KVM: x86: Use kernel timekeeping snapshots for getting kvmclock time since boot

Replace the KVM-private vgettsc()+do_kvmclock_base() timekeeping
reimplementation with calls to the recently crafted, generic
ktime_get_snapshot_id() interface.  This is the first step towards dropping
KVM's homebrewed implementation entirely (do_monotonic() and do_realtime()
will be converted in the near future).

As with KVM's implementation, the snapshot provides both the system time
and the raw_cycles (TSC), atomically paired using a sequence counter.  The
equivalents to vgettsc()'s TSC and HVCLOCK modes respectively are if the
clocksource itself is TSC (cs_id == CSID_X86_TSC) and if the underlying
hardware clocksource is TSC (hw_csid == CSID_X86_TSC).  In the Hyper-V
case, i.e. hw_csid == CSID_X86_TSC, if the clocksource couldn't provide a
raw hardware counter value, treat the clock not being based on TSC, which
which is equivalent to vgettsc() returning VDSO_CLOCKMODE_NONE.

Unlike KVM's current implementation, don't include offs_boot in the
atomically-acquired tuple as there's simply no need to do so: the time
since boot only changes at boot (duh) and at suspend/resume boundaries.
Unless processes aren't being frozen/thawed before/after suspend/resume,
which would completely break suspend/resume, TK_OFFS_BOOT can't change
while kvm_get_time_and_clockread() is running.  And if KVM does somehow try
to take a snapshot during suspend, timekeeping core will WARN and refuse to
provide the snapshot.

This is a step towards eliminating the pvclock_gtod_data private copy
of timekeeping state and the associated notifier callback.

Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
[sean: separate from other conversions, massage changelog accordingly]
Link: https://patch.msgid.link/20260826213303.914988-20-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>

1 files changed, 30 insertions, 27 deletions

diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index eecc3aa28f28..5746a77942de 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -35,6 +35,7 @@
 #include "smm.h"
 
 #include <linux/clocksource.h>
+#include <linux/timekeeping.h>
 #include <linux/interrupt.h>
 #include <linux/kvm.h>
 #include <linux/fs.h>
@@ -1438,29 +1439,6 @@ static inline u64 vgettsc(struct pvclock_clock *clock, u64 *tsc_timestamp,
 }
 
 /*
- * As with get_kvmclock_base_ns(), this counts from boot time, at the
- * frequency of CLOCK_MONOTONIC_RAW (hence adding gtos->offs_boot).
- */
-static int do_kvmclock_base(s64 *t, u64 *tsc_timestamp)
-{
-	struct pvclock_gtod_data *gtod = &pvclock_gtod_data;
-	unsigned long seq;
-	int mode;
-	u64 ns;
-
-	do {
-		seq = read_seqcount_begin(&gtod->seq);
-		ns = gtod->raw_clock.base_cycles;
-		ns += vgettsc(&gtod->raw_clock, tsc_timestamp, &mode);
-		ns >>= gtod->raw_clock.shift;
-		ns += ktime_to_ns(ktime_add(gtod->raw_clock.offset, gtod->offs_boot));
-	} while (unlikely(read_seqcount_retry(&gtod->seq, seq)));
-	*t = ns;
-
-	return mode;
-}
-
-/*
  * This calculates CLOCK_MONOTONIC at the time of the TSC snapshot, with
  * no boot time offset.
  */
@@ -1504,6 +1482,29 @@ static int do_realtime(struct timespec64 *ts, u64 *tsc_timestamp)
 	return mode;
 }
 
+static bool kvm_snapshot_has_tsc(struct system_time_snapshot *snap,
+				 u64 *tsc_timestamp)
+{
+	/*
+	 * ktime_get_snapshot_id() cannot fail for standard clock IDs
+	 * (only for invalid/aux clocks or during suspend, with a WARN).
+	 */
+	if (!snap->valid)
+		return false;
+
+	if (snap->cs_id == CSID_X86_TSC) {
+		*tsc_timestamp = snap->cycles;
+		return true;
+	}
+
+	if (snap->hw_csid == CSID_X86_TSC && snap->hw_cycles) {
+		*tsc_timestamp = snap->hw_cycles;
+		return true;
+	}
+
+	return false;
+}
+
 /*
  * Calculates the kvmclock_base_ns (CLOCK_MONOTONIC_RAW + boot time) and
  * reports the TSC value from which it do so. Returns true if host is
@@ -1511,12 +1512,14 @@ static int do_realtime(struct timespec64 *ts, u64 *tsc_timestamp)
  */
 static bool kvm_get_time_and_clockread(s64 *kernel_ns, u64 *tsc_timestamp)
 {
-	/* checked again under seqlock below */
-	if (!gtod_is_based_on_tsc(pvclock_gtod_data.clock.vclock_mode))
+	struct system_time_snapshot snap = {};
+
+	ktime_get_snapshot_id(CLOCK_MONOTONIC_RAW, &snap);
+	if (!kvm_snapshot_has_tsc(&snap, tsc_timestamp))
 		return false;
 
-	return gtod_is_based_on_tsc(do_kvmclock_base(kernel_ns,
-						     tsc_timestamp));
+	*kernel_ns = ktime_to_ns(ktime_mono_to_any(snap.systime, TK_OFFS_BOOT));
+	return true;
 }
 
 /*