From 3eca993740b8eb40f514b90b1877a4dbcf0a6710 Mon Sep 17 00:00:00 2001 From: Pavel Tatashin Date: Thu, 19 Jul 2018 16:55:34 -0400 Subject: 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 Signed-off-by: Thomas Gleixner 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 --- include/linux/timekeeping.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') 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); /* -- cgit v1.2.3 From 5d2a4e91a541cb04d20d11602f0f9340291322ac Mon Sep 17 00:00:00 2001 From: Pavel Tatashin Date: Thu, 19 Jul 2018 16:55:41 -0400 Subject: sched/clock: Move sched clock initialization and merge with generic clock sched_clock_postinit() initializes a generic clock on systems where no other clock is provided. This function may be called only after timekeeping_init(). Rename sched_clock_postinit to generic_clock_inti() and call it from sched_clock_init(). Move the call for sched_clock_init() until after time_init(). Suggested-by: Peter Zijlstra Signed-off-by: Pavel Tatashin Signed-off-by: Thomas Gleixner 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: 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/20180719205545.16512-23-pasha.tatashin@oracle.com --- include/linux/sched_clock.h | 5 ++--- init/main.c | 4 ++-- kernel/sched/clock.c | 27 +++++++++++++++++---------- kernel/sched/core.c | 1 - kernel/time/sched_clock.c | 2 +- 5 files changed, 22 insertions(+), 17 deletions(-) (limited to 'include') diff --git a/include/linux/sched_clock.h b/include/linux/sched_clock.h index 411b52e424e1..abe28d5cb3f4 100644 --- a/include/linux/sched_clock.h +++ b/include/linux/sched_clock.h @@ -9,17 +9,16 @@ #define LINUX_SCHED_CLOCK #ifdef CONFIG_GENERIC_SCHED_CLOCK -extern void sched_clock_postinit(void); +extern void generic_sched_clock_init(void); extern void sched_clock_register(u64 (*read)(void), int bits, unsigned long rate); #else -static inline void sched_clock_postinit(void) { } +static inline void generic_sched_clock_init(void) { } static inline void sched_clock_register(u64 (*read)(void), int bits, unsigned long rate) { - ; } #endif diff --git a/init/main.c b/init/main.c index 3b4ada11ed52..162d931c9511 100644 --- a/init/main.c +++ b/init/main.c @@ -79,7 +79,7 @@ #include #include #include -#include +#include #include #include #include @@ -642,7 +642,7 @@ asmlinkage __visible void __init start_kernel(void) softirq_init(); timekeeping_init(); time_init(); - sched_clock_postinit(); + sched_clock_init(); printk_safe_init(); perf_event_init(); profile_init(); diff --git a/kernel/sched/clock.c b/kernel/sched/clock.c index 10c83e73837a..0e9dbb2d9aea 100644 --- a/kernel/sched/clock.c +++ b/kernel/sched/clock.c @@ -53,6 +53,7 @@ * */ #include "sched.h" +#include /* * Scheduler clock - returns current time in nanosec units. @@ -68,11 +69,6 @@ EXPORT_SYMBOL_GPL(sched_clock); __read_mostly int sched_clock_running; -void sched_clock_init(void) -{ - sched_clock_running = 1; -} - #ifdef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK /* * We must start with !__sched_clock_stable because the unstable -> stable @@ -199,6 +195,15 @@ void clear_sched_clock_stable(void) __clear_sched_clock_stable(); } +static void __sched_clock_gtod_offset(void) +{ + __gtod_offset = (sched_clock() + __sched_clock_offset) - ktime_get_ns(); +} + +void __init sched_clock_init(void) +{ + sched_clock_running = 1; +} /* * We run this as late_initcall() such that it runs after all built-in drivers, * notably: acpi_processor and intel_idle, which can mark the TSC as unstable. @@ -385,8 +390,6 @@ void sched_clock_tick(void) void sched_clock_tick_stable(void) { - u64 gtod, clock; - if (!sched_clock_stable()) return; @@ -398,9 +401,7 @@ void sched_clock_tick_stable(void) * TSC to be unstable, any computation will be computing crap. */ local_irq_disable(); - gtod = ktime_get_ns(); - clock = sched_clock(); - __gtod_offset = (clock + __sched_clock_offset) - gtod; + __sched_clock_gtod_offset(); local_irq_enable(); } @@ -434,6 +435,12 @@ EXPORT_SYMBOL_GPL(sched_clock_idle_wakeup_event); #else /* CONFIG_HAVE_UNSTABLE_SCHED_CLOCK */ +void __init sched_clock_init(void) +{ + sched_clock_running = 1; + generic_sched_clock_init(); +} + u64 sched_clock_cpu(int cpu) { if (unlikely(!sched_clock_running)) diff --git a/kernel/sched/core.c b/kernel/sched/core.c index fe365c9a08e9..552406e9713b 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -5954,7 +5954,6 @@ void __init sched_init(void) int i, j; unsigned long alloc_size = 0, ptr; - sched_clock_init(); wait_bit_init(); #ifdef CONFIG_FAIR_GROUP_SCHED diff --git a/kernel/time/sched_clock.c b/kernel/time/sched_clock.c index 2d8f05aad442..cbc72c2c1fca 100644 --- a/kernel/time/sched_clock.c +++ b/kernel/time/sched_clock.c @@ -237,7 +237,7 @@ sched_clock_register(u64 (*read)(void), int bits, unsigned long rate) pr_debug("Registered %pF as sched_clock source\n", read); } -void __init sched_clock_postinit(void) +void __init generic_sched_clock_init(void) { /* * If no sched_clock() function has been provided at that point, -- cgit v1.2.3