summaryrefslogtreecommitdiff
path: root/kernel
diff options
context:
space:
mode:
authorThomas Gleixner <tglx@linutronix.de>2024-12-03 11:16:30 +0100
committerThomas Gleixner <tglx@linutronix.de>2024-12-05 16:03:24 +0100
commit76031d9536a076bf023bedbdb1b4317fc801dd67 (patch)
tree8a7f8e032c34da7ec0ace3b2109c1c7ae0e7fc78 /kernel
parente70140ba0d2b1a30467d4af6bcfe761327b9ec95 (diff)
clocksource: Make negative motion detection more robust
Guenter reported boot stalls on a emulated ARM 32-bit platform, which has a 24-bit wide clocksource. It turns out that the calculated maximal idle time, which limits idle sleeps to prevent clocksource wrap arounds, is close to the point where the negative motion detection triggers. max_idle_ns: 597268854 ns negative motion tripping point: 671088640 ns If the idle wakeup is delayed beyond that point, the clocksource advances far enough to trigger the negative motion detection. This prevents the clock to advance and in the worst case the system stalls completely if the consecutive sleeps based on the stale clock are delayed as well. Cure this by calculating a more robust cut-off value for negative motion, which covers 87.5% of the actual clocksource counter width. Compare the delta against this value to catch negative motion. This is specifically for clock sources with a small counter width as their wrap around time is close to the half counter width. For clock sources with wide counters this is not a problem because the maximum idle time is far from the half counter width due to the math overflow protection constraints. For the case at hand this results in a tripping point of 1174405120ns. Note, that this cannot prevent issues when the delay exceeds the 87.5% margin, but that's not different from the previous unchecked version which allowed arbitrary time jumps. Systems with small counter width are prone to invalid results, but this problem is unlikely to be seen on real hardware. If such a system completely stalls for more than half a second, then there are other more urgent problems than the counter wrapping around. Fixes: c163e40af9b2 ("timekeeping: Always check for negative motion") Reported-by: Guenter Roeck <linux@roeck-us.net> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Tested-by: Guenter Roeck <linux@roeck-us.net> Link: https://lore.kernel.org/all/8734j5ul4x.ffs@tglx Closes: https://lore.kernel.org/all/387b120b-d68a-45e8-b6ab-768cd95d11c2@roeck-us.net
Diffstat (limited to 'kernel')
-rw-r--r--kernel/time/clocksource.c11
-rw-r--r--kernel/time/timekeeping.c6
-rw-r--r--kernel/time/timekeeping_internal.h8
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. */