Merge tag 'v4.0-rc2' into timers/core, to refresh the tree before pulling more changes

12 files changed, 224 insertions, 101 deletions

diff --git a/kernel/time/Makefile b/kernel/time/Makefile
index f622cf2..c09c078 100644
--- a/kernel/time/Makefile
+++ b/kernel/time/Makefile
@@ -1,6 +1,6 @@
 obj-y += time.o timer.o hrtimer.o itimer.o posix-timers.o posix-cpu-timers.o
 obj-y += timekeeping.o ntp.o clocksource.o jiffies.o timer_list.o
-obj-y += timeconv.o posix-clock.o alarmtimer.o
+obj-y += timeconv.o timecounter.o posix-clock.o alarmtimer.o
 
 obj-$(CONFIG_GENERIC_CLOCKEVENTS_BUILD)		+= clockevents.o
 obj-$(CONFIG_GENERIC_CLOCKEVENTS)		+= tick-common.o
diff --git a/kernel/time/alarmtimer.c b/kernel/time/alarmtimer.c
index a7077d3..1b001ed 100644
--- a/kernel/time/alarmtimer.c
+++ b/kernel/time/alarmtimer.c
@@ -788,7 +788,7 @@ static int alarm_timer_nsleep(const clockid_t which_clock, int flags,
 			goto out;
 	}
 
-	restart = &current_thread_info()->restart_block;
+	restart = &current->restart_block;
 	restart->fn = alarm_timer_nsleep_restart;
 	restart->nanosleep.clockid = type;
 	restart->nanosleep.expires = exp.tv64;
diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c
index b79f39b..4892352 100644
--- a/kernel/time/clocksource.c
+++ b/kernel/time/clocksource.c
@@ -34,82 +34,6 @@
 #include "tick-internal.h"
 #include "timekeeping_internal.h"
 
-void timecounter_init(struct timecounter *tc,
-		      const struct cyclecounter *cc,
-		      u64 start_tstamp)
-{
-	tc->cc = cc;
-	tc->cycle_last = cc->read(cc);
-	tc->nsec = start_tstamp;
-}
-EXPORT_SYMBOL_GPL(timecounter_init);
-
-/**
- * timecounter_read_delta - get nanoseconds since last call of this function
- * @tc:         Pointer to time counter
- *
- * When the underlying cycle counter runs over, this will be handled
- * correctly as long as it does not run over more than once between
- * calls.
- *
- * The first call to this function for a new time counter initializes
- * the time tracking and returns an undefined result.
- */
-static u64 timecounter_read_delta(struct timecounter *tc)
-{
-	cycle_t cycle_now, cycle_delta;
-	u64 ns_offset;
-
-	/* read cycle counter: */
-	cycle_now = tc->cc->read(tc->cc);
-
-	/* calculate the delta since the last timecounter_read_delta(): */
-	cycle_delta = (cycle_now - tc->cycle_last) & tc->cc->mask;
-
-	/* convert to nanoseconds: */
-	ns_offset = cyclecounter_cyc2ns(tc->cc, cycle_delta);
-
-	/* update time stamp of timecounter_read_delta() call: */
-	tc->cycle_last = cycle_now;
-
-	return ns_offset;
-}
-
-u64 timecounter_read(struct timecounter *tc)
-{
-	u64 nsec;
-
-	/* increment time by nanoseconds since last call */
-	nsec = timecounter_read_delta(tc);
-	nsec += tc->nsec;
-	tc->nsec = nsec;
-
-	return nsec;
-}
-EXPORT_SYMBOL_GPL(timecounter_read);
-
-u64 timecounter_cyc2time(struct timecounter *tc,
-			 cycle_t cycle_tstamp)
-{
-	u64 cycle_delta = (cycle_tstamp - tc->cycle_last) & tc->cc->mask;
-	u64 nsec;
-
-	/*
-	 * Instead of always treating cycle_tstamp as more recent
-	 * than tc->cycle_last, detect when it is too far in the
-	 * future and treat it as old time stamp instead.
-	 */
-	if (cycle_delta > tc->cc->mask / 2) {
-		cycle_delta = (tc->cycle_last - cycle_tstamp) & tc->cc->mask;
-		nsec = tc->nsec - cyclecounter_cyc2ns(tc->cc, cycle_delta);
-	} else {
-		nsec = cyclecounter_cyc2ns(tc->cc, cycle_delta) + tc->nsec;
-	}
-
-	return nsec;
-}
-EXPORT_SYMBOL_GPL(timecounter_cyc2time);
-
 /**
  * clocks_calc_mult_shift - calculate mult/shift factors for scaled math of clocks
  * @mult:	pointer to mult variable
diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c
index ce8221a..bee0c1f 100644
--- a/kernel/time/hrtimer.c
+++ b/kernel/time/hrtimer.c
@@ -122,7 +122,7 @@ static void hrtimer_get_softirq_time(struct hrtimer_cpu_base *base)
 	mono = ktime_get_update_offsets_tick(&off_real, &off_boot, &off_tai);
 	boot = ktime_add(mono, off_boot);
 	xtim = ktime_add(mono, off_real);
-	tai = ktime_add(xtim, off_tai);
+	tai = ktime_add(mono, off_tai);
 
 	base->clock_base[HRTIMER_BASE_REALTIME].softirq_time = xtim;
 	base->clock_base[HRTIMER_BASE_MONOTONIC].softirq_time = mono;
@@ -1583,7 +1583,7 @@ long hrtimer_nanosleep(struct timespec *rqtp, struct timespec __user *rmtp,
 			goto out;
 	}
 
-	restart = &current_thread_info()->restart_block;
+	restart = &current->restart_block;
 	restart->fn = hrtimer_nanosleep_restart;
 	restart->nanosleep.clockid = t.timer.base->clockid;
 	restart->nanosleep.rmtp = rmtp;
diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c
index 183dfe2..0f60b08 100644
--- a/kernel/time/ntp.c
+++ b/kernel/time/ntp.c
@@ -633,6 +633,17 @@ int ntp_validate_timex(struct timex *txc)
 	if ((txc->modes & ADJ_SETOFFSET) && (!capable(CAP_SYS_TIME)))
 		return -EPERM;
 
+	/*
+	 * Check for potential multiplication overflows that can
+	 * only happen on 64-bit systems:
+	 */
+	if ((txc->modes & ADJ_FREQUENCY) && (BITS_PER_LONG == 64)) {
+		if (LLONG_MIN / PPM_SCALE > txc->freq)
+			return -EINVAL;
+		if (LLONG_MAX / PPM_SCALE < txc->freq)
+			return -EINVAL;
+	}
+
 	return 0;
 }
 
diff --git a/kernel/time/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c
index a16b678..0075da7 100644
--- a/kernel/time/posix-cpu-timers.c
+++ b/kernel/time/posix-cpu-timers.c
@@ -1334,8 +1334,7 @@ static long posix_cpu_nsleep_restart(struct restart_block *restart_block);
 static int posix_cpu_nsleep(const clockid_t which_clock, int flags,
 			    struct timespec *rqtp, struct timespec __user *rmtp)
 {
-	struct restart_block *restart_block =
-		&current_thread_info()->restart_block;
+	struct restart_block *restart_block = &current->restart_block;
 	struct itimerspec it;
 	int error;
 
diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c
index 7efeedf..f7c5155 100644
--- a/kernel/time/tick-common.c
+++ b/kernel/time/tick-common.c
@@ -394,6 +394,56 @@ void tick_resume(void)
 	}
 }
 
+static DEFINE_RAW_SPINLOCK(tick_freeze_lock);
+static unsigned int tick_freeze_depth;
+
+/**
+ * tick_freeze - Suspend the local tick and (possibly) timekeeping.
+ *
+ * Check if this is the last online CPU executing the function and if so,
+ * suspend timekeeping.  Otherwise suspend the local tick.
+ *
+ * Call with interrupts disabled.  Must be balanced with %tick_unfreeze().
+ * Interrupts must not be enabled before the subsequent %tick_unfreeze().
+ */
+void tick_freeze(void)
+{
+	raw_spin_lock(&tick_freeze_lock);
+
+	tick_freeze_depth++;
+	if (tick_freeze_depth == num_online_cpus()) {
+		timekeeping_suspend();
+	} else {
+		tick_suspend();
+		tick_suspend_broadcast();
+	}
+
+	raw_spin_unlock(&tick_freeze_lock);
+}
+
+/**
+ * tick_unfreeze - Resume the local tick and (possibly) timekeeping.
+ *
+ * Check if this is the first CPU executing the function and if so, resume
+ * timekeeping.  Otherwise resume the local tick.
+ *
+ * Call with interrupts disabled.  Must be balanced with %tick_freeze().
+ * Interrupts must not be enabled after the preceding %tick_freeze().
+ */
+void tick_unfreeze(void)
+{
+	raw_spin_lock(&tick_freeze_lock);
+
+	if (tick_freeze_depth == num_online_cpus())
+		timekeeping_resume();
+	else
+		tick_resume();
+
+	tick_freeze_depth--;
+
+	raw_spin_unlock(&tick_freeze_lock);
+}
+
 /**
  * tick_init - initialize the tick control
  */
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 1363d58..a4c4eda 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -326,13 +326,6 @@ static int tick_nohz_cpu_down_callback(struct notifier_block *nfb,
 	return NOTIFY_OK;
 }
 
-/*
- * Worst case string length in chunks of CPU range seems 2 steps
- * separations: 0,2,4,6,...
- * This is NR_CPUS + sizeof('\0')
- */
-static char __initdata nohz_full_buf[NR_CPUS + 1];
-
 static int tick_nohz_init_all(void)
 {
 	int err = -1;
@@ -393,8 +386,8 @@ void __init tick_nohz_init(void)
 		context_tracking_cpu_set(cpu);
 
 	cpu_notifier(tick_nohz_cpu_down_callback, 0);
-	cpulist_scnprintf(nohz_full_buf, sizeof(nohz_full_buf), tick_nohz_full_mask);
-	pr_info("NO_HZ: Full dynticks CPUs: %s.\n", nohz_full_buf);
+	pr_info("NO_HZ: Full dynticks CPUs: %*pbl.\n",
+		cpumask_pr_args(tick_nohz_full_mask));
 }
 #endif
 
diff --git a/kernel/time/time.c b/kernel/time/time.c
index 6390517..2c85b77 100644
--- a/kernel/time/time.c
+++ b/kernel/time/time.c
@@ -196,6 +196,10 @@ SYSCALL_DEFINE2(settimeofday, struct timeval __user *, tv,
 	if (tv) {
 		if (copy_from_user(&user_tv, tv, sizeof(*tv)))
 			return -EFAULT;
+
+		if (!timeval_valid(&user_tv))
+			return -EINVAL;
+
 		new_ts.tv_sec = user_tv.tv_sec;
 		new_ts.tv_nsec = user_tv.tv_usec * NSEC_PER_USEC;
 	}
diff --git a/kernel/time/timecounter.c b/kernel/time/timecounter.c
new file mode 100644
index 0000000..4687b31
--- /dev/null
+++ b/kernel/time/timecounter.c
@@ -0,0 +1,112 @@
+/*
+ * linux/kernel/time/timecounter.c
+ *
+ * based on code that migrated away from
+ * linux/kernel/time/clocksource.c
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/export.h>
+#include <linux/timecounter.h>
+
+void timecounter_init(struct timecounter *tc,
+		      const struct cyclecounter *cc,
+		      u64 start_tstamp)
+{
+	tc->cc = cc;
+	tc->cycle_last = cc->read(cc);
+	tc->nsec = start_tstamp;
+	tc->mask = (1ULL << cc->shift) - 1;
+	tc->frac = 0;
+}
+EXPORT_SYMBOL_GPL(timecounter_init);
+
+/**
+ * timecounter_read_delta - get nanoseconds since last call of this function
+ * @tc:         Pointer to time counter
+ *
+ * When the underlying cycle counter runs over, this will be handled
+ * correctly as long as it does not run over more than once between
+ * calls.
+ *
+ * The first call to this function for a new time counter initializes
+ * the time tracking and returns an undefined result.
+ */
+static u64 timecounter_read_delta(struct timecounter *tc)
+{
+	cycle_t cycle_now, cycle_delta;
+	u64 ns_offset;
+
+	/* read cycle counter: */
+	cycle_now = tc->cc->read(tc->cc);
+
+	/* calculate the delta since the last timecounter_read_delta(): */
+	cycle_delta = (cycle_now - tc->cycle_last) & tc->cc->mask;
+
+	/* convert to nanoseconds: */
+	ns_offset = cyclecounter_cyc2ns(tc->cc, cycle_delta,
+					tc->mask, &tc->frac);
+
+	/* update time stamp of timecounter_read_delta() call: */
+	tc->cycle_last = cycle_now;
+
+	return ns_offset;
+}
+
+u64 timecounter_read(struct timecounter *tc)
+{
+	u64 nsec;
+
+	/* increment time by nanoseconds since last call */
+	nsec = timecounter_read_delta(tc);
+	nsec += tc->nsec;
+	tc->nsec = nsec;
+
+	return nsec;
+}
+EXPORT_SYMBOL_GPL(timecounter_read);
+
+/*
+ * This is like cyclecounter_cyc2ns(), but it is used for computing a
+ * time previous to the time stored in the cycle counter.
+ */
+static u64 cc_cyc2ns_backwards(const struct cyclecounter *cc,
+			       cycle_t cycles, u64 mask, u64 frac)
+{
+	u64 ns = (u64) cycles;
+
+	ns = ((ns * cc->mult) - frac) >> cc->shift;
+
+	return ns;
+}
+
+u64 timecounter_cyc2time(struct timecounter *tc,
+			 cycle_t cycle_tstamp)
+{
+	u64 delta = (cycle_tstamp - tc->cycle_last) & tc->cc->mask;
+	u64 nsec = tc->nsec, frac = tc->frac;
+
+	/*
+	 * Instead of always treating cycle_tstamp as more recent
+	 * than tc->cycle_last, detect when it is too far in the
+	 * future and treat it as old time stamp instead.
+	 */
+	if (delta > tc->cc->mask / 2) {
+		delta = (tc->cycle_last - cycle_tstamp) & tc->cc->mask;
+		nsec -= cc_cyc2ns_backwards(tc->cc, delta, tc->mask, frac);
+	} else {
+		nsec += cyclecounter_cyc2ns(tc->cc, delta, tc->mask, &frac);
+	}
+
+	return nsec;
+}
+EXPORT_SYMBOL_GPL(timecounter_cyc2time);
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index b124af2..91db941 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -230,9 +230,7 @@ static inline s64 timekeeping_get_ns_raw(struct timekeeper *tk)
 
 /**
  * update_fast_timekeeper - Update the fast and NMI safe monotonic timekeeper.
- * @tk:		The timekeeper from which we take the update
- * @tkf:	The fast timekeeper to update
- * @tbase:	The time base for the fast timekeeper (mono/raw)
+ * @tkr: Timekeeping readout base from which we take the update
  *
  * We want to use this from any context including NMI and tracing /
  * instrumenting the timekeeping code itself.
@@ -244,11 +242,11 @@ static inline s64 timekeeping_get_ns_raw(struct timekeeper *tk)
  * smp_wmb();	<- Ensure that the last base[1] update is visible
  * tkf->seq++;
  * smp_wmb();	<- Ensure that the seqcount update is visible
- * update(tkf->base[0], tk);
+ * update(tkf->base[0], tkr);
  * smp_wmb();	<- Ensure that the base[0] update is visible
  * tkf->seq++;
  * smp_wmb();	<- Ensure that the seqcount update is visible
- * update(tkf->base[1], tk);
+ * update(tkf->base[1], tkr);
  *
  * The reader side does:
  *
@@ -269,7 +267,7 @@ static inline s64 timekeeping_get_ns_raw(struct timekeeper *tk)
  * slightly wrong timestamp (a few nanoseconds). See
  * @ktime_get_mono_fast_ns.
  */
-static void update_fast_timekeeper(struct timekeeper *tk)
+static void update_fast_timekeeper(struct tk_read_base *tkr)
 {
 	struct tk_read_base *base = tk_fast_mono.base;
 
@@ -277,7 +275,7 @@ static void update_fast_timekeeper(struct timekeeper *tk)
 	raw_write_seqcount_latch(&tk_fast_mono.seq);
 
 	/* Update base[0] */
-	memcpy(base, &tk->tkr, sizeof(*base));
+	memcpy(base, tkr, sizeof(*base));
 
 	/* Force readers back to base[0] */
 	raw_write_seqcount_latch(&tk_fast_mono.seq);
@@ -334,6 +332,35 @@ u64 notrace ktime_get_mono_fast_ns(void)
 }
 EXPORT_SYMBOL_GPL(ktime_get_mono_fast_ns);
 
+/* Suspend-time cycles value for halted fast timekeeper. */
+static cycle_t cycles_at_suspend;
+
+static cycle_t dummy_clock_read(struct clocksource *cs)
+{
+	return cycles_at_suspend;
+}
+
+/**
+ * halt_fast_timekeeper - Prevent fast timekeeper from accessing clocksource.
+ * @tk: Timekeeper to snapshot.
+ *
+ * It generally is unsafe to access the clocksource after timekeeping has been
+ * suspended, so take a snapshot of the readout base of @tk and use it as the
+ * fast timekeeper's readout base while suspended.  It will return the same
+ * number of cycles every time until timekeeping is resumed at which time the
+ * proper readout base for the fast timekeeper will be restored automatically.
+ */
+static void halt_fast_timekeeper(struct timekeeper *tk)
+{
+	static struct tk_read_base tkr_dummy;
+	struct tk_read_base *tkr = &tk->tkr;
+
+	memcpy(&tkr_dummy, tkr, sizeof(tkr_dummy));
+	cycles_at_suspend = tkr->read(tkr->clock);
+	tkr_dummy.read = dummy_clock_read;
+	update_fast_timekeeper(&tkr_dummy);
+}
+
 #ifdef CONFIG_GENERIC_TIME_VSYSCALL_OLD
 
 static inline void update_vsyscall(struct timekeeper *tk)
@@ -462,7 +489,7 @@ static void timekeeping_update(struct timekeeper *tk, unsigned int action)
 		memcpy(&shadow_timekeeper, &tk_core.timekeeper,
 		       sizeof(tk_core.timekeeper));
 
-	update_fast_timekeeper(tk);
+	update_fast_timekeeper(&tk->tkr);
 }
 
 /**
@@ -1170,7 +1197,7 @@ void timekeeping_inject_sleeptime64(struct timespec64 *delta)
  * xtime/wall_to_monotonic/jiffies/etc are
  * still managed by arch specific suspend/resume code.
  */
-static void timekeeping_resume(void)
+void timekeeping_resume(void)
 {
 	struct timekeeper *tk = &tk_core.timekeeper;
 	struct clocksource *clock = tk->tkr.clock;
@@ -1251,7 +1278,7 @@ static void timekeeping_resume(void)
 	hrtimers_resume();
 }
 
-static int timekeeping_suspend(void)
+int timekeeping_suspend(void)
 {
 	struct timekeeper *tk = &tk_core.timekeeper;
 	unsigned long flags;
@@ -1296,6 +1323,7 @@ static int timekeeping_suspend(void)
 	}
 
 	timekeeping_update(tk, TK_MIRROR);
+	halt_fast_timekeeper(tk);
 	write_seqcount_end(&tk_core.seq);
 	raw_spin_unlock_irqrestore(&timekeeper_lock, flags);
 
diff --git a/kernel/time/timekeeping.h b/kernel/time/timekeeping.h
index adc1fc9..1d91416 100644
--- a/kernel/time/timekeeping.h
+++ b/kernel/time/timekeeping.h
@@ -16,5 +16,7 @@ extern int timekeeping_inject_offset(struct timespec *ts);
 extern s32 timekeeping_get_tai_offset(void);
 extern void timekeeping_set_tai_offset(s32 tai_offset);
 extern void timekeeping_clocktai(struct timespec *ts);
+extern int timekeeping_suspend(void);
+extern void timekeeping_resume(void);
 
 #endif