Merge tag 'timers_urgent_for_v6.13_rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull timer fix from Borislav Petkov:

 - Handle the case where clocksources with small counter width can,
   in conjunction with overly long idle sleeps, falsely trigger the
   negative motion detection of clocksources

* tag 'timers_urgent_for_v6.13_rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  clocksource: Make negative motion detection more robust

3 files changed, 18 insertions, 7 deletions

diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c
index aab6472853fa..7304d7cf47f2 100644
--- a/kernel/time/clocksource.c
+++ b/kernel/time/clocksource.c
@@ -24,7 +24,7 @@ static void clocksource_enqueue(struct clocksource *cs);
 
 static noinline u64 cycles_to_nsec_safe(struct clocksource *cs, u64 start, u64 end)
 {
-	u64 delta = clocksource_delta(end, start, cs->mask);
+	u64 delta = clocksource_delta(end, start, cs->mask, cs->max_raw_delta);
 
 	if (likely(delta < cs->max_cycles))
 		return clocksource_cyc2ns(delta, cs->mult, cs->shift);
@@ -993,6 +993,15 @@ static inline void clocksource_update_max_deferment(struct clocksource *cs)
 	cs->max_idle_ns = clocks_calc_max_nsecs(cs->mult, cs->shift,
 						cs->maxadj, cs->mask,
 						&cs->max_cycles);
+
+	/*
+	 * Threshold for detecting negative motion in clocksource_delta().
+	 *
+	 * Allow for 0.875 of the counter width so that overly long idle
+	 * sleeps, which go slightly over mask/2, do not trigger the
+	 * negative motion detection.
+	 */
+	cs->max_raw_delta = (cs->mask >> 1) + (cs->mask >> 2) + (cs->mask >> 3);
 }
 
 static struct clocksource *clocksource_find_best(bool oneshot, bool skipcur)
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index 0ca85ff4fbb4..3d128825d343 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -755,7 +755,8 @@ static void timekeeping_forward_now(struct timekeeper *tk)
 	u64 cycle_now, delta;
 
 	cycle_now = tk_clock_read(&tk->tkr_mono);
-	delta = clocksource_delta(cycle_now, tk->tkr_mono.cycle_last, tk->tkr_mono.mask);
+	delta = clocksource_delta(cycle_now, tk->tkr_mono.cycle_last, tk->tkr_mono.mask,
+				  tk->tkr_mono.clock->max_raw_delta);
 	tk->tkr_mono.cycle_last = cycle_now;
 	tk->tkr_raw.cycle_last  = cycle_now;
 
@@ -2230,7 +2231,8 @@ static bool timekeeping_advance(enum timekeeping_adv_mode mode)
 		return false;
 
 	offset = clocksource_delta(tk_clock_read(&tk->tkr_mono),
-				   tk->tkr_mono.cycle_last, tk->tkr_mono.mask);
+				   tk->tkr_mono.cycle_last, tk->tkr_mono.mask,
+				   tk->tkr_mono.clock->max_raw_delta);
 
 	/* Check if there's really nothing to do */
 	if (offset < real_tk->cycle_interval && mode == TK_ADV_TICK)
diff --git a/kernel/time/timekeeping_internal.h b/kernel/time/timekeeping_internal.h
index 63e600e943a7..8c9079108ffb 100644
--- a/kernel/time/timekeeping_internal.h
+++ b/kernel/time/timekeeping_internal.h
@@ -30,15 +30,15 @@ static inline void timekeeping_inc_mg_floor_swaps(void)
 
 #endif
 
-static inline u64 clocksource_delta(u64 now, u64 last, u64 mask)
+static inline u64 clocksource_delta(u64 now, u64 last, u64 mask, u64 max_delta)
 {
 	u64 ret = (now - last) & mask;
 
 	/*
-	 * Prevent time going backwards by checking the MSB of mask in
-	 * the result. If set, return 0.
+	 * Prevent time going backwards by checking the result against
+	 * @max_delta. If greater, return 0.
 	 */
-	return ret & ~(mask >> 1) ? 0 : ret;
+	return ret > max_delta ? 0 : ret;
 }
 
 /* Semi public for serialization of non timekeeper VDSO updates. */