path: root/arch/arm64/kvm/nested.c

// SPDX-License-Identifier: GPL-2.0-only
/*
 * Copyright (C) 2017 - Columbia University and Linaro Ltd.
 * Author: Jintack Lim <jintack.lim@linaro.org>
 */

#include <linux/bitfield.h>
#include <linux/kvm.h>
#include <linux/kvm_host.h>

#include <asm/kvm_arm.h>
#include <asm/kvm_emulate.h>
#include <asm/kvm_mmu.h>
#include <asm/kvm_nested.h>
#include <asm/sysreg.h>

#include "sys_regs.h"

/* Protection against the sysreg repainting madness... */
#define NV_FTR(r, f)		ID_AA64##r##_EL1_##f

/*
 * Ratio of live shadow S2 MMU per vcpu. This is a trade-off between
 * memory usage and potential number of different sets of S2 PTs in
 * the guests. Running out of S2 MMUs only affects performance (we
 * will invalidate them more often).
 */
#define S2_MMU_PER_VCPU		2

void kvm_init_nested(struct kvm *kvm)
{
	kvm->arch.nested_mmus = NULL;
	kvm->arch.nested_mmus_size = 0;
}

static int init_nested_s2_mmu(struct kvm *kvm, struct kvm_s2_mmu *mmu)
{
	/*
	 * We only initialise the IPA range on the canonical MMU, which
	 * defines the contract between KVM and userspace on where the
	 * "hardware" is in the IPA space. This affects the validity of MMIO
	 * exits forwarded to userspace, for example.
	 *
	 * For nested S2s, we use the PARange as exposed to the guest, as it
	 * is allowed to use it at will to expose whatever memory map it
	 * wants to its own guests as it would be on real HW.
	 */
	return kvm_init_stage2_mmu(kvm, mmu, kvm_get_pa_bits(kvm));
}

int kvm_vcpu_init_nested(struct kvm_vcpu *vcpu)
{
	struct kvm *kvm = vcpu->kvm;
	struct kvm_s2_mmu *tmp;
	int num_mmus, ret = 0;

	/*
	 * Let's treat memory allocation failures as benign: If we fail to
	 * allocate anything, return an error and keep the allocated array
	 * alive. Userspace may try to recover by intializing the vcpu
	 * again, and there is no reason to affect the whole VM for this.
	 */
	num_mmus = atomic_read(&kvm->online_vcpus) * S2_MMU_PER_VCPU;
	tmp = kvrealloc(kvm->arch.nested_mmus,
			size_mul(sizeof(*kvm->arch.nested_mmus), num_mmus),
			GFP_KERNEL_ACCOUNT | __GFP_ZERO);
	if (!tmp)
		return -ENOMEM;

	/*
	 * If we went through a realocation, adjust the MMU back-pointers in
	 * the previously initialised kvm_pgtable structures.
	 */
	if (kvm->arch.nested_mmus != tmp)
		for (int i = 0; i < kvm->arch.nested_mmus_size; i++)
			tmp[i].pgt->mmu = &tmp[i];

	for (int i = kvm->arch.nested_mmus_size; !ret && i < num_mmus; i++)
		ret = init_nested_s2_mmu(kvm, &tmp[i]);

	if (ret) {
		for (int i = kvm->arch.nested_mmus_size; i < num_mmus; i++)
			kvm_free_stage2_pgd(&tmp[i]);

		return ret;
	}

	kvm->arch.nested_mmus_size = num_mmus;
	kvm->arch.nested_mmus = tmp;

	return 0;
}

struct s2_walk_info {
	int	     (*read_desc)(phys_addr_t pa, u64 *desc, void *data);
	void	     *data;
	u64	     baddr;
	unsigned int max_oa_bits;
	unsigned int pgshift;
	unsigned int sl;
	unsigned int t0sz;
	bool	     be;
};

static u32 compute_fsc(int level, u32 fsc)
{
	return fsc | (level & 0x3);
}

static int esr_s2_fault(struct kvm_vcpu *vcpu, int level, u32 fsc)
{
	u32 esr;

	esr = kvm_vcpu_get_esr(vcpu) & ~ESR_ELx_FSC;
	esr |= compute_fsc(level, fsc);
	return esr;
}

static int get_ia_size(struct s2_walk_info *wi)
{
	return 64 - wi->t0sz;
}

static int check_base_s2_limits(struct s2_walk_info *wi,
				int level, int input_size, int stride)
{
	int start_size, ia_size;

	ia_size = get_ia_size(wi);

	/* Check translation limits */
	switch (BIT(wi->pgshift)) {
	case SZ_64K:
		if (level == 0 || (level == 1 &&