aboutsummaryrefslogtreecommitdiffstats
path: root/net/tipc/cluster.c
diff options
context:
space:
mode:
Diffstat (limited to 'net/tipc/cluster.c')
0 files changed, 0 insertions, 0 deletions
generated by cgit v1.2.2 (git 2.25.0) at 2025-10-27 01:12:12 -0400
ref='#n239'>239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 
/*
 * Windfarm PowerMac thermal control.
 * Control loops for RackMack3,1 (Xserve G5)
 *
 * Copyright (C) 2012 Benjamin Herrenschmidt, IBM Corp.
 *
 * Use and redistribute under the terms of the GNU GPL v2.
 */
#include <linux/types.h>
#include <linux/errno.h>
#include <linux/kernel.h>
#include <linux/device.h>
#include <linux/platform_device.h>
#include <linux/reboot.h>
#include <asm/prom.h>
#include <asm/smu.h>

#include "windfarm.h"
#include "windfarm_pid.h"
#include "windfarm_mpu.h"

#define VERSION "1.0"

#undef DEBUG
#undef LOTSA_DEBUG

#ifdef DEBUG
#define DBG(args...)	printk(args)
#else
#define DBG(args...)	do { } while(0)
#endif

#ifdef LOTSA_DEBUG
#define DBG_LOTS(args...)	printk(args)
#else
#define DBG_LOTS(args...)	do { } while(0)
#endif

/* define this to force CPU overtemp to 60 degree, useful for testing
 * the overtemp code
 */
#undef HACKED_OVERTEMP

/* We currently only handle 2 chips */
#define NR_CHIPS	2
#define NR_CPU_FANS	3 * NR_CHIPS

/* Controls and sensors */
static struct wf_sensor *sens_cpu_temp[NR_CHIPS];
static struct wf_sensor *sens_cpu_volts[NR_CHIPS];
static struct wf_sensor *sens_cpu_amps[NR_CHIPS];
static struct wf_sensor *backside_temp;
static struct wf_sensor *slots_temp;
static struct wf_sensor *dimms_temp;

static struct wf_control *cpu_fans[NR_CHIPS][3];
static struct wf_control *backside_fan;
static struct wf_control *slots_fan;
static struct wf_control *cpufreq_clamp;

/* We keep a temperature history for average calculation of 180s */
#define CPU_TEMP_HIST_SIZE	180

/* PID loop state */
static const struct mpu_data *cpu_mpu_data[NR_CHIPS];
static struct wf_cpu_pid_state cpu_pid[NR_CHIPS];
static u32 cpu_thist[CPU_TEMP_HIST_SIZE];
static int cpu_thist_pt;
static s64 cpu_thist_total;
static s32 cpu_all_tmax = 100 << 16;
static struct wf_pid_state backside_pid;
static int backside_tick;
static struct wf_pid_state slots_pid;
static int slots_tick;
static int slots_speed;
static struct wf_pid_state dimms_pid;
static int dimms_output_clamp;

static int nr_chips;
static bool have_all_controls;
static bool have_all_sensors;
static bool started;

static int failure_state;
#define FAILURE_SENSOR		1
#define FAILURE_FAN		2
#define FAILURE_PERM		4
#define FAILURE_LOW_OVERTEMP	8
#define FAILURE_HIGH_OVERTEMP	16

/* Overtemp values */
#define LOW_OVER_AVERAGE	0
#define LOW_OVER_IMMEDIATE	(10 << 16)
#define LOW_OVER_CLEAR		((-10) << 16)
#define HIGH_OVER_IMMEDIATE	(14 << 16)
#define HIGH_OVER_AVERAGE	(10 << 16)
#define HIGH_OVER_IMMEDIATE	(14 << 16)


static void cpu_max_all_fans(void)
{
	int i;

	/* We max all CPU fans in case of a sensor error. We also do the
	 * cpufreq clamping now, even if it's supposedly done later by the
	 * generic code anyway, we do it earlier here to react faster
	 */
	if (cpufreq_clamp)
		wf_control_set_max(cpufreq_clamp);
	for (i = 0; i < nr_chips; i++) {
		if (cpu_fans[i][0])
			wf_control_set_max(cpu_fans[i][0]);
		if (cpu_fans[i][1])
			wf_control_set_max(cpu_fans[i][1]);
		if (cpu_fans[i][2])
			wf_control_set_max(cpu_fans[i][2]);
	}
}

static int cpu_check_overtemp(s32 temp)
{
	int new_state = 0;
	s32 t_avg, t_old;
	static bool first = true;

	/* First check for immediate overtemps */
	if (temp >= (cpu_all_tmax + LOW_OVER_IMMEDIATE)) {
		new_state |= FAILURE_LOW_OVERTEMP;
		if ((failure_state & FAILURE_LOW_OVERTEMP) == 0)
			printk(KERN_ERR "windfarm: Overtemp due to immediate CPU"
			       " temperature !\n");
	}
	if (temp >= (cpu_all_tmax + HIGH_OVER_IMMEDIATE)) {
		new_state |= FAILURE_HIGH_OVERTEMP;
		if ((failure_state & FAILURE_HIGH_OVERTEMP) == 0)
			printk(KERN_ERR "windfarm: Critical overtemp due to"
			       " immediate CPU temperature !\n");
	}

	/*
	 * The first time around, initialize the array with the first
	 * temperature reading
	 */
	if (first) {
		int i;

		cpu_thist_total = 0;
		for (i = 0; i < CPU_TEMP_HIST_SIZE; i++) {
			cpu_thist[i] = temp;
			cpu_thist_total += temp;
		}
		first = false;
	}

	/*
	 * We calculate a history of max temperatures and use that for the
	 * overtemp management
	 */
	t_old = cpu_thist[cpu_thist_pt];
	cpu_thist[cpu_thist_pt] = temp;
	cpu_thist_pt = (cpu_thist_pt + 1) % CPU_TEMP_HIST_SIZE;
	cpu_thist_total -= t_old;
	cpu_thist_total += temp;
	t_avg = cpu_thist_total / CPU_TEMP_HIST_SIZE;

	DBG_LOTS("  t_avg = %d.%03d (out: %d.%03d, in: %d.%03d)\n",
		 FIX32TOPRINT(t_avg), FIX32TOPRINT(t_old), FIX32TOPRINT(temp));

	/* Now check for average overtemps */
	if (t_avg >= (cpu_all_tmax + LOW_OVER_AVERAGE)) {
		new_state |= FAILURE_LOW_OVERTEMP;
		if ((failure_state & FAILURE_LOW_OVERTEMP) == 0)
			printk(KERN_ERR "windfarm: Overtemp due to average CPU"
			       " temperature !\n");
	}
	if (t_avg >= (cpu_all_tmax + HIGH_OVER_AVERAGE)) {
		new_state |= FAILURE_HIGH_OVERTEMP;
		if ((failure_state & FAILURE_HIGH_OVERTEMP) == 0)
			printk(KERN_ERR "windfarm: Critical overtemp due to"
			       " average CPU temperature !\n");
	}

	/* Now handle overtemp conditions. We don't currently use the windfarm
	 * overtemp handling core as it's not fully suited to the needs of those
	 * new machine. This will be fixed later.
	 */
	if (new_state) {
		/* High overtemp -> immediate shutdown */
		if (new_state & FAILURE_HIGH_OVERTEMP)
			machine_power_off();
		if ((failure_state & new_state) != new_state)
			cpu_max_all_fans();
		failure_state |= new_state;
	} else if ((failure_state & FAILURE_LOW_OVERTEMP) &&
		   (temp < (cpu_all_tmax + LOW_OVER_CLEAR))) {
		printk(KERN_ERR "windfarm: Overtemp condition cleared !\n");
		failure_state &= ~FAILURE_LOW_OVERTEMP;
	}

	return failure_state & (FAILURE_LOW_OVERTEMP | FAILURE_HIGH_OVERTEMP);
}

static int read_one_cpu_vals(int cpu, s32 *temp, s32 *power)
{
	s32 dtemp, volts, amps;