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

Pull timer fixes from Thomas Gleixner:
 "A few fixes for timekeeping and timers:

   - Plug a subtle race due to a missing READ_ONCE() in the timekeeping
     code where reloading of a pointer results in an inconsistent
     callback argument being supplied to the clocksource->read function.

   - Correct the CLOCK_MONOTONIC_RAW sub-nanosecond accounting in the
     time keeping core code, to prevent a possible discontuity.

   - Apply a similar fix to the arm64 vdso clock_gettime()
     implementation

   - Add missing includes to clocksource drivers, which relied on
     indirect includes which fails in certain configs.

   - Use the proper iomem pointer for read/iounmap in a probe function"

* 'timers-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  arm64/vdso: Fix nsec handling for CLOCK_MONOTONIC_RAW
  time: Fix CLOCK_MONOTONIC_RAW sub-nanosecond accounting
  time: Fix clock->read(clock) race around clocksource changes
  clocksource: Explicitly include linux/clocksource.h when needed
  clocksource/drivers/arm_arch_timer: Fix read and iounmap of incorrect variable

Author: torvalds

arch/arm64/kernel/vdso.c

@@ -221,10 +221,11 @@ void update_vsyscall(struct timekeeper *tk)
 		/* tkr_mono.cycle_last == tkr_raw.cycle_last */
 		vdso_data->cs_cycle_last	= tk->tkr_mono.cycle_last;
 		vdso_data->raw_time_sec		= tk->raw_time.tv_sec;
-		vdso_data->raw_time_nsec	= tk->raw_time.tv_nsec;
+		vdso_data->raw_time_nsec	= (tk->raw_time.tv_nsec <<
+						   tk->tkr_raw.shift) +
+						  tk->tkr_raw.xtime_nsec;
 		vdso_data->xtime_clock_sec	= tk->xtime_sec;
 		vdso_data->xtime_clock_nsec	= tk->tkr_mono.xtime_nsec;
-		/* tkr_raw.xtime_nsec == 0 */
 		vdso_data->cs_mono_mult		= tk->tkr_mono.mult;
 		vdso_data->cs_raw_mult		= tk->tkr_raw.mult;
 		/* tkr_mono.shift == tkr_raw.shift */

arch/arm64/kernel/vdso/gettimeofday.S

@@ -256,7 +256,6 @@ monotonic_raw:
 	seqcnt_check fail=monotonic_raw
 
 	/* All computations are done with left-shifted nsecs. */
-	lsl	x14, x14, x12
 	get_nsec_per_sec res=x9
 	lsl	x9, x9, x12
 

drivers/clocksource/arm_arch_timer.c

@@ -1209,9 +1209,9 @@ arch_timer_mem_frame_get_cntfrq(struct arch_timer_mem_frame *frame)
 		return 0;
 	}
 
-	rate = readl_relaxed(frame + CNTFRQ);
+	rate = readl_relaxed(base + CNTFRQ);
 
-	iounmap(frame);
+	iounmap(base);
 
 	return rate;
 }

drivers/clocksource/cadence_ttc_timer.c

@@ -18,6 +18,7 @@
 #include <linux/clk.h>
 #include <linux/interrupt.h>
 #include <linux/clockchips.h>
+#include <linux/clocksource.h>
 #include <linux/of_address.h>
 #include <linux/of_irq.h>
 #include <linux/slab.h>

drivers/clocksource/timer-sun5i.c

@@ -12,6 +12,7 @@
 
 #include <linux/clk.h>
 #include <linux/clockchips.h>
+#include <linux/clocksource.h>
 #include <linux/delay.h>
 #include <linux/interrupt.h>
 #include <linux/irq.h>

include/linux/timekeeper_internal.h

@@ -29,7 +29,6 @@
  */
 struct tk_read_base {
 	struct clocksource	*clock;
-	u64			(*read)(struct clocksource *cs);
 	u64			mask;
 	u64			cycle_last;
 	u32			mult;
@@ -58,7 +57,7 @@ struct tk_read_base {
  *			interval.
  * @xtime_remainder:	Shifted nano seconds left over when rounding
  *			@cycle_interval
- * @raw_interval:	Raw nano seconds accumulated per NTP interval.
+ * @raw_interval:	Shifted raw nano seconds accumulated per NTP interval.
  * @ntp_error:		Difference between accumulated time and NTP time in ntp
  *			shifted nano seconds.
  * @ntp_error_shift:	Shift conversion between clock shifted nano seconds and
@@ -100,7 +99,7 @@ struct timekeeper {
 	u64			cycle_interval;
 	u64			xtime_interval;
 	s64			xtime_remainder;
-	u32			raw_interval;
+	u64			raw_interval;
 	/* The ntp_tick_length() value currently being used.
 	 * This cached copy ensures we consistently apply the tick
 	 * length for an entire tick, as ntp_tick_length may change

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