x86/hyperv: Fix hv tsc page based sched_clock for hibernation

commit bcc80dec91ee745b3d66f3e48f0ec2efdea97149 upstream.

read_hv_sched_clock_tsc() assumes that the Hyper-V clock counter is
bigger than the variable hv_sched_clock_offset, which is cached during
early boot, but depending on the timing this assumption may be false
when a hibernated VM starts again (the clock counter starts from 0
again) and is resuming back (Note: hv_init_tsc_clocksource() is not
called during hibernation/resume); consequently,
read_hv_sched_clock_tsc() may return a negative integer (which is
interpreted as a huge positive integer since the return type is u64)
and new kernel messages are prefixed with huge timestamps before
read_hv_sched_clock_tsc() grows big enough (which typically takes
several seconds).

Fix the issue by saving the Hyper-V clock counter just before the
suspend, and using it to correct the hv_sched_clock_offset in
resume. This makes hv tsc page based sched_clock continuous and ensures
that post resume, it starts from where it left off during suspend.
Override x86_platform.save_sched_clock_state and
x86_platform.restore_sched_clock_state routines to correct this as soon
as possible.

Note: if Invariant TSC is available, the issue doesn't happen because
1) we don't register read_hv_sched_clock_tsc() for sched clock:
See commit e5313f1c5404 ("clocksource/drivers/hyper-v: Rework
clocksource and sched clock setup");
2) the common x86 code adjusts TSC similarly: see
__restore_processor_state() ->  tsc_verify_tsc_adjust(true) and
x86_platform.restore_sched_clock_state().

Cc: stable@vger.kernel.org
Fixes: 1349401ff1 ("clocksource/drivers/hyper-v: Suspend/resume Hyper-V clocksource for hibernation")
Co-developed-by: Dexuan Cui <decui@microsoft.com>
Signed-off-by: Dexuan Cui <decui@microsoft.com>
Signed-off-by: Naman Jain <namjain@linux.microsoft.com>
Reviewed-by: Michael Kelley <mhklinux@outlook.com>
Link: https://lore.kernel.org/r/20240917053917.76787-1-namjain@linux.microsoft.com
Signed-off-by: Wei Liu <wei.liu@kernel.org>
Message-ID: <20240917053917.76787-1-namjain@linux.microsoft.com>
Signed-off-by: Naman Jain <namjain@linux.microsoft.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

arch/x86/kernel/cpu/mshyperv.c

@@ -152,6 +152,63 @@ static void hv_machine_crash_shutdown(struct pt_regs *regs)
 	hyperv_cleanup();
 }
 #endif /* CONFIG_KEXEC_CORE */
+
+static u64 hv_ref_counter_at_suspend;
+static void (*old_save_sched_clock_state)(void);
+static void (*old_restore_sched_clock_state)(void);
+
+/*
+ * Hyper-V clock counter resets during hibernation. Save and restore clock
+ * offset during suspend/resume, while also considering the time passed
+ * before suspend. This is to make sure that sched_clock using hv tsc page
+ * based clocksource, proceeds from where it left off during suspend and
+ * it shows correct time for the timestamps of kernel messages after resume.
+ */
+static void save_hv_clock_tsc_state(void)
+{
+	hv_ref_counter_at_suspend = hv_read_reference_counter();
+}
+
+static void restore_hv_clock_tsc_state(void)
+{
+	/*
+	 * Adjust the offsets used by hv tsc clocksource to
+	 * account for the time spent before hibernation.
+	 * adjusted value = reference counter (time) at suspend
+	 *                - reference counter (time) now.
+	 */
+	hv_adj_sched_clock_offset(hv_ref_counter_at_suspend - hv_read_reference_counter());
+}
+
+/*
+ * Functions to override save_sched_clock_state and restore_sched_clock_state
+ * functions of x86_platform. The Hyper-V clock counter is reset during
+ * suspend-resume and the offset used to measure time needs to be
+ * corrected, post resume.
+ */
+static void hv_save_sched_clock_state(void)
+{
+	old_save_sched_clock_state();
+	save_hv_clock_tsc_state();
+}
+
+static void hv_restore_sched_clock_state(void)
+{
+	restore_hv_clock_tsc_state();
+	old_restore_sched_clock_state();
+}
+
+static void __init x86_setup_ops_for_tsc_pg_clock(void)
+{
+	if (!(ms_hyperv.features & HV_MSR_REFERENCE_TSC_AVAILABLE))
+		return;
+
+	old_save_sched_clock_state = x86_platform.save_sched_clock_state;
+	x86_platform.save_sched_clock_state = hv_save_sched_clock_state;
+
+	old_restore_sched_clock_state = x86_platform.restore_sched_clock_state;
+	x86_platform.restore_sched_clock_state = hv_restore_sched_clock_state;
+}
 #endif /* CONFIG_HYPERV */
 
 static uint32_t  __init ms_hyperv_platform(void)
@@ -454,6 +511,7 @@ static void __init ms_hyperv_init_platform(void)
 
 	/* Register Hyper-V specific clocksource */
 	hv_init_clocksource();
+	x86_setup_ops_for_tsc_pg_clock();
 #endif
 	/*
 	 * TSC should be marked as unstable only after Hyper-V

drivers/clocksource/hyperv_timer.c

@@ -27,7 +27,8 @@
 #include <asm/mshyperv.h>
 
 static struct clock_event_device __percpu *hv_clock_event;
-static u64 hv_sched_clock_offset __ro_after_init;
+/* Note: offset can hold negative values after hibernation. */
+static u64 hv_sched_clock_offset __read_mostly;
 
 /*
  * If false, we're using the old mechanism for stimer0 interrupts
@@ -417,6 +418,17 @@ static void resume_hv_clock_tsc(struct clocksource *arg)
 	hv_set_register(HV_REGISTER_REFERENCE_TSC, tsc_msr.as_uint64);
 }
 
+/*
+ * Called during resume from hibernation, from overridden
+ * x86_platform.restore_sched_clock_state routine. This is to adjust offsets
+ * used to calculate time for hv tsc page based sched_clock, to account for
+ * time spent before hibernation.
+ */
+void hv_adj_sched_clock_offset(u64 offset)
+{
+	hv_sched_clock_offset -= offset;
+}
+
 #ifdef HAVE_VDSO_CLOCKMODE_HVCLOCK
 static int hv_cs_enable(struct clocksource *cs)
 {

include/clocksource/hyperv_timer.h

@@ -34,6 +34,8 @@ extern void hv_init_clocksource(void);
 
 extern struct ms_hyperv_tsc_page *hv_get_tsc_page(void);
 
+extern void hv_adj_sched_clock_offset(u64 offset);
+
 static inline notrace u64
 hv_read_tsc_page_tsc(const struct ms_hyperv_tsc_page *tsc_pg, u64 *cur_tsc)
 {