alistair23-linux/arch/x86/lib/delay.c
Huang Rui b466bdb614 x86/asm/delay: Introduce an MWAITX-based delay with a configurable timer
MWAITX can enable a timer and a corresponding timer value
specified in SW P0 clocks. The SW P0 frequency is the same as
TSC. The timer provides an upper bound on how long the
instruction waits before exiting.

This way, a delay function in the kernel can leverage that
MWAITX timer of MWAITX.

When a CPU core executes MWAITX, it will be quiesced in a
waiting phase, diminishing its power consumption. This way, we
can save power in comparison to our default TSC-based delays.

A simple test shows that:

	$ cat /sys/bus/pci/devices/0000\:00\:18.4/hwmon/hwmon0/power1_acc
	$ sleep 10000s
	$ cat /sys/bus/pci/devices/0000\:00\:18.4/hwmon/hwmon0/power1_acc

Results:

	* TSC-based default delay:      485115 uWatts average power
	* MWAITX-based delay:           252738 uWatts average power

Thus, that's about 240 milliWatts less power consumption. The
test method relies on the support of AMD CPU accumulated power
algorithm in fam15h_power for which patches are forthcoming.

Suggested-by: Andy Lutomirski <luto@amacapital.net>
Suggested-by: Borislav Petkov <bp@suse.de>
Suggested-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Huang Rui <ray.huang@amd.com>
[ Fix delay truncation. ]
Signed-off-by: Borislav Petkov <bp@suse.de>
Cc: Aaron Lu <aaron.lu@intel.com>
Cc: Andreas Herrmann <herrmann.der.user@gmail.com>
Cc: Aravind Gopalakrishnan <Aravind.Gopalakrishnan@amd.com>
Cc: Fengguang Wu <fengguang.wu@intel.com>
Cc: Frédéric Weisbecker <fweisbec@gmail.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Hector Marco-Gisbert <hecmargi@upv.es>
Cc: Jacob Shin <jacob.w.shin@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: John Stultz <john.stultz@linaro.org>
Cc: Len Brown <lenb@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Rafael J. Wysocki <rjw@rjwysocki.net>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Tony Li <tony.li@amd.com>
Link: http://lkml.kernel.org/r/1438744732-1459-3-git-send-email-ray.huang@amd.com
Link: http://lkml.kernel.org/r/1439201994-28067-4-git-send-email-bp@alien8.de
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-08-22 14:52:16 +02:00

182 lines
3.7 KiB
C

/*
* Precise Delay Loops for i386
*
* Copyright (C) 1993 Linus Torvalds
* Copyright (C) 1997 Martin Mares <mj@atrey.karlin.mff.cuni.cz>
* Copyright (C) 2008 Jiri Hladky <hladky _dot_ jiri _at_ gmail _dot_ com>
*
* The __delay function must _NOT_ be inlined as its execution time
* depends wildly on alignment on many x86 processors. The additional
* jump magic is needed to get the timing stable on all the CPU's
* we have to worry about.
*/
#include <linux/module.h>
#include <linux/sched.h>
#include <linux/timex.h>
#include <linux/preempt.h>
#include <linux/delay.h>
#include <asm/processor.h>
#include <asm/delay.h>
#include <asm/timer.h>
#include <asm/mwait.h>
#ifdef CONFIG_SMP
# include <asm/smp.h>
#endif
/* simple loop based delay: */
static void delay_loop(unsigned long loops)
{
asm volatile(
" test %0,%0 \n"
" jz 3f \n"
" jmp 1f \n"
".align 16 \n"
"1: jmp 2f \n"
".align 16 \n"
"2: dec %0 \n"
" jnz 2b \n"
"3: dec %0 \n"
: /* we don't need output */
:"a" (loops)
);
}
/* TSC based delay: */
static void delay_tsc(unsigned long __loops)
{
u64 bclock, now, loops = __loops;
int cpu;
preempt_disable();
cpu = smp_processor_id();
bclock = rdtsc_ordered();
for (;;) {
now = rdtsc_ordered();
if ((now - bclock) >= loops)
break;
/* Allow RT tasks to run */
preempt_enable();
rep_nop();
preempt_disable();
/*
* It is possible that we moved to another CPU, and
* since TSC's are per-cpu we need to calculate
* that. The delay must guarantee that we wait "at
* least" the amount of time. Being moved to another
* CPU could make the wait longer but we just need to
* make sure we waited long enough. Rebalance the
* counter for this CPU.
*/
if (unlikely(cpu != smp_processor_id())) {
loops -= (now - bclock);
cpu = smp_processor_id();
bclock = rdtsc_ordered();
}
}
preempt_enable();
}
/*
* On some AMD platforms, MWAITX has a configurable 32-bit timer, that
* counts with TSC frequency. The input value is the loop of the
* counter, it will exit when the timer expires.
*/
static void delay_mwaitx(unsigned long __loops)
{
u64 start, end, delay, loops = __loops;
start = rdtsc_ordered();
for (;;) {
delay = min_t(u64, MWAITX_MAX_LOOPS, loops);
/*
* Use cpu_tss as a cacheline-aligned, seldomly
* accessed per-cpu variable as the monitor target.
*/
__monitorx(this_cpu_ptr(&cpu_tss), 0, 0);
/*
* AMD, like Intel, supports the EAX hint and EAX=0xf
* means, do not enter any deep C-state and we use it
* here in delay() to minimize wakeup latency.
*/
__mwaitx(MWAITX_DISABLE_CSTATES, delay, MWAITX_ECX_TIMER_ENABLE);
end = rdtsc_ordered();
if (loops <= end - start)
break;
loops -= end - start;
start = end;
}
}
/*
* Since we calibrate only once at boot, this
* function should be set once at boot and not changed
*/
static void (*delay_fn)(unsigned long) = delay_loop;
void use_tsc_delay(void)
{
if (delay_fn == delay_loop)
delay_fn = delay_tsc;
}
void use_mwaitx_delay(void)
{
delay_fn = delay_mwaitx;
}
int read_current_timer(unsigned long *timer_val)
{
if (delay_fn == delay_tsc) {
*timer_val = rdtsc();
return 0;
}
return -1;
}
void __delay(unsigned long loops)
{
delay_fn(loops);
}
EXPORT_SYMBOL(__delay);
inline void __const_udelay(unsigned long xloops)
{
int d0;
xloops *= 4;
asm("mull %%edx"
:"=d" (xloops), "=&a" (d0)
:"1" (xloops), "0"
(this_cpu_read(cpu_info.loops_per_jiffy) * (HZ/4)));
__delay(++xloops);
}
EXPORT_SYMBOL(__const_udelay);
void __udelay(unsigned long usecs)
{
__const_udelay(usecs * 0x000010c7); /* 2**32 / 1000000 (rounded up) */
}
EXPORT_SYMBOL(__udelay);
void __ndelay(unsigned long nsecs)
{
__const_udelay(nsecs * 0x00005); /* 2**32 / 1000000000 (rounded up) */
}
EXPORT_SYMBOL(__ndelay);