[PATCH v8 01/11] timekeeping: move multigrain timestamp floor handling into timekeeper

[Jeff Layton <jlayton@kernel.org>]

For multigrain timestamps, we must keep track of the latest timestamp
that has ever been handed out, and never hand out a coarse time below
that value.

Add a static singleton atomic64_t into timekeeper.c that we can use to
keep track of the latest fine-grained time ever handed out. This is
tracked as a monotonic ktime_t value to ensure that it isn't affected by
clock jumps.

Add two new public interfaces:

- ktime_get_coarse_real_ts64_mg() fills a timespec64 with the later of the
  coarse-grained clock and the floor time

- ktime_get_real_ts64_mg() gets the fine-grained clock value, and tries
  to swap it into the floor. A timespec64 is filled with the result.

Since the floor is global, we take great pains to avoid updating it
unless it's absolutely necessary. If we do the cmpxchg and find that the
value has been updated since we fetched it, then we discard the
fine-grained time that was fetched in favor of the recent update.

To maximize the window of this occurring when multiple tasks are racing
to update the floor, ktime_get_coarse_real_ts64_mg returns a cookie
value that represents the state of the floor tracking word, and
ktime_get_real_ts64_mg accepts a cookie value that it uses as the "old"
value when calling cmpxchg().

Signed-off-by: Jeff Layton <jlayton@kernel.org>
---
 include/linux/timekeeping.h |  4 +++
 kernel/time/timekeeping.c   | 82 +++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 86 insertions(+)

diff --git a/include/linux/timekeeping.h b/include/linux/timekeeping.h
index fc12a9ba2c88..7aa85246c183 100644
--- a/include/linux/timekeeping.h
+++ b/include/linux/timekeeping.h
@@ -45,6 +45,10 @@ extern void ktime_get_real_ts64(struct timespec64 *tv);
 extern void ktime_get_coarse_ts64(struct timespec64 *ts);
 extern void ktime_get_coarse_real_ts64(struct timespec64 *ts);
 
+/* Multigrain timestamp interfaces */
+extern void ktime_get_coarse_real_ts64_mg(struct timespec64 *ts);
+extern void ktime_get_real_ts64_mg(struct timespec64 *ts);
+
 void getboottime64(struct timespec64 *ts);
 
 /*
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index 5391e4167d60..16937242b904 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -114,6 +114,13 @@ static struct tk_fast tk_fast_raw  ____cacheline_aligned = {
 	.base[1] = FAST_TK_INIT,
 };
 
+/*
+ * This represents the latest fine-grained time that we have handed out as a
+ * timestamp on the system. Tracked as a monotonic ktime_t, and converted to the
+ * realtime clock on an as-needed basis.
+ */
+static __cacheline_aligned_in_smp atomic64_t mg_floor;
+
 static inline void tk_normalize_xtime(struct timekeeper *tk)
 {
 	while (tk->tkr_mono.xtime_nsec >= ((u64)NSEC_PER_SEC << tk->tkr_mono.shift)) {
@@ -2394,6 +2401,81 @@ void ktime_get_coarse_real_ts64(struct timespec64 *ts)
 }
 EXPORT_SYMBOL(ktime_get_coarse_real_ts64);
 
+/**
+ * ktime_get_coarse_real_ts64_mg - get later of coarse grained time or floor
+ * @ts: timespec64 to be filled
+ *
+ * Adjust floor to realtime and compare it to the coarse time. Fill
+ * @ts with the latest one. Note that this is a filesystem-specific
+ * interface and should be avoided outside of that context.
+ */
+void ktime_get_coarse_real_ts64_mg(struct timespec64 *ts)
+{
+	struct timekeeper *tk = &tk_core.timekeeper;
+	u64 floor = atomic64_read(&mg_floor);
+	ktime_t f_real, offset, coarse;
+	unsigned int seq;
+
+	WARN_ON(timekeeping_suspended);
+
+	do {
+		seq = read_seqcount_begin(&tk_core.seq);
+		*ts = tk_xtime(tk);
+		offset = *offsets[TK_OFFS_REAL];
+	} while (read_seqcount_retry(&tk_core.seq, seq));
+
+	coarse = timespec64_to_ktime(*ts);
+	f_real = ktime_add(floor, offset);
+	if (ktime_after(f_real, coarse))
+		*ts = ktime_to_timespec64(f_real);
+}
+EXPORT_SYMBOL_GPL(ktime_get_coarse_real_ts64_mg);
+
+/**
+ * ktime_get_real_ts64_mg - attempt to update floor value and return result
+ * @ts:		pointer to the timespec to be set
+ *
+ * Get a current monotonic fine-grained time value and attempt to swap
+ * it into the floor. @ts will be filled with the resulting floor value,
+ * regardless of the outcome of the swap. Note that this is a filesystem
+ * specific interface and should be avoided outside of that context.
+ */
+void ktime_get_real_ts64_mg(struct timespec64 *ts, u64 cookie)
+{
+	struct timekeeper *tk = &tk_core.timekeeper;
+	ktime_t old = atomic64_read(&mg_floor);
+	ktime_t offset, mono;
+	unsigned int seq;
+	u64 nsecs;
+
+	WARN_ON(timekeeping_suspended);
+
+	do {
+		seq = read_seqcount_begin(&tk_core.seq);
+
+		ts->tv_sec = tk->xtime_sec;
+		mono = tk->tkr_mono.base;
+		nsecs = timekeeping_get_ns(&tk->tkr_mono);
+		offset = *offsets[TK_OFFS_REAL];
+	} while (read_seqcount_retry(&tk_core.seq, seq));
+
+	mono = ktime_add_ns(mono, nsecs);
+
+	if (atomic64_try_cmpxchg(&mg_floor, &old, mono)) {
+		ts->tv_nsec = 0;
+		timespec64_add_ns(ts, nsecs);
+	} else {
+		/*
+		 * Something has changed mg_floor since "old" was
+		 * fetched. "old" has now been updated with the
+		 * current value of mg_floor, so use that to return
+		 * the current coarse floor value.
+		 */
+		*ts = ktime_to_timespec64(ktime_add(old, offset));
+	}
+}
+EXPORT_SYMBOL_GPL(ktime_get_real_ts64_mg);
+
 void ktime_get_coarse_ts64(struct timespec64 *ts)
 {
 	struct timekeeper *tk = &tk_core.timekeeper;

-- 
2.46.0