Merge tag 'timers-core-2020-10-12' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull timekeeping updates from Thomas Gleixner:
 "Updates for timekeeping, timers and related drivers:

  Core:

   - Early boot support for the NMI safe timekeeper by utilizing
     local_clock() up to the point where timekeeping is initialized.
     This allows printk() to store multiple timestamps in the ringbuffer
     which is useful for coordinating dmesg information across a fleet
     of machines.

   - Provide a multi-timestamp accessor for printk()

   - Make timer init more robust by checking for invalid timer flags.

   - Comma vs semicolon fixes

  Drivers:

   - Support for new platforms in existing drivers (SP804 and Renesas
     CMT)

   - Comma vs semicolon fixes

* tag 'timers-core-2020-10-12' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  clocksource/drivers/armada-370-xp: Use semicolons rather than commas to separate statements
  clocksource/drivers/mps2-timer: Use semicolons rather than commas to separate statements
  timers: Mask invalid flags in do_init_timer()
  clocksource/drivers/sp804: Enable Hisilicon sp804 timer 64bit mode
  clocksource/drivers/sp804: Add support for Hisilicon sp804 timer
  clocksource/drivers/sp804: Support non-standard register offset
  clocksource/drivers/sp804: Prepare for support non-standard register offset
  clocksource/drivers/sp804: Remove a mismatched comment
  clocksource/drivers/sp804: Delete the leading "__" of some functions
  clocksource/drivers/sp804: Remove unused sp804_timer_disable() and timer-sp804.h
  clocksource/drivers/sp804: Cleanup clk_get_sys()
  dt-bindings: timer: renesas,cmt: Document r8a774e1 CMT support
  dt-bindings: timer: renesas,cmt: Document r8a7742 CMT support
  alarmtimer: Convert comma to semicolon
  timekeeping: Provide multi-timestamp accessor to NMI safe timekeeper
  timekeeping: Utilize local_clock() for NMI safe timekeeper during early boot

kernel/time/alarmtimer.c

@@ -908,7 +908,7 @@ static int __init alarmtimer_init(void)
 	/* Initialize alarm bases */
 	alarm_bases[ALARM_REALTIME].base_clockid = CLOCK_REALTIME;
 	alarm_bases[ALARM_REALTIME].get_ktime = &ktime_get_real;
-	alarm_bases[ALARM_REALTIME].get_timespec = ktime_get_real_ts64,
+	alarm_bases[ALARM_REALTIME].get_timespec = ktime_get_real_ts64;
 	alarm_bases[ALARM_BOOTTIME].base_clockid = CLOCK_BOOTTIME;
 	alarm_bases[ALARM_BOOTTIME].get_ktime = &ktime_get_boottime;
 	alarm_bases[ALARM_BOOTTIME].get_timespec = get_boottime_timespec;

kernel/time/timekeeping.c

@@ -54,6 +54,9 @@ static struct {
 
 static struct timekeeper shadow_timekeeper;
 
+/* flag for if timekeeping is suspended */
+int __read_mostly timekeeping_suspended;
+
 /**
  * struct tk_fast - NMI safe timekeeper
  * @seq:	Sequence counter for protecting updates. The lowest bit
@@ -73,28 +76,42 @@ static u64 cycles_at_suspend;
 
 static u64 dummy_clock_read(struct clocksource *cs)
 {
-	return cycles_at_suspend;
+	if (timekeeping_suspended)
+		return cycles_at_suspend;
+	return local_clock();
 }
 
 static struct clocksource dummy_clock = {
 	.read = dummy_clock_read,
 };
 
+/*
+ * Boot time initialization which allows local_clock() to be utilized
+ * during early boot when clocksources are not available. local_clock()
+ * returns nanoseconds already so no conversion is required, hence mult=1
+ * and shift=0. When the first proper clocksource is installed then
+ * the fast time keepers are updated with the correct values.
+ */
+#define FAST_TK_INIT						\
+	{							\
+		.clock		= &dummy_clock,			\
+		.mask		= CLOCKSOURCE_MASK(64),		\
+		.mult		= 1,				\
+		.shift		= 0,				\
+	}
+
 static struct tk_fast tk_fast_mono ____cacheline_aligned = {
 	.seq     = SEQCNT_RAW_SPINLOCK_ZERO(tk_fast_mono.seq, &timekeeper_lock),
-	.base[0] = { .clock = &dummy_clock, },
-	.base[1] = { .clock = &dummy_clock, },
+	.base[0] = FAST_TK_INIT,
+	.base[1] = FAST_TK_INIT,
 };
 
 static struct tk_fast tk_fast_raw  ____cacheline_aligned = {
 	.seq     = SEQCNT_RAW_SPINLOCK_ZERO(tk_fast_raw.seq, &timekeeper_lock),
-	.base[0] = { .clock = &dummy_clock, },
-	.base[1] = { .clock = &dummy_clock, },
+	.base[0] = FAST_TK_INIT,
+	.base[1] = FAST_TK_INIT,
 };
 
-/* flag for if timekeeping is suspended */
-int __read_mostly timekeeping_suspended;
-
 static inline void tk_normalize_xtime(struct timekeeper *tk)
 {
 	while (tk->tkr_mono.xtime_nsec >= ((u64)NSEC_PER_SEC << tk->tkr_mono.shift)) {
@@ -513,29 +530,29 @@ u64 notrace ktime_get_boot_fast_ns(void)
 }
 EXPORT_SYMBOL_GPL(ktime_get_boot_fast_ns);
 
-
 /*
  * See comment for __ktime_get_fast_ns() vs. timestamp ordering
  */
-static __always_inline u64 __ktime_get_real_fast_ns(struct tk_fast *tkf)
+static __always_inline u64 __ktime_get_real_fast(struct tk_fast *tkf, u64 *mono)
 {
 	struct tk_read_base *tkr;
+	u64 basem, baser, delta;
 	unsigned int seq;
-	u64 now;
 
 	do {
 		seq = raw_read_seqcount_latch(&tkf->seq);
 		tkr = tkf->base + (seq & 0x01);
-		now = ktime_to_ns(tkr->base_real);
+		basem = ktime_to_ns(tkr->base);
+		baser = ktime_to_ns(tkr->base_real);
 
-		now += timekeeping_delta_to_ns(tkr,
-				clocksource_delta(
-					tk_clock_read(tkr),
-					tkr->cycle_last,
-					tkr->mask));
+		delta = timekeeping_delta_to_ns(tkr,
+				clocksource_delta(tk_clock_read(tkr),
+				tkr->cycle_last, tkr->mask));
 	} while (read_seqcount_retry(&tkf->seq, seq));
 
-	return now;
+	if (mono)
+		*mono = basem + delta;
+	return baser + delta;
 }
 
 /**
@@ -543,10 +560,64 @@ static __always_inline u64 __ktime_get_real_fast_ns(struct tk_fast *tkf)
  */
 u64 ktime_get_real_fast_ns(void)
 {
-	return __ktime_get_real_fast_ns(&tk_fast_mono);
+	return __ktime_get_real_fast(&tk_fast_mono, NULL);
 }
 EXPORT_SYMBOL_GPL(ktime_get_real_fast_ns);
 
+/**
+ * ktime_get_fast_timestamps: - NMI safe timestamps
+ * @snapshot:	Pointer to timestamp storage
+ *
+ * Stores clock monotonic, boottime and realtime timestamps.
+ *
+ * Boot time is a racy access on 32bit systems if the sleep time injection
+ * happens late during resume and not in timekeeping_resume(). That could
+ * be avoided by expanding struct tk_read_base with boot offset for 32bit
+ * and adding more overhead to the update. As this is a hard to observe
+ * once per resume event which can be filtered with reasonable effort using
+ * the accurate mono/real timestamps, it's probably not worth the trouble.
+ *
+ * Aside of that it might be possible on 32 and 64 bit to observe the
+ * following when the sleep time injection happens late:
+ *
+ * CPU 0				CPU 1
+ * timekeeping_resume()
+ * ktime_get_fast_timestamps()
+ *	mono, real = __ktime_get_real_fast()
+ *					inject_sleep_time()
+ *					   update boot offset
+ *	boot = mono + bootoffset;
+ *
+ * That means that boot time already has the sleep time adjustment, but
+ * real time does not. On the next readout both are in sync again.
+ *
+ * Preventing this for 64bit is not really feasible without destroying the
+ * careful cache layout of the timekeeper because the sequence count and
+ * struct tk_read_base would then need two cache lines instead of one.
+ *
+ * Access to the time keeper clock source is disabled accross the innermost
+ * steps of suspend/resume. The accessors still work, but the timestamps
+ * are frozen until time keeping is resumed which happens very early.
+ *
+ * For regular suspend/resume there is no observable difference vs. sched
+ * clock, but it might affect some of the nasty low level debug printks.
+ *
+ * OTOH, access to sched clock is not guaranteed accross suspend/resume on
+ * all systems either so it depends on the hardware in use.
+ *
+ * If that turns out to be a real problem then this could be mitigated by
+ * using sched clock in a similar way as during early boot. But it's not as
+ * trivial as on early boot because it needs some careful protection
+ * against the clock monotonic timestamp jumping backwards on resume.
+ */
+void ktime_get_fast_timestamps(struct ktime_timestamps *snapshot)
+{
+	struct timekeeper *tk = &tk_core.timekeeper;
+
+	snapshot->real = __ktime_get_real_fast(&tk_fast_mono, &snapshot->mono);
+	snapshot->boot = snapshot->mono + ktime_to_ns(data_race(tk->offs_boot));
+}
+
 /**
  * halt_fast_timekeeper - Prevent fast timekeeper from accessing clocksource.
  * @tk: Timekeeper to snapshot.

kernel/time/timer.c

@@ -794,6 +794,8 @@ static void do_init_timer(struct timer_list *timer,
 {
 	timer->entry.pprev = NULL;
 	timer->function = func;
+	if (WARN_ON_ONCE(flags & ~TIMER_INIT_FLAGS))
+		flags &= TIMER_INIT_FLAGS;
 	timer->flags = flags | raw_smp_processor_id();
 	lockdep_init_map(&timer->lockdep_map, name, key, 0);
 }