Merge tag 'timers-urgent-2025-05-11' of git://git.kernel.org/pub/scm/…

…linux/kernel/git/tip/tip

Pull misc timers fixes from Ingo Molnar:

 - Fix time keeping bugs in CLOCK_MONOTONIC_COARSE clocks

 - Work around absolute relocations into vDSO code that GCC erroneously
   emits in certain arm64 build environments

 - Fix a false positive lockdep warning in the i8253 clocksource driver

* tag 'timers-urgent-2025-05-11' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  clocksource/i8253: Use raw_spinlock_irqsave() in clockevent_i8253_disable()
  arm64: vdso: Work around invalid absolute relocations from GCC
  timekeeping: Prevent coarse clocks going backwards

arch/arm64/include/asm/vdso/gettimeofday.h

@@ -99,6 +99,19 @@ static __always_inline u64 __arch_get_hw_counter(s32 clock_mode,
 	return res;
 }
 
+#if IS_ENABLED(CONFIG_CC_IS_GCC) && IS_ENABLED(CONFIG_PAGE_SIZE_64KB)
+static __always_inline const struct vdso_time_data *__arch_get_vdso_u_time_data(void)
+{
+	const struct vdso_time_data *ret = &vdso_u_time_data;
+
+	/* Work around invalid absolute relocations */
+	OPTIMIZER_HIDE_VAR(ret);
+
+	return ret;
+}
+#define __arch_get_vdso_u_time_data __arch_get_vdso_u_time_data
+#endif /* IS_ENABLED(CONFIG_CC_IS_GCC) && IS_ENABLED(CONFIG_PAGE_SIZE_64KB) */
+
 #endif /* !__ASSEMBLY__ */
 
 #endif /* __ASM_VDSO_GETTIMEOFDAY_H */

drivers/clocksource/i8253.c

@@ -103,7 +103,7 @@ int __init clocksource_i8253_init(void)
 #ifdef CONFIG_CLKEVT_I8253
 void clockevent_i8253_disable(void)
 {
-	raw_spin_lock(&i8253_lock);
+	guard(raw_spinlock_irqsave)(&i8253_lock);
 
 	/*
 	 * Writing the MODE register should stop the counter, according to
@@ -132,8 +132,6 @@ void clockevent_i8253_disable(void)
 	outb_p(0, PIT_CH0);
 
 	outb_p(0x30, PIT_MODE);
-
-	raw_spin_unlock(&i8253_lock);
 }
 
 static int pit_shutdown(struct clock_event_device *evt)

include/linux/timekeeper_internal.h

@@ -51,7 +51,7 @@ struct tk_read_base {
  * @offs_real:			Offset clock monotonic -> clock realtime
  * @offs_boot:			Offset clock monotonic -> clock boottime
  * @offs_tai:			Offset clock monotonic -> clock tai
- * @tai_offset:			The current UTC to TAI offset in seconds
+ * @coarse_nsec:		The nanoseconds part for coarse time getters
  * @tkr_raw:			The readout base structure for CLOCK_MONOTONIC_RAW
  * @raw_sec:			CLOCK_MONOTONIC_RAW  time in seconds
  * @clock_was_set_seq:		The sequence number of clock was set events
@@ -76,6 +76,7 @@ struct tk_read_base {
  *				ntp shifted nano seconds.
  * @ntp_err_mult:		Multiplication factor for scaled math conversion
  * @skip_second_overflow:	Flag used to avoid updating NTP twice with same second
+ * @tai_offset:			The current UTC to TAI offset in seconds
  *
  * Note: For timespec(64) based interfaces wall_to_monotonic is what
  * we need to add to xtime (or xtime corrected for sub jiffy times)
@@ -100,7 +101,7 @@ struct tk_read_base {
  * which results in the following cacheline layout:
  *
  * 0:	seqcount, tkr_mono
- * 1:	xtime_sec ... tai_offset
+ * 1:	xtime_sec ... coarse_nsec
  * 2:	tkr_raw, raw_sec
  * 3,4: Internal variables
  *
@@ -121,7 +122,7 @@ struct timekeeper {
 	ktime_t			offs_real;
 	ktime_t			offs_boot;
 	ktime_t			offs_tai;
-	s32			tai_offset;
+	u32			coarse_nsec;
 
 	/* Cacheline 2: */
 	struct tk_read_base	tkr_raw;
@@ -144,6 +145,7 @@ struct timekeeper {
 	u32			ntp_error_shift;
 	u32			ntp_err_mult;
 	u32			skip_second_overflow;
+	s32			tai_offset;
 };
 
 #ifdef CONFIG_GENERIC_TIME_VSYSCALL

kernel/time/timekeeping.c

@@ -164,17 +164,42 @@ static inline struct timespec64 tk_xtime(const struct timekeeper *tk)
 	return ts;
 }
 
+static inline struct timespec64 tk_xtime_coarse(const struct timekeeper *tk)
+{
+	struct timespec64 ts;
+
+	ts.tv_sec = tk->xtime_sec;
+	ts.tv_nsec = tk->coarse_nsec;
+	return ts;
+}
+
+/*
+ * Update the nanoseconds part for the coarse time keepers. They can't rely
+ * on xtime_nsec because xtime_nsec could be adjusted by a small negative
+ * amount when the multiplication factor of the clock is adjusted, which
+ * could cause the coarse clocks to go slightly backwards. See
+ * timekeeping_apply_adjustment(). Thus we keep a separate copy for the coarse
+ * clockids which only is updated when the clock has been set or  we have
+ * accumulated time.
+ */
+static inline void tk_update_coarse_nsecs(struct timekeeper *tk)
+{
+	tk->coarse_nsec = tk->tkr_mono.xtime_nsec >> tk->tkr_mono.shift;
+}
+
 static void tk_set_xtime(struct timekeeper *tk, const struct timespec64 *ts)
 {
 	tk->xtime_sec = ts->tv_sec;
 	tk->tkr_mono.xtime_nsec = (u64)ts->tv_nsec << tk->tkr_mono.shift;
+	tk_update_coarse_nsecs(tk);
 }
 
 static void tk_xtime_add(struct timekeeper *tk, const struct timespec64 *ts)
 {
 	tk->xtime_sec += ts->tv_sec;
 	tk->tkr_mono.xtime_nsec += (u64)ts->tv_nsec << tk->tkr_mono.shift;
 	tk_normalize_xtime(tk);
+	tk_update_coarse_nsecs(tk);
 }
 
 static void tk_set_wall_to_mono(struct timekeeper *tk, struct timespec64 wtm)
@@ -708,6 +733,7 @@ static void timekeeping_forward_now(struct timekeeper *tk)
 		tk_normalize_xtime(tk);
 		delta -= incr;
 	}
+	tk_update_coarse_nsecs(tk);
 }
 
 /**
@@ -804,16 +830,16 @@ EXPORT_SYMBOL_GPL(ktime_get_with_offset);
 ktime_t ktime_get_coarse_with_offset(enum tk_offsets offs)
 {
 	struct timekeeper *tk = &tk_core.timekeeper;
-	unsigned int seq;
 	ktime_t base, *offset = offsets[offs];
+	unsigned int seq;
 	u64 nsecs;
 
 	WARN_ON(timekeeping_suspended);
 
 	do {
 		seq = read_seqcount_begin(&tk_core.seq);
 		base = ktime_add(tk->tkr_mono.base, *offset);
-		nsecs = tk->tkr_mono.xtime_nsec >> tk->tkr_mono.shift;
+		nsecs = tk->coarse_nsec;
 
 	} while (read_seqcount_retry(&tk_core.seq, seq));
 
@@ -2161,7 +2187,7 @@ static bool timekeeping_advance(enum timekeeping_adv_mode mode)
 	struct timekeeper *real_tk = &tk_core.timekeeper;
 	unsigned int clock_set = 0;
 	int shift = 0, maxshift;
-	u64 offset;
+	u64 offset, orig_offset;
 
 	guard(raw_spinlock_irqsave)(&tk_core.lock);
 
@@ -2172,7 +2198,7 @@ static bool timekeeping_advance(enum timekeeping_adv_mode mode)
 	offset = clocksource_delta(tk_clock_read(&tk->tkr_mono),
 				   tk->tkr_mono.cycle_last, tk->tkr_mono.mask,
 				   tk->tkr_mono.clock->max_raw_delta);
-
+	orig_offset = offset;
 	/* Check if there's really nothing to do */
 	if (offset < real_tk->cycle_interval && mode == TK_ADV_TICK)
 		return false;
@@ -2205,6 +2231,14 @@ static bool timekeeping_advance(enum timekeeping_adv_mode mode)
 	 */
 	clock_set |= accumulate_nsecs_to_secs(tk);
 
+	/*
+	 * To avoid inconsistencies caused adjtimex TK_ADV_FREQ calls
+	 * making small negative adjustments to the base xtime_nsec
+	 * value, only update the coarse clocks if we accumulated time
+	 */
+	if (orig_offset != offset)
+		tk_update_coarse_nsecs(tk);
+
 	timekeeping_update_from_shadow(&tk_core, clock_set);
 
 	return !!clock_set;
@@ -2248,7 +2282,7 @@ void ktime_get_coarse_real_ts64(struct timespec64 *ts)
 	do {
 		seq = read_seqcount_begin(&tk_core.seq);
 
-		*ts = tk_xtime(tk);
+		*ts = tk_xtime_coarse(tk);
 	} while (read_seqcount_retry(&tk_core.seq, seq));
 }
 EXPORT_SYMBOL(ktime_get_coarse_real_ts64);
@@ -2271,7 +2305,7 @@ void ktime_get_coarse_real_ts64_mg(struct timespec64 *ts)
 
 	do {
 		seq = read_seqcount_begin(&tk_core.seq);
-		*ts = tk_xtime(tk);
+		*ts = tk_xtime_coarse(tk);
 		offset = tk_core.timekeeper.offs_real;
 	} while (read_seqcount_retry(&tk_core.seq, seq));
 
@@ -2350,12 +2384,12 @@ void ktime_get_coarse_ts64(struct timespec64 *ts)
 	do {
 		seq = read_seqcount_begin(&tk_core.seq);
 
-		now = tk_xtime(tk);
+		now = tk_xtime_coarse(tk);
 		mono = tk->wall_to_monotonic;
 	} while (read_seqcount_retry(&tk_core.seq, seq));
 
 	set_normalized_timespec64(ts, now.tv_sec + mono.tv_sec,
-				now.tv_nsec + mono.tv_nsec);
+				  now.tv_nsec + mono.tv_nsec);
 }
 EXPORT_SYMBOL(ktime_get_coarse_ts64);
 

kernel/time/vsyscall.c

@@ -98,12 +98,12 @@ void update_vsyscall(struct timekeeper *tk)
 	/* CLOCK_REALTIME_COARSE */
 	vdso_ts		= &vc[CS_HRES_COARSE].basetime[CLOCK_REALTIME_COARSE];
 	vdso_ts->sec	= tk->xtime_sec;
-	vdso_ts->nsec	= tk->tkr_mono.xtime_nsec >> tk->tkr_mono.shift;
+	vdso_ts->nsec	= tk->coarse_nsec;
 
 	/* CLOCK_MONOTONIC_COARSE */
 	vdso_ts		= &vc[CS_HRES_COARSE].basetime[CLOCK_MONOTONIC_COARSE];
 	vdso_ts->sec	= tk->xtime_sec + tk->wall_to_monotonic.tv_sec;
-	nsec		= tk->tkr_mono.xtime_nsec >> tk->tkr_mono.shift;
+	nsec		= tk->coarse_nsec;
 	nsec		= nsec + tk->wall_to_monotonic.tv_nsec;
 	vdso_ts->sec	+= __iter_div_u64_rem(nsec, NSEC_PER_SEC, &vdso_ts->nsec);