linux-sg2042/arch/x86/lib/delay.c

182 lines
3.7 KiB
C
Raw Normal View History

/*
* 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>
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>
2015-08-10 18:19:54 +08:00
#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;
x86: enable preemption in delay The RT team has been searching for a nasty latency. This latency shows up out of the blue and has been seen to be as big as 5ms! Using ftrace I found the cause of the latency. pcscd-2995 3dNh1 52360300us : irq_exit (smp_apic_timer_interrupt) pcscd-2995 3dN.2 52360301us : idle_cpu (irq_exit) pcscd-2995 3dN.2 52360301us : rcu_irq_exit (irq_exit) pcscd-2995 3dN.1 52360771us : smp_apic_timer_interrupt (apic_timer_interrupt ) pcscd-2995 3dN.1 52360771us : exit_idle (smp_apic_timer_interrupt) Here's an example of a 400 us latency. pcscd took a timer interrupt and returned with "need resched" enabled, but did not reschedule until after the next interrupt came in at 52360771us 400us later! At first I thought we somehow missed a preemption check in entry.S. But I also noticed that this always seemed to happen during a __delay call. pcscd-2995 3dN.2 52360836us : rcu_irq_exit (irq_exit) pcscd-2995 3.N.. 52361265us : preempt_schedule (__delay) Looking at the x86 delay, I found my problem. In git commit 35d5d08a085c56f153458c3f5d8ce24123617faf, Andrew Morton placed preempt_disable around the entire delay due to TSC's not working nicely on SMP. Unfortunately for those that care about latencies this is devastating! Especially when we have callers to mdelay(8). Here I enable preemption during the loop and account for anytime the task migrates to a new CPU. The delay asked for may be extended a bit by the migration, but delay only guarantees that it will delay for that minimum time. Delaying longer should not be an issue. [ Thanks to Thomas Gleixner for spotting that cpu wasn't updated, and to place the rep_nop between preempt_enabled/disable. ] Signed-off-by: Steven Rostedt <srostedt@redhat.com> Cc: akpm@osdl.org Cc: Clark Williams <clark.williams@gmail.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: "Luis Claudio R. Goncalves" <lclaudio@uudg.org> Cc: Gregory Haskins <ghaskins@novell.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Andi Kleen <andi-suse@firstfloor.org> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2008-05-25 23:13:32 +08:00
int cpu;
x86: enable preemption in delay The RT team has been searching for a nasty latency. This latency shows up out of the blue and has been seen to be as big as 5ms! Using ftrace I found the cause of the latency. pcscd-2995 3dNh1 52360300us : irq_exit (smp_apic_timer_interrupt) pcscd-2995 3dN.2 52360301us : idle_cpu (irq_exit) pcscd-2995 3dN.2 52360301us : rcu_irq_exit (irq_exit) pcscd-2995 3dN.1 52360771us : smp_apic_timer_interrupt (apic_timer_interrupt ) pcscd-2995 3dN.1 52360771us : exit_idle (smp_apic_timer_interrupt) Here's an example of a 400 us latency. pcscd took a timer interrupt and returned with "need resched" enabled, but did not reschedule until after the next interrupt came in at 52360771us 400us later! At first I thought we somehow missed a preemption check in entry.S. But I also noticed that this always seemed to happen during a __delay call. pcscd-2995 3dN.2 52360836us : rcu_irq_exit (irq_exit) pcscd-2995 3.N.. 52361265us : preempt_schedule (__delay) Looking at the x86 delay, I found my problem. In git commit 35d5d08a085c56f153458c3f5d8ce24123617faf, Andrew Morton placed preempt_disable around the entire delay due to TSC's not working nicely on SMP. Unfortunately for those that care about latencies this is devastating! Especially when we have callers to mdelay(8). Here I enable preemption during the loop and account for anytime the task migrates to a new CPU. The delay asked for may be extended a bit by the migration, but delay only guarantees that it will delay for that minimum time. Delaying longer should not be an issue. [ Thanks to Thomas Gleixner for spotting that cpu wasn't updated, and to place the rep_nop between preempt_enabled/disable. ] Signed-off-by: Steven Rostedt <srostedt@redhat.com> Cc: akpm@osdl.org Cc: Clark Williams <clark.williams@gmail.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: "Luis Claudio R. Goncalves" <lclaudio@uudg.org> Cc: Gregory Haskins <ghaskins@novell.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Andi Kleen <andi-suse@firstfloor.org> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2008-05-25 23:13:32 +08:00
preempt_disable();
cpu = smp_processor_id();
bclock = rdtsc_ordered();
x86: enable preemption in delay The RT team has been searching for a nasty latency. This latency shows up out of the blue and has been seen to be as big as 5ms! Using ftrace I found the cause of the latency. pcscd-2995 3dNh1 52360300us : irq_exit (smp_apic_timer_interrupt) pcscd-2995 3dN.2 52360301us : idle_cpu (irq_exit) pcscd-2995 3dN.2 52360301us : rcu_irq_exit (irq_exit) pcscd-2995 3dN.1 52360771us : smp_apic_timer_interrupt (apic_timer_interrupt ) pcscd-2995 3dN.1 52360771us : exit_idle (smp_apic_timer_interrupt) Here's an example of a 400 us latency. pcscd took a timer interrupt and returned with "need resched" enabled, but did not reschedule until after the next interrupt came in at 52360771us 400us later! At first I thought we somehow missed a preemption check in entry.S. But I also noticed that this always seemed to happen during a __delay call. pcscd-2995 3dN.2 52360836us : rcu_irq_exit (irq_exit) pcscd-2995 3.N.. 52361265us : preempt_schedule (__delay) Looking at the x86 delay, I found my problem. In git commit 35d5d08a085c56f153458c3f5d8ce24123617faf, Andrew Morton placed preempt_disable around the entire delay due to TSC's not working nicely on SMP. Unfortunately for those that care about latencies this is devastating! Especially when we have callers to mdelay(8). Here I enable preemption during the loop and account for anytime the task migrates to a new CPU. The delay asked for may be extended a bit by the migration, but delay only guarantees that it will delay for that minimum time. Delaying longer should not be an issue. [ Thanks to Thomas Gleixner for spotting that cpu wasn't updated, and to place the rep_nop between preempt_enabled/disable. ] Signed-off-by: Steven Rostedt <srostedt@redhat.com> Cc: akpm@osdl.org Cc: Clark Williams <clark.williams@gmail.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: "Luis Claudio R. Goncalves" <lclaudio@uudg.org> Cc: Gregory Haskins <ghaskins@novell.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Andi Kleen <andi-suse@firstfloor.org> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2008-05-25 23:13:32 +08:00
for (;;) {
now = rdtsc_ordered();
x86: enable preemption in delay The RT team has been searching for a nasty latency. This latency shows up out of the blue and has been seen to be as big as 5ms! Using ftrace I found the cause of the latency. pcscd-2995 3dNh1 52360300us : irq_exit (smp_apic_timer_interrupt) pcscd-2995 3dN.2 52360301us : idle_cpu (irq_exit) pcscd-2995 3dN.2 52360301us : rcu_irq_exit (irq_exit) pcscd-2995 3dN.1 52360771us : smp_apic_timer_interrupt (apic_timer_interrupt ) pcscd-2995 3dN.1 52360771us : exit_idle (smp_apic_timer_interrupt) Here's an example of a 400 us latency. pcscd took a timer interrupt and returned with "need resched" enabled, but did not reschedule until after the next interrupt came in at 52360771us 400us later! At first I thought we somehow missed a preemption check in entry.S. But I also noticed that this always seemed to happen during a __delay call. pcscd-2995 3dN.2 52360836us : rcu_irq_exit (irq_exit) pcscd-2995 3.N.. 52361265us : preempt_schedule (__delay) Looking at the x86 delay, I found my problem. In git commit 35d5d08a085c56f153458c3f5d8ce24123617faf, Andrew Morton placed preempt_disable around the entire delay due to TSC's not working nicely on SMP. Unfortunately for those that care about latencies this is devastating! Especially when we have callers to mdelay(8). Here I enable preemption during the loop and account for anytime the task migrates to a new CPU. The delay asked for may be extended a bit by the migration, but delay only guarantees that it will delay for that minimum time. Delaying longer should not be an issue. [ Thanks to Thomas Gleixner for spotting that cpu wasn't updated, and to place the rep_nop between preempt_enabled/disable. ] Signed-off-by: Steven Rostedt <srostedt@redhat.com> Cc: akpm@osdl.org Cc: Clark Williams <clark.williams@gmail.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: "Luis Claudio R. Goncalves" <lclaudio@uudg.org> Cc: Gregory Haskins <ghaskins@novell.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Andi Kleen <andi-suse@firstfloor.org> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2008-05-25 23:13:32 +08:00
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();
x86: enable preemption in delay The RT team has been searching for a nasty latency. This latency shows up out of the blue and has been seen to be as big as 5ms! Using ftrace I found the cause of the latency. pcscd-2995 3dNh1 52360300us : irq_exit (smp_apic_timer_interrupt) pcscd-2995 3dN.2 52360301us : idle_cpu (irq_exit) pcscd-2995 3dN.2 52360301us : rcu_irq_exit (irq_exit) pcscd-2995 3dN.1 52360771us : smp_apic_timer_interrupt (apic_timer_interrupt ) pcscd-2995 3dN.1 52360771us : exit_idle (smp_apic_timer_interrupt) Here's an example of a 400 us latency. pcscd took a timer interrupt and returned with "need resched" enabled, but did not reschedule until after the next interrupt came in at 52360771us 400us later! At first I thought we somehow missed a preemption check in entry.S. But I also noticed that this always seemed to happen during a __delay call. pcscd-2995 3dN.2 52360836us : rcu_irq_exit (irq_exit) pcscd-2995 3.N.. 52361265us : preempt_schedule (__delay) Looking at the x86 delay, I found my problem. In git commit 35d5d08a085c56f153458c3f5d8ce24123617faf, Andrew Morton placed preempt_disable around the entire delay due to TSC's not working nicely on SMP. Unfortunately for those that care about latencies this is devastating! Especially when we have callers to mdelay(8). Here I enable preemption during the loop and account for anytime the task migrates to a new CPU. The delay asked for may be extended a bit by the migration, but delay only guarantees that it will delay for that minimum time. Delaying longer should not be an issue. [ Thanks to Thomas Gleixner for spotting that cpu wasn't updated, and to place the rep_nop between preempt_enabled/disable. ] Signed-off-by: Steven Rostedt <srostedt@redhat.com> Cc: akpm@osdl.org Cc: Clark Williams <clark.williams@gmail.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: "Luis Claudio R. Goncalves" <lclaudio@uudg.org> Cc: Gregory Haskins <ghaskins@novell.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Andi Kleen <andi-suse@firstfloor.org> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2008-05-25 23:13:32 +08:00
}
}
preempt_enable();
}
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>
2015-08-10 18:19:54 +08:00
/*
* 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)
{
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>
2015-08-10 18:19:54 +08:00
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);