timekeeping: Provide ktime_get_snapshot_id()

ktime_get_snapshot() provides a snapshot of the underlying clocksource
counter value and the corresponding CLOCK_MONOTONIC_RAW, CLOCK_REALTIME and
CLOCK_BOOTTIME timestamps.

There is no usage of CLOCK_REALTIME and CLOCK_BOOTTIME at the same time and
CLOCK_BOOTTIME support was just added for the ARM64 KVM tracing mechanism,
which needs CLOCK_BOOTTIME and the underlying clocksource counter value.

ktime_get_snapshot() is also not suitable for usage with CLOCK_AUX, but
that's a prerequisite to support PTP hardware timestamping for CLOCK_AUX
steering.

As a first step, rename ktime_get_snapshot() to ktime_get_snapshot_id(),
which now takes a clockid argument to select the clock which needs to be
captured. The result is stored in system_time_snapshot::systime, which will
replace the system_time_snapshot::real/boot members once all usage sites
have been converted.

ktime_get_snapshot() is a simple wrapper which hands in CLOCK_REALTIME as
clockid argument for the conversion period. That means CLOCK_REALTIME is
now captured twice, but that redunancy is only temporary.

As all usage sites of struct system_time_snapshot has to be updated anyway,
rename the 'raw' member to 'monoraw' for clarity.

No functional change vs. current users of ktime_get_snapshot()

Signed-off-by: Thomas Gleixner <tglx@kernel.org>
Tested-by: David Woodhouse <dwmw@amazon.co.uk>
Tested-by: Arthur Kiyanovski <akiyano@amazon.com>
Reviewed-by: David Woodhouse <dwmw@amazon.co.uk>
Reviewed-by: Thomas Weißschuh <thomas.weissschuh@linutronix.de>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Link: https://patch.msgid.link/20260529195556.971591633@kernel.org

2 files changed, 90 insertions, 33 deletions

diff --git a/include/linux/timekeeping.h b/include/linux/timekeeping.h
index aee2c1a46e47..161157c8d27e 100644
--- a/include/linux/timekeeping.h
+++ b/include/linux/timekeeping.h
@@ -276,24 +276,32 @@ static inline bool ktime_get_aux_ts64(clockid_t id, struct timespec64 *kt) { ret
 #endif
 
 /**
- * struct system_time_snapshot - simultaneous raw/real time capture with
- *				 counter value
- * @cycles:	Clocksource counter value to produce the system times
- * @real:	Realtime system time
- * @boot:	Boot time
- * @raw:	Monotonic raw system time
- * @cs_id:	Clocksource ID
+ * struct system_time_snapshot - Simultaneous time capture of CLOCK_MONOTONIC_RAW,
+ *				 a selected CLOCK_* and the clocksource counter value
+ * @cycles:		Clocksource counter value to produce the system times
+ * @systime:		The system time of the selected CLOCK ID
+ * @real:		Realtime system time
+ * @boot:		Boot time
+ * @raw:		Monotonic raw system time
+ * @monoraw:		Monotonic raw system time
+ * @cs_id:		Clocksource ID
  * @clock_was_set_seq:	The sequence number of clock-was-set events
  * @cs_was_changed_seq:	The sequence number of clocksource change events
+ * @valid:		True if the snapshot is valid
  */
 struct system_time_snapshot {
 	u64			cycles;
+	ktime_t			systime;
 	ktime_t			real;
 	ktime_t			boot;
-	ktime_t			raw;
+	union {
+		ktime_t		raw;
+		ktime_t		monoraw;
+	};
 	enum clocksource_ids	cs_id;
 	unsigned int		clock_was_set_seq;
 	u8			cs_was_changed_seq;
+	u8			valid;
 };
 
 /**
@@ -341,9 +349,15 @@ extern int get_device_system_crosststamp(
 			struct system_device_crosststamp *xtstamp);
 
 /*
- * Simultaneously snapshot realtime and monotonic raw clocks
+ * Simultaneously snapshot a given clock with MONOTONIC_RAW and the underlying
+ * clocksource counter value.
  */
-extern void ktime_get_snapshot(struct system_time_snapshot *systime_snapshot);
+extern void ktime_get_snapshot_id(clockid_t clock_id, struct system_time_snapshot *systime_snapshot);
+
+static inline void ktime_get_snapshot(struct system_time_snapshot *systime_snapshot)
+{
+	ktime_get_snapshot_id(CLOCK_REALTIME, systime_snapshot);
+}
 
 /*
  * Persistent clock related interfaces
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index c493a4010305..0053dc0010f4 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -1183,43 +1183,86 @@ noinstr time64_t __ktime_get_real_seconds(void)
 }
 
 /**
- * ktime_get_snapshot - snapshots the realtime/monotonic raw clocks with counter
- * @systime_snapshot:	pointer to struct receiving the system time snapshot
- */
-void ktime_get_snapshot(struct system_time_snapshot *systime_snapshot)
-{
-	struct timekeeper *tk = &tk_core.timekeeper;
+ * ktime_get_snapshot_id -  Simultaneously snapshot a given clock ID with
+ *			    CLOCK_MONOTONIC_RAW and the underlying
+ *			    clocksource counter value.
+ * @clock_id:		The clock ID to snapshot
+ * @systime_snapshot:	Pointer to struct receiving the system time snapshot
+ */
+void ktime_get_snapshot_id(clockid_t clock_id, struct system_time_snapshot *systime_snapshot)
+{
+	ktime_t base_raw, base_sys, offs_sys, *offs, offs_zero = 0;
+	u64 nsec_raw, nsec_sys, now;
+	struct timekeeper *tk;
+	struct tk_data *tkd;
 	unsigned int seq;
-	ktime_t base_raw;
 	ktime_t base_real;
 	ktime_t base_boot;
-	u64 nsec_raw;
-	u64 nsec_real;
-	u64 now;
 
-	WARN_ON_ONCE(timekeeping_suspended);
+	/* Invalidate the snapshot for all failure cases */
+	systime_snapshot->valid = false;
+
+	if (WARN_ON_ONCE(timekeeping_suspended))
+		return;
+
+	switch (clock_id) {
+	case CLOCK_REALTIME:
+		tkd = &tk_core;
+		offs = &tk_core.timekeeper.offs_real;
+		break;
+	/* Map RAW to MONOTONIC so the loop below is trivial */
+	case CLOCK_MONOTONIC_RAW:
+	case CLOCK_MONOTONIC:
+		tkd = &tk_core;
+		offs = &offs_zero;
+		break;
+	case CLOCK_BOOTTIME:
+		tkd = &tk_core;
+		offs = &tk_core.timekeeper.offs_boot;
+		break;
+	default:
+		WARN_ON_ONCE(1);
+		return;
+	}
+
+	tk = &tkd->timekeeper;
 
 	do {
-		seq = read_seqcount_begin(&tk_core.seq);
+		seq = read_seqcount_begin(&tkd->seq);
+
 		now = tk_clock_read(&tk->tkr_mono);
 		systime_snapshot->cs_id = tk->tkr_mono.clock->id;
 		systime_snapshot->cs_was_changed_seq = tk->cs_was_changed_seq;
 		systime_snapshot->clock_was_set_seq = tk->clock_was_set_seq;
-		base_real = ktime_add(tk->tkr_mono.base,
-				      tk_core.timekeeper.offs_real);
-		base_boot = ktime_add(tk->tkr_mono.base,
-				      tk_core.timekeeper.offs_boot);
+
+		base_sys = tk->tkr_mono.base;
+		offs_sys = *offs;
 		base_raw = tk->tkr_raw.base;
-		nsec_real = timekeeping_cycles_to_ns(&tk->tkr_mono, now);
-		nsec_raw  = timekeeping_cycles_to_ns(&tk->tkr_raw, now);
-	} while (read_seqcount_retry(&tk_core.seq, seq));
+
+		/* Kept around until the callers are fixed up */
+		base_real = ktime_add(base_sys, tk_core.timekeeper.offs_real);
+		base_boot = ktime_add(base_sys, tk_core.timekeeper.offs_boot);
+
+		nsec_sys = timekeeping_cycles_to_ns(&tk->tkr_mono, now);
+		nsec_raw = timekeeping_cycles_to_ns(&tk->tkr_raw, now);
+	} while (read_seqcount_retry(&tkd->seq, seq));
 
 	systime_snapshot->cycles = now;
-	systime_snapshot->real = ktime_add_ns(base_real, nsec_real);
-	systime_snapshot->boot = ktime_add_ns(base_boot, nsec_real);
-	systime_snapshot->raw = ktime_add_ns(base_raw, nsec_raw);
+	systime_snapshot->systime = ktime_add_ns(base_sys, offs_sys + nsec_sys);
+	systime_snapshot->real = ktime_add_ns(base_real, nsec_sys);
+	systime_snapshot->boot = ktime_add_ns(base_boot, nsec_sys);
+	systime_snapshot->monoraw = ktime_add_ns(base_raw, nsec_raw);
+
+	/*
+	 * Special case for PTP. Just transfer the raw time into sys,
+	 * so the call sites can consistently use snap::systime.
+	 */
+	if (clock_id == CLOCK_MONOTONIC_RAW)
+		systime_snapshot->systime = systime_snapshot->monoraw;
+	/* Tell the consumer that this snapshot is valid */
+	systime_snapshot->valid = true;
 }
-EXPORT_SYMBOL_GPL(ktime_get_snapshot);
+EXPORT_SYMBOL_GPL(ktime_get_snapshot_id);
 
 /* Scale base by mult/div checking for overflow */
 static int scale64_check_overflow(u64 mult, u64 div, u64 *base)