Loading...
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 | #include <linux/kernel.h>
#include <linux/sched.h>
#include <linux/init.h>
#include <linux/module.h>
#include <linux/timer.h>
#include <linux/acpi_pmtmr.h>
#include <linux/cpufreq.h>
#include <linux/dmi.h>
#include <linux/delay.h>
#include <linux/clocksource.h>
#include <linux/percpu.h>
#include <asm/hpet.h>
#include <asm/timer.h>
#include <asm/vgtod.h>
#include <asm/time.h>
#include <asm/delay.h>
unsigned int cpu_khz; /* TSC clocks / usec, not used here */
EXPORT_SYMBOL(cpu_khz);
unsigned int tsc_khz;
EXPORT_SYMBOL(tsc_khz);
/*
* TSC can be unstable due to cpufreq or due to unsynced TSCs
*/
static int tsc_unstable;
/* native_sched_clock() is called before tsc_init(), so
we must start with the TSC soft disabled to prevent
erroneous rdtsc usage on !cpu_has_tsc processors */
static int tsc_disabled = -1;
/*
* Scheduler clock - returns current time in nanosec units.
*/
u64 native_sched_clock(void)
{
u64 this_offset;
/*
* Fall back to jiffies if there's no TSC available:
* ( But note that we still use it if the TSC is marked
* unstable. We do this because unlike Time Of Day,
* the scheduler clock tolerates small errors and it's
* very important for it to be as fast as the platform
* can achive it. )
*/
if (unlikely(tsc_disabled)) {
/* No locking but a rare wrong value is not a big deal: */
return (jiffies_64 - INITIAL_JIFFIES) * (1000000000 / HZ);
}
/* read the Time Stamp Counter: */
rdtscll(this_offset);
/* return the value in ns */
return cycles_2_ns(this_offset);
}
/* We need to define a real function for sched_clock, to override the
weak default version */
#ifdef CONFIG_PARAVIRT
unsigned long long sched_clock(void)
{
return paravirt_sched_clock();
}
#else
unsigned long long
sched_clock(void) __attribute__((alias("native_sched_clock")));
#endif
int check_tsc_unstable(void)
{
return tsc_unstable;
}
EXPORT_SYMBOL_GPL(check_tsc_unstable);
#ifdef CONFIG_X86_TSC
int __init notsc_setup(char *str)
{
printk(KERN_WARNING "notsc: Kernel compiled with CONFIG_X86_TSC, "
"cannot disable TSC completely.\n");
tsc_disabled = 1;
return 1;
}
#else
/*
* disable flag for tsc. Takes effect by clearing the TSC cpu flag
* in cpu/common.c
*/
int __init notsc_setup(char *str)
{
setup_clear_cpu_cap(X86_FEATURE_TSC);
return 1;
}
#endif
__setup("notsc", notsc_setup);
#define MAX_RETRIES 5
#define SMI_TRESHOLD 50000
/*
* Read TSC and the reference counters. Take care of SMI disturbance
*/
static u64 tsc_read_refs(u64 *pm, u64 *hpet)
{
u64 t1, t2;
int i;
for (i = 0; i < MAX_RETRIES; i++) {
t1 = get_cycles();
if (hpet)
*hpet = hpet_readl(HPET_COUNTER) & 0xFFFFFFFF;
else
*pm = acpi_pm_read_early();
t2 = get_cycles();
if ((t2 - t1) < SMI_TRESHOLD)
return t2;
}
return ULLONG_MAX;
}
/*
* Try to calibrate the TSC against the Programmable
* Interrupt Timer and return the frequency of the TSC
* in kHz.
*
* Return ULONG_MAX on failure to calibrate.
*/
static unsigned long pit_calibrate_tsc(void)
{
u64 tsc, t1, t2, delta;
unsigned long tscmin, tscmax;
int pitcnt;
/* Set the Gate high, disable speaker */
outb((inb(0x61) & ~0x02) | 0x01, 0x61);
/*
* Setup CTC channel 2* for mode 0, (interrupt on terminal
* count mode), binary count. Set the latch register to 50ms
* (LSB then MSB) to begin countdown.
*/
outb(0xb0, 0x43);
outb((CLOCK_TICK_RATE / (1000 / 50)) & 0xff, 0x42);
outb((CLOCK_TICK_RATE / (1000 / 50)) >> 8, 0x42);
tsc = t1 = t2 = get_cycles();
pitcnt = 0;
tscmax = 0;
tscmin = ULONG_MAX;
while ((inb(0x61) & 0x20) == 0) {
t2 = get_cycles();
delta = t2 - tsc;
tsc = t2;
if ((unsigned long) delta < tscmin)
tscmin = (unsigned int) delta;
if ((unsigned long) delta > tscmax)
tscmax = (unsigned int) delta;
pitcnt++;
}
/*
* Sanity checks:
*
* If we were not able to read the PIT more than 5000
* times, then we have been hit by a massive SMI
*
* If the maximum is 10 times larger than the minimum,
* then we got hit by an SMI as well.
*/
if (pitcnt < 5000 || tscmax > 10 * tscmin)
return ULONG_MAX;
/* Calculate the PIT value */
delta = t2 - t1;
do_div(delta, 50);
return delta;
}
/**
* native_calibrate_tsc - calibrate the tsc on boot
*/
unsigned long native_calibrate_tsc(void)
{
u64 tsc1, tsc2, delta, pm1, pm2, hpet1, hpet2;
unsigned long tsc_pit_min = ULONG_MAX, tsc_ref_min = ULONG_MAX;
unsigned long flags;
int hpet = is_hpet_enabled(), i;
/*
* Run 5 calibration loops to get the lowest frequency value
* (the best estimate). We use two different calibration modes
* here:
*
* 1) PIT loop. We set the PIT Channel 2 to oneshot mode and
* load a timeout of 50ms. We read the time right after we
* started the timer and wait until the PIT count down reaches
* zero. In each wait loop iteration we read the TSC and check
* the delta to the previous read. We keep track of the min
* and max values of that delta. The delta is mostly defined
* by the IO time of the PIT access, so we can detect when a
* SMI/SMM disturbance happend between the two reads. If the
* maximum time is significantly larger than the minimum time,
* then we discard the result and have another try.
*
* 2) Reference counter. If available we use the HPET or the
* PMTIMER as a reference to check the sanity of that value.
* We use separate TSC readouts and check inside of the
* reference read for a SMI/SMM disturbance. We dicard
* disturbed values here as well. We do that around the PIT
* calibration delay loop as we have to wait for a certain
* amount of time anyway.
*/
for (i = 0; i < 5; i++) {
unsigned long tsc_pit_khz;
/*
* Read the start value and the reference count of
* hpet/pmtimer when available. Then do the PIT
* calibration, which will take at least 50ms, and
* read the end value.
*/
local_irq_save(flags);
tsc1 = tsc_read_refs(&pm1, hpet ? &hpet1 : NULL);
tsc_pit_khz = pit_calibrate_tsc();
tsc2 = tsc_read_refs(&pm2, hpet ? &hpet2 : NULL);
local_irq_restore(flags);
/* Pick the lowest PIT TSC calibration so far */
tsc_pit_min = min(tsc_pit_min, tsc_pit_khz);
/* hpet or pmtimer available ? */
if (!hpet && !pm1 && !pm2)
continue;
/* Check, whether the sampling was disturbed by an SMI */
if (tsc1 == ULLONG_MAX || tsc2 == ULLONG_MAX)
continue;
tsc2 = (tsc2 - tsc1) * 1000000LL;
if (hpet) {
if (hpet2 < hpet1)
hpet2 += 0x100000000ULL;
hpet2 -= hpet1;
tsc1 = ((u64)hpet2 * hpet_readl(HPET_PERIOD));
do_div(tsc1, 1000000);
} else {
if (pm2 < pm1)
pm2 += (u64)ACPI_PM_OVRRUN;
pm2 -= pm1;
tsc1 = pm2 * 1000000000LL;
do_div(tsc1, PMTMR_TICKS_PER_SEC);
}
do_div(tsc2, tsc1);
tsc_ref_min = min(tsc_ref_min, (unsigned long) tsc2);
}
/*
* Now check the results.
*/
if (tsc_pit_min == ULONG_MAX) {
/* PIT gave no useful value */
printk(KERN_WARNING "TSC: Unable to calibrate against PIT\n");
/* We don't have an alternative source, disable TSC */
if (!hpet && !pm1 && !pm2) {
printk("TSC: No reference (HPET/PMTIMER) available\n");
return 0;
}
/* The alternative source failed as well, disable TSC */
if (tsc_ref_min == ULONG_MAX) {
printk(KERN_WARNING "TSC: HPET/PMTIMER calibration "
"failed due to SMI disturbance.\n");
return 0;
}
/* Use the alternative source */
printk(KERN_INFO "TSC: using %s reference calibration\n",
hpet ? "HPET" : "PMTIMER");
return tsc_ref_min;
}
/* We don't have an alternative source, use the PIT calibration value */
if (!hpet && !pm1 && !pm2) {
printk(KERN_INFO "TSC: Using PIT calibration value\n");
return tsc_pit_min;
}
/* The alternative source failed, use the PIT calibration value */
if (tsc_ref_min == ULONG_MAX) {
printk(KERN_WARNING "TSC: HPET/PMTIMER calibration failed due "
"to SMI disturbance. Using PIT calibration\n");
return tsc_pit_min;
}
/* Check the reference deviation */
delta = ((u64) tsc_pit_min) * 100;
do_div(delta, tsc_ref_min);
/*
* If both calibration results are inside a 5% window, the we
* use the lower frequency of those as it is probably the
* closest estimate.
*/
if (delta >= 95 && delta <= 105) {
printk(KERN_INFO "TSC: PIT calibration confirmed by %s.\n",
hpet ? "HPET" : "PMTIMER");
printk(KERN_INFO "TSC: using %s calibration value\n",
tsc_pit_min <= tsc_ref_min ? "PIT" :
hpet ? "HPET" : "PMTIMER");
return tsc_pit_min <= tsc_ref_min ? tsc_pit_min : tsc_ref_min;
}
printk(KERN_WARNING "TSC: PIT calibration deviates from %s: %lu %lu.\n",
hpet ? "HPET" : "PMTIMER", tsc_pit_min, tsc_ref_min);
/*
* The calibration values differ too much. In doubt, we use
* the PIT value as we know that there are PMTIMERs around
* running at double speed.
*/
printk(KERN_INFO "TSC: Using PIT calibration value\n");
return tsc_pit_min;
}
#ifdef CONFIG_X86_32
/* Only called from the Powernow K7 cpu freq driver */
int recalibrate_cpu_khz(void)
{
#ifndef CONFIG_SMP
unsigned long cpu_khz_old = cpu_khz;
if (cpu_has_tsc) {
tsc_khz = calibrate_tsc();
cpu_khz = tsc_khz;
cpu_data(0).loops_per_jiffy =
cpufreq_scale(cpu_data(0).loops_per_jiffy,
cpu_khz_old, cpu_khz);
return 0;
} else
return -ENODEV;
#else
return -ENODEV;
#endif
}
EXPORT_SYMBOL(recalibrate_cpu_khz);
#endif /* CONFIG_X86_32 */
/* Accelerators for sched_clock()
* convert from cycles(64bits) => nanoseconds (64bits)
* basic equation:
* ns = cycles / (freq / ns_per_sec)
* ns = cycles * (ns_per_sec / freq)
* ns = cycles * (10^9 / (cpu_khz * 10^3))
* ns = cycles * (10^6 / cpu_khz)
*
* Then we use scaling math (suggested by george@mvista.com) to get:
* ns = cycles * (10^6 * SC / cpu_khz) / SC
* ns = cycles * cyc2ns_scale / SC
*
* And since SC is a constant power of two, we can convert the div
* into a shift.
*
* We can use khz divisor instead of mhz to keep a better precision, since
* cyc2ns_scale is limited to 10^6 * 2^10, which fits in 32 bits.
* (mathieu.desnoyers@polymtl.ca)
*
* -johnstul@us.ibm.com "math is hard, lets go shopping!"
*/
DEFINE_PER_CPU(unsigned long, cyc2ns);
static void set_cyc2ns_scale(unsigned long cpu_khz, int cpu)
{
unsigned long long tsc_now, ns_now;
unsigned long flags, *scale;
local_irq_save(flags);
sched_clock_idle_sleep_event();
scale = &per_cpu(cyc2ns, cpu);
rdtscll(tsc_now);
ns_now = __cycles_2_ns(tsc_now);
if (cpu_khz)
*scale = (NSEC_PER_MSEC << CYC2NS_SCALE_FACTOR)/cpu_khz;
sched_clock_idle_wakeup_event(0);
local_irq_restore(flags);
}
#ifdef CONFIG_CPU_FREQ
/* Frequency scaling support. Adjust the TSC based timer when the cpu frequency
* changes.
*
* RED-PEN: On SMP we assume all CPUs run with the same frequency. It's
* not that important because current Opteron setups do not support
* scaling on SMP anyroads.
*
* Should fix up last_tsc too. Currently gettimeofday in the
* first tick after the change will be slightly wrong.
*/
static unsigned int ref_freq;
static unsigned long loops_per_jiffy_ref;
static unsigned long tsc_khz_ref;
static int time_cpufreq_notifier(struct notifier_block *nb, unsigned long val,
void *data)
{
struct cpufreq_freqs *freq = data;
unsigned long *lpj, dummy;
if (cpu_has(&cpu_data(freq->cpu), X86_FEATURE_CONSTANT_TSC))
return 0;
lpj = &dummy;
if (!(freq->flags & CPUFREQ_CONST_LOOPS))
#ifdef CONFIG_SMP
lpj = &cpu_data(freq->cpu).loops_per_jiffy;
#else
lpj = &boot_cpu_data.loops_per_jiffy;
#endif
if (!ref_freq) {
ref_freq = freq->old;
loops_per_jiffy_ref = *lpj;
tsc_khz_ref = tsc_khz;
}
if ((val == CPUFREQ_PRECHANGE && freq->old < freq->new) ||
(val == CPUFREQ_POSTCHANGE && freq->old > freq->new) ||
(val == CPUFREQ_RESUMECHANGE)) {
*lpj = cpufreq_scale(loops_per_jiffy_ref, ref_freq, freq->new);
tsc_khz = cpufreq_scale(tsc_khz_ref, ref_freq, freq->new);
if (!(freq->flags & CPUFREQ_CONST_LOOPS))
mark_tsc_unstable("cpufreq changes");
}
set_cyc2ns_scale(tsc_khz, freq->cpu);
return 0;
}
static struct notifier_block time_cpufreq_notifier_block = {
.notifier_call = time_cpufreq_notifier
};
static int __init cpufreq_tsc(void)
{
if (!cpu_has_tsc)
return 0;
if (boot_cpu_has(X86_FEATURE_CONSTANT_TSC))
return 0;
cpufreq_register_notifier(&time_cpufreq_notifier_block,
CPUFREQ_TRANSITION_NOTIFIER);
return 0;
}
core_initcall(cpufreq_tsc);
#endif /* CONFIG_CPU_FREQ */
/* clocksource code */
static struct clocksource clocksource_tsc;
/*
* We compare the TSC to the cycle_last value in the clocksource
* structure to avoid a nasty time-warp. This can be observed in a
* very small window right after one CPU updated cycle_last under
* xtime/vsyscall_gtod lock and the other CPU reads a TSC value which
* is smaller than the cycle_last reference value due to a TSC which
* is slighty behind. This delta is nowhere else observable, but in
* that case it results in a forward time jump in the range of hours
* due to the unsigned delta calculation of the time keeping core
* code, which is necessary to support wrapping clocksources like pm
* timer.
*/
static cycle_t read_tsc(void)
{
cycle_t ret = (cycle_t)get_cycles();
return ret >= clocksource_tsc.cycle_last ?
ret : clocksource_tsc.cycle_last;
}
#ifdef CONFIG_X86_64
static cycle_t __vsyscall_fn vread_tsc(void)
{
cycle_t ret = (cycle_t)vget_cycles();
return ret >= __vsyscall_gtod_data.clock.cycle_last ?
ret : __vsyscall_gtod_data.clock.cycle_last;
}
#endif
static struct clocksource clocksource_tsc = {
.name = "tsc",
.rating = 300,
.read = read_tsc,
.mask = CLOCKSOURCE_MASK(64),
.shift = 22,
.flags = CLOCK_SOURCE_IS_CONTINUOUS |
CLOCK_SOURCE_MUST_VERIFY,
#ifdef CONFIG_X86_64
.vread = vread_tsc,
#endif
};
void mark_tsc_unstable(char *reason)
{
if (!tsc_unstable) {
tsc_unstable = 1;
printk("Marking TSC unstable due to %s\n", reason);
/* Change only the rating, when not registered */
if (clocksource_tsc.mult)
clocksource_change_rating(&clocksource_tsc, 0);
else
clocksource_tsc.rating = 0;
}
}
EXPORT_SYMBOL_GPL(mark_tsc_unstable);
static int __init dmi_mark_tsc_unstable(const struct dmi_system_id *d)
{
printk(KERN_NOTICE "%s detected: marking TSC unstable.\n",
d->ident);
tsc_unstable = 1;
return 0;
}
/* List of systems that have known TSC problems */
static struct dmi_system_id __initdata bad_tsc_dmi_table[] = {
{
.callback = dmi_mark_tsc_unstable,
.ident = "IBM Thinkpad 380XD",
.matches = {
DMI_MATCH(DMI_BOARD_VENDOR, "IBM"),
DMI_MATCH(DMI_BOARD_NAME, "2635FA0"),
},
},
{}
};
/*
* Geode_LX - the OLPC CPU has a possibly a very reliable TSC
*/
#ifdef CONFIG_MGEODE_LX
/* RTSC counts during suspend */
#define RTSC_SUSP 0x100
static void __init check_geode_tsc_reliable(void)
{
unsigned long res_low, res_high;
rdmsr_safe(MSR_GEODE_BUSCONT_CONF0, &res_low, &res_high);
if (res_low & RTSC_SUSP)
clocksource_tsc.flags &= ~CLOCK_SOURCE_MUST_VERIFY;
}
#else
static inline void check_geode_tsc_reliable(void) { }
#endif
/*
* Make an educated guess if the TSC is trustworthy and synchronized
* over all CPUs.
*/
__cpuinit int unsynchronized_tsc(void)
{
if (!cpu_has_tsc || tsc_unstable)
return 1;
#ifdef CONFIG_SMP
if (apic_is_clustered_box())
return 1;
#endif
if (boot_cpu_has(X86_FEATURE_CONSTANT_TSC))
return 0;
/*
* Intel systems are normally all synchronized.
* Exceptions must mark TSC as unstable:
*/
if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL) {
/* assume multi socket systems are not synchronized: */
if (num_possible_cpus() > 1)
tsc_unstable = 1;
}
return tsc_unstable;
}
static void __init init_tsc_clocksource(void)
{
clocksource_tsc.mult = clocksource_khz2mult(tsc_khz,
clocksource_tsc.shift);
/* lower the rating if we already know its unstable: */
if (check_tsc_unstable()) {
clocksource_tsc.rating = 0;
clocksource_tsc.flags &= ~CLOCK_SOURCE_IS_CONTINUOUS;
}
clocksource_register(&clocksource_tsc);
}
void __init tsc_init(void)
{
u64 lpj;
int cpu;
if (!cpu_has_tsc)
return;
tsc_khz = calibrate_tsc();
cpu_khz = tsc_khz;
if (!tsc_khz) {
mark_tsc_unstable("could not calculate TSC khz");
return;
}
#ifdef CONFIG_X86_64
if (cpu_has(&boot_cpu_data, X86_FEATURE_CONSTANT_TSC) &&
(boot_cpu_data.x86_vendor == X86_VENDOR_AMD))
cpu_khz = calibrate_cpu();
#endif
lpj = ((u64)tsc_khz * 1000);
do_div(lpj, HZ);
lpj_fine = lpj;
printk("Detected %lu.%03lu MHz processor.\n",
(unsigned long)cpu_khz / 1000,
(unsigned long)cpu_khz % 1000);
/*
* Secondary CPUs do not run through tsc_init(), so set up
* all the scale factors for all CPUs, assuming the same
* speed as the bootup CPU. (cpufreq notifiers will fix this
* up if their speed diverges)
*/
for_each_possible_cpu(cpu)
set_cyc2ns_scale(cpu_khz, cpu);
if (tsc_disabled > 0)
return;
/* now allow native_sched_clock() to use rdtsc */
tsc_disabled = 0;
use_tsc_delay();
/* Check and install the TSC clocksource */
dmi_check_system(bad_tsc_dmi_table);
if (unsynchronized_tsc())
mark_tsc_unstable("TSCs unsynchronized");
check_geode_tsc_reliable();
init_tsc_clocksource();
}
|