2010-05-29 11:09:12 +08:00
|
|
|
/*
|
|
|
|
* Copyright 2010 Tilera Corporation. All Rights Reserved.
|
|
|
|
*
|
|
|
|
* This program is free software; you can redistribute it and/or
|
|
|
|
* modify it under the terms of the GNU General Public License
|
|
|
|
* as published by the Free Software Foundation, version 2.
|
|
|
|
*
|
|
|
|
* This program is distributed in the hope that it will be useful, but
|
|
|
|
* WITHOUT ANY WARRANTY; without even the implied warranty of
|
|
|
|
* MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
|
|
|
|
* NON INFRINGEMENT. See the GNU General Public License for
|
|
|
|
* more details.
|
|
|
|
*
|
|
|
|
* Support the cycle counter clocksource and tile timer clock event device.
|
|
|
|
*/
|
|
|
|
|
|
|
|
#include <linux/time.h>
|
|
|
|
#include <linux/timex.h>
|
|
|
|
#include <linux/clocksource.h>
|
|
|
|
#include <linux/clockchips.h>
|
|
|
|
#include <linux/hardirq.h>
|
|
|
|
#include <linux/sched.h>
|
|
|
|
#include <linux/smp.h>
|
|
|
|
#include <linux/delay.h>
|
arch/tile: various header improvements for building drivers
This change adds a number of missing headers in asm (fb.h, parport.h,
serial.h, and vga.h) using the minimal generic versions.
It also adds a number of missing interfaces that showed up as build
failures when trying to build various drivers not normally included in the
"tile" distribution: ioremap_wc(), memset_io(), io{read,write}{16,32}be(),
virt_to_bus(), bus_to_virt(), irq_canonicalize(), __pte(), __pgd(),
and __pmd(). I also added a cast in virt_to_page() since not all callers
pass a pointer.
I fixed <asm/stat.h> to properly include a __KERNEL__ guard for the
__ARCH_WANT_STAT64 symbol, and <asm/swab.h> to use __builtin_bswap32()
even for our 64-bit architecture, since the same code is produced.
I added an export for get_cycles(), since it's used in some modules.
And I made <arch/spr_def.h> properly include the __KERNEL__ guard,
even though it's not yet exported, since it likely will be soon.
Signed-off-by: Chris Metcalf <cmetcalf@tilera.com>
2011-05-03 04:06:42 +08:00
|
|
|
#include <linux/module.h>
|
2010-05-29 11:09:12 +08:00
|
|
|
#include <asm/irq_regs.h>
|
2010-06-26 05:04:17 +08:00
|
|
|
#include <asm/traps.h>
|
2010-05-29 11:09:12 +08:00
|
|
|
#include <hv/hypervisor.h>
|
|
|
|
#include <arch/interrupts.h>
|
|
|
|
#include <arch/spr_def.h>
|
|
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Define the cycle counter clock source.
|
|
|
|
*/
|
|
|
|
|
|
|
|
/* How many cycles per second we are running at. */
|
|
|
|
static cycles_t cycles_per_sec __write_once;
|
|
|
|
|
2010-06-26 05:04:17 +08:00
|
|
|
cycles_t get_clock_rate(void)
|
2010-05-29 11:09:12 +08:00
|
|
|
{
|
|
|
|
return cycles_per_sec;
|
|
|
|
}
|
|
|
|
|
|
|
|
#if CHIP_HAS_SPLIT_CYCLE()
|
2010-06-26 05:04:17 +08:00
|
|
|
cycles_t get_cycles(void)
|
2010-05-29 11:09:12 +08:00
|
|
|
{
|
|
|
|
unsigned int high = __insn_mfspr(SPR_CYCLE_HIGH);
|
|
|
|
unsigned int low = __insn_mfspr(SPR_CYCLE_LOW);
|
|
|
|
unsigned int high2 = __insn_mfspr(SPR_CYCLE_HIGH);
|
|
|
|
|
|
|
|
while (unlikely(high != high2)) {
|
|
|
|
low = __insn_mfspr(SPR_CYCLE_LOW);
|
|
|
|
high = high2;
|
|
|
|
high2 = __insn_mfspr(SPR_CYCLE_HIGH);
|
|
|
|
}
|
|
|
|
|
|
|
|
return (((cycles_t)high) << 32) | low;
|
|
|
|
}
|
arch/tile: various header improvements for building drivers
This change adds a number of missing headers in asm (fb.h, parport.h,
serial.h, and vga.h) using the minimal generic versions.
It also adds a number of missing interfaces that showed up as build
failures when trying to build various drivers not normally included in the
"tile" distribution: ioremap_wc(), memset_io(), io{read,write}{16,32}be(),
virt_to_bus(), bus_to_virt(), irq_canonicalize(), __pte(), __pgd(),
and __pmd(). I also added a cast in virt_to_page() since not all callers
pass a pointer.
I fixed <asm/stat.h> to properly include a __KERNEL__ guard for the
__ARCH_WANT_STAT64 symbol, and <asm/swab.h> to use __builtin_bswap32()
even for our 64-bit architecture, since the same code is produced.
I added an export for get_cycles(), since it's used in some modules.
And I made <arch/spr_def.h> properly include the __KERNEL__ guard,
even though it's not yet exported, since it likely will be soon.
Signed-off-by: Chris Metcalf <cmetcalf@tilera.com>
2011-05-03 04:06:42 +08:00
|
|
|
EXPORT_SYMBOL(get_cycles);
|
2010-05-29 11:09:12 +08:00
|
|
|
#endif
|
|
|
|
|
2010-08-13 20:24:22 +08:00
|
|
|
/*
|
|
|
|
* We use a relatively small shift value so that sched_clock()
|
|
|
|
* won't wrap around very often.
|
|
|
|
*/
|
|
|
|
#define SCHED_CLOCK_SHIFT 10
|
|
|
|
|
|
|
|
static unsigned long sched_clock_mult __write_once;
|
|
|
|
|
2010-06-26 05:04:17 +08:00
|
|
|
static cycles_t clocksource_get_cycles(struct clocksource *cs)
|
2010-05-29 11:09:12 +08:00
|
|
|
{
|
|
|
|
return get_cycles();
|
|
|
|
}
|
|
|
|
|
|
|
|
static struct clocksource cycle_counter_cs = {
|
|
|
|
.name = "cycle counter",
|
|
|
|
.rating = 300,
|
|
|
|
.read = clocksource_get_cycles,
|
|
|
|
.mask = CLOCKSOURCE_MASK(64),
|
|
|
|
.flags = CLOCK_SOURCE_IS_CONTINUOUS,
|
|
|
|
};
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Called very early from setup_arch() to set cycles_per_sec.
|
|
|
|
* We initialize it early so we can use it to set up loops_per_jiffy.
|
|
|
|
*/
|
|
|
|
void __init setup_clock(void)
|
|
|
|
{
|
|
|
|
cycles_per_sec = hv_sysconf(HV_SYSCONF_CPU_SPEED);
|
2010-08-13 20:24:22 +08:00
|
|
|
sched_clock_mult =
|
|
|
|
clocksource_hz2mult(cycles_per_sec, SCHED_CLOCK_SHIFT);
|
2010-05-29 11:09:12 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
void __init calibrate_delay(void)
|
|
|
|
{
|
|
|
|
loops_per_jiffy = get_clock_rate() / HZ;
|
|
|
|
pr_info("Clock rate yields %lu.%02lu BogoMIPS (lpj=%lu)\n",
|
|
|
|
loops_per_jiffy/(500000/HZ),
|
|
|
|
(loops_per_jiffy/(5000/HZ)) % 100, loops_per_jiffy);
|
|
|
|
}
|
|
|
|
|
|
|
|
/* Called fairly late in init/main.c, but before we go smp. */
|
|
|
|
void __init time_init(void)
|
|
|
|
{
|
|
|
|
/* Initialize and register the clock source. */
|
2011-06-01 15:32:50 +08:00
|
|
|
clocksource_register_hz(&cycle_counter_cs, cycles_per_sec);
|
2010-05-29 11:09:12 +08:00
|
|
|
|
|
|
|
/* Start up the tile-timer interrupt source on the boot cpu. */
|
|
|
|
setup_tile_timer();
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Define the tile timer clock event device. The timer is driven by
|
|
|
|
* the TILE_TIMER_CONTROL register, which consists of a 31-bit down
|
|
|
|
* counter, plus bit 31, which signifies that the counter has wrapped
|
|
|
|
* from zero to (2**31) - 1. The INT_TILE_TIMER interrupt will be
|
|
|
|
* raised as long as bit 31 is set.
|
2010-08-13 20:24:22 +08:00
|
|
|
*
|
|
|
|
* The TILE_MINSEC value represents the largest range of real-time
|
|
|
|
* we can possibly cover with the timer, based on MAX_TICK combined
|
|
|
|
* with the slowest reasonable clock rate we might run at.
|
2010-05-29 11:09:12 +08:00
|
|
|
*/
|
|
|
|
|
|
|
|
#define MAX_TICK 0x7fffffff /* we have 31 bits of countdown timer */
|
2010-08-13 20:24:22 +08:00
|
|
|
#define TILE_MINSEC 5 /* timer covers no more than 5 seconds */
|
2010-05-29 11:09:12 +08:00
|
|
|
|
|
|
|
static int tile_timer_set_next_event(unsigned long ticks,
|
|
|
|
struct clock_event_device *evt)
|
|
|
|
{
|
|
|
|
BUG_ON(ticks > MAX_TICK);
|
|
|
|
__insn_mtspr(SPR_TILE_TIMER_CONTROL, ticks);
|
2010-11-02 03:24:29 +08:00
|
|
|
arch_local_irq_unmask_now(INT_TILE_TIMER);
|
2010-05-29 11:09:12 +08:00
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Whenever anyone tries to change modes, we just mask interrupts
|
|
|
|
* and wait for the next event to get set.
|
|
|
|
*/
|
|
|
|
static void tile_timer_set_mode(enum clock_event_mode mode,
|
|
|
|
struct clock_event_device *evt)
|
|
|
|
{
|
2010-11-02 03:24:29 +08:00
|
|
|
arch_local_irq_mask_now(INT_TILE_TIMER);
|
2010-05-29 11:09:12 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Set min_delta_ns to 1 microsecond, since it takes about
|
|
|
|
* that long to fire the interrupt.
|
|
|
|
*/
|
|
|
|
static DEFINE_PER_CPU(struct clock_event_device, tile_timer) = {
|
|
|
|
.name = "tile timer",
|
|
|
|
.features = CLOCK_EVT_FEAT_ONESHOT,
|
|
|
|
.min_delta_ns = 1000,
|
|
|
|
.rating = 100,
|
|
|
|
.irq = -1,
|
|
|
|
.set_next_event = tile_timer_set_next_event,
|
|
|
|
.set_mode = tile_timer_set_mode,
|
|
|
|
};
|
|
|
|
|
|
|
|
void __cpuinit setup_tile_timer(void)
|
|
|
|
{
|
|
|
|
struct clock_event_device *evt = &__get_cpu_var(tile_timer);
|
|
|
|
|
|
|
|
/* Fill in fields that are speed-specific. */
|
|
|
|
clockevents_calc_mult_shift(evt, cycles_per_sec, TILE_MINSEC);
|
|
|
|
evt->max_delta_ns = clockevent_delta2ns(MAX_TICK, evt);
|
|
|
|
|
|
|
|
/* Mark as being for this cpu only. */
|
|
|
|
evt->cpumask = cpumask_of(smp_processor_id());
|
|
|
|
|
|
|
|
/* Start out with timer not firing. */
|
2010-11-02 03:24:29 +08:00
|
|
|
arch_local_irq_mask_now(INT_TILE_TIMER);
|
2010-05-29 11:09:12 +08:00
|
|
|
|
|
|
|
/* Register tile timer. */
|
|
|
|
clockevents_register_device(evt);
|
|
|
|
}
|
|
|
|
|
|
|
|
/* Called from the interrupt vector. */
|
|
|
|
void do_timer_interrupt(struct pt_regs *regs, int fault_num)
|
|
|
|
{
|
|
|
|
struct pt_regs *old_regs = set_irq_regs(regs);
|
|
|
|
struct clock_event_device *evt = &__get_cpu_var(tile_timer);
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Mask the timer interrupt here, since we are a oneshot timer
|
|
|
|
* and there are now by definition no events pending.
|
|
|
|
*/
|
2010-11-02 03:24:29 +08:00
|
|
|
arch_local_irq_mask(INT_TILE_TIMER);
|
2010-05-29 11:09:12 +08:00
|
|
|
|
|
|
|
/* Track time spent here in an interrupt context */
|
|
|
|
irq_enter();
|
|
|
|
|
|
|
|
/* Track interrupt count. */
|
|
|
|
__get_cpu_var(irq_stat).irq_timer_count++;
|
|
|
|
|
|
|
|
/* Call the generic timer handler */
|
|
|
|
evt->event_handler(evt);
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Track time spent against the current process again and
|
|
|
|
* process any softirqs if they are waiting.
|
|
|
|
*/
|
|
|
|
irq_exit();
|
|
|
|
|
|
|
|
set_irq_regs(old_regs);
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Scheduler clock - returns current time in nanosec units.
|
|
|
|
* Note that with LOCKDEP, this is called during lockdep_init(), and
|
|
|
|
* we will claim that sched_clock() is zero for a little while, until
|
|
|
|
* we run setup_clock(), above.
|
|
|
|
*/
|
|
|
|
unsigned long long sched_clock(void)
|
|
|
|
{
|
|
|
|
return clocksource_cyc2ns(get_cycles(),
|
2010-08-13 20:24:22 +08:00
|
|
|
sched_clock_mult, SCHED_CLOCK_SHIFT);
|
2010-05-29 11:09:12 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
int setup_profiling_timer(unsigned int multiplier)
|
|
|
|
{
|
|
|
|
return -EINVAL;
|
|
|
|
}
|
2011-03-01 02:21:52 +08:00
|
|
|
|
|
|
|
/*
|
|
|
|
* Use the tile timer to convert nsecs to core clock cycles, relying
|
|
|
|
* on it having the same frequency as SPR_CYCLE.
|
|
|
|
*/
|
|
|
|
cycles_t ns2cycles(unsigned long nsecs)
|
|
|
|
{
|
2013-03-26 15:16:42 +08:00
|
|
|
/*
|
|
|
|
* We do not have to disable preemption here as each core has the same
|
|
|
|
* clock frequency.
|
|
|
|
*/
|
|
|
|
struct clock_event_device *dev = &__raw_get_cpu_var(tile_timer);
|
2011-03-01 02:21:52 +08:00
|
|
|
return ((u64)nsecs * dev->mult) >> dev->shift;
|
|
|
|
}
|