path: root/arch/x86/kernel/kvm.c

// SPDX-License-Identifier: GPL-2.0-or-later
/*
 * KVM paravirt_ops implementation
 *
 * Copyright (C) 2007, Red Hat, Inc., Ingo Molnar <mingo@redhat.com>
 * Copyright IBM Corporation, 2007
 *   Authors: Anthony Liguori <aliguori@us.ibm.com>
 */

#define pr_fmt(fmt) "kvm-guest: " fmt

#include <linux/context_tracking.h>
#include <linux/init.h>
#include <linux/irq.h>
#include <linux/kernel.h>
#include <linux/kvm_para.h>
#include <linux/cpu.h>
#include <linux/mm.h>
#include <linux/highmem.h>
#include <linux/hardirq.h>
#include <linux/notifier.h>
#include <linux/reboot.h>
#include <linux/hash.h>
#include <linux/sched.h>
#include <linux/slab.h>
#include <linux/kprobes.h>
#include <linux/nmi.h>
#include <linux/swait.h>
#include <linux/syscore_ops.h>
#include <asm/timer.h>
#include <asm/cpu.h>
#include <asm/traps.h>
#include <asm/desc.h>
#include <asm/tlbflush.h>
#include <asm/apic.h>
#include <asm/apicdef.h>
#include <asm/hypervisor.h>
#include <asm/tlb.h>
#include <asm/cpuidle_haltpoll.h>
#include <asm/ptrace.h>
#include <asm/reboot.h>
#include <asm/svm.h>

DEFINE_STATIC_KEY_FALSE(kvm_async_pf_enabled);

static int kvmapf = 1;

static int __init parse_no_kvmapf(char *arg)
{
        kvmapf = 0;
        return 0;
}

early_param("no-kvmapf", parse_no_kvmapf);

static int steal_acc = 1;
static int __init parse_no_stealacc(char *arg)
{
        steal_acc = 0;
        return 0;
}

early_param("no-steal-acc", parse_no_stealacc);

static DEFINE_PER_CPU_DECRYPTED(struct kvm_vcpu_pv_apf_data, apf_reason) __aligned(64);
DEFINE_PER_CPU_DECRYPTED(struct kvm_steal_time, steal_time) __aligned(64) __visible;
static int has_steal_clock = 0;

/*
 * No need for any "IO delay" on KVM
 */
static void kvm_io_delay(void)
{
}

#define KVM_TASK_SLEEP_HASHBITS 8
#define KVM_TASK_SLEEP_HASHSIZE (1<<KVM_TASK_SLEEP_HASHBITS)

struct kvm_task_sleep_node {
	struct hlist_node link;
	struct swait_queue_head wq;
	u32 token;
	int cpu;
};

static struct kvm_task_sleep_head {
	raw_spinlock_t lock;
	struct hlist_head list;
} async_pf_sleepers[KVM_TASK_SLEEP_HASHSIZE];

static struct kvm_task_sleep_node *_find_apf_task(struct kvm_task_sleep_head *b,
						  u32 token)
{
	struct hlist_node *p;

	hlist_for_each(p, &b->list) {
		struct kvm_task_sleep_node *n =
			hlist_entry(p, typeof(*n), link);
		if (n->token == token)
			return n;
	}

	return NULL;
}

static bool kvm_async_pf_queue_task(u32 token, struct kvm_task_sleep_node *n)
{
	u32 key = hash_32(token, KVM_TASK_SLEEP_HASHBITS);
	struct kvm_task_sleep_head *b = &async_pf_sleepers[key];
	struct kvm_task_sleep_node *e;

	raw_spin_lock(&b->lock);
	e = _find_apf_task(b, token);
	if (e) {
		/* dummy entry exist -> wake up was delivered ahead of PF */
		hlist_del(&e->link);
		raw_spin_unlock(&b->lock);
		kfree(e);
		return false;
	}

	n->token = token;
	n->cpu = smp_processor_id();
	init_swait_queue_head(&n->wq);
	hlist_add_head(&n->link, &b->list);
	raw_spin_unlock(&b->lock);
	return true;
}

/*
 * kvm_async_pf_task_wait_schedule - Wait for pagefault to be handled
 * @token:	Token to identify the sleep node entry
 *
 * Invoked from the async pagefault handling code or from the VM exit page
 * fault handler. In both cases RCU is watching.
 */
void kvm_async_pf_task_wait_schedule(u32 token)
{
	struct kvm_task_sleep_node n;
	DECLARE_SWAITQUEUE(wait);

	lockdep_assert_irqs_disabled();

	if (!kvm_async_pf_queue_task(token, &n))
		return;

	for (;;) {
		prepare_to_swait_exclusive(&n.wq, &wait, TASK_UNINTERRUPTIBLE);
		if (hlist_unhashed(&n.link))
			break;

		local_irq_enable();
		schedule();
		local_irq_disable();
	}
	finish_swait(&n.wq, &wait);
}
EXPORT_SYMBOL_GPL(kvm_async_pf_task_wait_schedule);

static void apf_task_wake_one(struct kvm_task_sleep_node *n)
{
	hlist_del_init(&n->link);
	if (swq_has_sleeper(&n->wq))
		swake_up_one(&n->wq);
}

static void apf_task_wake_all(void)
{
	int i;

	for (i = 0; i < KVM_TASK_SLEEP_HASHSIZE; i++) {
		struct kvm_task_sleep_head *b = &async_pf_sleepers[i];
		struct kvm_task_sleep_node *n;
		struct hlist_node *p, *next;

		raw_spin_lock(&b->lock);
		hlist_for_each_safe(p, next, &b->list) {
			n = hlist_entry(p, typeof(*n), link);
			if (n->cpu == smp_processor_id())
				apf_task_wake_one(n);
		}
		raw_spin_unlock(&b->lock);
	}
}

void kvm_async_pf_task_wake(u32 token)
{
	u32 key = hash_32(token, KVM_TASK_SLEEP_HASHBITS);
	struct kvm_task_sleep_head *b = &async_pf_sleepers[key];
	struct kvm_task_sleep_node *n;

	if (token == ~0) {
		apf_task_wake_all();
		return;
	}

again:
	raw_spin_lock(&b->lock);
	n = _find_apf_task(b, token);
	if (!n) {
		/*
		 * async PF was not yet handled.
		 * Add dummy entry for the token.
		 */
		n = kzalloc(sizeof(*n), GFP_ATOMIC);
		if