SmartisanOS_Kernel_Source/virt/kvm/kvm_main.c at master · ActiveProgram/SmartisanOS_Kernel_Source · GitHub

Repository navigation

History

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

729

730

731

732

733

734

735

736

737

738

739

740

741

742

743

744

745

746

747

748

749

750

751

752

753

754

755

756

757

758

759

760

761

762

763

764

765

766

767

768

769

770

771

772

773

774

775

776

777

778

779

780

781

782

783

784

785

786

787

788

789

790

791

792

793

794

795

796

797

798

799

800

801

802

803

804

805

806

807

808

809

810

811

812

813

814

815

816

817

818

819

820

821

822

823

824

825

826

827

828

829

830

831

832

833

834

835

836

837

838

839

840

841

842

843

844

845

846

847

848

849

850

851

852

853

854

855

856

857

858

859

860

861

862

863

864

865

866

867

868

869

870

871

872

873

874

875

876

877

878

879

880

881

882

883

884

885

886

887

888

889

890

891

892

893

894

895

896

897

898

899

900

901

902

903

904

905

906

907

908

909

910

911

912

913

914

915

916

917

918

919

920

921

922

923

924

925

926

927

928

929

930

931

932

933

934

935

936

937

938

939

940

941

942

943

944

945

946

947

948

949

950

951

952

953

954

955

956

957

958

959

960

961

962

963

964

965

966

967

968

969

970

971

972

973

974

975

976

977

978

979

980

981

982

983

984

985

986

987

988

989

990

991

992

993

994

995

996

997

998

999

1000

* Kernel-based Virtual Machine driver for Linux

* This module enables machines with Intel VT-x extensions to run virtual

* machines without emulation or binary translation.

* Authors:

* Avi Kivity <avi@qumranet.com>

* Yaniv Kamay <yaniv@qumranet.com>

* This work is licensed under the terms of the GNU GPL, version 2. See

* the COPYING file in the top-level directory.

#include "iodev.h"

#include <linux/kvm_host.h>

#include <linux/kvm.h>

#include <linux/module.h>

#include <linux/errno.h>

#include <linux/percpu.h>

#include <linux/mm.h>

#include <linux/miscdevice.h>

#include <linux/vmalloc.h>

#include <linux/reboot.h>

#include <linux/debugfs.h>

#include <linux/highmem.h>

#include <linux/file.h>

#include <linux/syscore_ops.h>

#include <linux/cpu.h>

#include <linux/sched.h>

#include <linux/cpumask.h>

#include <linux/smp.h>

#include <linux/anon_inodes.h>

#include <linux/profile.h>

#include <linux/kvm_para.h>

#include <linux/pagemap.h>

#include <linux/mman.h>

#include <linux/swap.h>

#include <linux/bitops.h>

#include <linux/spinlock.h>

#include <linux/compat.h>

#include <linux/srcu.h>

#include <linux/hugetlb.h>

#include <linux/slab.h>

#include <linux/sort.h>

#include <linux/bsearch.h>

#include <asm/processor.h>

#include <asm/io.h>

#include <asm/uaccess.h>

#include <asm/pgtable.h>

#include "coalesced_mmio.h"

#include "async_pf.h"

#define CREATE_TRACE_POINTS

#include <trace/events/kvm.h>

MODULE_AUTHOR("Qumranet");

MODULE_LICENSE("GPL");

* Ordering of locks:

* kvm->lock --> kvm->slots_lock --> kvm->irq_lock

DEFINE_RAW_SPINLOCK(kvm_lock);

LIST_HEAD(vm_list);

static cpumask_var_t cpus_hardware_enabled;

static int kvm_usage_count = 0;

static atomic_t hardware_enable_failed;

struct kmem_cache *kvm_vcpu_cache;

EXPORT_SYMBOL_GPL(kvm_vcpu_cache);

static __read_mostly struct preempt_ops kvm_preempt_ops;

struct dentry *kvm_debugfs_dir;

static long kvm_vcpu_ioctl(struct file *file, unsigned int ioctl,

unsigned long arg);

#ifdef CONFIG_COMPAT

static long kvm_vcpu_compat_ioctl(struct file *file, unsigned int ioctl,

unsigned long arg);

#endif

static int hardware_enable_all(void);

static void hardware_disable_all(void);

static void kvm_io_bus_destroy(struct kvm_io_bus *bus);

bool kvm_rebooting;

EXPORT_SYMBOL_GPL(kvm_rebooting);

static bool largepages_enabled = true;

static struct page *hwpoison_page;

static pfn_t hwpoison_pfn;

struct page *fault_page;

pfn_t fault_pfn;

inline int kvm_is_mmio_pfn(pfn_t pfn)

{

if (pfn_valid(pfn)) {

int reserved;

struct page *tail = pfn_to_page(pfn);

struct page *head = compound_trans_head(tail);

reserved = PageReserved(head);

if (head != tail) {

* "head" is not a dangling pointer

* (compound_trans_head takes care of that)

* but the hugepage may have been splitted

* from under us (and we may not hold a

* reference count on the head page so it can

* be reused before we run PageReferenced), so

* we've to check PageTail before returning

* what we just read.

smp_rmb();

if (PageTail(tail))

return reserved;

}

return PageReserved(tail);

}

return true;

}

* Switches to specified vcpu, until a matching vcpu_put()

void vcpu_load(struct kvm_vcpu *vcpu)

{

int cpu;

mutex_lock(&vcpu->mutex);

if (unlikely(vcpu->pid != current->pids[PIDTYPE_PID].pid)) {

/* The thread running this VCPU changed. */

struct pid *oldpid = vcpu->pid;

struct pid *newpid = get_task_pid(current, PIDTYPE_PID);

rcu_assign_pointer(vcpu->pid, newpid);

synchronize_rcu();

put_pid(oldpid);

}

cpu = get_cpu();

preempt_notifier_register(&vcpu->preempt_notifier);

kvm_arch_vcpu_load(vcpu, cpu);

put_cpu();

}

void vcpu_put(struct kvm_vcpu *vcpu)

{

preempt_disable();

kvm_arch_vcpu_put(vcpu);

preempt_notifier_unregister(&vcpu->preempt_notifier);

preempt_enable();

mutex_unlock(&vcpu->mutex);

}

static void ack_flush(void *_completed)

{

}

static bool make_all_cpus_request(struct kvm *kvm, unsigned int req)

{

int i, cpu, me;

cpumask_var_t cpus;

bool called = true;

struct kvm_vcpu *vcpu;

zalloc_cpumask_var(&cpus, GFP_ATOMIC);

me = get_cpu();

kvm_for_each_vcpu(i, vcpu, kvm) {

kvm_make_request(req, vcpu);

cpu = vcpu->cpu;

/* Set ->requests bit before we read ->mode */

smp_mb();

if (cpus != NULL && cpu != -1 && cpu != me &&

kvm_vcpu_exiting_guest_mode(vcpu) != OUTSIDE_GUEST_MODE)

cpumask_set_cpu(cpu, cpus);

}

if (unlikely(cpus == NULL))

smp_call_function_many(cpu_online_mask, ack_flush, NULL, 1);

else if (!cpumask_empty(cpus))

smp_call_function_many(cpus, ack_flush, NULL, 1);

else

called = false;

put_cpu();

free_cpumask_var(cpus);

return called;

}

void kvm_flush_remote_tlbs(struct kvm *kvm)

{

long dirty_count = kvm->tlbs_dirty;

smp_mb();

if (make_all_cpus_request(kvm, KVM_REQ_TLB_FLUSH))

++kvm->stat.remote_tlb_flush;

cmpxchg(&kvm->tlbs_dirty, dirty_count, 0);

}

void kvm_reload_remote_mmus(struct kvm *kvm)

{

make_all_cpus_request(kvm, KVM_REQ_MMU_RELOAD);

}

int kvm_vcpu_init(struct kvm_vcpu *vcpu, struct kvm *kvm, unsigned id)

{

struct page *page;

int r;

mutex_init(&vcpu->mutex);

vcpu->cpu = -1;

vcpu->kvm = kvm;

vcpu->vcpu_id = id;

vcpu->pid = NULL;

init_waitqueue_head(&vcpu->wq);

kvm_async_pf_vcpu_init(vcpu);

page = alloc_page(GFP_KERNEL | __GFP_ZERO);

if (!page) {

r = -ENOMEM;

goto fail;

}

vcpu->run = page_address(page);

r = kvm_arch_vcpu_init(vcpu);

if (r < 0)

goto fail_free_run;

return 0;

fail_free_run:

free_page((unsigned long)vcpu->run);

fail:

return r;

}

EXPORT_SYMBOL_GPL(kvm_vcpu_init);

void kvm_vcpu_uninit(struct kvm_vcpu *vcpu)

{

put_pid(vcpu->pid);

kvm_arch_vcpu_uninit(vcpu);

free_page((unsigned long)vcpu->run);

}

EXPORT_SYMBOL_GPL(kvm_vcpu_uninit);

#if defined(CONFIG_MMU_NOTIFIER) && defined(KVM_ARCH_WANT_MMU_NOTIFIER)

static inline struct kvm *mmu_notifier_to_kvm(struct mmu_notifier *mn)

{

return container_of(mn, struct kvm, mmu_notifier);

}

static void kvm_mmu_notifier_invalidate_page(struct mmu_notifier *mn,

struct mm_struct *mm,

unsigned long address)

{

struct kvm *kvm = mmu_notifier_to_kvm(mn);

int need_tlb_flush, idx;

* When ->invalidate_page runs, the linux pte has been zapped

* already but the page is still allocated until

* ->invalidate_page returns. So if we increase the sequence

* here the kvm page fault will notice if the spte can't be

* established because the page is going to be freed. If

* instead the kvm page fault establishes the spte before

* ->invalidate_page runs, kvm_unmap_hva will release it

* before returning.

* The sequence increase only need to be seen at spin_unlock

* time, and not at spin_lock time.

* Increasing the sequence after the spin_unlock would be

* unsafe because the kvm page fault could then establish the

* pte after kvm_unmap_hva returned, without noticing the page

* is going to be freed.

idx = srcu_read_lock(&kvm->srcu);

spin_lock(&kvm->mmu_lock);

kvm->mmu_notifier_seq++;

need_tlb_flush = kvm_unmap_hva(kvm, address) | kvm->tlbs_dirty;

/* we've to flush the tlb before the pages can be freed */

if (need_tlb_flush)

kvm_flush_remote_tlbs(kvm);

spin_unlock(&kvm->mmu_lock);

srcu_read_unlock(&kvm->srcu, idx);

}

static void kvm_mmu_notifier_change_pte(struct mmu_notifier *mn,

struct mm_struct *mm,

unsigned long address,

pte_t pte)

{

struct kvm *kvm = mmu_notifier_to_kvm(mn);

int idx;

idx = srcu_read_lock(&kvm->srcu);

spin_lock(&kvm->mmu_lock);

kvm->mmu_notifier_seq++;

kvm_set_spte_hva(kvm, address, pte);

spin_unlock(&kvm->mmu_lock);

srcu_read_unlock(&kvm->srcu, idx);

}

static void kvm_mmu_notifier_invalidate_range_start(struct mmu_notifier *mn,

struct mm_struct *mm,

unsigned long start,

unsigned long end)

{

struct kvm *kvm = mmu_notifier_to_kvm(mn);

int need_tlb_flush = 0, idx;

idx = srcu_read_lock(&kvm->srcu);

spin_lock(&kvm->mmu_lock);

* The count increase must become visible at unlock time as no

* spte can be established without taking the mmu_lock and

* count is also read inside the mmu_lock critical section.

kvm->mmu_notifier_count++;

for (; start < end; start += PAGE_SIZE)

need_tlb_flush |= kvm_unmap_hva(kvm, start);

need_tlb_flush |= kvm->tlbs_dirty;

/* we've to flush the tlb before the pages can be freed */

if (need_tlb_flush)

kvm_flush_remote_tlbs(kvm);

spin_unlock(&kvm->mmu_lock);

srcu_read_unlock(&kvm->srcu, idx);

}

static void kvm_mmu_notifier_invalidate_range_end(struct mmu_notifier *mn,

struct mm_struct *mm,

unsigned long start,

unsigned long end)

{

struct kvm *kvm = mmu_notifier_to_kvm(mn);

spin_lock(&kvm->mmu_lock);

* This sequence increase will notify the kvm page fault that

* the page that is going to be mapped in the spte could have

* been freed.

kvm->mmu_notifier_seq++;

smp_wmb();

* The above sequence increase must be visible before the

* below count decrease, which is ensured by the smp_wmb above

* in conjunction with the smp_rmb in mmu_notifier_retry().

kvm->mmu_notifier_count--;

spin_unlock(&kvm->mmu_lock);

BUG_ON(kvm->mmu_notifier_count < 0);

}

static int kvm_mmu_notifier_clear_flush_young(struct mmu_notifier *mn,

struct mm_struct *mm,

unsigned long address)

{

struct kvm *kvm = mmu_notifier_to_kvm(mn);

int young, idx;

idx = srcu_read_lock(&kvm->srcu);

spin_lock(&kvm->mmu_lock);

young = kvm_age_hva(kvm, address);

if (young)

kvm_flush_remote_tlbs(kvm);

spin_unlock(&kvm->mmu_lock);

srcu_read_unlock(&kvm->srcu, idx);

return young;

}

static int kvm_mmu_notifier_test_young(struct mmu_notifier *mn,

struct mm_struct *mm,

unsigned long address)

{

struct kvm *kvm = mmu_notifier_to_kvm(mn);

int young, idx;

idx = srcu_read_lock(&kvm->srcu);

spin_lock(&kvm->mmu_lock);

young = kvm_test_age_hva(kvm, address);

spin_unlock(&kvm->mmu_lock);

srcu_read_unlock(&kvm->srcu, idx);

return young;

}

static void kvm_mmu_notifier_release(struct mmu_notifier *mn,

struct mm_struct *mm)

{

struct kvm *kvm = mmu_notifier_to_kvm(mn);

int idx;

idx = srcu_read_lock(&kvm->srcu);

kvm_arch_flush_shadow(kvm);

srcu_read_unlock(&kvm->srcu, idx);

}

static const struct mmu_notifier_ops kvm_mmu_notifier_ops = {

.invalidate_page = kvm_mmu_notifier_invalidate_page,

.invalidate_range_start = kvm_mmu_notifier_invalidate_range_start,

.invalidate_range_end = kvm_mmu_notifier_invalidate_range_end,

.clear_flush_young = kvm_mmu_notifier_clear_flush_young,

.test_young = kvm_mmu_notifier_test_young,

.change_pte = kvm_mmu_notifier_change_pte,

.release = kvm_mmu_notifier_release,

};

static int kvm_init_mmu_notifier(struct kvm *kvm)

{

kvm->mmu_notifier.ops = &kvm_mmu_notifier_ops;

return mmu_notifier_register(&kvm->mmu_notifier, current->mm);

}

#else /* !(CONFIG_MMU_NOTIFIER && KVM_ARCH_WANT_MMU_NOTIFIER) */

static int kvm_init_mmu_notifier(struct kvm *kvm)

{

return 0;

}

#endif /* CONFIG_MMU_NOTIFIER && KVM_ARCH_WANT_MMU_NOTIFIER */

static void kvm_init_memslots_id(struct kvm *kvm)

{

int i;

struct kvm_memslots *slots = kvm->memslots;

for (i = 0; i < KVM_MEM_SLOTS_NUM; i++)

slots->id_to_index[i] = slots->memslots[i].id = i;

}

static struct kvm *kvm_create_vm(unsigned long type)

{

int r, i;

struct kvm *kvm = kvm_arch_alloc_vm();

if (!kvm)

return ERR_PTR(-ENOMEM);

r = kvm_arch_init_vm(kvm, type);

if (r)

goto out_err_nodisable;

r = hardware_enable_all();

if (r)

goto out_err_nodisable;

#ifdef CONFIG_HAVE_KVM_IRQCHIP

INIT_HLIST_HEAD(&kvm->mask_notifier_list);

INIT_HLIST_HEAD(&kvm->irq_ack_notifier_list);

#endif

r = -ENOMEM;

kvm->memslots = kzalloc(sizeof(struct kvm_memslots), GFP_KERNEL);

if (!kvm->memslots)

goto out_err_nosrcu;

kvm_init_memslots_id(kvm);

if (init_srcu_struct(&kvm->srcu))

goto out_err_nosrcu;

for (i = 0; i < KVM_NR_BUSES; i++) {

kvm->buses[i] = kzalloc(sizeof(struct kvm_io_bus),

GFP_KERNEL);

if (!kvm->buses[i])

goto out_err;

}

spin_lock_init(&kvm->mmu_lock);

kvm->mm = current->mm;

atomic_inc(&kvm->mm->mm_count);

kvm_eventfd_init(kvm);

mutex_init(&kvm->lock);

mutex_init(&kvm->irq_lock);

mutex_init(&kvm->slots_lock);

atomic_set(&kvm->users_count, 1);

r = kvm_init_mmu_notifier(kvm);

if (r)

goto out_err;

raw_spin_lock(&kvm_lock);

list_add(&kvm->vm_list, &vm_list);

raw_spin_unlock(&kvm_lock);

return kvm;

out_err:

cleanup_srcu_struct(&kvm->srcu);

out_err_nosrcu:

hardware_disable_all();

out_err_nodisable:

for (i = 0; i < KVM_NR_BUSES; i++)

kfree(kvm->buses[i]);

kfree(kvm->memslots);

kvm_arch_free_vm(kvm);

return ERR_PTR(r);

}

static void kvm_destroy_dirty_bitmap(struct kvm_memory_slot *memslot)

{

if (!memslot->dirty_bitmap)

return;

if (2 * kvm_dirty_bitmap_bytes(memslot) > PAGE_SIZE)

vfree(memslot->dirty_bitmap_head);

else

kfree(memslot->dirty_bitmap_head);

memslot->dirty_bitmap = NULL;

memslot->dirty_bitmap_head = NULL;

}

* Free any memory in @free but not in @dont.

static void kvm_free_physmem_slot(struct kvm_memory_slot *free,

struct kvm_memory_slot *dont)

{

if (!dont || free->rmap != dont->rmap)

vfree(free->rmap);

if (!dont || free->dirty_bitmap != dont->dirty_bitmap)

kvm_destroy_dirty_bitmap(free);

kvm_arch_free_memslot(free, dont);

free->npages = 0;

free->rmap = NULL;

}

void kvm_free_physmem(struct kvm *kvm)

{

struct kvm_memslots *slots = kvm->memslots;

struct kvm_memory_slot *memslot;

kvm_for_each_memslot(memslot, slots)

kvm_free_physmem_slot(memslot, NULL);

kfree(kvm->memslots);

}

static void kvm_destroy_vm(struct kvm *kvm)

{

int i;

struct mm_struct *mm = kvm->mm;

kvm_arch_sync_events(kvm);

raw_spin_lock(&kvm_lock);

list_del(&kvm->vm_list);

raw_spin_unlock(&kvm_lock);

kvm_free_irq_routing(kvm);

for (i = 0; i < KVM_NR_BUSES; i++)

kvm_io_bus_destroy(kvm->buses[i]);

kvm_coalesced_mmio_free(kvm);

#if defined(CONFIG_MMU_NOTIFIER) && defined(KVM_ARCH_WANT_MMU_NOTIFIER)

mmu_notifier_unregister(&kvm->mmu_notifier, kvm->mm);

#else

kvm_arch_flush_shadow(kvm);

#endif

kvm_arch_destroy_vm(kvm);

kvm_free_physmem(kvm);

cleanup_srcu_struct(&kvm->srcu);

kvm_arch_free_vm(kvm);

hardware_disable_all();

mmdrop(mm);

}

void kvm_get_kvm(struct kvm *kvm)

{

atomic_inc(&kvm->users_count);

}

EXPORT_SYMBOL_GPL(kvm_get_kvm);

void kvm_put_kvm(struct kvm *kvm)

{

if (atomic_dec_and_test(&kvm->users_count))

kvm_destroy_vm(kvm);

}

EXPORT_SYMBOL_GPL(kvm_put_kvm);

static int kvm_vm_release(struct inode *inode, struct file *filp)

{

struct kvm *kvm = filp->private_data;

kvm_irqfd_release(kvm);

kvm_put_kvm(kvm);

return 0;

}

* Allocation size is twice as large as the actual dirty bitmap size.

* This makes it possible to do double buffering: see x86's

* kvm_vm_ioctl_get_dirty_log().

static int kvm_create_dirty_bitmap(struct kvm_memory_slot *memslot)

{

#ifndef CONFIG_S390

unsigned long dirty_bytes = 2 * kvm_dirty_bitmap_bytes(memslot);

if (dirty_bytes > PAGE_SIZE)

memslot->dirty_bitmap = vzalloc(dirty_bytes);

else

memslot->dirty_bitmap = kzalloc(dirty_bytes, GFP_KERNEL);

if (!memslot->dirty_bitmap)

return -ENOMEM;

memslot->dirty_bitmap_head = memslot->dirty_bitmap;

memslot->nr_dirty_pages = 0;

#endif /* !CONFIG_S390 */

return 0;

}

static int cmp_memslot(const void *slot1, const void *slot2)

{

struct kvm_memory_slot *s1, *s2;

s1 = (struct kvm_memory_slot *)slot1;

s2 = (struct kvm_memory_slot *)slot2;

if (s1->npages < s2->npages)

return 1;

if (s1->npages > s2->npages)

return -1;

return 0;

}

* Sort the memslots base on its size, so the larger slots

* will get better fit.

static void sort_memslots(struct kvm_memslots *slots)

{

int i;

sort(slots->memslots, KVM_MEM_SLOTS_NUM,

sizeof(struct kvm_memory_slot), cmp_memslot, NULL);

for (i = 0; i < KVM_MEM_SLOTS_NUM; i++)

slots->id_to_index[slots->memslots[i].id] = i;

}

void update_memslots(struct kvm_memslots *slots, struct kvm_memory_slot *new)

{

if (new) {

int id = new->id;

struct kvm_memory_slot *old = id_to_memslot(slots, id);

unsigned long npages = old->npages;

*old = *new;

if (new->npages != npages)

sort_memslots(slots);

}

slots->generation++;

}

* Allocate some memory and give it an address in the guest physical address

* space.

* Discontiguous memory is allowed, mostly for framebuffers.

* Must be called holding mmap_sem for write.

int __kvm_set_memory_region(struct kvm *kvm,

struct kvm_userspace_memory_region *mem,

int user_alloc)

{

int r;

gfn_t base_gfn;

unsigned long npages;

unsigned long i;

struct kvm_memory_slot *memslot;

struct kvm_memory_slot old, new;

struct kvm_memslots *slots, *old_memslots;

r = -EINVAL;

/* General sanity checks */

if (mem->memory_size & (PAGE_SIZE - 1))

goto out;

if (mem->guest_phys_addr & (PAGE_SIZE - 1))

goto out;

/* We can read the guest memory with __xxx_user() later on. */

if (user_alloc &&

((mem->userspace_addr & (PAGE_SIZE - 1)) ||

!access_ok(VERIFY_WRITE,

(void __user *)(unsigned long)mem->userspace_addr,

mem->memory_size)))

goto out;

if (mem->slot >= KVM_MEM_SLOTS_NUM)

goto out;

if (mem->guest_phys_addr + mem->memory_size < mem->guest_phys_addr)

goto out;

memslot = id_to_memslot(kvm->memslots, mem->slot);

base_gfn = mem->guest_phys_addr >> PAGE_SHIFT;

npages = mem->memory_size >> PAGE_SHIFT;

r = -EINVAL;

if (npages > KVM_MEM_MAX_NR_PAGES)

goto out;

if (!npages)

mem->flags &= ~KVM_MEM_LOG_DIRTY_PAGES;

new = old = *memslot;

new.id = mem->slot;

new.base_gfn = base_gfn;

new.npages = npages;

new.flags = mem->flags;

/* Disallow changing a memory slot's size. */

r = -EINVAL;

if (npages && old.npages && npages != old.npages)

goto out_free;

/* Check for overlaps */

r = -EEXIST;

for (i = 0; i < KVM_MEMORY_SLOTS; ++i) {

struct kvm_memory_slot *s = &kvm->memslots->memslots[i];

if (s == memslot || !s->npages)

continue;

if (!((base_gfn + npages <= s->base_gfn) ||

(base_gfn >= s->base_gfn + s->npages)))

goto out_free;

}

/* Free page dirty bitmap if unneeded */

if (!(new.flags & KVM_MEM_LOG_DIRTY_PAGES))

new.dirty_bitmap = NULL;

r = -ENOMEM;

/* Allocate if a slot is being created */

if (npages && !old.npages) {

new.user_alloc = user_alloc;

new.userspace_addr = mem->userspace_addr;

#ifndef CONFIG_S390

new.rmap = vzalloc(npages * sizeof(*new.rmap));

if (!new.rmap)

goto out_free;

#endif /* not defined CONFIG_S390 */

if (kvm_arch_create_memslot(&new, npages))

goto out_free;

}

/* Allocate page dirty bitmap if needed */

if ((new.flags & KVM_MEM_LOG_DIRTY_PAGES) && !new.dirty_bitmap) {

if (kvm_create_dirty_bitmap(&new) < 0)

goto out_free;

/* destroy any largepage mappings for dirty tracking */

}

if (!npages) {

struct kvm_memory_slot *slot;

r = -ENOMEM;

slots = kmemdup(kvm->memslots, sizeof(struct kvm_memslots),

GFP_KERNEL);

if (!slots)

goto out_free;

slot = id_to_memslot(slots, mem->slot);

slot->flags |= KVM_MEMSLOT_INVALID;

update_memslots(slots, NULL);

old_memslots = kvm->memslots;

rcu_assign_pointer(kvm->memslots, slots);

synchronize_srcu_expedited(&kvm->srcu);

/* From this point no new shadow pages pointing to a deleted

* memslot will be created.

* validation of sp->gfn happens in:

* - gfn_to_hva (kvm_read_guest, gfn_to_pfn)

* - kvm_is_visible_gfn (mmu_check_roots)

kvm_arch_flush_shadow(kvm);

kfree(old_memslots);

}

r = kvm_arch_prepare_memory_region(kvm, &new, old, mem, user_alloc);

if (r)

goto out_free;

/* map/unmap the pages in iommu page table */

if (npages) {

r = kvm_iommu_map_pages(kvm, &new);

if (r)

goto out_free;

} else

kvm_iommu_unmap_pages(kvm, &old);

r = -ENOMEM;

slots = kmemdup(kvm->memslots, sizeof(struct kvm_memslots),

GFP_KERNEL);

if (!slots)

goto out_free;

/* actual memory is freed via old in kvm_free_physmem_slot below */

if (!npages) {

new.rmap = NULL;

new.dirty_bitmap = NULL;

memset(&new.arch, 0, sizeof(new.arch));

}

update_memslots(slots, &new);

old_memslots = kvm->memslots;

rcu_assign_pointer(kvm->memslots, slots);

synchronize_srcu_expedited(&kvm->srcu);

kvm_arch_commit_memory_region(kvm, mem, old, user_alloc);

* If the new memory slot is created, we need to clear all

* mmio sptes.

if (npages && old.base_gfn != mem->guest_phys_addr >> PAGE_SHIFT)

kvm_arch_flush_shadow(kvm);

kvm_free_physmem_slot(&old, &new);

kfree(old_memslots);

return 0;

out_free:

kvm_free_physmem_slot(&new, &old);

out:

return r;

}

EXPORT_SYMBOL_GPL(__kvm_set_memory_region);

int kvm_set_memory_region(struct kvm *kvm,

struct kvm_userspace_memory_region *mem,

int user_alloc)

{

int r;

mutex_lock(&kvm->slots_lock);

r = __kvm_set_memory_region(kvm, mem, user_alloc);

mutex_unlock(&kvm->slots_lock);

return r;

}

EXPORT_SYMBOL_GPL(kvm_set_memory_region);

int kvm_vm_ioctl_set_memory_region(struct kvm *kvm,

struct

kvm_userspace_memory_region *mem,

int user_alloc)

{

if (mem->slot >= KVM_MEMORY_SLOTS)

return -EINVAL;

return kvm_set_memory_region(kvm, mem, user_alloc);

}

int kvm_get_dirty_log(struct kvm *kvm,

struct kvm_dirty_log *log, int *is_dirty)

{

struct kvm_memory_slot *memslot;

int r, i;

unsigned long n;

unsigned long any = 0;

r = -EINVAL;

if (log->slot >= KVM_MEMORY_SLOTS)

goto out;

memslot = id_to_memslot(kvm->memslots, log->slot);

r = -ENOENT;

if (!memslot->dirty_bitmap)

goto out;

n = kvm_dirty_bitmap_bytes(memslot);

for (i = 0; !any && i < n/sizeof(long); ++i)

any = memslot->dirty_bitmap[i];

r = -EFAULT;

if (copy_to_user(log->dirty_bitmap, memslot->dirty_bitmap, n))

goto out;

if (any)

*is_dirty = 1;

r = 0;

out:

return r;

}

bool kvm_largepages_enabled(void)

{

return largepages_enabled;

}

void kvm_disable_largepages(void)

{

largepages_enabled = false;

}

EXPORT_SYMBOL_GPL(kvm_disable_largepages);

int is_error_page(struct page *page)

{

return page == bad_page || page == hwpoison_page || page == fault_page;

}

EXPORT_SYMBOL_GPL(is_error_page);

int is_error_pfn(pfn_t pfn)

{

return pfn == bad_pfn || pfn == hwpoison_pfn || pfn == fault_pfn;

}

EXPORT_SYMBOL_GPL(is_error_pfn);

int is_hwpoison_pfn(pfn_t pfn)

{

return pfn == hwpoison_pfn;

}

EXPORT_SYMBOL_GPL(is_hwpoison_pfn);

int is_fault_pfn(pfn_t pfn)

{

return pfn == fault_pfn;

}

EXPORT_SYMBOL_GPL(is_fault_pfn);

int is_noslot_pfn(pfn_t pfn)

{

return pfn == bad_pfn;

}

EXPORT_SYMBOL_GPL(is_noslot_pfn);

int is_invalid_pfn(pfn_t pfn)

{

return pfn == hwpoison_pfn || pfn == fault_pfn;

}

EXPORT_SYMBOL_GPL(is_invalid_pfn);

static inline unsigned long bad_hva(void)

{

return PAGE_OFFSET;

}

int kvm_is_error_hva(unsigned long addr)

{

return addr == bad_hva();

}

EXPORT_SYMBOL_GPL(kvm_is_error_hva);

struct kvm_memory_slot *gfn_to_memslot(struct kvm *kvm, gfn_t gfn)

{

return __gfn_to_memslot(kvm_memslots(kvm), gfn);

}

EXPORT_SYMBOL_GPL(gfn_to_memslot);

int kvm_is_visible_gfn(struct kvm *kvm, gfn_t gfn)

{

struct kvm_memory_slot *memslot = gfn_to_memslot(kvm, gfn);

if (!memslot || memslot->id >= KVM_MEMORY_SLOTS ||

memslot->flags & KVM_MEMSLOT_INVALID)

return 0;

return 1;

}

EXPORT_SYMBOL_GPL(kvm_is_visible_gfn);

unsigned long kvm_host_page_size(struct kvm *kvm, gfn_t gfn)

{

struct vm_area_struct *vma;

unsigned long addr, size;

size = PAGE_SIZE;

addr = gfn_to_hva(kvm, gfn);

if (kvm_is_error_hva(addr))

View remainder of file in raw view

SmartisanOS_Kernel_Source/virt/kvm/kvm_main.c at master · ActiveProgram/SmartisanOS_Kernel_Source · GitHub

Repository navigation

Expand file tree

Breadcrumbs

kvm_main.c

Latest commit

History

Breadcrumbs

kvm_main.c

File metadata and controls