktime_add(tk->offs_boot, delta);
 }
 
+/*
+ * tk_clock_read - atomic clocksource read() helper
+ *
+ * This helper is necessary to use in the read paths because, while the
+ * seqlock ensures we don't return a bad value while structures are updated,
+ * it doesn't protect from potential crashes. There is the possibility that
+ * the tkr's clocksource may change between the read reference, and the
+ * clock reference passed to the read function.  This can cause crashes if
+ * the wrong clocksource is passed to the wrong read function.
+ * This isn't necessary to use when holding the timekeeper_lock or doing
+ * a read of the fast-timekeeper tkrs (which is protected by its own locking
+ * and update logic).
+ */
+static inline u64 tk_clock_read(struct tk_read_base *tkr)
+{
+	struct clocksource *clock = READ_ONCE(tkr->clock);
+
+	return clock->read(clock);
+}
+
 #ifdef CONFIG_DEBUG_TIMEKEEPING
 #define WARNING_FREQ (HZ*300) /* 5 minute rate-limiting */
 
@@ -175,7 +195,7 @@ static inline u64 timekeeping_get_delta(struct tk_read_base *tkr)
 	 */
 	do {
 		seq = read_seqcount_begin(&tk_core.seq);
-		now = tkr->read(tkr->clock);
+		now = tk_clock_read(tkr);
 		last = tkr->cycle_last;
 		mask = tkr->mask;
 		max = tkr->clock->max_cycles;
@@ -209,7 +229,7 @@ static inline u64 timekeeping_get_delta(struct tk_read_base *tkr)
 	u64 cycle_now, delta;
 
 	/* read clocksource */
-	cycle_now = tkr->read(tkr->clock);
+	cycle_now = tk_clock_read(tkr);
 
 	/* calculate the delta since the last update_wall_time */
 	delta = clocksource_delta(cycle_now, tkr->cycle_last, tkr->mask);
@@ -238,12 +258,10 @@ static void tk_setup_internals(struct timekeeper *tk, struct clocksource *clock)
 	++tk->cs_was_changed_seq;
 	old_clock = tk->tkr_mono.clock;
 	tk->tkr_mono.clock = clock;
-	tk->tkr_mono.read = clock->read;
 	tk->tkr_mono.mask = clock->mask;
-	tk->tkr_mono.cycle_last = tk->tkr_mono.read(clock);
+	tk->tkr_mono.cycle_last = tk_clock_read(&tk->tkr_mono);
 
 	tk->tkr_raw.clock = clock;
-	tk->tkr_raw.read = clock->read;
 	tk->tkr_raw.mask = clock->mask;
 	tk->tkr_raw.cycle_last = tk->tkr_mono.cycle_last;
 
@@ -262,7 +280,7 @@ static void tk_setup_internals(struct timekeeper *tk, struct clocksource *clock)
 	/* Go back from cycles -> shifted ns */
 	tk->xtime_interval = interval * clock->mult;
 	tk->xtime_remainder = ntpinterval - tk->xtime_interval;
-	tk->raw_interval = (interval * clock->mult) >> clock->shift;
+	tk->raw_interval = interval * clock->mult;
 
 	 /* if changing clocks, convert xtime_nsec shift units */
 	if (old_clock) {
@@ -404,7 +422,7 @@ static __always_inline u64 __ktime_get_fast_ns(struct tk_fast *tkf)
 
 		now += timekeeping_delta_to_ns(tkr,
 				clocksource_delta(
-					tkr->read(tkr->clock),
+					tk_clock_read(tkr),
 					tkr->cycle_last,
 					tkr->mask));
 	} while (read_seqcount_retry(&tkf->seq, seq));
@@ -461,6 +479,10 @@ static u64 dummy_clock_read(struct clocksource *cs)
 	return cycles_at_suspend;
 }
 
+static struct clocksource dummy_clock = {
+	.read = dummy_clock_read,
+};
+
 /**
  * halt_fast_timekeeper - Prevent fast timekeeper from accessing clocksource.
  * @tk: Timekeeper to snapshot.
@@ -477,13 +499,13 @@ static void halt_fast_timekeeper(struct timekeeper *tk)
 	struct tk_read_base *tkr = &tk->tkr_mono;
 
 	memcpy(&tkr_dummy, tkr, sizeof(tkr_dummy));
-	cycles_at_suspend = tkr->read(tkr->clock);
-	tkr_dummy.read = dummy_clock_read;
+	cycles_at_suspend = tk_clock_read(tkr);
+	tkr_dummy.clock = &dummy_clock;
 	update_fast_timekeeper(&tkr_dummy, &tk_fast_mono);
 
 	tkr = &tk->tkr_raw;
 	memcpy(&tkr_dummy, tkr, sizeof(tkr_dummy));
-	tkr_dummy.read = dummy_clock_read;
+	tkr_dummy.clock = &dummy_clock;
 	update_fast_timekeeper(&tkr_dummy, &tk_fast_raw);
 }
 
@@ -649,11 +671,10 @@ static void timekeeping_update(struct timekeeper *tk, unsigned int action)
  */
 static void timekeeping_forward_now(struct timekeeper *tk)
 {
-	struct clocksource *clock = tk->tkr_mono.clock;
 	u64 cycle_now, delta;
 	u64 nsec;
 
-	cycle_now = tk->tkr_mono.read(clock);
+	cycle_now = tk_clock_read(&tk->tkr_mono);
 	delta = clocksource_delta(cycle_now, tk->tkr_mono.cycle_last, tk->tkr_mono.mask);
 	tk->tkr_mono.cycle_last = cycle_now;
 	tk->tkr_raw.cycle_last  = cycle_now;
@@ -929,8 +950,7 @@ void ktime_get_snapshot(struct system_time_snapshot *systime_snapshot)
 
 	do {
 		seq = read_seqcount_begin(&tk_core.seq);
-
-		now = tk->tkr_mono.read(tk->tkr_mono.clock);
+		now = tk_clock_read(&tk->tkr_mono);
 		systime_snapshot->cs_was_changed_seq = tk->cs_was_changed_seq;
 		systime_snapshot->clock_was_set_seq = tk->clock_was_set_seq;
 		base_real = ktime_add(tk->tkr_mono.base,
@@ -1108,7 +1128,7 @@ int get_device_system_crosststamp(int (*get_time_fn)
 		 * Check whether the system counter value provided by the
 		 * device driver is on the current timekeeping interval.
 		 */
-		now = tk->tkr_mono.read(tk->tkr_mono.clock);
+		now = tk_clock_read(&tk->tkr_mono);
 		interval_start = tk->tkr_mono.cycle_last;
 		if (!cycle_between(interval_start, cycles, now)) {
 			clock_was_set_seq = tk->clock_was_set_seq;
@@ -1629,7 +1649,7 @@ void timekeeping_resume(void)
 	 * The less preferred source will only be tried if there is no better
 	 * usable source. The rtc part is handled separately in rtc core code.
 	 */
-	cycle_now = tk->tkr_mono.read(clock);
+	cycle_now = tk_clock_read(&tk->tkr_mono);
 	if ((clock->flags & CLOCK_SOURCE_SUSPEND_NONSTOP) &&
 		cycle_now > tk->tkr_mono.cycle_last) {
 		u64 nsec, cyc_delta;
@@ -1976,7 +1996,7 @@ static u64 logarithmic_accumulation(struct timekeeper *tk, u64 offset,
 				    u32 shift, unsigned int *clock_set)
 {
 	u64 interval = tk->cycle_interval << shift;
-	u64 raw_nsecs;
+	u64 snsec_per_sec;
 
 	/* If the offset is smaller than a shifted interval, do nothing */
 	if (offset < interval)
@@ -1991,14 +2011,15 @@ static u64 logarithmic_accumulation(struct timekeeper *tk, u64 offset,
 	*clock_set |= accumulate_nsecs_to_secs(tk);
 
 	/* Accumulate raw time */
-	raw_nsecs = (u64)tk->raw_interval << shift;
-	raw_nsecs += tk->raw_time.tv_nsec;
-	if (raw_nsecs >= NSEC_PER_SEC) {
-		u64 raw_secs = raw_nsecs;
-		raw_nsecs = do_div(raw_secs, NSEC_PER_SEC);
-		tk->raw_time.tv_sec += raw_secs;
+	tk->tkr_raw.xtime_nsec += (u64)tk->raw_time.tv_nsec << tk->tkr_raw.shift;
+	tk->tkr_raw.xtime_nsec += tk->raw_interval << shift;
+	snsec_per_sec = (u64)NSEC_PER_SEC << tk->tkr_raw.shift;
+	while (tk->tkr_raw.xtime_nsec >= snsec_per_sec) {
+		tk->tkr_raw.xtime_nsec -= snsec_per_sec;
+		tk->raw_time.tv_sec++;
 	}
-	tk->raw_time.tv_nsec = raw_nsecs;
+	tk->raw_time.tv_nsec = tk->tkr_raw.xtime_nsec >> tk->tkr_raw.shift;
+	tk->tkr_raw.xtime_nsec -= (u64)tk->raw_time.tv_nsec << tk->tkr_raw.shift;
 
 	/* Accumulate error between NTP and clock interval */
 	tk->ntp_error += tk->ntp_tick << shift;
@@ -2030,7 +2051,7 @@ void update_wall_time(void)
 #ifdef CONFIG_ARCH_USES_GETTIMEOFFSET
 	offset = real_tk->cycle_interval;
 #else
-	offset = clocksource_delta(tk->tkr_mono.read(tk->tkr_mono.clock),
+	offset = clocksource_delta(tk_clock_read(&tk->tkr_mono),
 				   tk->tkr_mono.cycle_last, tk->tkr_mono.mask);
 #endif