1 files changed, 118 insertions, 65 deletions

diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index 4786df904c22..f3b22f456fac 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -17,6 +17,7 @@
 #include <linux/nmi.h>
 #include <linux/sched.h>
 #include <linux/sched/loadavg.h>
+#include <linux/sched/clock.h>
 #include <linux/syscore_ops.h>
 #include <linux/clocksource.h>
 #include <linux/jiffies.h>
@@ -34,6 +35,14 @@
 #define TK_MIRROR		(1 << 1)
 #define TK_CLOCK_WAS_SET	(1 << 2)
 
+enum timekeeping_adv_mode {
+	/* Update timekeeper when a tick has passed */
+	TK_ADV_TICK,
+
+	/* Update timekeeper on a direct frequency change */
+	TK_ADV_FREQ
+};
+
 /*
  * The most important data for readout fits into a single 64 byte
  * cache line.
@@ -97,7 +106,7 @@ static inline void tk_normalize_xtime(struct timekeeper *tk)
 	}
 }
 
-static inline struct timespec64 tk_xtime(struct timekeeper *tk)
+static inline struct timespec64 tk_xtime(const struct timekeeper *tk)
 {
 	struct timespec64 ts;
 
@@ -154,7 +163,7 @@ static inline void tk_update_sleep_time(struct timekeeper *tk, ktime_t delta)
  * 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)
+static inline u64 tk_clock_read(const struct tk_read_base *tkr)
 {
 	struct clocksource *clock = READ_ONCE(tkr->clock);
 
@@ -203,7 +212,7 @@ static void timekeeping_check_update(struct timekeeper *tk, u64 offset)
 	}
 }
 
-static inline u64 timekeeping_get_delta(struct tk_read_base *tkr)
+static inline u64 timekeeping_get_delta(const struct tk_read_base *tkr)
 {
 	struct timekeeper *tk = &tk_core.timekeeper;
 	u64 now, last, mask, max, delta;
@@ -247,7 +256,7 @@ static inline u64 timekeeping_get_delta(struct tk_read_base *tkr)
 static inline void timekeeping_check_update(struct timekeeper *tk, u64 offset)
 {
 }
-static inline u64 timekeeping_get_delta(struct tk_read_base *tkr)
+static inline u64 timekeeping_get_delta(const struct tk_read_base *tkr)
 {
 	u64 cycle_now, delta;
 
@@ -344,7 +353,7 @@ u32 (*arch_gettimeoffset)(void) = default_arch_gettimeoffset;
 static inline u32 arch_gettimeoffset(void) { return 0; }
 #endif
 
-static inline u64 timekeeping_delta_to_ns(struct tk_read_base *tkr, u64 delta)
+static inline u64 timekeeping_delta_to_ns(const struct tk_read_base *tkr, u64 delta)
 {
 	u64 nsec;
 
@@ -355,7 +364,7 @@ static inline u64 timekeeping_delta_to_ns(struct tk_read_base *tkr, u64 delta)
 	return nsec + arch_gettimeoffset();
 }
 
-static inline u64 timekeeping_get_ns(struct tk_read_base *tkr)
+static inline u64 timekeeping_get_ns(const struct tk_read_base *tkr)
 {
 	u64 delta;
 
@@ -363,7 +372,7 @@ static inline u64 timekeeping_get_ns(struct tk_read_base *tkr)
 	return timekeeping_delta_to_ns(tkr, delta);
 }
 
-static inline u64 timekeeping_cycles_to_ns(struct tk_read_base *tkr, u64 cycles)
+static inline u64 timekeeping_cycles_to_ns(const struct tk_read_base *tkr, u64 cycles)
 {
 	u64 delta;
 
@@ -386,7 +395,8 @@ static inline u64 timekeeping_cycles_to_ns(struct tk_read_base *tkr, u64 cycles)
  * slightly wrong timestamp (a few nanoseconds). See
  * @ktime_get_mono_fast_ns.
  */
-static void update_fast_timekeeper(struct tk_read_base *tkr, struct tk_fast *tkf)
+static void update_fast_timekeeper(const struct tk_read_base *tkr,
+				   struct tk_fast *tkf)
 {
 	struct tk_read_base *base = tkf->base;
 
@@ -541,10 +551,10 @@ EXPORT_SYMBOL_GPL(ktime_get_real_fast_ns);
  * 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 void halt_fast_timekeeper(const struct timekeeper *tk)
 {
 	static struct tk_read_base tkr_dummy;
-	struct tk_read_base *tkr = &tk->tkr_mono;
+	const struct tk_read_base *tkr = &tk->tkr_mono;
 
 	memcpy(&tkr_dummy, tkr, sizeof(tkr_dummy));
 	cycles_at_suspend = tk_clock_read(tkr);
@@ -1269,7 +1279,7 @@ EXPORT_SYMBOL(do_settimeofday64);
  *
  * Adds or subtracts an offset value from the current time.
  */
-static int timekeeping_inject_offset(struct timespec64 *ts)
+static int timekeeping_inject_offset(const struct timespec64 *ts)
 {
 	struct timekeeper *tk = &tk_core.timekeeper;
 	unsigned long flags;
@@ -1496,22 +1506,39 @@ void __weak read_persistent_clock64(struct timespec64 *ts64)
 }
 
 /**
- * read_boot_clock64 -  Return time of the system start.
+ * read_persistent_wall_and_boot_offset - Read persistent clock, and also offset
+ *                                        from the boot.
  *
  * Weak dummy function for arches that do not yet support it.
- * Function to read the exact time the system has been started.
- * Returns a timespec64 with tv_sec=0 and tv_nsec=0 if unsupported.
- *
- *  XXX - Do be sure to remove it once all arches implement it.
+ * wall_time	- current time as returned by persistent clock
+ * boot_offset	- offset that is defined as wall_time - boot_time
+ * The default function calculates offset based on the current value of
+ * local_clock(). This way architectures that support sched_clock() but don't
+ * support dedicated boot time clock will provide the best estimate of the
+ * boot time.
  */
-void __weak read_boot_clock64(struct timespec64 *ts)
+void __weak __init
+read_persistent_wall_and_boot_offset(struct timespec64 *wall_time,
+				     struct timespec64 *boot_offset)
 {
-	ts->tv_sec = 0;
-	ts->tv_nsec = 0;
+	read_persistent_clock64(wall_time);
+	*boot_offset = ns_to_timespec64(local_clock());
 }
 
-/* Flag for if timekeeping_resume() has injected sleeptime */
-static bool sleeptime_injected;
+/*
+ * Flag reflecting whether timekeeping_resume() has injected sleeptime.
+ *
+ * The flag starts of false and is only set when a suspend reaches
+ * timekeeping_suspend(), timekeeping_resume() sets it to false when the
+ * timekeeper clocksource is not stopping across suspend and has been
+ * used to update sleep time. If the timekeeper clocksource has stopped
+ * then the flag stays true and is used by the RTC resume code to decide
+ * whether sleeptime must be injected and if so the flag gets false then.
+ *
+ * If a suspend fails before reaching timekeeping_resume() then the flag
+ * stays false and prevents erroneous sleeptime injection.
+ */
+static bool suspend_timing_needed;
 
 /* Flag for if there is a persistent clock on this platform */
 static bool persistent_clock_exists;
@@ -1521,28 +1548,29 @@ static bool persistent_clock_exists;
  */
 void __init timekeeping_init(void)
 {
+	struct timespec64 wall_time, boot_offset, wall_to_mono;
 	struct timekeeper *tk = &tk_core.timekeeper;
 	struct clocksource *clock;
 	unsigned long flags;
-	struct timespec64 now, boot, tmp;
-
-	read_persistent_clock64(&now);
-	if (!timespec64_valid_strict(&now)) {
-		pr_warn("WARNING: Persistent clock returned invalid value!\n"
-			"         Check your CMOS/BIOS settings.\n");
-		now.tv_sec = 0;
-		now.tv_nsec = 0;
-	} else if (now.tv_sec || now.tv_nsec)
-		persistent_clock_exists = true;
 
-	read_boot_clock64(&boot);
-	if (!timespec64_valid_strict(&boot)) {
-		pr_warn("WARNING: Boot clock returned invalid value!\n"
-			"         Check your CMOS/BIOS settings.\n");
-		boot.tv_sec = 0;
-		boot.tv_nsec = 0;
+	read_persistent_wall_and_boot_offset(&wall_time, &boot_offset);
+	if (timespec64_valid_strict(&wall_time) &&
+	    timespec64_to_ns(&wall_time) > 0) {
+		persistent_clock_exists = true;
+	} else if (timespec64_to_ns(&wall_time) != 0) {
+		pr_warn("Persistent clock returned invalid value");
+		wall_time = (struct timespec64){0};
 	}
 
+	if (timespec64_compare(&wall_time, &boot_offset) < 0)
+		boot_offset = (struct timespec64){0};
+
+	/*
+	 * We want set wall_to_mono, so the following is true:
+	 * wall time + wall_to_mono = boot time
+	 */
+	wall_to_mono = timespec64_sub(boot_offset, wall_time);
+
 	raw_spin_lock_irqsave(&timekeeper_lock, flags);
 	write_seqcount_begin(&tk_core.seq);
 	ntp_init();
@@ -1552,13 +1580,10 @@ void __init timekeeping_init(void)
 		clock->enable(clock);
 	tk_setup_internals(tk, clock);
 
-	tk_set_xtime(tk, &now);
+	tk_set_xtime(tk, &wall_time);
 	tk->raw_sec = 0;
-	if (boot.tv_sec == 0 && boot.tv_nsec == 0)
-		boot = tk_xtime(tk);
 
-	set_normalized_timespec64(&tmp, -boot.tv_sec, -boot.tv_nsec);
-	tk_set_wall_to_mono(tk, tmp);
+	tk_set_wall_to_mono(tk, wall_to_mono);
 
 	timekeeping_update(tk, TK_MIRROR | TK_CLOCK_WAS_SET);
 
@@ -1577,7 +1602,7 @@ static struct timespec64 timekeeping_suspend_time;
  * adds the sleep offset to the timekeeping variables.
  */
 static void __timekeeping_inject_sleeptime(struct timekeeper *tk,
-					   struct timespec64 *delta)
+					   const struct timespec64 *delta)
 {
 	if (!timespec64_valid_strict(delta)) {
 		printk_deferred(KERN_WARNING
@@ -1610,7 +1635,7 @@ static void __timekeeping_inject_sleeptime(struct timekeeper *tk,
  */
 bool timekeeping_rtc_skipresume(void)
 {
-	return sleeptime_injected;
+	return !suspend_timing_needed;
 }
 
 /**
@@ -1638,7 +1663,7 @@ bool timekeeping_rtc_skipsuspend(void)
  * This function should only be called by rtc_resume(), and allows
  * a suspend offset to be injected into the timekeeping values.
  */
-void timekeeping_inject_sleeptime64(struct timespec64 *delta)
+void timekeeping_inject_sleeptime64(const struct timespec64 *delta)
 {
 	struct timekeeper *tk = &tk_core.timekeeper;
 	unsigned long flags;
@@ -1646,6 +1671,8 @@ void timekeeping_inject_sleeptime64(struct timespec64 *delta)
 	raw_spin_lock_irqsave(&timekeeper_lock, flags);
 	write_seqcount_begin(&tk_core.seq);
 
+	suspend_timing_needed = false;
+
 	timekeeping_forward_now(tk);
 
 	__timekeeping_inject_sleeptime(tk, delta);
@@ -1669,9 +1696,9 @@ void timekeeping_resume(void)
 	struct clocksource *clock = tk->tkr_mono.clock;
 	unsigned long flags;
 	struct timespec64 ts_new, ts_delta;
-	u64 cycle_now;
+	u64 cycle_now, nsec;
+	bool inject_sleeptime = false;
 
-	sleeptime_injected = false;
 	read_persistent_clock64(&ts_new);
 
 	clockevents_resume();
@@ -1693,22 +1720,19 @@ void timekeeping_resume(void)
 	 * usable source. The rtc part is handled separately in rtc core code.
 	 */
 	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;
-
-		cyc_delta = clocksource_delta(cycle_now, tk->tkr_mono.cycle_last,
-					      tk->tkr_mono.mask);
-		nsec = mul_u64_u32_shr(cyc_delta, clock->mult, clock->shift);
+	nsec = clocksource_stop_suspend_timing(clock, cycle_now);
+	if (nsec > 0) {
 		ts_delta = ns_to_timespec64(nsec);
-		sleeptime_injected = true;
+		inject_sleeptime = true;
 	} else if (timespec64_compare(&ts_new, &timekeeping_suspend_time) > 0) {
 		ts_delta = timespec64_sub(ts_new, timekeeping_suspend_time);
-		sleeptime_injected = true;
+		inject_sleeptime = true;
 	}
 
-	if (sleeptime_injected)
+	if (inject_sleeptime) {
+		suspend_timing_needed = false;
 		__timekeeping_inject_sleeptime(tk, &ts_delta);
+	}
 
 	/* Re-base the last cycle value */
 	tk->tkr_mono.cycle_last = cycle_now;
@@ -1732,6 +1756,8 @@ int timekeeping_suspend(void)
 	unsigned long flags;
 	struct timespec64		delta, delta_delta;
 	static struct timespec64	old_delta;
+	struct clocksource *curr_clock;
+	u64 cycle_now;
 
 	read_persistent_clock64(&timekeeping_suspend_time);
 
@@ -1743,11 +1769,22 @@ int timekeeping_suspend(void)
 	if (timekeeping_suspend_time.tv_sec || timekeeping_suspend_time.tv_nsec)
 		persistent_clock_exists = true;
 
+	suspend_timing_needed = true;
+
 	raw_spin_lock_irqsave(&timekeeper_lock, flags);
 	write_seqcount_begin(&tk_core.seq);
 	timekeeping_forward_now(tk);
 	timekeeping_suspended = 1;
 
+	/*
+	 * Since we've called forward_now, cycle_last stores the value
+	 * just read from the current clocksource. Save this to potentially
+	 * use in suspend timing.
+	 */
+	curr_clock = tk->tkr_mono.clock;
+	cycle_now = tk->tkr_mono.cycle_last;
+	clocksource_start_suspend_timing(curr_clock, cycle_now);
+
 	if (persistent_clock_exists) {
 		/*
 		 * To avoid drift caused by repeated suspend/resumes,
@@ -2021,11 +2058,11 @@ static u64 logarithmic_accumulation(struct timekeeper *tk, u64 offset,
 	return offset;
 }
 
-/**
- * update_wall_time - Uses the current clocksource to increment the wall time
- *
+/*
+ * timekeeping_advance - Updates the timekeeper to the current time and
+ * current NTP tick length
  */
-void update_wall_time(void)
+static void timekeeping_advance(enum timekeeping_adv_mode mode)
 {
 	struct timekeeper *real_tk = &tk_core.timekeeper;
 	struct timekeeper *tk = &shadow_timekeeper;
@@ -2042,14 +2079,17 @@ void update_wall_time(void)
 
 #ifdef CONFIG_ARCH_USES_GETTIMEOFFSET
 	offset = real_tk->cycle_interval;
+
+	if (mode != TK_ADV_TICK)
+		goto out;
 #else
 	offset = clocksource_delta(tk_clock_read(&tk->tkr_mono),
 				   tk->tkr_mono.cycle_last, tk->tkr_mono.mask);
-#endif
 
 	/* Check if there's really nothing to do */
-	if (offset < real_tk->cycle_interval)
+	if (offset < real_tk->cycle_interval && mode == TK_ADV_TICK)
 		goto out;
+#endif
 
 	/* Do some additional sanity checking */
 	timekeeping_check_update(tk, offset);
@@ -2106,6 +2146,15 @@ out:
 }
 
 /**
+ * update_wall_time - Uses the current clocksource to increment the wall time
+ *
+ */
+void update_wall_time(void)
+{
+	timekeeping_advance(TK_ADV_TICK);
+}
+
+/**
  * getboottime64 - Return the real time of system boot.
  * @ts:		pointer to the timespec64 to be set
  *
@@ -2220,7 +2269,7 @@ ktime_t ktime_get_update_offsets_now(unsigned int *cwsseq, ktime_t *offs_real,
 /**
  * timekeeping_validate_timex - Ensures the timex is ok for use in do_adjtimex
  */
-static int timekeeping_validate_timex(struct timex *txc)
+static int timekeeping_validate_timex(const struct timex *txc)
 {
 	if (txc->modes & ADJ_ADJTIME) {
 		/* singleshot must not be used with any other mode bits */
@@ -2310,7 +2359,7 @@ int do_adjtimex(struct timex *txc)
 			return ret;
 	}
 
-	getnstimeofday64(&ts);
+	ktime_get_real_ts64(&ts);
 
 	raw_spin_lock_irqsave(&timekeeper_lock, flags);
 	write_seqcount_begin(&tk_core.seq);
@@ -2327,6 +2376,10 @@ int do_adjtimex(struct timex *txc)
 	write_seqcount_end(&tk_core.seq);
 	raw_spin_unlock_irqrestore(&timekeeper_lock, flags);
 
+	/* Update the multiplier immediately if frequency was set directly */
+	if (txc->modes & (ADJ_FREQUENCY | ADJ_TICK))
+		timekeeping_advance(TK_ADV_FREQ);
+
 	if (tai != orig_tai)
 		clock_was_set();