linux/kernel/cpu.c at master · fabgithub/linux · GitHub

Repository navigation

History

728 lines (612 loc) · 17.1 KB

Raw

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

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

/* CPU control.

* This code is licenced under the GPL.

#include <linux/proc_fs.h>

#include <linux/smp.h>

#include <linux/init.h>

#include <linux/notifier.h>

#include <linux/sched.h>

#include <linux/unistd.h>

#include <linux/cpu.h>

#include <linux/oom.h>

#include <linux/rcupdate.h>

#include <linux/export.h>

#include <linux/bug.h>

#include <linux/kthread.h>

#include <linux/stop_machine.h>

#include <linux/mutex.h>

#include <linux/gfp.h>

#include <linux/suspend.h>

#include "smpboot.h"

#ifdef CONFIG_SMP

/* Serializes the updates to cpu_online_mask, cpu_present_mask */

static DEFINE_MUTEX(cpu_add_remove_lock);

* The following two API's must be used when attempting

* to serialize the updates to cpu_online_mask, cpu_present_mask.

void cpu_maps_update_begin(void)

{

mutex_lock(&cpu_add_remove_lock);

}

void cpu_maps_update_done(void)

{

mutex_unlock(&cpu_add_remove_lock);

}

static RAW_NOTIFIER_HEAD(cpu_chain);

/* If set, cpu_up and cpu_down will return -EBUSY and do nothing.

* Should always be manipulated under cpu_add_remove_lock

static int cpu_hotplug_disabled;

#ifdef CONFIG_HOTPLUG_CPU

static struct {

struct task_struct *active_writer;

struct mutex lock; /* Synchronizes accesses to refcount, */

* Also blocks the new readers during

* an ongoing cpu hotplug operation.

int refcount;

} cpu_hotplug = {

.active_writer = NULL,

.lock = __MUTEX_INITIALIZER(cpu_hotplug.lock),

.refcount = 0,

};

void get_online_cpus(void)

{

might_sleep();

if (cpu_hotplug.active_writer == current)

return;

mutex_lock(&cpu_hotplug.lock);

cpu_hotplug.refcount++;

mutex_unlock(&cpu_hotplug.lock);

}

EXPORT_SYMBOL_GPL(get_online_cpus);

void put_online_cpus(void)

{

if (cpu_hotplug.active_writer == current)

return;

mutex_lock(&cpu_hotplug.lock);

if (WARN_ON(!cpu_hotplug.refcount))

cpu_hotplug.refcount++; /* try to fix things up */

if (!--cpu_hotplug.refcount && unlikely(cpu_hotplug.active_writer))

wake_up_process(cpu_hotplug.active_writer);

mutex_unlock(&cpu_hotplug.lock);

}

EXPORT_SYMBOL_GPL(put_online_cpus);

* This ensures that the hotplug operation can begin only when the

* refcount goes to zero.

* Note that during a cpu-hotplug operation, the new readers, if any,

* will be blocked by the cpu_hotplug.lock

* Since cpu_hotplug_begin() is always called after invoking

* cpu_maps_update_begin(), we can be sure that only one writer is active.

* Note that theoretically, there is a possibility of a livelock:

* - Refcount goes to zero, last reader wakes up the sleeping

* writer.

* - Last reader unlocks the cpu_hotplug.lock.

* - A new reader arrives at this moment, bumps up the refcount.

* - The writer acquires the cpu_hotplug.lock finds the refcount

* non zero and goes to sleep again.

* However, this is very difficult to achieve in practice since

* get_online_cpus() not an api which is called all that often.

static void cpu_hotplug_begin(void)

{

cpu_hotplug.active_writer = current;

for (;;) {

mutex_lock(&cpu_hotplug.lock);

if (likely(!cpu_hotplug.refcount))

break;

__set_current_state(TASK_UNINTERRUPTIBLE);

mutex_unlock(&cpu_hotplug.lock);

schedule();

}

static void cpu_hotplug_done(void)

{

cpu_hotplug.active_writer = NULL;

mutex_unlock(&cpu_hotplug.lock);

}

* Wait for currently running CPU hotplug operations to complete (if any) and

* disable future CPU hotplug (from sysfs). The 'cpu_add_remove_lock' protects

* the 'cpu_hotplug_disabled' flag. The same lock is also acquired by the

* hotplug path before performing hotplug operations. So acquiring that lock

* guarantees mutual exclusion from any currently running hotplug operations.

void cpu_hotplug_disable(void)

{

cpu_maps_update_begin();

cpu_hotplug_disabled = 1;

cpu_maps_update_done();

}

void cpu_hotplug_enable(void)

{

cpu_maps_update_begin();

cpu_hotplug_disabled = 0;

cpu_maps_update_done();

}

#else /* #if CONFIG_HOTPLUG_CPU */

static void cpu_hotplug_begin(void) {}

static void cpu_hotplug_done(void) {}

#endif /* #else #if CONFIG_HOTPLUG_CPU */

/* Need to know about CPUs going up/down? */

int __ref register_cpu_notifier(struct notifier_block *nb)

{

int ret;

cpu_maps_update_begin();

ret = raw_notifier_chain_register(&cpu_chain, nb);

cpu_maps_update_done();

return ret;

}

static int __cpu_notify(unsigned long val, void *v, int nr_to_call,

int *nr_calls)

{

int ret;

ret = __raw_notifier_call_chain(&cpu_chain, val, v, nr_to_call,

nr_calls);

return notifier_to_errno(ret);

}

static int cpu_notify(unsigned long val, void *v)

{

return __cpu_notify(val, v, -1, NULL);

}

#ifdef CONFIG_HOTPLUG_CPU

static void cpu_notify_nofail(unsigned long val, void *v)

{

BUG_ON(cpu_notify(val, v));

}

EXPORT_SYMBOL(register_cpu_notifier);

void __ref unregister_cpu_notifier(struct notifier_block *nb)

{

cpu_maps_update_begin();

raw_notifier_chain_unregister(&cpu_chain, nb);

cpu_maps_update_done();

}

EXPORT_SYMBOL(unregister_cpu_notifier);

/**

* clear_tasks_mm_cpumask - Safely clear tasks' mm_cpumask for a CPU

* @cpu: a CPU id

* This function walks all processes, finds a valid mm struct for each one and

* then clears a corresponding bit in mm's cpumask. While this all sounds

* trivial, there are various non-obvious corner cases, which this function

* tries to solve in a safe manner.

* Also note that the function uses a somewhat relaxed locking scheme, so it may

* be called only for an already offlined CPU.

void clear_tasks_mm_cpumask(int cpu)

{

struct task_struct *p;

* This function is called after the cpu is taken down and marked

* offline, so its not like new tasks will ever get this cpu set in

* their mm mask. -- Peter Zijlstra

* Thus, we may use rcu_read_lock() here, instead of grabbing

* full-fledged tasklist_lock.

WARN_ON(cpu_online(cpu));

rcu_read_lock();

for_each_process(p) {

struct task_struct *t;

* Main thread might exit, but other threads may still have

* a valid mm. Find one.

t = find_lock_task_mm(p);

if (!t)

continue;

cpumask_clear_cpu(cpu, mm_cpumask(t->mm));

task_unlock(t);

}

rcu_read_unlock();

}

static inline void check_for_tasks(int cpu)

{

struct task_struct *p;

cputime_t utime, stime;

write_lock_irq(&tasklist_lock);

for_each_process(p) {

task_cputime(p, &utime, &stime);

if (task_cpu(p) == cpu && p->state == TASK_RUNNING &&

(utime || stime))

printk(KERN_WARNING "Task %s (pid = %d) is on cpu %d "

"(state = %ld, flags = %x)\n",

p->comm, task_pid_nr(p), cpu,

p->state, p->flags);

}

write_unlock_irq(&tasklist_lock);

}

struct take_cpu_down_param {

unsigned long mod;

void *hcpu;

};

/* Take this CPU down. */

static int __ref take_cpu_down(void *_param)

{

struct take_cpu_down_param *param = _param;

int err;

/* Ensure this CPU doesn't handle any more interrupts. */

err = __cpu_disable();

if (err < 0)

return err;

cpu_notify(CPU_DYING | param->mod, param->hcpu);

/* Park the stopper thread */

kthread_park(current);

return 0;

}

/* Requires cpu_add_remove_lock to be held */

static int __ref _cpu_down(unsigned int cpu, int tasks_frozen)

{

int err, nr_calls = 0;

void *hcpu = (void *)(long)cpu;

unsigned long mod = tasks_frozen ? CPU_TASKS_FROZEN : 0;

struct take_cpu_down_param tcd_param = {

.mod = mod,

.hcpu = hcpu,

};

if (num_online_cpus() == 1)

return -EBUSY;

if (!cpu_online(cpu))

return -EINVAL;

cpu_hotplug_begin();

err = __cpu_notify(CPU_DOWN_PREPARE | mod, hcpu, -1, &nr_calls);

if (err) {

nr_calls--;

__cpu_notify(CPU_DOWN_FAILED | mod, hcpu, nr_calls, NULL);

printk("%s: attempt to take down CPU %u failed\n",

__func__, cpu);

goto out_release;

}

smpboot_park_threads(cpu);

err = __stop_machine(take_cpu_down, &tcd_param, cpumask_of(cpu));

if (err) {

/* CPU didn't die: tell everyone. Can't complain. */

smpboot_unpark_threads(cpu);

cpu_notify_nofail(CPU_DOWN_FAILED | mod, hcpu);

goto out_release;

}

BUG_ON(cpu_online(cpu));

* The migration_call() CPU_DYING callback will have removed all

* runnable tasks from the cpu, there's only the idle task left now

* that the migration thread is done doing the stop_machine thing.

* Wait for the stop thread to go away.

while (!idle_cpu(cpu))

cpu_relax();

/* This actually kills the CPU. */

__cpu_die(cpu);

/* CPU is completely dead: tell everyone. Too late to complain. */

cpu_notify_nofail(CPU_DEAD | mod, hcpu);

check_for_tasks(cpu);

out_release:

cpu_hotplug_done();

if (!err)

cpu_notify_nofail(CPU_POST_DEAD | mod, hcpu);

return err;

}

int __ref cpu_down(unsigned int cpu)

{

int err;

cpu_maps_update_begin();

if (cpu_hotplug_disabled) {

err = -EBUSY;

goto out;

}

err = _cpu_down(cpu, 0);

out:

cpu_maps_update_done();

return err;

}

EXPORT_SYMBOL(cpu_down);

#endif /*CONFIG_HOTPLUG_CPU*/

/* Requires cpu_add_remove_lock to be held */

static int _cpu_up(unsigned int cpu, int tasks_frozen)

{

int ret, nr_calls = 0;

void *hcpu = (void *)(long)cpu;

unsigned long mod = tasks_frozen ? CPU_TASKS_FROZEN : 0;

struct task_struct *idle;

cpu_hotplug_begin();

if (cpu_online(cpu) || !cpu_present(cpu)) {

ret = -EINVAL;

goto out;

}

idle = idle_thread_get(cpu);

if (IS_ERR(idle)) {

ret = PTR_ERR(idle);

goto out;

}

ret = smpboot_create_threads(cpu);

if (ret)

goto out;

ret = __cpu_notify(CPU_UP_PREPARE | mod, hcpu, -1, &nr_calls);

if (ret) {

nr_calls--;

printk(KERN_WARNING "%s: attempt to bring up CPU %u failed\n",

__func__, cpu);

goto out_notify;

}

/* Arch-specific enabling code. */

ret = __cpu_up(cpu, idle);

if (ret != 0)

goto out_notify;

BUG_ON(!cpu_online(cpu));

/* Wake the per cpu threads */

smpboot_unpark_threads(cpu);

/* Now call notifier in preparation. */

cpu_notify(CPU_ONLINE | mod, hcpu);

out_notify:

if (ret != 0)

__cpu_notify(CPU_UP_CANCELED | mod, hcpu, nr_calls, NULL);

out:

cpu_hotplug_done();

return ret;

}

int cpu_up(unsigned int cpu)

{

int err = 0;

#ifdef CONFIG_MEMORY_HOTPLUG

int nid;

pg_data_t *pgdat;

#endif

if (!cpu_possible(cpu)) {

printk(KERN_ERR "can't online cpu %d because it is not "

"configured as may-hotadd at boot time\n", cpu);

#if defined(CONFIG_IA64)

printk(KERN_ERR "please check additional_cpus= boot "

"parameter\n");

#endif

return -EINVAL;

}

#ifdef CONFIG_MEMORY_HOTPLUG

nid = cpu_to_node(cpu);

if (!node_online(nid)) {

err = mem_online_node(nid);

if (err)

return err;

}

pgdat = NODE_DATA(nid);

if (!pgdat) {

printk(KERN_ERR

"Can't online cpu %d due to NULL pgdat\n", cpu);

return -ENOMEM;

}

if (pgdat->node_zonelists->_zonerefs->zone == NULL) {

mutex_lock(&zonelists_mutex);

build_all_zonelists(NULL, NULL);

mutex_unlock(&zonelists_mutex);

}

#endif

cpu_maps_update_begin();

if (cpu_hotplug_disabled) {

err = -EBUSY;

goto out;

}

err = _cpu_up(cpu, 0);

out:

cpu_maps_update_done();

return err;

}

EXPORT_SYMBOL_GPL(cpu_up);

#ifdef CONFIG_PM_SLEEP_SMP

static cpumask_var_t frozen_cpus;

int disable_nonboot_cpus(void)

{

int cpu, first_cpu, error = 0;

cpu_maps_update_begin();

first_cpu = cpumask_first(cpu_online_mask);

* We take down all of the non-boot CPUs in one shot to avoid races

* with the userspace trying to use the CPU hotplug at the same time

cpumask_clear(frozen_cpus);

printk("Disabling non-boot CPUs ...\n");

for_each_online_cpu(cpu) {

if (cpu == first_cpu)

continue;

error = _cpu_down(cpu, 1);

if (!error)

cpumask_set_cpu(cpu, frozen_cpus);

else {

printk(KERN_ERR "Error taking CPU%d down: %d\n",

cpu, error);

break;

}

if (!error) {

BUG_ON(num_online_cpus() > 1);

/* Make sure the CPUs won't be enabled by someone else */

cpu_hotplug_disabled = 1;

} else {

printk(KERN_ERR "Non-boot CPUs are not disabled\n");

}

cpu_maps_update_done();

return error;

}

void __weak arch_enable_nonboot_cpus_begin(void)

{

}

void __weak arch_enable_nonboot_cpus_end(void)

{

}

void __ref enable_nonboot_cpus(void)

{

int cpu, error;

/* Allow everyone to use the CPU hotplug again */

cpu_maps_update_begin();

cpu_hotplug_disabled = 0;

if (cpumask_empty(frozen_cpus))

goto out;

printk(KERN_INFO "Enabling non-boot CPUs ...\n");

arch_enable_nonboot_cpus_begin();

for_each_cpu(cpu, frozen_cpus) {

error = _cpu_up(cpu, 1);

if (!error) {

printk(KERN_INFO "CPU%d is up\n", cpu);

continue;

}

printk(KERN_WARNING "Error taking CPU%d up: %d\n", cpu, error);

}

arch_enable_nonboot_cpus_end();

cpumask_clear(frozen_cpus);

out:

cpu_maps_update_done();

}

static int __init alloc_frozen_cpus(void)

{

if (!alloc_cpumask_var(&frozen_cpus, GFP_KERNEL|__GFP_ZERO))

return -ENOMEM;

return 0;

}

core_initcall(alloc_frozen_cpus);

* When callbacks for CPU hotplug notifications are being executed, we must

* ensure that the state of the system with respect to the tasks being frozen

* or not, as reported by the notification, remains unchanged *throughout the

* duration* of the execution of the callbacks.

* Hence we need to prevent the freezer from racing with regular CPU hotplug.

* This synchronization is implemented by mutually excluding regular CPU

* hotplug and Suspend/Hibernate call paths by hooking onto the Suspend/

* Hibernate notifications.

static int

cpu_hotplug_pm_callback(struct notifier_block *nb,

unsigned long action, void *ptr)

{

switch (action) {

case PM_SUSPEND_PREPARE:

case PM_HIBERNATION_PREPARE:

cpu_hotplug_disable();

break;

case PM_POST_SUSPEND:

case PM_POST_HIBERNATION:

cpu_hotplug_enable();

break;

default:

return NOTIFY_DONE;

}

return NOTIFY_OK;

}

static int __init cpu_hotplug_pm_sync_init(void)

{

* cpu_hotplug_pm_callback has higher priority than x86

* bsp_pm_callback which depends on cpu_hotplug_pm_callback

* to disable cpu hotplug to avoid cpu hotplug race.

pm_notifier(cpu_hotplug_pm_callback, 0);

return 0;

}

core_initcall(cpu_hotplug_pm_sync_init);

#endif /* CONFIG_PM_SLEEP_SMP */

/**

* notify_cpu_starting(cpu) - call the CPU_STARTING notifiers

* @cpu: cpu that just started

* This function calls the cpu_chain notifiers with CPU_STARTING.

* It must be called by the arch code on the new cpu, before the new cpu

* enables interrupts and before the "boot" cpu returns from __cpu_up().

void notify_cpu_starting(unsigned int cpu)

{

unsigned long val = CPU_STARTING;

#ifdef CONFIG_PM_SLEEP_SMP

if (frozen_cpus != NULL && cpumask_test_cpu(cpu, frozen_cpus))

val = CPU_STARTING_FROZEN;

#endif /* CONFIG_PM_SLEEP_SMP */

cpu_notify(val, (void *)(long)cpu);

}

#endif /* CONFIG_SMP */

* cpu_bit_bitmap[] is a special, "compressed" data structure that

* represents all NR_CPUS bits binary values of 1<<nr.

* It is used by cpumask_of() to get a constant address to a CPU

* mask value that has a single bit set only.

/* cpu_bit_bitmap[0] is empty - so we can back into it */

#define MASK_DECLARE_1(x) [x+1][0] = (1UL << (x))

#define MASK_DECLARE_2(x) MASK_DECLARE_1(x), MASK_DECLARE_1(x+1)

#define MASK_DECLARE_4(x) MASK_DECLARE_2(x), MASK_DECLARE_2(x+2)

#define MASK_DECLARE_8(x) MASK_DECLARE_4(x), MASK_DECLARE_4(x+4)

const unsigned long cpu_bit_bitmap[BITS_PER_LONG+1][BITS_TO_LONGS(NR_CPUS)] = {

MASK_DECLARE_8(0), MASK_DECLARE_8(8),

MASK_DECLARE_8(16), MASK_DECLARE_8(24),

#if BITS_PER_LONG > 32

MASK_DECLARE_8(32), MASK_DECLARE_8(40),

MASK_DECLARE_8(48), MASK_DECLARE_8(56),

#endif

};

EXPORT_SYMBOL_GPL(cpu_bit_bitmap);

const DECLARE_BITMAP(cpu_all_bits, NR_CPUS) = CPU_BITS_ALL;

EXPORT_SYMBOL(cpu_all_bits);

#ifdef CONFIG_INIT_ALL_POSSIBLE

static DECLARE_BITMAP(cpu_possible_bits, CONFIG_NR_CPUS) __read_mostly

= CPU_BITS_ALL;

#else

static DECLARE_BITMAP(cpu_possible_bits, CONFIG_NR_CPUS) __read_mostly;

#endif

const struct cpumask *const cpu_possible_mask = to_cpumask(cpu_possible_bits);

EXPORT_SYMBOL(cpu_possible_mask);

static DECLARE_BITMAP(cpu_online_bits, CONFIG_NR_CPUS) __read_mostly;

const struct cpumask *const cpu_online_mask = to_cpumask(cpu_online_bits);

EXPORT_SYMBOL(cpu_online_mask);

static DECLARE_BITMAP(cpu_present_bits, CONFIG_NR_CPUS) __read_mostly;

const struct cpumask *const cpu_present_mask = to_cpumask(cpu_present_bits);

EXPORT_SYMBOL(cpu_present_mask);

static DECLARE_BITMAP(cpu_active_bits, CONFIG_NR_CPUS) __read_mostly;

const struct cpumask *const cpu_active_mask = to_cpumask(cpu_active_bits);

EXPORT_SYMBOL(cpu_active_mask);

void set_cpu_possible(unsigned int cpu, bool possible)

{

if (possible)

cpumask_set_cpu(cpu, to_cpumask(cpu_possible_bits));

else

cpumask_clear_cpu(cpu, to_cpumask(cpu_possible_bits));

}

void set_cpu_present(unsigned int cpu, bool present)

{

if (present)

cpumask_set_cpu(cpu, to_cpumask(cpu_present_bits));

else

cpumask_clear_cpu(cpu, to_cpumask(cpu_present_bits));

}

void set_cpu_online(unsigned int cpu, bool online)

{

if (online)

cpumask_set_cpu(cpu, to_cpumask(cpu_online_bits));

else

cpumask_clear_cpu(cpu, to_cpumask(cpu_online_bits));

}

void set_cpu_active(unsigned int cpu, bool active)

{

if (active)

cpumask_set_cpu(cpu, to_cpumask(cpu_active_bits));

else

cpumask_clear_cpu(cpu, to_cpumask(cpu_active_bits));

}

void init_cpu_present(const struct cpumask *src)

{

cpumask_copy(to_cpumask(cpu_present_bits), src);

}

void init_cpu_possible(const struct cpumask *src)

{

cpumask_copy(to_cpumask(cpu_possible_bits), src);

}

void init_cpu_online(const struct cpumask *src)

{

cpumask_copy(to_cpumask(cpu_online_bits), src);

}

linux/kernel/cpu.c at master · fabgithub/linux · GitHub

Repository navigation

Expand file tree

Breadcrumbs

cpu.c

Latest commit

History

Breadcrumbs

cpu.c

File metadata and controls