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@oracle.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: steven.sistare@oracle.com
Cc: daniel.m.jordan@oracle.com
Cc: linux@armlinux.org.uk
Cc: schwidefsky@de.ibm.com
Cc: heiko.carstens@de.ibm.com
Cc: john.stultz@linaro.org
Cc: sboyd@codeaurora.org
Cc: hpa@zytor.com
Cc: douly.fnst@cn.fujitsu.com
Cc: peterz@infradead.org
Cc: prarit@redhat.com
Cc: feng.tang@intel.com
Cc: pmladek@suse.com
Cc: gnomes@lxorguk.ukuu.org.uk
Cc: linux-s390@vger.kernel.org
Cc: boris.ostrovsky@oracle.com
Cc: jgross@suse.com
Cc: pbonzini@redhat.com
Link: https://lkml.kernel.org/r/20180719205545.16512-16-pasha.tatashin@oracle.com

diff --git a/include/linux/timekeeping.h b/include/linux/timekeeping.h
index 86bc2026efcea4fd9af338eb19cb63bcea3a9547..686bc27acef0621f0c47731896e1b59281c028de 100644 (file)
--- 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 4786df904c22d0a8e9473e600efee97244eb5782..cb738f825c12b2c889b6bb8f4e35945c9c8521d8 100644 (file)
--- 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);