Merge tag 'timers-ptp-2025-07-27' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull timekeeping and VDSO updates from Thomas Gleixner:

 - Introduce support for auxiliary timekeepers

   PTP clocks can be disconnected from the universal CLOCK_TAI reality
   for various reasons including regularatory requirements for
   functional safety redundancy.

   The kernel so far only supports a single notion of time, which means
   that all clocks are correlated in frequency and only differ by offset
   to each other.

   Access to non-correlated PTP clocks has been available so far only
   through the file descriptor based "POSIX clock IDs", which are
   subject to locking and have to go all the way out to the hardware.

   The access is not only horribly slow, as it has to go all the way out
   to the NIC/PTP hardware, but that also prevents the kernel to read
   the time of such clocks e.g. from the network stack, where it is
   required for TSN networking both on the transmit and receive side
   unless the hardware provides offloading.

   The auxiliary clocks provide a mechanism to support arbitrary clocks
   which are not correlated to the system clock. This is not restricted
   to the PTP use case on purpose as there is no kernel side association
   of these clocks to a particular PTP device because that's a pure user
   space configuration decision. Having them independent allows to
   utilize them for other purposes and also enables them to be tested
   without hardware dependencies.

   To avoid pointless overhead these clocks have to be enabled
   individualy via a new sysfs interface to reduce the overhead to a
   single compare in the hotpath if they are enabled at the Kconfig
   level at all.

   These clocks utilize the existing timekeeping/NTP infrastructures,
   which has been made possible over the recent releases by incrementaly
   converting these infrastructures over from a single static instance
   to a multi-instance pointer based implementation without any
   performance regression reported.

   The auxiliary clocks provide the same "emulation" of a "correct"
   clock as the existing CLOCK_* variants do with an independent
   instance of data and provide the same steering mechanism through the
   existing sys_clock_adjtime() interface, which has been confirmed to
   work by the chronyd(8) maintainer.

   That allows to provide lockless kernel internal and VDSO support so
   that applications and kernel internal functionalities can access
   these clocks without restrictions and at the same performance as the
   existing system clocks.

 - Avoid double notifications in the adjtimex() syscall. Not a big
   issue, but a trivial to avoid latency source.

* tag 'timers-ptp-2025-07-27' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (39 commits)
  vdso/gettimeofday: Add support for auxiliary clocks
  vdso/vsyscall: Update auxiliary clock data in the datapage
  vdso: Introduce aux_clock_resolution_ns()
  vdso/gettimeofday: Introduce vdso_get_timestamp()
  vdso/gettimeofday: Introduce vdso_set_timespec()
  vdso/gettimeofday: Introduce vdso_clockid_valid()
  vdso/gettimeofday: Return bool from clock_gettime() helpers
  vdso/gettimeofday: Return bool from clock_getres() helpers
  vdso/helpers: Add helpers for seqlocks of single vdso_clock
  vdso/vsyscall: Split up __arch_update_vsyscall() into __arch_update_vdso_clock()
  vdso/vsyscall: Introduce a helper to fill clock configurations
  timekeeping: Remove the temporary CLOCK_AUX workaround
  timekeeping: Provide ktime_get_clock_ts64()
  timekeeping: Provide interface to control auxiliary clocks
  timekeeping: Provide update for auxiliary timekeepers
  timekeeping: Provide adjtimex() for auxiliary clocks
  timekeeping: Prepare do_adtimex() for auxiliary clocks
  timekeeping: Make do_adjtimex() reusable
  timekeeping: Add auxiliary clock support to __timekeeping_inject_offset()
  timekeeping: Make timekeeping_inject_offset() reusable
  ...

1 files changed, 140 insertions, 84 deletions

diff --git a/lib/vdso/gettimeofday.c b/lib/vdso/gettimeofday.c
index 93ef801a97ef..02ea19f67164 100644
--- a/lib/vdso/gettimeofday.c
+++ b/lib/vdso/gettimeofday.c
@@ -2,6 +2,7 @@
 /*
  * Generic userspace implementations of gettimeofday() and similar.
  */
+#include <vdso/auxclock.h>
 #include <vdso/datapage.h>
 #include <vdso/helpers.h>
 
@@ -71,6 +72,42 @@ static inline bool vdso_cycles_ok(u64 cycles)
 }
 #endif
 
+static __always_inline bool vdso_clockid_valid(clockid_t clock)
+{
+	/* Check for negative values or invalid clocks */
+	return likely((u32) clock <= CLOCK_AUX_LAST);
+}
+
+/*
+ * Must not be invoked within the sequence read section as a race inside
+ * that loop could result in __iter_div_u64_rem() being extremely slow.
+ */
+static __always_inline void vdso_set_timespec(struct __kernel_timespec *ts, u64 sec, u64 ns)
+{
+	ts->tv_sec = sec + __iter_div_u64_rem(ns, NSEC_PER_SEC, &ns);
+	ts->tv_nsec = ns;
+}
+
+static __always_inline
+bool vdso_get_timestamp(const struct vdso_time_data *vd, const struct vdso_clock *vc,
+			unsigned int clkidx, u64 *sec, u64 *ns)
+{
+	const struct vdso_timestamp *vdso_ts = &vc->basetime[clkidx];
+	u64 cycles;
+
+	if (unlikely(!vdso_clocksource_ok(vc)))
+		return false;
+
+	cycles = __arch_get_hw_counter(vc->clock_mode, vd);
+	if (unlikely(!vdso_cycles_ok(cycles)))
+		return false;
+
+	*ns = vdso_calc_ns(vc, cycles, vdso_ts->nsec);
+	*sec = vdso_ts->sec;
+
+	return true;
+}
+
 #ifdef CONFIG_TIME_NS
 
 #ifdef CONFIG_GENERIC_VDSO_DATA_STORE
@@ -82,48 +119,35 @@ const struct vdso_time_data *__arch_get_vdso_u_timens_data(const struct vdso_tim
 #endif /* CONFIG_GENERIC_VDSO_DATA_STORE */
 
 static __always_inline
-int do_hres_timens(const struct vdso_time_data *vdns, const struct vdso_clock *vcns,
-		   clockid_t clk, struct __kernel_timespec *ts)
+bool do_hres_timens(const struct vdso_time_data *vdns, const struct vdso_clock *vcns,
+		    clockid_t clk, struct __kernel_timespec *ts)
 {
 	const struct vdso_time_data *vd = __arch_get_vdso_u_timens_data(vdns);
 	const struct timens_offset *offs = &vcns->offset[clk];
 	const struct vdso_clock *vc = vd->clock_data;
-	const struct vdso_timestamp *vdso_ts;
-	u64 cycles, ns;
 	u32 seq;
 	s64 sec;
+	u64 ns;
 
 	if (clk != CLOCK_MONOTONIC_RAW)
 		vc = &vc[CS_HRES_COARSE];
 	else
 		vc = &vc[CS_RAW];
-	vdso_ts = &vc->basetime[clk];
 
 	do {
 		seq = vdso_read_begin(vc);
 
-		if (unlikely(!vdso_clocksource_ok(vc)))
-			return -1;
-
-		cycles = __arch_get_hw_counter(vc->clock_mode, vd);
-		if (unlikely(!vdso_cycles_ok(cycles)))
-			return -1;
-		ns = vdso_calc_ns(vc, cycles, vdso_ts->nsec);
-		sec = vdso_ts->sec;
+		if (!vdso_get_timestamp(vd, vc, clk, &sec, &ns))
+			return false;
 	} while (unlikely(vdso_read_retry(vc, seq)));
 
 	/* Add the namespace offset */
 	sec += offs->sec;
 	ns += offs->nsec;
 
-	/*
-	 * Do this outside the loop: a race inside the loop could result
-	 * in __iter_div_u64_rem() being extremely slow.
-	 */
-	ts->tv_sec = sec + __iter_div_u64_rem(ns, NSEC_PER_SEC, &ns);
-	ts->tv_nsec = ns;
+	vdso_set_timespec(ts, sec, ns);
 
-	return 0;
+	return true;
 }
 #else
 static __always_inline
@@ -133,24 +157,23 @@ const struct vdso_time_data *__arch_get_vdso_u_timens_data(const struct vdso_tim
 }
 
 static __always_inline
-int do_hres_timens(const struct vdso_time_data *vdns, const struct vdso_clock *vcns,
-		   clockid_t clk, struct __kernel_timespec *ts)
+bool do_hres_timens(const struct vdso_time_data *vdns, const struct vdso_clock *vcns,
+		    clockid_t clk, struct __kernel_timespec *ts)
 {
-	return -EINVAL;
+	return false;
 }
 #endif
 
 static __always_inline
-int do_hres(const struct vdso_time_data *vd, const struct vdso_clock *vc,
-	    clockid_t clk, struct __kernel_timespec *ts)
+bool do_hres(const struct vdso_time_data *vd, const struct vdso_clock *vc,
+	     clockid_t clk, struct __kernel_timespec *ts)
 {
-	const struct vdso_timestamp *vdso_ts = &vc->basetime[clk];
-	u64 cycles, sec, ns;
+	u64 sec, ns;
 	u32 seq;
 
 	/* Allows to compile the high resolution parts out */
 	if (!__arch_vdso_hres_capable())
-		return -1;
+		return false;
 
 	do {
 		/*
@@ -172,30 +195,19 @@ int do_hres(const struct vdso_time_data *vd, const struct vdso_clock *vc,
 		}
 		smp_rmb();
 
-		if (unlikely(!vdso_clocksource_ok(vc)))
-			return -1;
-
-		cycles = __arch_get_hw_counter(vc->clock_mode, vd);
-		if (unlikely(!vdso_cycles_ok(cycles)))
-			return -1;
-		ns = vdso_calc_ns(vc, cycles, vdso_ts->nsec);
-		sec = vdso_ts->sec;
+		if (!vdso_get_timestamp(vd, vc, clk, &sec, &ns))
+			return false;
 	} while (unlikely(vdso_read_retry(vc, seq)));
 
-	/*
-	 * Do this outside the loop: a race inside the loop could result
-	 * in __iter_div_u64_rem() being extremely slow.
-	 */
-	ts->tv_sec = sec + __iter_div_u64_rem(ns, NSEC_PER_SEC, &ns);
-	ts->tv_nsec = ns;
+	vdso_set_timespec(ts, sec, ns);
 
-	return 0;
+	return true;
 }
 
 #ifdef CONFIG_TIME_NS
 static __always_inline
-int do_coarse_timens(const struct vdso_time_data *vdns, const struct vdso_clock *vcns,
-		     clockid_t clk, struct __kernel_timespec *ts)
+bool do_coarse_timens(const struct vdso_time_data *vdns, const struct vdso_clock *vcns,
+		      clockid_t clk, struct __kernel_timespec *ts)
 {
 	const struct vdso_time_data *vd = __arch_get_vdso_u_timens_data(vdns);
 	const struct timens_offset *offs = &vcns->offset[clk];
@@ -217,26 +229,22 @@ int do_coarse_timens(const struct vdso_time_data *vdns, const struct vdso_clock
 	sec += offs->sec;
 	nsec += offs->nsec;
 
-	/*
-	 * Do this outside the loop: a race inside the loop could result
-	 * in __iter_div_u64_rem() being extremely slow.
-	 */
-	ts->tv_sec = sec + __iter_div_u64_rem(nsec, NSEC_PER_SEC, &nsec);
-	ts->tv_nsec = nsec;
-	return 0;
+	vdso_set_timespec(ts, sec, nsec);
+
+	return true;
 }
 #else
 static __always_inline
-int do_coarse_timens(const struct vdso_time_data *vdns, const struct vdso_clock *vcns,
-		     clockid_t clk, struct __kernel_timespec *ts)
+bool do_coarse_timens(const struct vdso_time_data *vdns, const struct vdso_clock *vcns,
+		      clockid_t clk, struct __kernel_timespec *ts)
 {
-	return -1;
+	return false;
 }
 #endif
 
 static __always_inline
-int do_coarse(const struct vdso_time_data *vd, const struct vdso_clock *vc,
-	      clockid_t clk, struct __kernel_timespec *ts)
+bool do_coarse(const struct vdso_time_data *vd, const struct vdso_clock *vc,
+	       clockid_t clk, struct __kernel_timespec *ts)
 {
 	const struct vdso_timestamp *vdso_ts = &vc->basetime[clk];
 	u32 seq;
@@ -258,19 +266,60 @@ int do_coarse(const struct vdso_time_data *vd, const struct vdso_clock *vc,
 		ts->tv_nsec = vdso_ts->nsec;
 	} while (unlikely(vdso_read_retry(vc, seq)));
 
-	return 0;
+	return true;
+}
+
+static __always_inline
+bool do_aux(const struct vdso_time_data *vd, clockid_t clock, struct __kernel_timespec *ts)
+{
+	const struct vdso_clock *vc;
+	u32 seq, idx;
+	u64 sec, ns;
+
+	if (!IS_ENABLED(CONFIG_POSIX_AUX_CLOCKS))
+		return false;
+
+	idx = clock - CLOCK_AUX;
+	vc = &vd->aux_clock_data[idx];
+
+	do {
+		/*
+		 * Open coded function vdso_read_begin() to handle
+		 * VDSO_CLOCK_TIMENS. See comment in do_hres().
+		 */
+		while ((seq = READ_ONCE(vc->seq)) & 1) {
+			if (IS_ENABLED(CONFIG_TIME_NS) && vc->clock_mode == VDSO_CLOCKMODE_TIMENS) {
+				vd = __arch_get_vdso_u_timens_data(vd);
+				vc = &vd->aux_clock_data[idx];
+				/* Re-read from the real time data page */
+				continue;
+			}
+			cpu_relax();
+		}
+		smp_rmb();
+
+		/* Auxclock disabled? */
+		if (vc->clock_mode == VDSO_CLOCKMODE_NONE)
+			return false;
+
+		if (!vdso_get_timestamp(vd, vc, VDSO_BASE_AUX, &sec, &ns))
+			return false;
+	} while (unlikely(vdso_read_retry(vc, seq)));
+
+	vdso_set_timespec(ts, sec, ns);
+
+	return true;
 }
 
-static __always_inline int
+static __always_inline bool
 __cvdso_clock_gettime_common(const struct vdso_time_data *vd, clockid_t clock,
 			     struct __kernel_timespec *ts)
 {
 	const struct vdso_clock *vc = vd->clock_data;
 	u32 msk;
 
-	/* Check for negative values or invalid clocks */
-	if (unlikely((u32) clock >= MAX_CLOCKS))
-		return -1;
+	if (!vdso_clockid_valid(clock))
+		return false;
 
 	/*
 	 * Convert the clockid to a bitmask and use it to check which
@@ -283,8 +332,10 @@ __cvdso_clock_gettime_common(const struct vdso_time_data *vd, clockid_t clock,
 		return do_coarse(vd, &vc[CS_HRES_COARSE], clock, ts);
 	else if (msk & VDSO_RAW)
 		vc = &vc[CS_RAW];
+	else if (msk & VDSO_AUX)
+		return do_aux(vd, clock, ts);
 	else
-		return -1;
+		return false;
 
 	return do_hres(vd, vc, clock, ts);
 }
@@ -293,9 +344,11 @@ static __maybe_unused int
 __cvdso_clock_gettime_data(const struct vdso_time_data *vd, clockid_t clock,
 			   struct __kernel_timespec *ts)
 {
-	int ret = __cvdso_clock_gettime_common(vd, clock, ts);
+	bool ok;
+
+	ok = __cvdso_clock_gettime_common(vd, clock, ts);
 
-	if (unlikely(ret))
+	if (unlikely(!ok))
 		return clock_gettime_fallback(clock, ts);
 	return 0;
 }
@@ -312,18 +365,18 @@ __cvdso_clock_gettime32_data(const struct vdso_time_data *vd, clockid_t clock,
 			     struct old_timespec32 *res)
 {
 	struct __kernel_timespec ts;
-	int ret;
+	bool ok;
 
-	ret = __cvdso_clock_gettime_common(vd, clock, &ts);
+	ok = __cvdso_clock_gettime_common(vd, clock, &ts);
 
-	if (unlikely(ret))
+	if (unlikely(!ok))
 		return clock_gettime32_fallback(clock, res);
 
-	/* For ret == 0 */
+	/* For ok == true */
 	res->tv_sec = ts.tv_sec;
 	res->tv_nsec = ts.tv_nsec;
 
-	return ret;
+	return 0;
 }
 
 static __maybe_unused int
@@ -342,7 +395,7 @@ __cvdso_gettimeofday_data(const struct vdso_time_data *vd,
 	if (likely(tv != NULL)) {
 		struct __kernel_timespec ts;
 
-		if (do_hres(vd, &vc[CS_HRES_COARSE], CLOCK_REALTIME, &ts))
+		if (!do_hres(vd, &vc[CS_HRES_COARSE], CLOCK_REALTIME, &ts))
 			return gettimeofday_fallback(tv, tz);
 
 		tv->tv_sec = ts.tv_sec;
@@ -396,16 +449,15 @@ static __maybe_unused __kernel_old_time_t __cvdso_time(__kernel_old_time_t *time
 
 #ifdef VDSO_HAS_CLOCK_GETRES
 static __maybe_unused
-int __cvdso_clock_getres_common(const struct vdso_time_data *vd, clockid_t clock,
-				struct __kernel_timespec *res)
+bool __cvdso_clock_getres_common(const struct vdso_time_data *vd, clockid_t clock,
+				 struct __kernel_timespec *res)
 {
 	const struct vdso_clock *vc = vd->clock_data;
 	u32 msk;
 	u64 ns;
 
-	/* Check for negative values or invalid clocks */
-	if (unlikely((u32) clock >= MAX_CLOCKS))
-		return -1;
+	if (!vdso_clockid_valid(clock))
+		return false;
 
 	if (IS_ENABLED(CONFIG_TIME_NS) &&
 	    vc->clock_mode == VDSO_CLOCKMODE_TIMENS)
@@ -426,24 +478,28 @@ int __cvdso_clock_getres_common(const struct vdso_time_data *vd, clockid_t clock
 		 * Preserves the behaviour of posix_get_coarse_res().
 		 */
 		ns = LOW_RES_NSEC;
+	} else if (msk & VDSO_AUX) {
+		ns = aux_clock_resolution_ns();
 	} else {
-		return -1;
+		return false;
 	}
 
 	if (likely(res)) {
 		res->tv_sec = 0;
 		res->tv_nsec = ns;
 	}
-	return 0;
+	return true;
 }
 
 static __maybe_unused
 int __cvdso_clock_getres_data(const struct vdso_time_data *vd, clockid_t clock,
 			      struct __kernel_timespec *res)
 {
-	int ret = __cvdso_clock_getres_common(vd, clock, res);
+	bool ok;
 
-	if (unlikely(ret))
+	ok =  __cvdso_clock_getres_common(vd, clock, res);
+
+	if (unlikely(!ok))
 		return clock_getres_fallback(clock, res);
 	return 0;
 }
@@ -460,18 +516,18 @@ __cvdso_clock_getres_time32_data(const struct vdso_time_data *vd, clockid_t cloc
 				 struct old_timespec32 *res)
 {
 	struct __kernel_timespec ts;
-	int ret;
+	bool ok;
 
-	ret = __cvdso_clock_getres_common(vd, clock, &ts);
+	ok = __cvdso_clock_getres_common(vd, clock, &ts);
 
-	if (unlikely(ret))
+	if (unlikely(!ok))
 		return clock_getres32_fallback(clock, res);
 
 	if (likely(res)) {
 		res->tv_sec = ts.tv_sec;
 		res->tv_nsec = ts.tv_nsec;
 	}
-	return ret;
+	return 0;
 }
 
 static __maybe_unused int