arm.c 23.3 KB
Newer Older
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
/*
 * Copyright (C) 2012 - Virtual Open Systems and Columbia University
 * Author: Christoffer Dall <c.dall@virtualopensystems.com>
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License, version 2, as
 * published by the Free Software Foundation.
 *
 * This program is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 * GNU General Public License for more details.
 *
 * You should have received a copy of the GNU General Public License
 * along with this program; if not, write to the Free Software
 * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301, USA.
 */

#include <linux/errno.h>
#include <linux/err.h>
#include <linux/kvm_host.h>
#include <linux/module.h>
#include <linux/vmalloc.h>
#include <linux/fs.h>
#include <linux/mman.h>
#include <linux/sched.h>
27
#include <linux/kvm.h>
28 29 30 31 32 33 34 35 36 37
#include <trace/events/kvm.h>

#define CREATE_TRACE_POINTS
#include "trace.h"

#include <asm/unified.h>
#include <asm/uaccess.h>
#include <asm/ptrace.h>
#include <asm/mman.h>
#include <asm/cputype.h>
38
#include <asm/tlbflush.h>
39
#include <asm/cacheflush.h>
40 41 42 43
#include <asm/virt.h>
#include <asm/kvm_arm.h>
#include <asm/kvm_asm.h>
#include <asm/kvm_mmu.h>
44
#include <asm/kvm_emulate.h>
45
#include <asm/kvm_coproc.h>
46
#include <asm/kvm_psci.h>
47
#include <asm/opcodes.h>
48 49 50 51 52

#ifdef REQUIRES_VIRT
__asm__(".arch_extension	virt");
#endif

53 54 55 56
static DEFINE_PER_CPU(unsigned long, kvm_arm_hyp_stack_page);
static struct vfp_hard_struct __percpu *kvm_host_vfp_state;
static unsigned long hyp_default_vectors;

57 58 59 60
/* The VMID used in the VTTBR */
static atomic64_t kvm_vmid_gen = ATOMIC64_INIT(1);
static u8 kvm_next_vmid;
static DEFINE_SPINLOCK(kvm_vmid_lock);
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
int kvm_arch_hardware_enable(void *garbage)
{
	return 0;
}

int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu)
{
	return kvm_vcpu_exiting_guest_mode(vcpu) == IN_GUEST_MODE;
}

void kvm_arch_hardware_disable(void *garbage)
{
}

int kvm_arch_hardware_setup(void)
{
	return 0;
}

void kvm_arch_hardware_unsetup(void)
{
}

void kvm_arch_check_processor_compat(void *rtn)
{
	*(int *)rtn = 0;
}

void kvm_arch_sync_events(struct kvm *kvm)
{
}

94 95 96 97
/**
 * kvm_arch_init_vm - initializes a VM data structure
 * @kvm:	pointer to the KVM struct
 */
98 99
int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
{
100 101
	int ret = 0;

102 103 104
	if (type)
		return -EINVAL;

105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120
	ret = kvm_alloc_stage2_pgd(kvm);
	if (ret)
		goto out_fail_alloc;

	ret = create_hyp_mappings(kvm, kvm + 1);
	if (ret)
		goto out_free_stage2_pgd;

	/* Mark the initial VMID generation invalid */
	kvm->arch.vmid_gen = 0;

	return ret;
out_free_stage2_pgd:
	kvm_free_stage2_pgd(kvm);
out_fail_alloc:
	return ret;
121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137
}

int kvm_arch_vcpu_fault(struct kvm_vcpu *vcpu, struct vm_fault *vmf)
{
	return VM_FAULT_SIGBUS;
}

void kvm_arch_free_memslot(struct kvm_memory_slot *free,
			   struct kvm_memory_slot *dont)
{
}

int kvm_arch_create_memslot(struct kvm_memory_slot *slot, unsigned long npages)
{
	return 0;
}

138 139 140 141
/**
 * kvm_arch_destroy_vm - destroy the VM data structure
 * @kvm:	pointer to the KVM struct
 */
142 143 144 145
void kvm_arch_destroy_vm(struct kvm *kvm)
{
	int i;

146 147
	kvm_free_stage2_pgd(kvm);

148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163
	for (i = 0; i < KVM_MAX_VCPUS; ++i) {
		if (kvm->vcpus[i]) {
			kvm_arch_vcpu_free(kvm->vcpus[i]);
			kvm->vcpus[i] = NULL;
		}
	}
}

int kvm_dev_ioctl_check_extension(long ext)
{
	int r;
	switch (ext) {
	case KVM_CAP_USER_MEMORY:
	case KVM_CAP_SYNC_MMU:
	case KVM_CAP_DESTROY_MEMORY_REGION_WORKS:
	case KVM_CAP_ONE_REG:
164
	case KVM_CAP_ARM_PSCI:
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
		r = 1;
		break;
	case KVM_CAP_COALESCED_MMIO:
		r = KVM_COALESCED_MMIO_PAGE_OFFSET;
		break;
	case KVM_CAP_NR_VCPUS:
		r = num_online_cpus();
		break;
	case KVM_CAP_MAX_VCPUS:
		r = KVM_MAX_VCPUS;
		break;
	default:
		r = 0;
		break;
	}
	return r;
}

long kvm_arch_dev_ioctl(struct file *filp,
			unsigned int ioctl, unsigned long arg)
{
	return -EINVAL;
}

int kvm_arch_set_memory_region(struct kvm *kvm,
			       struct kvm_userspace_memory_region *mem,
			       struct kvm_memory_slot old,
			       int user_alloc)
{
	return 0;
}

int kvm_arch_prepare_memory_region(struct kvm *kvm,
				   struct kvm_memory_slot *memslot,
				   struct kvm_memory_slot old,
				   struct kvm_userspace_memory_region *mem,
				   int user_alloc)
{
	return 0;
}

void kvm_arch_commit_memory_region(struct kvm *kvm,
				   struct kvm_userspace_memory_region *mem,
				   struct kvm_memory_slot old,
				   int user_alloc)
{
}

void kvm_arch_flush_shadow_all(struct kvm *kvm)
{
}

void kvm_arch_flush_shadow_memslot(struct kvm *kvm,
				   struct kvm_memory_slot *slot)
{
}

struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, unsigned int id)
{
	int err;
	struct kvm_vcpu *vcpu;

	vcpu = kmem_cache_zalloc(kvm_vcpu_cache, GFP_KERNEL);
	if (!vcpu) {
		err = -ENOMEM;
		goto out;
	}

	err = kvm_vcpu_init(vcpu, kvm, id);
	if (err)
		goto free_vcpu;

237 238 239 240
	err = create_hyp_mappings(vcpu, vcpu + 1);
	if (err)
		goto vcpu_uninit;

241
	return vcpu;
242 243
vcpu_uninit:
	kvm_vcpu_uninit(vcpu);
244 245 246 247 248 249 250 251 252 253 254 255 256
free_vcpu:
	kmem_cache_free(kvm_vcpu_cache, vcpu);
out:
	return ERR_PTR(err);
}

int kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu)
{
	return 0;
}

void kvm_arch_vcpu_free(struct kvm_vcpu *vcpu)
{
257 258
	kvm_mmu_free_memory_caches(vcpu);
	kmem_cache_free(kvm_vcpu_cache, vcpu);
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
}

void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu)
{
	kvm_arch_vcpu_free(vcpu);
}

int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu)
{
	return 0;
}

int __attribute_const__ kvm_target_cpu(void)
{
	unsigned long implementor = read_cpuid_implementor();
	unsigned long part_number = read_cpuid_part_number();

	if (implementor != ARM_CPU_IMP_ARM)
		return -EINVAL;

	switch (part_number) {
	case ARM_CPU_PART_CORTEX_A15:
		return KVM_ARM_TARGET_CORTEX_A15;
	default:
		return -EINVAL;
	}
}

int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
{
289 290
	/* Force users to call KVM_ARM_VCPU_INIT */
	vcpu->arch.target = -1;
291 292 293 294 295 296 297 298 299
	return 0;
}

void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu)
{
}

void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
{
300
	vcpu->cpu = cpu;
301
	vcpu->arch.vfp_host = this_cpu_ptr(kvm_host_vfp_state);
302 303 304 305 306 307 308 309 310

	/*
	 * Check whether this vcpu requires the cache to be flushed on
	 * this physical CPU. This is a consequence of doing dcache
	 * operations by set/way on this vcpu. We do it here to be in
	 * a non-preemptible section.
	 */
	if (cpumask_test_and_clear_cpu(cpu, &vcpu->arch.require_dcache_flush))
		flush_cache_all(); /* We'd really want v7_flush_dcache_all() */
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
}

void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
{
}

int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu,
					struct kvm_guest_debug *dbg)
{
	return -EINVAL;
}


int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu,
				    struct kvm_mp_state *mp_state)
{
	return -EINVAL;
}

int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu,
				    struct kvm_mp_state *mp_state)
{
	return -EINVAL;
}

336 337 338 339 340 341 342
/**
 * kvm_arch_vcpu_runnable - determine if the vcpu can be scheduled
 * @v:		The VCPU pointer
 *
 * If the guest CPU is not waiting for interrupts or an interrupt line is
 * asserted, the CPU is by definition runnable.
 */
343 344
int kvm_arch_vcpu_runnable(struct kvm_vcpu *v)
{
345
	return !!v->arch.irq_lines;
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
/* Just ensure a guest exit from a particular CPU */
static void exit_vm_noop(void *info)
{
}

void force_vm_exit(const cpumask_t *mask)
{
	smp_call_function_many(mask, exit_vm_noop, NULL, true);
}

/**
 * need_new_vmid_gen - check that the VMID is still valid
 * @kvm: The VM's VMID to checkt
 *
 * return true if there is a new generation of VMIDs being used
 *
 * The hardware supports only 256 values with the value zero reserved for the
 * host, so we check if an assigned value belongs to a previous generation,
 * which which requires us to assign a new value. If we're the first to use a
 * VMID for the new generation, we must flush necessary caches and TLBs on all
 * CPUs.
 */
static bool need_new_vmid_gen(struct kvm *kvm)
{
	return unlikely(kvm->arch.vmid_gen != atomic64_read(&kvm_vmid_gen));
}

/**
 * update_vttbr - Update the VTTBR with a valid VMID before the guest runs
 * @kvm	The guest that we are about to run
 *
 * Called from kvm_arch_vcpu_ioctl_run before entering the guest to ensure the
 * VM has a valid VMID, otherwise assigns a new one and flushes corresponding
 * caches and TLBs.
 */
static void update_vttbr(struct kvm *kvm)
{
	phys_addr_t pgd_phys;
	u64 vmid;

	if (!need_new_vmid_gen(kvm))
		return;

	spin_lock(&kvm_vmid_lock);

	/*
	 * We need to re-check the vmid_gen here to ensure that if another vcpu
	 * already allocated a valid vmid for this vm, then this vcpu should
	 * use the same vmid.
	 */
	if (!need_new_vmid_gen(kvm)) {
		spin_unlock(&kvm_vmid_lock);
		return;
	}

	/* First user of a new VMID generation? */
	if (unlikely(kvm_next_vmid == 0)) {
		atomic64_inc(&kvm_vmid_gen);
		kvm_next_vmid = 1;

		/*
		 * On SMP we know no other CPUs can use this CPU's or each
		 * other's VMID after force_vm_exit returns since the
		 * kvm_vmid_lock blocks them from reentry to the guest.
		 */
		force_vm_exit(cpu_all_mask);
		/*
		 * Now broadcast TLB + ICACHE invalidation over the inner
		 * shareable domain to make sure all data structures are
		 * clean.
		 */
		kvm_call_hyp(__kvm_flush_vm_context);
	}

	kvm->arch.vmid_gen = atomic64_read(&kvm_vmid_gen);
	kvm->arch.vmid = kvm_next_vmid;
	kvm_next_vmid++;

	/* update vttbr to be used with the new vmid */
	pgd_phys = virt_to_phys(kvm->arch.pgd);
	vmid = ((u64)(kvm->arch.vmid) << VTTBR_VMID_SHIFT) & VTTBR_VMID_MASK;
	kvm->arch.vttbr = pgd_phys & VTTBR_BADDR_MASK;
	kvm->arch.vttbr |= vmid;

	spin_unlock(&kvm_vmid_lock);
}

435 436 437 438 439 440 441 442 443 444 445 446 447
static int handle_svc_hyp(struct kvm_vcpu *vcpu, struct kvm_run *run)
{
	/* SVC called from Hyp mode should never get here */
	kvm_debug("SVC called from Hyp mode shouldn't go here\n");
	BUG();
	return -EINVAL; /* Squash warning */
}

static int handle_hvc(struct kvm_vcpu *vcpu, struct kvm_run *run)
{
	trace_kvm_hvc(*vcpu_pc(vcpu), *vcpu_reg(vcpu, 0),
		      vcpu->arch.hsr & HSR_HVC_IMM_MASK);

448 449 450
	if (kvm_psci_call(vcpu))
		return 1;

451 452 453 454 455 456
	kvm_inject_undefined(vcpu);
	return 1;
}

static int handle_smc(struct kvm_vcpu *vcpu, struct kvm_run *run)
{
457 458 459
	if (kvm_psci_call(vcpu))
		return 1;

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
	kvm_inject_undefined(vcpu);
	return 1;
}

static int handle_pabt_hyp(struct kvm_vcpu *vcpu, struct kvm_run *run)
{
	/* The hypervisor should never cause aborts */
	kvm_err("Prefetch Abort taken from Hyp mode at %#08x (HSR: %#08x)\n",
		vcpu->arch.hxfar, vcpu->arch.hsr);
	return -EFAULT;
}

static int handle_dabt_hyp(struct kvm_vcpu *vcpu, struct kvm_run *run)
{
	/* This is either an error in the ws. code or an external abort */
	kvm_err("Data Abort taken from Hyp mode at %#08x (HSR: %#08x)\n",
		vcpu->arch.hxfar, vcpu->arch.hsr);
	return -EFAULT;
}

typedef int (*exit_handle_fn)(struct kvm_vcpu *, struct kvm_run *);
static exit_handle_fn arm_exit_handlers[] = {
	[HSR_EC_WFI]		= kvm_handle_wfi,
	[HSR_EC_CP15_32]	= kvm_handle_cp15_32,
	[HSR_EC_CP15_64]	= kvm_handle_cp15_64,
	[HSR_EC_CP14_MR]	= kvm_handle_cp14_access,
	[HSR_EC_CP14_LS]	= kvm_handle_cp14_load_store,
	[HSR_EC_CP14_64]	= kvm_handle_cp14_access,
	[HSR_EC_CP_0_13]	= kvm_handle_cp_0_13_access,
	[HSR_EC_CP10_ID]	= kvm_handle_cp10_id,
	[HSR_EC_SVC_HYP]	= handle_svc_hyp,
	[HSR_EC_HVC]		= handle_hvc,
	[HSR_EC_SMC]		= handle_smc,
	[HSR_EC_IABT]		= kvm_handle_guest_abort,
	[HSR_EC_IABT_HYP]	= handle_pabt_hyp,
	[HSR_EC_DABT]		= kvm_handle_guest_abort,
	[HSR_EC_DABT_HYP]	= handle_dabt_hyp,
};

/*
 * A conditional instruction is allowed to trap, even though it
 * wouldn't be executed.  So let's re-implement the hardware, in
 * software!
 */
static bool kvm_condition_valid(struct kvm_vcpu *vcpu)
{
	unsigned long cpsr, cond, insn;

	/*
	 * Exception Code 0 can only happen if we set HCR.TGE to 1, to
	 * catch undefined instructions, and then we won't get past
	 * the arm_exit_handlers test anyway.
	 */
	BUG_ON(((vcpu->arch.hsr & HSR_EC) >> HSR_EC_SHIFT) == 0);

	/* Top two bits non-zero?  Unconditional. */
	if (vcpu->arch.hsr >> 30)
		return true;

	cpsr = *vcpu_cpsr(vcpu);

	/* Is condition field valid? */
	if ((vcpu->arch.hsr & HSR_CV) >> HSR_CV_SHIFT)
		cond = (vcpu->arch.hsr & HSR_COND) >> HSR_COND_SHIFT;
	else {
		/* This can happen in Thumb mode: examine IT state. */
		unsigned long it;

		it = ((cpsr >> 8) & 0xFC) | ((cpsr >> 25) & 0x3);

		/* it == 0 => unconditional. */
		if (it == 0)
			return true;

		/* The cond for this insn works out as the top 4 bits. */
		cond = (it >> 4);
	}

	/* Shift makes it look like an ARM-mode instruction */
	insn = cond << 28;
	return arm_check_condition(insn, cpsr) != ARM_OPCODE_CONDTEST_FAIL;
}

543 544 545 546 547 548 549
/*
 * Return > 0 to return to guest, < 0 on error, 0 (and set exit_reason) on
 * proper exit to QEMU.
 */
static int handle_exit(struct kvm_vcpu *vcpu, struct kvm_run *run,
		       int exception_index)
{
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
	unsigned long hsr_ec;

	switch (exception_index) {
	case ARM_EXCEPTION_IRQ:
		return 1;
	case ARM_EXCEPTION_UNDEFINED:
		kvm_err("Undefined exception in Hyp mode at: %#08x\n",
			vcpu->arch.hyp_pc);
		BUG();
		panic("KVM: Hypervisor undefined exception!\n");
	case ARM_EXCEPTION_DATA_ABORT:
	case ARM_EXCEPTION_PREF_ABORT:
	case ARM_EXCEPTION_HVC:
		hsr_ec = (vcpu->arch.hsr & HSR_EC) >> HSR_EC_SHIFT;

		if (hsr_ec >= ARRAY_SIZE(arm_exit_handlers)
		    || !arm_exit_handlers[hsr_ec]) {
			kvm_err("Unkown exception class: %#08lx, "
				"hsr: %#08x\n", hsr_ec,
				(unsigned int)vcpu->arch.hsr);
			BUG();
		}

		/*
		 * See ARM ARM B1.14.1: "Hyp traps on instructions
		 * that fail their condition code check"
		 */
		if (!kvm_condition_valid(vcpu)) {
			bool is_wide = vcpu->arch.hsr & HSR_IL;
			kvm_skip_instr(vcpu, is_wide);
			return 1;
		}

		return arm_exit_handlers[hsr_ec](vcpu, run);
	default:
		kvm_pr_unimpl("Unsupported exception type: %d",
			      exception_index);
		run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
		return 0;
	}
590 591 592 593 594 595 596 597
}

static int kvm_vcpu_first_run_init(struct kvm_vcpu *vcpu)
{
	if (likely(vcpu->arch.has_run_once))
		return 0;

	vcpu->arch.has_run_once = true;
598 599 600 601 602 603 604 605 606 607

	/*
	 * Handle the "start in power-off" case by calling into the
	 * PSCI code.
	 */
	if (test_and_clear_bit(KVM_ARM_VCPU_POWER_OFF, vcpu->arch.features)) {
		*vcpu_reg(vcpu, 0) = KVM_PSCI_FN_CPU_OFF;
		kvm_psci_call(vcpu);
	}

608 609 610
	return 0;
}

611 612 613 614 615 616 617
static void vcpu_pause(struct kvm_vcpu *vcpu)
{
	wait_queue_head_t *wq = kvm_arch_vcpu_wq(vcpu);

	wait_event_interruptible(*wq, !vcpu->arch.pause);
}

618 619 620 621 622 623 624 625 626 627 628
/**
 * kvm_arch_vcpu_ioctl_run - the main VCPU run function to execute guest code
 * @vcpu:	The VCPU pointer
 * @run:	The kvm_run structure pointer used for userspace state exchange
 *
 * This function is called through the VCPU_RUN ioctl called from user space. It
 * will execute VM code in a loop until the time slice for the process is used
 * or some emulation is needed from user space in which case the function will
 * return with return value 0 and with the kvm_run structure filled in with the
 * required data for the requested emulation.
 */
629 630
int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
{
631 632 633 634 635 636 637 638 639 640 641
	int ret;
	sigset_t sigsaved;

	/* Make sure they initialize the vcpu with KVM_ARM_VCPU_INIT */
	if (unlikely(vcpu->arch.target < 0))
		return -ENOEXEC;

	ret = kvm_vcpu_first_run_init(vcpu);
	if (ret)
		return ret;

C
Christoffer Dall 已提交
642 643 644 645 646 647
	if (run->exit_reason == KVM_EXIT_MMIO) {
		ret = kvm_handle_mmio_return(vcpu, vcpu->run);
		if (ret)
			return ret;
	}

648 649 650 651 652 653 654 655 656 657 658 659 660
	if (vcpu->sigset_active)
		sigprocmask(SIG_SETMASK, &vcpu->sigset, &sigsaved);

	ret = 1;
	run->exit_reason = KVM_EXIT_UNKNOWN;
	while (ret > 0) {
		/*
		 * Check conditions before entering the guest
		 */
		cond_resched();

		update_vttbr(vcpu->kvm);

661 662 663
		if (vcpu->arch.pause)
			vcpu_pause(vcpu);

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
		local_irq_disable();

		/*
		 * Re-check atomic conditions
		 */
		if (signal_pending(current)) {
			ret = -EINTR;
			run->exit_reason = KVM_EXIT_INTR;
		}

		if (ret <= 0 || need_new_vmid_gen(vcpu->kvm)) {
			local_irq_enable();
			continue;
		}

		/**************************************************************
		 * Enter the guest
		 */
		trace_kvm_entry(*vcpu_pc(vcpu));
		kvm_guest_enter();
		vcpu->mode = IN_GUEST_MODE;

		ret = kvm_call_hyp(__kvm_vcpu_run, vcpu);

		vcpu->mode = OUTSIDE_GUEST_MODE;
689
		vcpu->arch.last_pcpu = smp_processor_id();
690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713
		kvm_guest_exit();
		trace_kvm_exit(*vcpu_pc(vcpu));
		/*
		 * We may have taken a host interrupt in HYP mode (ie
		 * while executing the guest). This interrupt is still
		 * pending, as we haven't serviced it yet!
		 *
		 * We're now back in SVC mode, with interrupts
		 * disabled.  Enabling the interrupts now will have
		 * the effect of taking the interrupt again, in SVC
		 * mode this time.
		 */
		local_irq_enable();

		/*
		 * Back from guest
		 *************************************************************/

		ret = handle_exit(vcpu, run, ret);
	}

	if (vcpu->sigset_active)
		sigprocmask(SIG_SETMASK, &sigsaved, NULL);
	return ret;
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
static int vcpu_interrupt_line(struct kvm_vcpu *vcpu, int number, bool level)
{
	int bit_index;
	bool set;
	unsigned long *ptr;

	if (number == KVM_ARM_IRQ_CPU_IRQ)
		bit_index = __ffs(HCR_VI);
	else /* KVM_ARM_IRQ_CPU_FIQ */
		bit_index = __ffs(HCR_VF);

	ptr = (unsigned long *)&vcpu->arch.irq_lines;
	if (level)
		set = test_and_set_bit(bit_index, ptr);
	else
		set = test_and_clear_bit(bit_index, ptr);

	/*
	 * If we didn't change anything, no need to wake up or kick other CPUs
	 */
	if (set == level)
		return 0;

	/*
	 * The vcpu irq_lines field was updated, wake up sleeping VCPUs and
	 * trigger a world-switch round on the running physical CPU to set the
	 * virtual IRQ/FIQ fields in the HCR appropriately.
	 */
	kvm_vcpu_kick(vcpu);

	return 0;
}

int kvm_vm_ioctl_irq_line(struct kvm *kvm, struct kvm_irq_level *irq_level)
{
	u32 irq = irq_level->irq;
	unsigned int irq_type, vcpu_idx, irq_num;
	int nrcpus = atomic_read(&kvm->online_vcpus);
	struct kvm_vcpu *vcpu = NULL;
	bool level = irq_level->level;

	irq_type = (irq >> KVM_ARM_IRQ_TYPE_SHIFT) & KVM_ARM_IRQ_TYPE_MASK;
	vcpu_idx = (irq >> KVM_ARM_IRQ_VCPU_SHIFT) & KVM_ARM_IRQ_VCPU_MASK;
	irq_num = (irq >> KVM_ARM_IRQ_NUM_SHIFT) & KVM_ARM_IRQ_NUM_MASK;

	trace_kvm_irq_line(irq_type, vcpu_idx, irq_num, irq_level->level);

	if (irq_type != KVM_ARM_IRQ_TYPE_CPU)
		return -EINVAL;

	if (vcpu_idx >= nrcpus)
		return -EINVAL;

	vcpu = kvm_get_vcpu(kvm, vcpu_idx);
	if (!vcpu)
		return -EINVAL;

	if (irq_num > KVM_ARM_IRQ_CPU_FIQ)
		return -EINVAL;

	return vcpu_interrupt_line(vcpu, irq_num, level);
}

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
long kvm_arch_vcpu_ioctl(struct file *filp,
			 unsigned int ioctl, unsigned long arg)
{
	struct kvm_vcpu *vcpu = filp->private_data;
	void __user *argp = (void __user *)arg;

	switch (ioctl) {
	case KVM_ARM_VCPU_INIT: {
		struct kvm_vcpu_init init;

		if (copy_from_user(&init, argp, sizeof(init)))
			return -EFAULT;

		return kvm_vcpu_set_target(vcpu, &init);

	}
	case KVM_SET_ONE_REG:
	case KVM_GET_ONE_REG: {
		struct kvm_one_reg reg;
		if (copy_from_user(&reg, argp, sizeof(reg)))
			return -EFAULT;
		if (ioctl == KVM_SET_ONE_REG)
			return kvm_arm_set_reg(vcpu, &reg);
		else
			return kvm_arm_get_reg(vcpu, &reg);
	}
	case KVM_GET_REG_LIST: {
		struct kvm_reg_list __user *user_list = argp;
		struct kvm_reg_list reg_list;
		unsigned n;

		if (copy_from_user(&reg_list, user_list, sizeof(reg_list)))
			return -EFAULT;
		n = reg_list.n;
		reg_list.n = kvm_arm_num_regs(vcpu);
		if (copy_to_user(user_list, &reg_list, sizeof(reg_list)))
			return -EFAULT;
		if (n < reg_list.n)
			return -E2BIG;
		return kvm_arm_copy_reg_indices(vcpu, user_list->reg);
	}
	default:
		return -EINVAL;
	}
}

int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, struct kvm_dirty_log *log)
{
	return -EINVAL;
}

long kvm_arch_vm_ioctl(struct file *filp,
		       unsigned int ioctl, unsigned long arg)
{
	return -EINVAL;
}

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
static void cpu_init_hyp_mode(void *vector)
{
	unsigned long long pgd_ptr;
	unsigned long pgd_low, pgd_high;
	unsigned long hyp_stack_ptr;
	unsigned long stack_page;
	unsigned long vector_ptr;

	/* Switch from the HYP stub to our own HYP init vector */
	__hyp_set_vectors((unsigned long)vector);

	pgd_ptr = (unsigned long long)kvm_mmu_get_httbr();
	pgd_low = (pgd_ptr & ((1ULL << 32) - 1));
	pgd_high = (pgd_ptr >> 32ULL);
	stack_page = __get_cpu_var(kvm_arm_hyp_stack_page);
	hyp_stack_ptr = stack_page + PAGE_SIZE;
	vector_ptr = (unsigned long)__kvm_hyp_vector;

	/*
	 * Call initialization code, and switch to the full blown
	 * HYP code. The init code doesn't need to preserve these registers as
	 * r1-r3 and r12 are already callee save according to the AAPCS.
	 * Note that we slightly misuse the prototype by casing the pgd_low to
	 * a void *.
	 */
	kvm_call_hyp((void *)pgd_low, pgd_high, hyp_stack_ptr, vector_ptr);
}

/**
 * Inits Hyp-mode on all online CPUs
 */
static int init_hyp_mode(void)
{
	phys_addr_t init_phys_addr;
	int cpu;
	int err = 0;

	/*
	 * Allocate Hyp PGD and setup Hyp identity mapping
	 */
	err = kvm_mmu_init();
	if (err)
		goto out_err;

	/*
	 * It is probably enough to obtain the default on one
	 * CPU. It's unlikely to be different on the others.
	 */
	hyp_default_vectors = __hyp_get_vectors();

	/*
	 * Allocate stack pages for Hypervisor-mode
	 */
	for_each_possible_cpu(cpu) {
		unsigned long stack_page;

		stack_page = __get_free_page(GFP_KERNEL);
		if (!stack_page) {
			err = -ENOMEM;
			goto out_free_stack_pages;
		}

		per_cpu(kvm_arm_hyp_stack_page, cpu) = stack_page;
	}

	/*
	 * Execute the init code on each CPU.
	 *
	 * Note: The stack is not mapped yet, so don't do anything else than
	 * initializing the hypervisor mode on each CPU using a local stack
	 * space for temporary storage.
	 */
	init_phys_addr = virt_to_phys(__kvm_hyp_init);
	for_each_online_cpu(cpu) {
		smp_call_function_single(cpu, cpu_init_hyp_mode,
					 (void *)(long)init_phys_addr, 1);
	}

	/*
	 * Unmap the identity mapping
	 */
	kvm_clear_hyp_idmap();

	/*
	 * Map the Hyp-code called directly from the host
	 */
	err = create_hyp_mappings(__kvm_hyp_code_start, __kvm_hyp_code_end);
	if (err) {
		kvm_err("Cannot map world-switch code\n");
		goto out_free_mappings;
	}

	/*
	 * Map the Hyp stack pages
	 */
	for_each_possible_cpu(cpu) {
		char *stack_page = (char *)per_cpu(kvm_arm_hyp_stack_page, cpu);
		err = create_hyp_mappings(stack_page, stack_page + PAGE_SIZE);

		if (err) {
			kvm_err("Cannot map hyp stack\n");
			goto out_free_mappings;
		}
	}

	/*
	 * Map the host VFP structures
	 */
	kvm_host_vfp_state = alloc_percpu(struct vfp_hard_struct);
	if (!kvm_host_vfp_state) {
		err = -ENOMEM;
		kvm_err("Cannot allocate host VFP state\n");
		goto out_free_mappings;
	}

	for_each_possible_cpu(cpu) {
		struct vfp_hard_struct *vfp;

		vfp = per_cpu_ptr(kvm_host_vfp_state, cpu);
		err = create_hyp_mappings(vfp, vfp + 1);

		if (err) {
			kvm_err("Cannot map host VFP state: %d\n", err);
			goto out_free_vfp;
		}
	}

	kvm_info("Hyp mode initialized successfully\n");
	return 0;
out_free_vfp:
	free_percpu(kvm_host_vfp_state);
out_free_mappings:
	free_hyp_pmds();
out_free_stack_pages:
	for_each_possible_cpu(cpu)
		free_page(per_cpu(kvm_arm_hyp_stack_page, cpu));
out_err:
	kvm_err("error initializing Hyp mode: %d\n", err);
	return err;
}

/**
 * Initialize Hyp-mode and memory mappings on all CPUs.
 */
980 981
int kvm_arch_init(void *opaque)
{
982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997
	int err;

	if (!is_hyp_mode_available()) {
		kvm_err("HYP mode not available\n");
		return -ENODEV;
	}

	if (kvm_target_cpu() < 0) {
		kvm_err("Target CPU not supported!\n");
		return -ENODEV;
	}

	err = init_hyp_mode();
	if (err)
		goto out_err;

998
	kvm_coproc_table_init();
999
	return 0;
1000 1001
out_err:
	return err;
1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015
}

/* NOP: Compiling as a module not supported */
void kvm_arch_exit(void)
{
}

static int arm_init(void)
{
	int rc = kvm_init(NULL, sizeof(struct kvm_vcpu), 0, THIS_MODULE);
	return rc;
}

module_init(arm_init);