linux/arch/x86/lib/delay_64.c

86 lines
1.8 KiB
C
Raw Normal View History

/*
* Precise Delay Loops for x86-64
*
* Copyright (C) 1993 Linus Torvalds
* Copyright (C) 1997 Martin Mares <mj@atrey.karlin.mff.cuni.cz>
*
* The __delay function must _NOT_ be inlined as its execution time
* depends wildly on alignment on many x86 processors.
*/
#include <linux/module.h>
#include <linux/sched.h>
#include <linux/timex.h>
#include <linux/preempt.h>
#include <linux/delay.h>
#include <linux/init.h>
#include <asm/delay.h>
[PATCH] Platform SMIs and their interferance with tsc based delay calibration Issue: Current tsc based delay_calibration can result in significant errors in loops_per_jiffy count when the platform events like SMIs (System Management Interrupts that are non-maskable) are present. This could lead to potential kernel panic(). This issue is becoming more visible with 2.6 kernel (as default HZ is 1000) and on platforms with higher SMI handling latencies. During the boot time, SMIs are mostly used by BIOS (for things like legacy keyboard emulation). Description: The psuedocode for current delay calibration with tsc based delay looks like (0) Estimate a value for loops_per_jiffy (1) While (loops_per_jiffy estimate is accurate enough) (2) wait for jiffy transition (jiffy1) (3) Note down current tsc (tsc1) (4) loop until tsc becomes tsc1 + loops_per_jiffy (5) check whether jiffy changed since jiffy1 or not and refine loops_per_jiffy estimate Consider the following cases Case 1: If SMIs happen between (2) and (3) above, we can end up with a loops_per_jiffy value that is too low. This results in shorted delays and kernel can panic () during boot (Mostly at IOAPIC timer initialization timer_irq_works() as we don't have enough timer interrupts in a specified interval). Case 2: If SMIs happen between (3) and (4) above, then we can end up with a loops_per_jiffy value that is too high. And with current i386 code, too high lpj value (greater than 17M) can result in a overflow in delay.c:__const_udelay() again resulting in shorter delay and panic(). Solution: The patch below makes the calibration routine aware of asynchronous events like SMIs. We increase the delay calibration time and also identify any significant errors (greater than 12.5%) in the calibration and notify it to user. Patch below changes both i386 and x86-64 architectures to use this new and improved calibrate_delay_direct() routine. Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Adrian Bunk <bunk@stusta.de> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-06-23 07:08:13 +00:00
#include <asm/msr.h>
#ifdef CONFIG_SMP
#include <asm/smp.h>
#endif
int __devinit read_current_timer(unsigned long *timer_value)
[PATCH] Platform SMIs and their interferance with tsc based delay calibration Issue: Current tsc based delay_calibration can result in significant errors in loops_per_jiffy count when the platform events like SMIs (System Management Interrupts that are non-maskable) are present. This could lead to potential kernel panic(). This issue is becoming more visible with 2.6 kernel (as default HZ is 1000) and on platforms with higher SMI handling latencies. During the boot time, SMIs are mostly used by BIOS (for things like legacy keyboard emulation). Description: The psuedocode for current delay calibration with tsc based delay looks like (0) Estimate a value for loops_per_jiffy (1) While (loops_per_jiffy estimate is accurate enough) (2) wait for jiffy transition (jiffy1) (3) Note down current tsc (tsc1) (4) loop until tsc becomes tsc1 + loops_per_jiffy (5) check whether jiffy changed since jiffy1 or not and refine loops_per_jiffy estimate Consider the following cases Case 1: If SMIs happen between (2) and (3) above, we can end up with a loops_per_jiffy value that is too low. This results in shorted delays and kernel can panic () during boot (Mostly at IOAPIC timer initialization timer_irq_works() as we don't have enough timer interrupts in a specified interval). Case 2: If SMIs happen between (3) and (4) above, then we can end up with a loops_per_jiffy value that is too high. And with current i386 code, too high lpj value (greater than 17M) can result in a overflow in delay.c:__const_udelay() again resulting in shorter delay and panic(). Solution: The patch below makes the calibration routine aware of asynchronous events like SMIs. We increase the delay calibration time and also identify any significant errors (greater than 12.5%) in the calibration and notify it to user. Patch below changes both i386 and x86-64 architectures to use this new and improved calibrate_delay_direct() routine. Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Adrian Bunk <bunk@stusta.de> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-06-23 07:08:13 +00:00
{
rdtscll(*timer_value);
return 0;
}
void __delay(unsigned long loops)
{
unsigned bclock, now;
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 15:13:32 +00:00
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 15:13:32 +00:00
preempt_disable();
cpu = smp_processor_id();
rdtscl(bclock);
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 15:13:32 +00:00
for (;;) {
rdtscl(now);
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 15:13:32 +00:00
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();
rdtscl(bclock);
}
}
preempt_enable();
}
EXPORT_SYMBOL(__delay);
inline void __const_udelay(unsigned long xloops)
{
__delay(((xloops * HZ *
cpu_data(raw_smp_processor_id()).loops_per_jiffy) >> 32) + 1);
}
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);