OpenCloudOS-Kernel/arch/powerpc/kvm/book3s_hv_nested.c

// SPDX-License-Identifier: GPL-2.0
/*
 * Copyright IBM Corporation, 2018
 * Authors Suraj Jitindar Singh <sjitindarsingh@gmail.com>
 *	   Paul Mackerras <paulus@ozlabs.org>
 *
 * Description: KVM functions specific to running nested KVM-HV guests
 * on Book3S processors (specifically POWER9 and later).
 */

#include <linux/kernel.h>
#include <linux/kvm_host.h>

#include <asm/kvm_ppc.h>
#include <asm/kvm_book3s.h>
#include <asm/mmu.h>
#include <asm/pgtable.h>
#include <asm/pgalloc.h>
#include <asm/pte-walk.h>
#include <asm/reg.h>

static struct patb_entry *pseries_partition_tb;

static void kvmhv_update_ptbl_cache(struct kvm_nested_guest *gp);

void kvmhv_save_hv_regs(struct kvm_vcpu *vcpu, struct hv_guest_state *hr)
{
	struct kvmppc_vcore *vc = vcpu->arch.vcore;

	hr->pcr = vc->pcr;
	hr->dpdes = vc->dpdes;
	hr->hfscr = vcpu->arch.hfscr;
	hr->tb_offset = vc->tb_offset;
	hr->dawr0 = vcpu->arch.dawr;
	hr->dawrx0 = vcpu->arch.dawrx;
	hr->ciabr = vcpu->arch.ciabr;
	hr->purr = vcpu->arch.purr;
	hr->spurr = vcpu->arch.spurr;
	hr->ic = vcpu->arch.ic;
	hr->vtb = vc->vtb;
	hr->srr0 = vcpu->arch.shregs.srr0;
	hr->srr1 = vcpu->arch.shregs.srr1;
	hr->sprg[0] = vcpu->arch.shregs.sprg0;
	hr->sprg[1] = vcpu->arch.shregs.sprg1;
	hr->sprg[2] = vcpu->arch.shregs.sprg2;
	hr->sprg[3] = vcpu->arch.shregs.sprg3;
	hr->pidr = vcpu->arch.pid;
	hr->cfar = vcpu->arch.cfar;
	hr->ppr = vcpu->arch.ppr;
}

static void save_hv_return_state(struct kvm_vcpu *vcpu, int trap,
				 struct hv_guest_state *hr)
{
	struct kvmppc_vcore *vc = vcpu->arch.vcore;

	hr->dpdes = vc->dpdes;
	hr->hfscr = vcpu->arch.hfscr;
	hr->purr = vcpu->arch.purr;
	hr->spurr = vcpu->arch.spurr;
	hr->ic = vcpu->arch.ic;
	hr->vtb = vc->vtb;
	hr->srr0 = vcpu->arch.shregs.srr0;
	hr->srr1 = vcpu->arch.shregs.srr1;
	hr->sprg[0] = vcpu->arch.shregs.sprg0;
	hr->sprg[1] = vcpu->arch.shregs.sprg1;
	hr->sprg[2] = vcpu->arch.shregs.sprg2;
	hr->sprg[3] = vcpu->arch.shregs.sprg3;
	hr->pidr = vcpu->arch.pid;
	hr->cfar = vcpu->arch.cfar;
	hr->ppr = vcpu->arch.ppr;
	switch (trap) {
	case BOOK3S_INTERRUPT_H_DATA_STORAGE:
		hr->hdar = vcpu->arch.fault_dar;
		hr->hdsisr = vcpu->arch.fault_dsisr;
		hr->asdr = vcpu->arch.fault_gpa;
		break;
	case BOOK3S_INTERRUPT_H_INST_STORAGE:
		hr->asdr = vcpu->arch.fault_gpa;
		break;
	case BOOK3S_INTERRUPT_H_EMUL_ASSIST:
		hr->heir = vcpu->arch.emul_inst;
		break;
	}
}

static void restore_hv_regs(struct kvm_vcpu *vcpu, struct hv_guest_state *hr)
{
	struct kvmppc_vcore *vc = vcpu->arch.vcore;

	vc->pcr = hr->pcr;
	vc->dpdes = hr->dpdes;
	vcpu->arch.hfscr = hr->hfscr;
	vcpu->arch.dawr = hr->dawr0;
	vcpu->arch.dawrx = hr->dawrx0;
	vcpu->arch.ciabr = hr->ciabr;
	vcpu->arch.purr = hr->purr;
	vcpu->arch.spurr = hr->spurr;
	vcpu->arch.ic = hr->ic;
	vc->vtb = hr->vtb;
	vcpu->arch.shregs.srr0 = hr->srr0;
	vcpu->arch.shregs.srr1 = hr->srr1;
	vcpu->arch.shregs.sprg0 = hr->sprg[0];
	vcpu->arch.shregs.sprg1 = hr->sprg[1];
	vcpu->arch.shregs.sprg2 = hr->sprg[2];
	vcpu->arch.shregs.sprg3 = hr->sprg[3];
	vcpu->arch.pid = hr->pidr;
	vcpu->arch.cfar = hr->cfar;
	vcpu->arch.ppr = hr->ppr;
}

void kvmhv_restore_hv_return_state(struct kvm_vcpu *vcpu,
				   struct hv_guest_state *hr)
{
	struct kvmppc_vcore *vc = vcpu->arch.vcore;

	vc->dpdes = hr->dpdes;
	vcpu->arch.hfscr = hr->hfscr;
	vcpu->arch.purr = hr->purr;
	vcpu->arch.spurr = hr->spurr;
	vcpu->arch.ic = hr->ic;
	vc->vtb = hr->vtb;
	vcpu->arch.fault_dar = hr->hdar;
	vcpu->arch.fault_dsisr = hr->hdsisr;
	vcpu->arch.fault_gpa = hr->asdr;
	vcpu->arch.emul_inst = hr->heir;
	vcpu->arch.shregs.srr0 = hr->srr0;
	vcpu->arch.shregs.srr1 = hr->srr1;
	vcpu->arch.shregs.sprg0 = hr->sprg[0];
	vcpu->arch.shregs.sprg1 = hr->sprg[1];
	vcpu->arch.shregs.sprg2 = hr->sprg[2];
	vcpu->arch.shregs.sprg3 = hr->sprg[3];
	vcpu->arch.pid = hr->pidr;
	vcpu->arch.cfar = hr->cfar;
	vcpu->arch.ppr = hr->ppr;
}

long kvmhv_enter_nested_guest(struct kvm_vcpu *vcpu)
{
	long int err, r;
	struct kvm_nested_guest *l2;
	struct pt_regs l2_regs, saved_l1_regs;
	struct hv_guest_state l2_hv, saved_l1_hv;
	struct kvmppc_vcore *vc = vcpu->arch.vcore;
	u64 hv_ptr, regs_ptr;
	u64 hdec_exp;
	s64 delta_purr, delta_spurr, delta_ic, delta_vtb;
	u64 mask;
	unsigned long lpcr;

	if (vcpu->kvm->arch.l1_ptcr == 0)
		return H_NOT_AVAILABLE;

	/* copy parameters in */
	hv_ptr = kvmppc_get_gpr(vcpu, 4);
	err = kvm_vcpu_read_guest(vcpu, hv_ptr, &l2_hv,
				  sizeof(struct hv_guest_state));
	if (err)
		return H_PARAMETER;
	if (l2_hv.version != HV_GUEST_STATE_VERSION)
		return H_P2;

	regs_ptr = kvmppc_get_gpr(vcpu, 5);
	err = kvm_vcpu_read_guest(vcpu, regs_ptr, &l2_regs,
				  sizeof(struct pt_regs));
	if (err)
		return H_PARAMETER;

	/* translate lpid */
	l2 = kvmhv_get_nested(vcpu->kvm, l2_hv.lpid, true);
	if (!l2)
		return H_PARAMETER;
	if (!l2->l1_gr_to_hr) {
		mutex_lock(&l2->tlb_lock);
		kvmhv_update_ptbl_cache(l2);
		mutex_unlock(&l2->tlb_lock);
	}

	/* save l1 values of things */
	vcpu->arch.regs.msr = vcpu->arch.shregs.msr;
	saved_l1_regs = vcpu->arch.regs;
	kvmhv_save_hv_regs(vcpu, &saved_l1_hv);

	/* convert TB values/offsets to host (L0) values */
	hdec_exp = l2_hv.hdec_expiry - vc->tb_offset;
	vc->tb_offset += l2_hv.tb_offset;

	/* set L1 state to L2 state */
	vcpu->arch.nested = l2;
	vcpu->arch.nested_vcpu_id = l2_hv.vcpu_token;
	vcpu->arch.regs = l2_regs;
	vcpu->arch.shregs.msr = vcpu->arch.regs.msr;
	mask = LPCR_DPFD | LPCR_ILE | LPCR_TC | LPCR_AIL | LPCR_LD |
		LPCR_LPES | LPCR_MER;
	lpcr = (vc->lpcr & ~mask) | (l2_hv.lpcr & mask);
	restore_hv_regs(vcpu, &l2_hv);

	vcpu->arch.ret = RESUME_GUEST;
	vcpu->arch.trap = 0;
	do {
		if (mftb() >= hdec_exp) {
			vcpu->arch.trap = BOOK3S_INTERRUPT_HV_DECREMENTER;
			r = RESUME_HOST;
			break;
		}
		r = kvmhv_run_single_vcpu(vcpu->arch.kvm_run, vcpu, hdec_exp,
					  lpcr);
	} while (is_kvmppc_resume_guest(r));

	/* save L2 state for return */
	l2_regs = vcpu->arch.regs;
	l2_regs.msr = vcpu->arch.shregs.msr;
	delta_purr = vcpu->arch.purr - l2_hv.purr;
	delta_spurr = vcpu->arch.spurr - l2_hv.spurr;
	delta_ic = vcpu->arch.ic - l2_hv.ic;
	delta_vtb = vc->vtb - l2_hv.vtb;
	save_hv_return_state(vcpu, vcpu->arch.trap, &l2_hv);

	/* restore L1 state */
	vcpu->arch.nested = NULL;
	vcpu->arch.regs = saved_l1_regs;
	vcpu->arch.shregs.msr = saved_l1_regs.msr & ~MSR_TS_MASK;
	/* set L1 MSR TS field according to L2 transaction state */
	if (l2_regs.msr & MSR_TS_MASK)
		vcpu->arch.shregs.msr |= MSR_TS_S;
	vc->tb_offset = saved_l1_hv.tb_offset;
	restore_hv_regs(vcpu, &saved_l1_hv);
	vcpu->arch.purr += delta_purr;
	vcpu->arch.spurr += delta_spurr;
	vcpu->arch.ic += delta_ic;
	vc->vtb += delta_vtb;

	kvmhv_put_nested(l2);

	/* copy l2_hv_state and regs back to guest */
	err = kvm_vcpu_write_guest(vcpu, hv_ptr, &l2_hv,
				   sizeof(struct hv_guest_state));
	if (err)
		return H_AUTHORITY;
	err = kvm_vcpu_write_guest(vcpu, regs_ptr, &l2_regs,
				   sizeof(struct pt_regs));
	if (err)
		return H_AUTHORITY;

	if (r == -EINTR)
		return H_INTERRUPT;

	return vcpu->arch.trap;
}

long kvmhv_nested_init(void)
{
	long int ptb_order;
	unsigned long ptcr;
	long rc;

	if (!kvmhv_on_pseries())
		return 0;
	if (!radix_enabled())
		return -ENODEV;

	/* find log base 2 of KVMPPC_NR_LPIDS, rounding up */
	ptb_order = __ilog2(KVMPPC_NR_LPIDS - 1) + 1;
	if (ptb_order < 8)
		ptb_order = 8;
	pseries_partition_tb = kmalloc(sizeof(struct patb_entry) << ptb_order,
				       GFP_KERNEL);
	if (!pseries_partition_tb) {
		pr_err("kvm-hv: failed to allocated nested partition table\n");
		return -ENOMEM;
	}

	ptcr = __pa(pseries_partition_tb) | (ptb_order - 8);
	rc = plpar_hcall_norets(H_SET_PARTITION_TABLE, ptcr);
	if (rc != H_SUCCESS) {
		pr_err("kvm-hv: Parent hypervisor does not support nesting (rc=%ld)\n",
		       rc);
		kfree(pseries_partition_tb);
		pseries_partition_tb = NULL;
		return -ENODEV;
	}

	return 0;
}

void kvmhv_nested_exit(void)
{
	/*
	 * N.B. the kvmhv_on_pseries() test is there because it enables
	 * the compiler to remove the call to plpar_hcall_norets()
	 * when CONFIG_PPC_PSERIES=n.
	 */
	if (kvmhv_on_pseries() && pseries_partition_tb) {
		plpar_hcall_norets(H_SET_PARTITION_TABLE, 0);
		kfree(pseries_partition_tb);
		pseries_partition_tb = NULL;
	}
}

void kvmhv_set_ptbl_entry(unsigned int lpid, u64 dw0, u64 dw1)
{
	if (cpu_has_feature(CPU_FTR_HVMODE)) {
		mmu_partition_table_set_entry(lpid, dw0, dw1);
	} else {
		pseries_partition_tb[lpid].patb0 = cpu_to_be64(dw0);
		pseries_partition_tb[lpid].patb1 = cpu_to_be64(dw1);
	}
}

static void kvmhv_set_nested_ptbl(struct kvm_nested_guest *gp)
{
	unsigned long dw0;

	dw0 = PATB_HR | radix__get_tree_size() |
		__pa(gp->shadow_pgtable) | RADIX_PGD_INDEX_SIZE;
	kvmhv_set_ptbl_entry(gp->shadow_lpid, dw0, gp->process_table);
}

void kvmhv_vm_nested_init(struct kvm *kvm)
{
	kvm->arch.max_nested_lpid = -1;
}

/*
 * Handle the H_SET_PARTITION_TABLE hcall.
 * r4 = guest real address of partition table + log_2(size) - 12
 * (formatted as for the PTCR).
 */
long kvmhv_set_partition_table(struct kvm_vcpu *vcpu)
{
	struct kvm *kvm = vcpu->kvm;
	unsigned long ptcr = kvmppc_get_gpr(vcpu, 4);
	int srcu_idx;
	long ret = H_SUCCESS;

	srcu_idx = srcu_read_lock(&kvm->srcu);
	/*
	 * Limit the partition table to 4096 entries (because that's what
	 * hardware supports), and check the base address.
	 */
	if ((ptcr & PRTS_MASK) > 12 - 8 ||
	    !kvm_is_visible_gfn(vcpu->kvm, (ptcr & PRTB_MASK) >> PAGE_SHIFT))
		ret = H_PARAMETER;
	srcu_read_unlock(&kvm->srcu, srcu_idx);
	if (ret == H_SUCCESS)
		kvm->arch.l1_ptcr = ptcr;
	return ret;
}

/*
 * Reload the partition table entry for a guest.
 * Caller must hold gp->tlb_lock.
 */
static void kvmhv_update_ptbl_cache(struct kvm_nested_guest *gp)
{
	int ret;
	struct patb_entry ptbl_entry;
	unsigned long ptbl_addr;
	struct kvm *kvm = gp->l1_host;

	ret = -EFAULT;
	ptbl_addr = (kvm->arch.l1_ptcr & PRTB_MASK) + (gp->l1_lpid << 4);
	if (gp->l1_lpid < (1ul << ((kvm->arch.l1_ptcr & PRTS_MASK) + 8)))
		ret = kvm_read_guest(kvm, ptbl_addr,
				     &ptbl_entry, sizeof(ptbl_entry));
	if (ret) {
		gp->l1_gr_to_hr = 0;
		gp->process_table = 0;
	} else {
		gp->l1_gr_to_hr = be64_to_cpu(ptbl_entry.patb0);
		gp->process_table = be64_to_cpu(ptbl_entry.patb1);
	}
	kvmhv_set_nested_ptbl(gp);
}

struct kvm_nested_guest *kvmhv_alloc_nested(struct kvm *kvm, unsigned int lpid)
{
	struct kvm_nested_guest *gp;
	long shadow_lpid;

	gp = kzalloc(sizeof(*gp), GFP_KERNEL);
	if (!gp)
		return NULL;
	gp->l1_host = kvm;
	gp->l1_lpid = lpid;
	mutex_init(&gp->tlb_lock);
	gp->shadow_pgtable = pgd_alloc(kvm->mm);
	if (!gp->shadow_pgtable)
		goto out_free;
	shadow_lpid = kvmppc_alloc_lpid();
	if (shadow_lpid < 0)
		goto out_free2;
	gp->shadow_lpid = shadow_lpid;

	return gp;

 out_free2:
	pgd_free(kvm->mm, gp->shadow_pgtable);
 out_free:
	kfree(gp);
	return NULL;
}

/*
 * Free up any resources allocated for a nested guest.
 */
static void kvmhv_release_nested(struct kvm_nested_guest *gp)
{
	struct kvm *kvm = gp->l1_host;

	if (gp->shadow_pgtable) {
		/*
		 * No vcpu is using this struct and no call to
		 * kvmhv_get_nested can find this struct,
		 * so we don't need to hold kvm->mmu_lock.
		 */
		kvmppc_free_pgtable_radix(kvm, gp->shadow_pgtable,
					  gp->shadow_lpid);
		pgd_free(kvm->mm, gp->shadow_pgtable);
	}
	kvmhv_set_ptbl_entry(gp->shadow_lpid, 0, 0);
	kvmppc_free_lpid(gp->shadow_lpid);
	kfree(gp);
}

static void kvmhv_remove_nested(struct kvm_nested_guest *gp)
{
	struct kvm *kvm = gp->l1_host;
	int lpid = gp->l1_lpid;
	long ref;

	spin_lock(&kvm->mmu_lock);
	if (gp == kvm->arch.nested_guests[lpid]) {
		kvm->arch.nested_guests[lpid] = NULL;
		if (lpid == kvm->arch.max_nested_lpid) {
			while (--lpid >= 0 && !kvm->arch.nested_guests[lpid])
				;
			kvm->arch.max_nested_lpid = lpid;
		}
		--gp->refcnt;
	}
	ref = gp->refcnt;
	spin_unlock(&kvm->mmu_lock);
	if (ref == 0)
		kvmhv_release_nested(gp);
}

/*
 * Free up all nested resources allocated for this guest.
 * This is called with no vcpus of the guest running, when
 * switching the guest to HPT mode or when destroying the
 * guest.
 */
void kvmhv_release_all_nested(struct kvm *kvm)
{
	int i;
	struct kvm_nested_guest *gp;
	struct kvm_nested_guest *freelist = NULL;

	spin_lock(&kvm->mmu_lock);
	for (i = 0; i <= kvm->arch.max_nested_lpid; i++) {
		gp = kvm->arch.nested_guests[i];
		if (!gp)
			continue;
		kvm->arch.nested_guests[i] = NULL;
		if (--gp->refcnt == 0) {
			gp->next = freelist;
			freelist = gp;
		}
	}
	kvm->arch.max_nested_lpid = -1;
	spin_unlock(&kvm->mmu_lock);
	while ((gp = freelist) != NULL) {
		freelist = gp->next;
		kvmhv_release_nested(gp);
	}
}

/* caller must hold gp->tlb_lock */
void kvmhv_flush_nested(struct kvm_nested_guest *gp)
{
	struct kvm *kvm = gp->l1_host;

	spin_lock(&kvm->mmu_lock);
	kvmppc_free_pgtable_radix(kvm, gp->shadow_pgtable, gp->shadow_lpid);
	spin_unlock(&kvm->mmu_lock);
	radix__flush_tlb_lpid(gp->shadow_lpid);
	kvmhv_update_ptbl_cache(gp);
	if (gp->l1_gr_to_hr == 0)
		kvmhv_remove_nested(gp);
}

struct kvm_nested_guest *kvmhv_get_nested(struct kvm *kvm, int l1_lpid,
					  bool create)
{
	struct kvm_nested_guest *gp, *newgp;

	if (l1_lpid >= KVM_MAX_NESTED_GUESTS ||
	    l1_lpid >= (1ul << ((kvm->arch.l1_ptcr & PRTS_MASK) + 12 - 4)))
		return NULL;

	spin_lock(&kvm->mmu_lock);
	gp = kvm->arch.nested_guests[l1_lpid];
	if (gp)
		++gp->refcnt;
	spin_unlock(&kvm->mmu_lock);

	if (gp || !create)
		return gp;

	newgp = kvmhv_alloc_nested(kvm, l1_lpid);
	if (!newgp)
		return NULL;
	spin_lock(&kvm->mmu_lock);
	if (kvm->arch.nested_guests[l1_lpid]) {
		/* someone else beat us to it */
		gp = kvm->arch.nested_guests[l1_lpid];
	} else {
		kvm->arch.nested_guests[l1_lpid] = newgp;
		++newgp->refcnt;
		gp = newgp;
		newgp = NULL;
		if (l1_lpid > kvm->arch.max_nested_lpid)
			kvm->arch.max_nested_lpid = l1_lpid;
	}
	++gp->refcnt;
	spin_unlock(&kvm->mmu_lock);

	if (newgp)
		kvmhv_release_nested(newgp);

	return gp;
}

void kvmhv_put_nested(struct kvm_nested_guest *gp)
{
	struct kvm *kvm = gp->l1_host;
	long ref;

	spin_lock(&kvm->mmu_lock);
	ref = --gp->refcnt;
	spin_unlock(&kvm->mmu_lock);
	if (ref == 0)
		kvmhv_release_nested(gp);
}

static bool kvmhv_invalidate_shadow_pte(struct kvm_vcpu *vcpu,
					struct kvm_nested_guest *gp,
					long gpa, int *shift_ret)
{
	struct kvm *kvm = vcpu->kvm;
	bool ret = false;
	pte_t *ptep;
	int shift;

	spin_lock(&kvm->mmu_lock);
	ptep = __find_linux_pte(gp->shadow_pgtable, gpa, NULL, &shift);
	if (!shift)
		shift = PAGE_SHIFT;
	if (ptep && pte_present(*ptep)) {
		kvmppc_unmap_pte(kvm, ptep, gpa, shift, NULL, gp->shadow_lpid);
		ret = true;
	}
	spin_unlock(&kvm->mmu_lock);

	if (shift_ret)
		*shift_ret = shift;
	return ret;
}

/* Used to convert a nested guest real address to a L1 guest real address */
static int kvmhv_translate_addr_nested(struct kvm_vcpu *vcpu,
				       struct kvm_nested_guest *gp,
				       unsigned long n_gpa, unsigned long dsisr,
				       struct kvmppc_pte *gpte_p)
{
	u64 fault_addr, flags = dsisr & DSISR_ISSTORE;
	int ret;

	ret = kvmppc_mmu_walk_radix_tree(vcpu, n_gpa, gpte_p, gp->l1_gr_to_hr,
					 &fault_addr);

	if (ret) {
		/* We didn't find a pte */
		if (ret == -EINVAL) {
			/* Unsupported mmu config */
			flags |= DSISR_UNSUPP_MMU;
		} else if (ret == -ENOENT) {
			/* No translation found */
			flags |= DSISR_NOHPTE;
		} else if (ret == -EFAULT) {
			/* Couldn't access L1 real address */
			flags |= DSISR_PRTABLE_FAULT;
			vcpu->arch.fault_gpa = fault_addr;
		} else {
			/* Unknown error */
			return ret;
		}
		goto forward_to_l1;
	} else {
		/* We found a pte -> check permissions */
		if (dsisr & DSISR_ISSTORE) {
			/* Can we write? */
			if (!gpte_p->may_write) {
				flags |= DSISR_PROTFAULT;
				goto forward_to_l1;
			}
		} else if (vcpu->arch.trap == BOOK3S_INTERRUPT_H_INST_STORAGE) {
			/* Can we execute? */
			if (!gpte_p->may_execute) {
				flags |= SRR1_ISI_N_OR_G;
				goto forward_to_l1;
			}
		} else {
			/* Can we read? */
			if (!gpte_p->may_read && !gpte_p->may_write) {
				flags |= DSISR_PROTFAULT;
				goto forward_to_l1;
			}
		}
	}

	return 0;

forward_to_l1:
	vcpu->arch.fault_dsisr = flags;
	if (vcpu->arch.trap == BOOK3S_INTERRUPT_H_INST_STORAGE) {
		vcpu->arch.shregs.msr &= ~0x783f0000ul;
		vcpu->arch.shregs.msr |= flags;
	}
	return RESUME_HOST;
}

static long kvmhv_handle_nested_set_rc(struct kvm_vcpu *vcpu,
				       struct kvm_nested_guest *gp,
				       unsigned long n_gpa,
				       struct kvmppc_pte gpte,
				       unsigned long dsisr)
{
	struct kvm *kvm = vcpu->kvm;
	bool writing = !!(dsisr & DSISR_ISSTORE);
	u64 pgflags;
	bool ret;

	/* Are the rc bits set in the L1 partition scoped pte? */
	pgflags = _PAGE_ACCESSED;
	if (writing)
		pgflags |= _PAGE_DIRTY;
	if (pgflags & ~gpte.rc)
		return RESUME_HOST;

	spin_lock(&kvm->mmu_lock);
	/* Set the rc bit in the pte of our (L0) pgtable for the L1 guest */
	ret = kvmppc_hv_handle_set_rc(kvm, kvm->arch.pgtable, writing,
				     gpte.raddr, kvm->arch.lpid);
	spin_unlock(&kvm->mmu_lock);
	if (!ret)
		return -EINVAL;

	/* Set the rc bit in the pte of the shadow_pgtable for the nest guest */
	ret = kvmppc_hv_handle_set_rc(kvm, gp->shadow_pgtable, writing, n_gpa,
				      gp->shadow_lpid);
	if (!ret)
		return -EINVAL;
	return 0;
}

static inline int kvmppc_radix_level_to_shift(int level)
{
	switch (level) {
	case 2:
		return PUD_SHIFT;
	case 1:
		return PMD_SHIFT;
	default:
		return PAGE_SHIFT;
	}
}

static inline int kvmppc_radix_shift_to_level(int shift)
{
	if (shift == PUD_SHIFT)
		return 2;
	if (shift == PMD_SHIFT)
		return 1;
	if (shift == PAGE_SHIFT)
		return 0;
	WARN_ON_ONCE(1);
	return 0;
}

/* called with gp->tlb_lock held */
static long int __kvmhv_nested_page_fault(struct kvm_vcpu *vcpu,
					  struct kvm_nested_guest *gp)
{
	struct kvm *kvm = vcpu->kvm;
	struct kvm_memory_slot *memslot;
	struct kvmppc_pte gpte;
	pte_t pte, *pte_p;
	unsigned long mmu_seq;
	unsigned long dsisr = vcpu->arch.fault_dsisr;
	unsigned long ea = vcpu->arch.fault_dar;
	unsigned long n_gpa, gpa, gfn, perm = 0UL;
	unsigned int shift, l1_shift, level;
	bool writing = !!(dsisr & DSISR_ISSTORE);
	bool kvm_ro = false;
	long int ret;

	if (!gp->l1_gr_to_hr) {
		kvmhv_update_ptbl_cache(gp);
		if (!gp->l1_gr_to_hr)
			return RESUME_HOST;
	}

	/* Convert the nested guest real address into a L1 guest real address */

	n_gpa = vcpu->arch.fault_gpa & ~0xF000000000000FFFULL;
	if (!(dsisr & DSISR_PRTABLE_FAULT))
		n_gpa |= ea & 0xFFF;
	ret = kvmhv_translate_addr_nested(vcpu, gp, n_gpa, dsisr, &gpte);

	/*
	 * If the hardware found a translation but we don't now have a usable
	 * translation in the l1 partition-scoped tree, remove the shadow pte
	 * and let the guest retry.
	 */
	if (ret == RESUME_HOST &&
	    (dsisr & (DSISR_PROTFAULT | DSISR_BADACCESS | DSISR_NOEXEC_OR_G |
		      DSISR_BAD_COPYPASTE)))
		goto inval;
	if (ret)
		return ret;

	/* Failed to set the reference/change bits */
	if (dsisr & DSISR_SET_RC) {
		ret = kvmhv_handle_nested_set_rc(vcpu, gp, n_gpa, gpte, dsisr);
		if (ret == RESUME_HOST)
			return ret;
		if (ret)
			goto inval;
		dsisr &= ~DSISR_SET_RC;
		if (!(dsisr & (DSISR_BAD_FAULT_64S | DSISR_NOHPTE |
			       DSISR_PROTFAULT)))
			return RESUME_GUEST;
	}

	/*
	 * We took an HISI or HDSI while we were running a nested guest which
	 * means we have no partition scoped translation for that. This means
	 * we need to insert a pte for the mapping into our shadow_pgtable.
	 */

	l1_shift = gpte.page_shift;
	if (l1_shift < PAGE_SHIFT) {
		/* We don't support l1 using a page size smaller than our own */
		pr_err("KVM: L1 guest page shift (%d) less than our own (%d)\n",
			l1_shift, PAGE_SHIFT);
		return -EINVAL;
	}
	gpa = gpte.raddr;
	gfn = gpa >> PAGE_SHIFT;

	/* 1. Get the corresponding host memslot */

	memslot = gfn_to_memslot(kvm, gfn);
	if (!memslot || (memslot->flags & KVM_MEMSLOT_INVALID)) {
		if (dsisr & (DSISR_PRTABLE_FAULT | DSISR_BADACCESS)) {
			/* unusual error -> reflect to the guest as a DSI */
			kvmppc_core_queue_data_storage(vcpu, ea, dsisr);
			return RESUME_GUEST;
		}
		/* passthrough of emulated MMIO case... */
		pr_err("emulated MMIO passthrough?\n");
		return -EINVAL;
	}
	if (memslot->flags & KVM_MEM_READONLY) {
		if (writing) {
			/* Give the guest a DSI */
			kvmppc_core_queue_data_storage(vcpu, ea,
					DSISR_ISSTORE | DSISR_PROTFAULT);
			return RESUME_GUEST;
		}
		kvm_ro = true;
	}

	/* 2. Find the host pte for this L1 guest real address */

	/* Used to check for invalidations in progress */
	mmu_seq = kvm->mmu_notifier_seq;
	smp_rmb();

	/* See if can find translation in our partition scoped tables for L1 */
	pte = __pte(0);
	spin_lock(&kvm->mmu_lock);
	pte_p = __find_linux_pte(kvm->arch.pgtable, gpa, NULL, &shift);
	if (!shift)
		shift = PAGE_SHIFT;
	if (pte_p)
		pte = *pte_p;
	spin_unlock(&kvm->mmu_lock);

	if (!pte_present(pte) || (writing && !(pte_val(pte) & _PAGE_WRITE))) {
		/* No suitable pte found -> try to insert a mapping */
		ret = kvmppc_book3s_instantiate_page(vcpu, gpa, memslot,
					writing, kvm_ro, &pte, &level);
		if (ret == -EAGAIN)
			return RESUME_GUEST;
		else if (ret)
			return ret;
		shift = kvmppc_radix_level_to_shift(level);
	}

	/* 3. Compute the pte we need to insert for nest_gpa -> host r_addr */

	/* The permissions is the combination of the host and l1 guest ptes */
	perm |= gpte.may_read ? 0UL : _PAGE_READ;
	perm |= gpte.may_write ? 0UL : _PAGE_WRITE;
	perm |= gpte.may_execute ? 0UL : _PAGE_EXEC;
	pte = __pte(pte_val(pte) & ~perm);

	/* What size pte can we insert? */
	if (shift > l1_shift) {
		u64 mask;
		unsigned int actual_shift = PAGE_SHIFT;
		if (PMD_SHIFT < l1_shift)
			actual_shift = PMD_SHIFT;
		mask = (1UL << shift) - (1UL << actual_shift);
		pte = __pte(pte_val(pte) | (gpa & mask));
		shift = actual_shift;
	}
	level = kvmppc_radix_shift_to_level(shift);
	n_gpa &= ~((1UL << shift) - 1);

	/* 4. Insert the pte into our shadow_pgtable */

	ret = kvmppc_create_pte(kvm, gp->shadow_pgtable, pte, n_gpa, level,
				mmu_seq, gp->shadow_lpid);
	if (ret == -EAGAIN)
		ret = RESUME_GUEST;	/* Let the guest try again */

	return ret;

 inval:
	kvmhv_invalidate_shadow_pte(vcpu, gp, n_gpa, NULL);
	return RESUME_GUEST;
}

long int kvmhv_nested_page_fault(struct kvm_vcpu *vcpu)
{
	struct kvm_nested_guest *gp = vcpu->arch.nested;
	long int ret;

	mutex_lock(&gp->tlb_lock);
	ret = __kvmhv_nested_page_fault(vcpu, gp);
	mutex_unlock(&gp->tlb_lock);
	return ret;
}