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, 35 insertions, 2 deletions

diff --git a/include/linux/timekeeper_internal.h b/include/linux/timekeeper_internal.h
index 785048a3b3e6..c27aac67cb3f 100644
--- a/include/linux/timekeeper_internal.h
+++ b/include/linux/timekeeper_internal.h
@@ -12,6 +12,22 @@
 #include <linux/time.h>
 
 /**
+ * timekeeper_ids - IDs for various time keepers in the kernel
+ * @TIMEKEEPER_CORE:		The central core timekeeper managing system time
+ * @TIMEKEEPER_AUX_FIRST:	The first AUX timekeeper
+ * @TIMEKEEPER_AUX_LAST:	The last AUX timekeeper
+ * @TIMEKEEPERS_MAX:		The maximum number of timekeepers managed
+ */
+enum timekeeper_ids {
+	TIMEKEEPER_CORE,
+#ifdef CONFIG_POSIX_AUX_CLOCKS
+	TIMEKEEPER_AUX_FIRST,
+	TIMEKEEPER_AUX_LAST = TIMEKEEPER_AUX_FIRST + MAX_AUX_CLOCKS - 1,
+#endif
+	TIMEKEEPERS_MAX,
+};
+
+/**
  * struct tk_read_base - base structure for timekeeping readout
  * @clock:	Current clocksource used for timekeeping.
  * @mask:	Bitmask for two's complement subtraction of non 64bit clocks
@@ -51,11 +67,14 @@ 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
+ * @offs_aux:			Offset clock monotonic -> clock AUX
  * @coarse_nsec:		The nanoseconds part for coarse time getters
+ * @id:				The timekeeper ID
  * @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
  * @cs_was_changed_seq:		The sequence number of clocksource change events
+ * @clock_valid:		Indicator for valid clock
  * @monotonic_to_boot:		CLOCK_MONOTONIC to CLOCK_BOOTTIME offset
  * @cycle_interval:		Number of clock cycles in one NTP interval
  * @xtime_interval:		Number of clock shifted nano seconds in one NTP
@@ -95,13 +114,16 @@ struct tk_read_base {
  * @monotonic_to_boottime is a timespec64 representation of @offs_boot to
  * accelerate the VDSO update for CLOCK_BOOTTIME.
  *
+ * @offs_aux is used by the auxiliary timekeepers which do not utilize any
+ * of the regular timekeeper offset fields.
+ *
  * The cacheline ordering of the structure is optimized for in kernel usage of
  * the ktime_get() and ktime_get_ts64() family of time accessors. Struct
  * timekeeper is prepended in the core timekeeping code with a sequence count,
  * which results in the following cacheline layout:
  *
  * 0:	seqcount, tkr_mono
- * 1:	xtime_sec ... coarse_nsec
+ * 1:	xtime_sec ... id
  * 2:	tkr_raw, raw_sec
  * 3,4: Internal variables
  *
@@ -121,8 +143,12 @@ struct timekeeper {
 	struct timespec64	wall_to_monotonic;
 	ktime_t			offs_real;
 	ktime_t			offs_boot;
-	ktime_t			offs_tai;
+	union {
+		ktime_t		offs_tai;
+		ktime_t		offs_aux;
+	};
 	u32			coarse_nsec;
+	enum timekeeper_ids	id;
 
 	/* Cacheline 2: */
 	struct tk_read_base	tkr_raw;
@@ -131,6 +157,7 @@ struct timekeeper {
 	/* Cachline 3 and 4 (timekeeping internal variables): */
 	unsigned int		clock_was_set_seq;
 	u8			cs_was_changed_seq;
+	u8			clock_valid;
 
 	struct timespec64	monotonic_to_boot;
 
@@ -163,4 +190,10 @@ static inline void update_vsyscall_tz(void)
 }
 #endif
 
+#if defined(CONFIG_GENERIC_GETTIMEOFDAY) && defined(CONFIG_POSIX_AUX_CLOCKS)
+extern void vdso_time_update_aux(struct timekeeper *tk);
+#else
+static inline void vdso_time_update_aux(struct timekeeper *tk) { }
+#endif
+
 #endif /* _LINUX_TIMEKEEPER_INTERNAL_H */