2007-10-11 09:17:24 +00:00
|
|
|
/*
|
2007-10-13 01:10:53 +00:00
|
|
|
* check TSC synchronization.
|
2007-10-11 09:17:24 +00:00
|
|
|
*
|
|
|
|
* Copyright (C) 2006, Red Hat, Inc., Ingo Molnar
|
|
|
|
*
|
|
|
|
* We check whether all boot CPUs have their TSC's synchronized,
|
|
|
|
* print a warning if not and turn off the TSC clock-source.
|
|
|
|
*
|
|
|
|
* The warp-check is point-to-point between two CPUs, the CPU
|
|
|
|
* initiating the bootup is the 'source CPU', the freshly booting
|
|
|
|
* CPU is the 'target CPU'.
|
|
|
|
*
|
|
|
|
* Only two CPUs may participate - they can enter in any order.
|
|
|
|
* ( The serial nature of the boot logic and the CPU hotplug lock
|
|
|
|
* protects against more than 2 CPUs entering this code. )
|
|
|
|
*/
|
|
|
|
#include <linux/spinlock.h>
|
|
|
|
#include <linux/kernel.h>
|
|
|
|
#include <linux/init.h>
|
|
|
|
#include <linux/smp.h>
|
|
|
|
#include <linux/nmi.h>
|
|
|
|
#include <asm/tsc.h>
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Entry/exit counters that make sure that both CPUs
|
|
|
|
* run the measurement code at once:
|
|
|
|
*/
|
|
|
|
static __cpuinitdata atomic_t start_count;
|
|
|
|
static __cpuinitdata atomic_t stop_count;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* We use a raw spinlock in this exceptional case, because
|
|
|
|
* we want to have the fastest, inlined, non-debug version
|
|
|
|
* of a critical section, to be able to prove TSC time-warps:
|
|
|
|
*/
|
|
|
|
static __cpuinitdata raw_spinlock_t sync_lock = __RAW_SPIN_LOCK_UNLOCKED;
|
|
|
|
static __cpuinitdata cycles_t last_tsc;
|
|
|
|
static __cpuinitdata cycles_t max_warp;
|
|
|
|
static __cpuinitdata int nr_warps;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* TSC-warp measurement loop running on both CPUs:
|
|
|
|
*/
|
|
|
|
static __cpuinit void check_tsc_warp(void)
|
|
|
|
{
|
|
|
|
cycles_t start, now, prev, end;
|
|
|
|
int i;
|
|
|
|
|
2008-01-30 12:32:39 +00:00
|
|
|
start = get_cycles();
|
2007-10-11 09:17:24 +00:00
|
|
|
/*
|
|
|
|
* The measurement runs for 20 msecs:
|
|
|
|
*/
|
|
|
|
end = start + tsc_khz * 20ULL;
|
|
|
|
now = start;
|
|
|
|
|
|
|
|
for (i = 0; ; i++) {
|
|
|
|
/*
|
|
|
|
* We take the global lock, measure TSC, save the
|
|
|
|
* previous TSC that was measured (possibly on
|
|
|
|
* another CPU) and update the previous TSC timestamp.
|
|
|
|
*/
|
|
|
|
__raw_spin_lock(&sync_lock);
|
|
|
|
prev = last_tsc;
|
2008-01-30 12:32:39 +00:00
|
|
|
now = get_cycles();
|
2007-10-11 09:17:24 +00:00
|
|
|
last_tsc = now;
|
|
|
|
__raw_spin_unlock(&sync_lock);
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Be nice every now and then (and also check whether
|
2008-01-30 12:33:23 +00:00
|
|
|
* measurement is done [we also insert a 10 million
|
2007-10-11 09:17:24 +00:00
|
|
|
* loops safety exit, so we dont lock up in case the
|
|
|
|
* TSC readout is totally broken]):
|
|
|
|
*/
|
|
|
|
if (unlikely(!(i & 7))) {
|
2008-01-30 12:33:23 +00:00
|
|
|
if (now > end || i > 10000000)
|
2007-10-11 09:17:24 +00:00
|
|
|
break;
|
|
|
|
cpu_relax();
|
|
|
|
touch_nmi_watchdog();
|
|
|
|
}
|
|
|
|
/*
|
|
|
|
* Outside the critical section we can now see whether
|
|
|
|
* we saw a time-warp of the TSC going backwards:
|
|
|
|
*/
|
|
|
|
if (unlikely(prev > now)) {
|
|
|
|
__raw_spin_lock(&sync_lock);
|
|
|
|
max_warp = max(max_warp, prev - now);
|
|
|
|
nr_warps++;
|
|
|
|
__raw_spin_unlock(&sync_lock);
|
|
|
|
}
|
2008-01-30 12:33:24 +00:00
|
|
|
}
|
2008-07-08 16:51:56 +00:00
|
|
|
WARN(!(now-start),
|
|
|
|
"Warning: zero tsc calibration delta: %Ld [max: %Ld]\n",
|
2008-01-30 12:33:24 +00:00
|
|
|
now-start, end-start);
|
2007-10-11 09:17:24 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Source CPU calls into this - it waits for the freshly booted
|
|
|
|
* target CPU to arrive and then starts the measurement:
|
|
|
|
*/
|
|
|
|
void __cpuinit check_tsc_sync_source(int cpu)
|
|
|
|
{
|
|
|
|
int cpus = 2;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* No need to check if we already know that the TSC is not
|
|
|
|
* synchronized:
|
|
|
|
*/
|
|
|
|
if (unsynchronized_tsc())
|
|
|
|
return;
|
|
|
|
|
|
|
|
printk(KERN_INFO "checking TSC synchronization [CPU#%d -> CPU#%d]:",
|
|
|
|
smp_processor_id(), cpu);
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Reset it - in case this is a second bootup:
|
|
|
|
*/
|
|
|
|
atomic_set(&stop_count, 0);
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Wait for the target to arrive:
|
|
|
|
*/
|
|
|
|
while (atomic_read(&start_count) != cpus-1)
|
|
|
|
cpu_relax();
|
|
|
|
/*
|
|
|
|
* Trigger the target to continue into the measurement too:
|
|
|
|
*/
|
|
|
|
atomic_inc(&start_count);
|
|
|
|
|
|
|
|
check_tsc_warp();
|
|
|
|
|
|
|
|
while (atomic_read(&stop_count) != cpus-1)
|
|
|
|
cpu_relax();
|
|
|
|
|
|
|
|
if (nr_warps) {
|
|
|
|
printk("\n");
|
|
|
|
printk(KERN_WARNING "Measured %Ld cycles TSC warp between CPUs,"
|
|
|
|
" turning off TSC clock.\n", max_warp);
|
|
|
|
mark_tsc_unstable("check_tsc_sync_source failed");
|
|
|
|
} else {
|
|
|
|
printk(" passed.\n");
|
|
|
|
}
|
|
|
|
|
x86: fix: s2ram + P4 + tsc = annoyance
s2ram recently became useful here, except for the kernel's annoying
habit of disabling my P4's perfectly good TSC.
[ 107.894470] CPU 1 is now offline
[ 107.894474] SMP alternatives: switching to UP code
[ 107.895832] CPU0 attaching sched-domain:
[ 107.895836] domain 0: span 1
[ 107.895838] groups: 1
[ 107.896097] CPU1 is down
[ 3.726156] Intel machine check architecture supported.
[ 3.726165] Intel machine check reporting enabled on CPU#0.
[ 3.726167] CPU0: Intel P4/Xeon Extended MCE MSRs (12) available
[ 3.726170] CPU0: Thermal monitoring enabled
[ 3.726175] Back to C!
[ 3.726708] Force enabled HPET at resume
[ 3.726775] Enabling non-boot CPUs ...
[ 3.727049] CPU0 attaching NULL sched-domain.
[ 3.727165] SMP alternatives: switching to SMP code
[ 3.727858] Booting processor 1/1 eip 3000
[ 3.727862] CPU 1 irqstacks, hard=b042f000 soft=b042d000
[ 3.738173] Initializing CPU#1
[ 3.798912] Calibrating delay using timer specific routine.. 5986.12 BogoMIPS (lpj=2993061)
[ 3.798920] CPU: After generic identify, caps: bfebfbff 00000000 00000000 00000000 00004400 00000000 00000000 00000000
[ 3.798931] CPU: Trace cache: 12K uops, L1 D cache: 8K
[ 3.798934] CPU: L2 cache: 512K
[ 3.798936] CPU: Physical Processor ID: 0
[ 3.798938] CPU: After all inits, caps: bfebfbff 00000000 00000000 0000b080 00004400 00000000 00000000 00000000
[ 3.798946] Intel machine check architecture supported.
[ 3.798952] Intel machine check reporting enabled on CPU#1.
[ 3.798955] CPU1: Intel P4/Xeon Extended MCE MSRs (12) available
[ 3.798959] CPU1: Thermal monitoring enabled
[ 3.799161] CPU1: Intel(R) Pentium(R) 4 CPU 3.00GHz stepping 09
[ 3.799187] checking TSC synchronization [CPU#0 -> CPU#1]:
[ 3.819181] Measured 63588552840 cycles TSC warp between CPUs, turning off TSC clock.
[ 3.819184] Marking TSC unstable due to: check_tsc_sync_source failed.
If check_tsc_warp() is called after initial boot, and the TSC has in the
meantime been set (BIOS, user, silicon, elves) to a value lower than the
last stored/stale value, we blame the TSC. Reset to pristine condition
after every test.
Signed-off-by: Mike Galbraith <efault@gmx.de>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2008-01-30 12:30:04 +00:00
|
|
|
/*
|
|
|
|
* Reset it - just in case we boot another CPU later:
|
|
|
|
*/
|
|
|
|
atomic_set(&start_count, 0);
|
|
|
|
nr_warps = 0;
|
|
|
|
max_warp = 0;
|
|
|
|
last_tsc = 0;
|
|
|
|
|
2007-10-11 09:17:24 +00:00
|
|
|
/*
|
|
|
|
* Let the target continue with the bootup:
|
|
|
|
*/
|
|
|
|
atomic_inc(&stop_count);
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Freshly booted CPUs call into this:
|
|
|
|
*/
|
|
|
|
void __cpuinit check_tsc_sync_target(void)
|
|
|
|
{
|
|
|
|
int cpus = 2;
|
|
|
|
|
|
|
|
if (unsynchronized_tsc())
|
|
|
|
return;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Register this CPU's participation and wait for the
|
|
|
|
* source CPU to start the measurement:
|
|
|
|
*/
|
|
|
|
atomic_inc(&start_count);
|
|
|
|
while (atomic_read(&start_count) != cpus)
|
|
|
|
cpu_relax();
|
|
|
|
|
|
|
|
check_tsc_warp();
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Ok, we are done:
|
|
|
|
*/
|
|
|
|
atomic_inc(&stop_count);
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Wait for the source CPU to print stuff:
|
|
|
|
*/
|
|
|
|
while (atomic_read(&stop_count) != cpus)
|
|
|
|
cpu_relax();
|
|
|
|
}
|
|
|
|
#undef NR_LOOPS
|
|
|
|
|