5d2a4e91a5
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 <peterz@infradead.org> 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: 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
309 lines
8.3 KiB
C
309 lines
8.3 KiB
C
/*
|
|
* sched_clock.c: Generic sched_clock() support, to extend low level
|
|
* hardware time counters to full 64-bit ns values.
|
|
*
|
|
* This program is free software; you can redistribute it and/or modify
|
|
* it under the terms of the GNU General Public License version 2 as
|
|
* published by the Free Software Foundation.
|
|
*/
|
|
#include <linux/clocksource.h>
|
|
#include <linux/init.h>
|
|
#include <linux/jiffies.h>
|
|
#include <linux/ktime.h>
|
|
#include <linux/kernel.h>
|
|
#include <linux/moduleparam.h>
|
|
#include <linux/sched.h>
|
|
#include <linux/sched/clock.h>
|
|
#include <linux/syscore_ops.h>
|
|
#include <linux/hrtimer.h>
|
|
#include <linux/sched_clock.h>
|
|
#include <linux/seqlock.h>
|
|
#include <linux/bitops.h>
|
|
|
|
/**
|
|
* struct clock_read_data - data required to read from sched_clock()
|
|
*
|
|
* @epoch_ns: sched_clock() value at last update
|
|
* @epoch_cyc: Clock cycle value at last update.
|
|
* @sched_clock_mask: Bitmask for two's complement subtraction of non 64bit
|
|
* clocks.
|
|
* @read_sched_clock: Current clock source (or dummy source when suspended).
|
|
* @mult: Multipler for scaled math conversion.
|
|
* @shift: Shift value for scaled math conversion.
|
|
*
|
|
* Care must be taken when updating this structure; it is read by
|
|
* some very hot code paths. It occupies <=40 bytes and, when combined
|
|
* with the seqcount used to synchronize access, comfortably fits into
|
|
* a 64 byte cache line.
|
|
*/
|
|
struct clock_read_data {
|
|
u64 epoch_ns;
|
|
u64 epoch_cyc;
|
|
u64 sched_clock_mask;
|
|
u64 (*read_sched_clock)(void);
|
|
u32 mult;
|
|
u32 shift;
|
|
};
|
|
|
|
/**
|
|
* struct clock_data - all data needed for sched_clock() (including
|
|
* registration of a new clock source)
|
|
*
|
|
* @seq: Sequence counter for protecting updates. The lowest
|
|
* bit is the index for @read_data.
|
|
* @read_data: Data required to read from sched_clock.
|
|
* @wrap_kt: Duration for which clock can run before wrapping.
|
|
* @rate: Tick rate of the registered clock.
|
|
* @actual_read_sched_clock: Registered hardware level clock read function.
|
|
*
|
|
* The ordering of this structure has been chosen to optimize cache
|
|
* performance. In particular 'seq' and 'read_data[0]' (combined) should fit
|
|
* into a single 64-byte cache line.
|
|
*/
|
|
struct clock_data {
|
|
seqcount_t seq;
|
|
struct clock_read_data read_data[2];
|
|
ktime_t wrap_kt;
|
|
unsigned long rate;
|
|
|
|
u64 (*actual_read_sched_clock)(void);
|
|
};
|
|
|
|
static struct hrtimer sched_clock_timer;
|
|
static int irqtime = -1;
|
|
|
|
core_param(irqtime, irqtime, int, 0400);
|
|
|
|
static u64 notrace jiffy_sched_clock_read(void)
|
|
{
|
|
/*
|
|
* We don't need to use get_jiffies_64 on 32-bit arches here
|
|
* because we register with BITS_PER_LONG
|
|
*/
|
|
return (u64)(jiffies - INITIAL_JIFFIES);
|
|
}
|
|
|
|
static struct clock_data cd ____cacheline_aligned = {
|
|
.read_data[0] = { .mult = NSEC_PER_SEC / HZ,
|
|
.read_sched_clock = jiffy_sched_clock_read, },
|
|
.actual_read_sched_clock = jiffy_sched_clock_read,
|
|
};
|
|
|
|
static inline u64 notrace cyc_to_ns(u64 cyc, u32 mult, u32 shift)
|
|
{
|
|
return (cyc * mult) >> shift;
|
|
}
|
|
|
|
unsigned long long notrace sched_clock(void)
|
|
{
|
|
u64 cyc, res;
|
|
unsigned long seq;
|
|
struct clock_read_data *rd;
|
|
|
|
do {
|
|
seq = raw_read_seqcount(&cd.seq);
|
|
rd = cd.read_data + (seq & 1);
|
|
|
|
cyc = (rd->read_sched_clock() - rd->epoch_cyc) &
|
|
rd->sched_clock_mask;
|
|
res = rd->epoch_ns + cyc_to_ns(cyc, rd->mult, rd->shift);
|
|
} while (read_seqcount_retry(&cd.seq, seq));
|
|
|
|
return res;
|
|
}
|
|
|
|
/*
|
|
* Updating the data required to read the clock.
|
|
*
|
|
* sched_clock() will never observe mis-matched data even if called from
|
|
* an NMI. We do this by maintaining an odd/even copy of the data and
|
|
* steering sched_clock() to one or the other using a sequence counter.
|
|
* In order to preserve the data cache profile of sched_clock() as much
|
|
* as possible the system reverts back to the even copy when the update
|
|
* completes; the odd copy is used *only* during an update.
|
|
*/
|
|
static void update_clock_read_data(struct clock_read_data *rd)
|
|
{
|
|
/* update the backup (odd) copy with the new data */
|
|
cd.read_data[1] = *rd;
|
|
|
|
/* steer readers towards the odd copy */
|
|
raw_write_seqcount_latch(&cd.seq);
|
|
|
|
/* now its safe for us to update the normal (even) copy */
|
|
cd.read_data[0] = *rd;
|
|
|
|
/* switch readers back to the even copy */
|
|
raw_write_seqcount_latch(&cd.seq);
|
|
}
|
|
|
|
/*
|
|
* Atomically update the sched_clock() epoch.
|
|
*/
|
|
static void update_sched_clock(void)
|
|
{
|
|
u64 cyc;
|
|
u64 ns;
|
|
struct clock_read_data rd;
|
|
|
|
rd = cd.read_data[0];
|
|
|
|
cyc = cd.actual_read_sched_clock();
|
|
ns = rd.epoch_ns + cyc_to_ns((cyc - rd.epoch_cyc) & rd.sched_clock_mask, rd.mult, rd.shift);
|
|
|
|
rd.epoch_ns = ns;
|
|
rd.epoch_cyc = cyc;
|
|
|
|
update_clock_read_data(&rd);
|
|
}
|
|
|
|
static enum hrtimer_restart sched_clock_poll(struct hrtimer *hrt)
|
|
{
|
|
update_sched_clock();
|
|
hrtimer_forward_now(hrt, cd.wrap_kt);
|
|
|
|
return HRTIMER_RESTART;
|
|
}
|
|
|
|
void __init
|
|
sched_clock_register(u64 (*read)(void), int bits, unsigned long rate)
|
|
{
|
|
u64 res, wrap, new_mask, new_epoch, cyc, ns;
|
|
u32 new_mult, new_shift;
|
|
unsigned long r;
|
|
char r_unit;
|
|
struct clock_read_data rd;
|
|
|
|
if (cd.rate > rate)
|
|
return;
|
|
|
|
WARN_ON(!irqs_disabled());
|
|
|
|
/* Calculate the mult/shift to convert counter ticks to ns. */
|
|
clocks_calc_mult_shift(&new_mult, &new_shift, rate, NSEC_PER_SEC, 3600);
|
|
|
|
new_mask = CLOCKSOURCE_MASK(bits);
|
|
cd.rate = rate;
|
|
|
|
/* Calculate how many nanosecs until we risk wrapping */
|
|
wrap = clocks_calc_max_nsecs(new_mult, new_shift, 0, new_mask, NULL);
|
|
cd.wrap_kt = ns_to_ktime(wrap);
|
|
|
|
rd = cd.read_data[0];
|
|
|
|
/* Update epoch for new counter and update 'epoch_ns' from old counter*/
|
|
new_epoch = read();
|
|
cyc = cd.actual_read_sched_clock();
|
|
ns = rd.epoch_ns + cyc_to_ns((cyc - rd.epoch_cyc) & rd.sched_clock_mask, rd.mult, rd.shift);
|
|
cd.actual_read_sched_clock = read;
|
|
|
|
rd.read_sched_clock = read;
|
|
rd.sched_clock_mask = new_mask;
|
|
rd.mult = new_mult;
|
|
rd.shift = new_shift;
|
|
rd.epoch_cyc = new_epoch;
|
|
rd.epoch_ns = ns;
|
|
|
|
update_clock_read_data(&rd);
|
|
|
|
if (sched_clock_timer.function != NULL) {
|
|
/* update timeout for clock wrap */
|
|
hrtimer_start(&sched_clock_timer, cd.wrap_kt, HRTIMER_MODE_REL);
|
|
}
|
|
|
|
r = rate;
|
|
if (r >= 4000000) {
|
|
r /= 1000000;
|
|
r_unit = 'M';
|
|
} else {
|
|
if (r >= 1000) {
|
|
r /= 1000;
|
|
r_unit = 'k';
|
|
} else {
|
|
r_unit = ' ';
|
|
}
|
|
}
|
|
|
|
/* Calculate the ns resolution of this counter */
|
|
res = cyc_to_ns(1ULL, new_mult, new_shift);
|
|
|
|
pr_info("sched_clock: %u bits at %lu%cHz, resolution %lluns, wraps every %lluns\n",
|
|
bits, r, r_unit, res, wrap);
|
|
|
|
/* Enable IRQ time accounting if we have a fast enough sched_clock() */
|
|
if (irqtime > 0 || (irqtime == -1 && rate >= 1000000))
|
|
enable_sched_clock_irqtime();
|
|
|
|
pr_debug("Registered %pF as sched_clock source\n", read);
|
|
}
|
|
|
|
void __init generic_sched_clock_init(void)
|
|
{
|
|
/*
|
|
* If no sched_clock() function has been provided at that point,
|
|
* make it the final one one.
|
|
*/
|
|
if (cd.actual_read_sched_clock == jiffy_sched_clock_read)
|
|
sched_clock_register(jiffy_sched_clock_read, BITS_PER_LONG, HZ);
|
|
|
|
update_sched_clock();
|
|
|
|
/*
|
|
* Start the timer to keep sched_clock() properly updated and
|
|
* sets the initial epoch.
|
|
*/
|
|
hrtimer_init(&sched_clock_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
|
|
sched_clock_timer.function = sched_clock_poll;
|
|
hrtimer_start(&sched_clock_timer, cd.wrap_kt, HRTIMER_MODE_REL);
|
|
}
|
|
|
|
/*
|
|
* Clock read function for use when the clock is suspended.
|
|
*
|
|
* This function makes it appear to sched_clock() as if the clock
|
|
* stopped counting at its last update.
|
|
*
|
|
* This function must only be called from the critical
|
|
* section in sched_clock(). It relies on the read_seqcount_retry()
|
|
* at the end of the critical section to be sure we observe the
|
|
* correct copy of 'epoch_cyc'.
|
|
*/
|
|
static u64 notrace suspended_sched_clock_read(void)
|
|
{
|
|
unsigned long seq = raw_read_seqcount(&cd.seq);
|
|
|
|
return cd.read_data[seq & 1].epoch_cyc;
|
|
}
|
|
|
|
static int sched_clock_suspend(void)
|
|
{
|
|
struct clock_read_data *rd = &cd.read_data[0];
|
|
|
|
update_sched_clock();
|
|
hrtimer_cancel(&sched_clock_timer);
|
|
rd->read_sched_clock = suspended_sched_clock_read;
|
|
|
|
return 0;
|
|
}
|
|
|
|
static void sched_clock_resume(void)
|
|
{
|
|
struct clock_read_data *rd = &cd.read_data[0];
|
|
|
|
rd->epoch_cyc = cd.actual_read_sched_clock();
|
|
hrtimer_start(&sched_clock_timer, cd.wrap_kt, HRTIMER_MODE_REL);
|
|
rd->read_sched_clock = cd.actual_read_sched_clock;
|
|
}
|
|
|
|
static struct syscore_ops sched_clock_ops = {
|
|
.suspend = sched_clock_suspend,
|
|
.resume = sched_clock_resume,
|
|
};
|
|
|
|
static int __init sched_clock_syscore_init(void)
|
|
{
|
|
register_syscore_ops(&sched_clock_ops);
|
|
|
|
return 0;
|
|
}
|
|
device_initcall(sched_clock_syscore_init);
|