[tip:x86/timers] timekeeping: Replace read_boot_clock64() with read_persistent_wall_and_boot_offset()

From: tip-bot for Pavel Tatashin
Date: Thu Jul 19 2018 - 18:29:25 EST


Commit-ID: 3eca993740b8eb40f514b90b1877a4dbcf0a6710
Gitweb: https://git.kernel.org/tip/3eca993740b8eb40f514b90b1877a4dbcf0a6710
Author: Pavel Tatashin <pasha.tatashin@xxxxxxxxxx>
AuthorDate: Thu, 19 Jul 2018 16:55:34 -0400
Committer: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
CommitDate: Fri, 20 Jul 2018 00:02:40 +0200

timekeeping: Replace read_boot_clock64() with read_persistent_wall_and_boot_offset()

If architecture does not support exact boot time, it is challenging to
estimate boot time without having a reference to the current persistent
clock value. Yet, it cannot read the persistent clock time again, because
this may lead to math discrepancies with the caller of read_boot_clock64()
who have read the persistent clock at a different time.

This is why it is better to provide two values simultaneously: the
persistent clock value, and the boot time.

Replace read_boot_clock64() with:
read_persistent_wall_and_boot_offset(wall_time, boot_offset)

Where wall_time is returned by read_persistent_clock() And boot_offset is
wall_time - boot time, which defaults to 0.

Signed-off-by: Pavel Tatashin <pasha.tatashin@xxxxxxxxxx>
Signed-off-by: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Cc: steven.sistare@xxxxxxxxxx
Cc: daniel.m.jordan@xxxxxxxxxx
Cc: linux@xxxxxxxxxxxxxxx
Cc: schwidefsky@xxxxxxxxxx
Cc: heiko.carstens@xxxxxxxxxx
Cc: john.stultz@xxxxxxxxxx
Cc: sboyd@xxxxxxxxxxxxxx
Cc: hpa@xxxxxxxxx
Cc: douly.fnst@xxxxxxxxxxxxxx
Cc: peterz@xxxxxxxxxxxxx
Cc: prarit@xxxxxxxxxx
Cc: feng.tang@xxxxxxxxx
Cc: pmladek@xxxxxxxx
Cc: gnomes@xxxxxxxxxxxxxxxxxxx
Cc: linux-s390@xxxxxxxxxxxxxxx
Cc: boris.ostrovsky@xxxxxxxxxx
Cc: jgross@xxxxxxxx
Cc: pbonzini@xxxxxxxxxx
Link: https://lkml.kernel.org/r/20180719205545.16512-16-pasha.tatashin@xxxxxxxxxx

---
include/linux/timekeeping.h | 3 ++-
kernel/time/timekeeping.c | 59 +++++++++++++++++++++++----------------------
2 files changed, 32 insertions(+), 30 deletions(-)

diff --git a/include/linux/timekeeping.h b/include/linux/timekeeping.h
index 86bc2026efce..686bc27acef0 100644
--- a/include/linux/timekeeping.h
+++ b/include/linux/timekeeping.h
@@ -243,7 +243,8 @@ extern void ktime_get_snapshot(struct system_time_snapshot *systime_snapshot);
extern int persistent_clock_is_local;

extern void read_persistent_clock64(struct timespec64 *ts);
-extern void read_boot_clock64(struct timespec64 *ts);
+void read_persistent_clock_and_boot_offset(struct timespec64 *wall_clock,
+ struct timespec64 *boot_offset);
extern int update_persistent_clock64(struct timespec64 now);

/*
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index 4786df904c22..cb738f825c12 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -17,6 +17,7 @@
#include <linux/nmi.h>
#include <linux/sched.h>
#include <linux/sched/loadavg.h>
+#include <linux/sched/clock.h>
#include <linux/syscore_ops.h>
#include <linux/clocksource.h>
#include <linux/jiffies.h>
@@ -1496,18 +1497,20 @@ void __weak read_persistent_clock64(struct timespec64 *ts64)
}

/**
- * read_boot_clock64 - Return time of the system start.
+ * read_persistent_wall_and_boot_offset - Read persistent clock, and also offset
+ * from the boot.
*
* Weak dummy function for arches that do not yet support it.
- * Function to read the exact time the system has been started.
- * Returns a timespec64 with tv_sec=0 and tv_nsec=0 if unsupported.
- *
- * XXX - Do be sure to remove it once all arches implement it.
+ * wall_time - current time as returned by persistent clock
+ * boot_offset - offset that is defined as wall_time - boot_time
+ * default to 0.
*/
-void __weak read_boot_clock64(struct timespec64 *ts)
+void __weak __init
+read_persistent_wall_and_boot_offset(struct timespec64 *wall_time,
+ struct timespec64 *boot_offset)
{
- ts->tv_sec = 0;
- ts->tv_nsec = 0;
+ read_persistent_clock64(wall_time);
+ *boot_offset = (struct timespec64){0};
}

/* Flag for if timekeeping_resume() has injected sleeptime */
@@ -1521,28 +1524,29 @@ static bool persistent_clock_exists;
*/
void __init timekeeping_init(void)
{
+ struct timespec64 wall_time, boot_offset, wall_to_mono;
struct timekeeper *tk = &tk_core.timekeeper;
struct clocksource *clock;
unsigned long flags;
- struct timespec64 now, boot, tmp;
-
- read_persistent_clock64(&now);
- if (!timespec64_valid_strict(&now)) {
- pr_warn("WARNING: Persistent clock returned invalid value!\n"
- " Check your CMOS/BIOS settings.\n");
- now.tv_sec = 0;
- now.tv_nsec = 0;
- } else if (now.tv_sec || now.tv_nsec)
- persistent_clock_exists = true;

- read_boot_clock64(&boot);
- if (!timespec64_valid_strict(&boot)) {
- pr_warn("WARNING: Boot clock returned invalid value!\n"
- " Check your CMOS/BIOS settings.\n");
- boot.tv_sec = 0;
- boot.tv_nsec = 0;
+ read_persistent_wall_and_boot_offset(&wall_time, &boot_offset);
+ if (timespec64_valid_strict(&wall_time) &&
+ timespec64_to_ns(&wall_time) > 0) {
+ persistent_clock_exists = true;
+ } else {
+ pr_warn("Persistent clock returned invalid value");
+ wall_time = (struct timespec64){0};
}

+ if (timespec64_compare(&wall_time, &boot_offset) < 0)
+ boot_offset = (struct timespec64){0};
+
+ /*
+ * We want set wall_to_mono, so the following is true:
+ * wall time + wall_to_mono = boot time
+ */
+ wall_to_mono = timespec64_sub(boot_offset, wall_time);
+
raw_spin_lock_irqsave(&timekeeper_lock, flags);
write_seqcount_begin(&tk_core.seq);
ntp_init();
@@ -1552,13 +1556,10 @@ void __init timekeeping_init(void)
clock->enable(clock);
tk_setup_internals(tk, clock);

- tk_set_xtime(tk, &now);
+ tk_set_xtime(tk, &wall_time);
tk->raw_sec = 0;
- if (boot.tv_sec == 0 && boot.tv_nsec == 0)
- boot = tk_xtime(tk);

- set_normalized_timespec64(&tmp, -boot.tv_sec, -boot.tv_nsec);
- tk_set_wall_to_mono(tk, tmp);
+ tk_set_wall_to_mono(tk, wall_to_mono);

timekeeping_update(tk, TK_MIRROR | TK_CLOCK_WAS_SET);