mem_protect.c (revision fa1219ec8c03d09b7a62046ea9680c0cf141bc4a) - OpenGrok cross reference for /linux/arch/arm64/kvm/hyp/nvhe/mem_protect.c

// SPDX-License-Identifier: GPL-2.0-only
/*
 * Copyright (C) 2020 Google LLC
 * Author: Quentin Perret <qperret@google.com>
 */

#include <linux/kvm_host.h>

#include <asm/kvm_emulate.h>
#include <asm/kvm_hyp.h>
#include <asm/kvm_mmu.h>
#include <asm/kvm_pgtable.h>
#include <asm/kvm_pkvm.h>
#include <asm/stage2_pgtable.h>

#include <hyp/fault.h>

#include <nvhe/arm-smccc.h>
#include <nvhe/gfp.h>
#include <nvhe/memory.h>
#include <nvhe/mem_protect.h>
#include <nvhe/mm.h>
#include <nvhe/trap_handler.h>

#define KVM_HOST_S2_FLAGS (KVM_PGTABLE_S2_AS_S1 | KVM_PGTABLE_S2_IDMAP)

struct host_mmu host_mmu;

static struct hyp_pool host_s2_pool;

static DEFINE_PER_CPU(struct pkvm_hyp_vm *, __current_vm);
#define current_vm (*this_cpu_ptr(&__current_vm))

static void pkvm_sme_dvmsync_fw_call(void)
{
	if (alternative_has_cap_unlikely(ARM64_WORKAROUND_4193714)) {
		struct arm_smccc_res res;

		/*
		 * Ignore the return value. Probing for the workaround
		 * availability took place in init_hyp_mode().
		 */
		hyp_smccc_1_1_smc(ARM_SMCCC_CPU_WORKAROUND_4193714, &res);
	}
}

static void guest_lock_component(struct pkvm_hyp_vm *vm)
{
	hyp_spin_lock(&vm->lock);
	current_vm = vm;
}

static void guest_unlock_component(struct pkvm_hyp_vm *vm)
{
	current_vm = NULL;
	hyp_spin_unlock(&vm->lock);
}

static void host_lock_component(void)
{
	hyp_spin_lock(&host_mmu.lock);
}

static void host_unlock_component(void)
{
	hyp_spin_unlock(&host_mmu.lock);
}

static void hyp_lock_component(void)
{
	hyp_spin_lock(&pkvm_pgd_lock);
}

static void hyp_unlock_component(void)
{
	hyp_spin_unlock(&pkvm_pgd_lock);
}

#define for_each_hyp_page(__p, __st, __sz)				\
	for (struct hyp_page *__p = hyp_phys_to_page(__st),		\
			     *__e = __p + ((__sz) >> PAGE_SHIFT);	\
	     __p < __e; __p++)

static void *host_s2_zalloc_pages_exact(size_t size)
{
	void *addr = hyp_alloc_pages(&host_s2_pool, get_order(size));

	hyp_split_page(hyp_virt_to_page(addr));

	/*
	 * The size of concatenated PGDs is always a power of two of PAGE_SIZE,
	 * so there should be no need to free any of the tail pages to make the
	 * allocation exact.
	 */
	WARN_ON(size != (PAGE_SIZE << get_order(size)));

	return addr;
}

static void *host_s2_zalloc_page(void *pool)
{
	return hyp_alloc_pages(pool, 0);
}

static void host_s2_get_page(void *addr)
{
	hyp_get_page(&host_s2_pool, addr);
}

static void host_s2_put_page(void *addr)
{
	hyp_put_page(&host_s2_pool, addr);
}

static void host_s2_free_unlinked_table(void *addr, s8 level)
{
	kvm_pgtable_stage2_free_unlinked(&host_mmu.mm_ops, addr, level);
}

static int prepare_s2_pool(void *pgt_pool_base)
{
	unsigned long nr_pages, pfn;
	int ret;

	pfn = hyp_virt_to_pfn(pgt_pool_base);
	nr_pages = host_s2_pgtable_pages();
	ret = hyp_pool_init(&host_s2_pool, pfn, nr_pages, 0);
	if (ret)
		return ret;

	host_mmu.mm_ops = (struct kvm_pgtable_mm_ops) {
		.zalloc_pages_exact = host_s2_zalloc_pages_exact,
		.zalloc_page = host_s2_zalloc_page,
		.free_unlinked_table = host_s2_free_unlinked_table,
		.phys_to_virt = hyp_phys_to_virt,
		.virt_to_phys = hyp_virt_to_phys,
		.page_count = hyp_page_count,
		.get_page = host_s2_get_page,
		.put_page = host_s2_put_page,
	};

	return 0;
}

static void prepare_host_vtcr(void)
{
	u32 parange, phys_shift;

	/* The host stage 2 is id-mapped, so use parange for T0SZ */
	parange = kvm_get_parange(id_aa64mmfr0_el1_sys_val);
	phys_shift = id_aa64mmfr0_parange_to_phys_shift(parange);

	host_mmu.arch.mmu.vtcr = kvm_get_vtcr(id_aa64mmfr0_el1_sys_val,
					      id_aa64mmfr1_el1_sys_val, phys_shift);
}

static bool host_stage2_force_pte_cb(u64 addr, u64 end, enum kvm_pgtable_prot prot);

int kvm_host_prepare_stage2(void *pgt_pool_base)
{
	struct kvm_s2_mmu *mmu = &host_mmu.arch.mmu;
	int ret;

	prepare_host_vtcr();
	hyp_spin_lock_init(&host_mmu.lock);
	mmu->arch = &host_mmu.arch;

	ret = prepare_s2_pool(pgt_pool_base);
	if (ret)
		return ret;

	ret = __kvm_pgtable_stage2_init(&host_mmu.pgt, mmu,
					&host_mmu.mm_ops, KVM_HOST_S2_FLAGS,
					host_stage2_force_pte_cb);
	if (ret)
		return ret;

	mmu->pgd_phys = __hyp_pa(host_mmu.pgt.pgd);
	mmu->pgt = &host_mmu.pgt;
	atomic64_set(&mmu->vmid.id, 0);

	return 0;
}

static void *guest_s2_zalloc_pages_exact(size_t size)
{
	void *addr = hyp_alloc_pages(&current_vm->pool, get_order(size));

	WARN_ON(size != (PAGE_SIZE << get_order(size)));
	hyp_split_page(hyp_virt_to_page(addr));

	return addr;
}

static void guest_s2_free_pages_exact(void *addr, unsigned long size)
{
	u8 order = get_order(size);
	unsigned int i;

	for (i = 0; i < (1 << order); i++)
		hyp_put_page(&current_vm->pool, addr + (i * PAGE_SIZE));
}

static void *guest_s2_zalloc_page(void *mc)
{
	struct hyp_page *p;
	void *addr;

	addr = hyp_alloc_pages(&current_vm->pool, 0);
	if (addr)
		return addr;

	addr = pop_hyp_memcache(mc, hyp_phys_to_virt);
	if (!addr)
		return addr;

	memset(addr, 0, PAGE_SIZE);
	p = hyp_virt_to_page(addr);
	p->refcount = 1;

	return addr;
}

static void guest_s2_get_page(void *addr)
{
	hyp_get_page(&current_vm->pool, addr);
}

static void guest_s2_put_page(void *addr)
{
	hyp_put_page(&current_vm->pool, addr);
}

static void __apply_guest_page(void *va, size_t size,
			       void (*func)(void *addr, size_t size))
{
	size += va - PTR_ALIGN_DOWN(va, PAGE_SIZE);
	va = PTR_ALIGN_DOWN(va, PAGE_SIZE);
	size = PAGE_ALIGN(size);

	while (size) {
		size_t map_size = PAGE_SIZE;
		void *map;

		if (IS_ALIGNED((unsigned long)va, PMD_SIZE) && size >= PMD_SIZE)
			map = hyp_fixblock_map(__hyp_pa(va), &map_size);
		else
			map = hyp_fixmap_map(__hyp_pa(va));

		func(map, map_size);

		if (map_size == PMD_SIZE)
			hyp_fixblock_unmap();
		else
			hyp_fixmap_unmap();

		size -= map_size;
		va += map_size;
	}
}

static void clean_dcache_guest_page(void *va, size_t size)
{
	/* See comment in __clean_dcache_guest_page() */
	if (cpus_have_final_cap(ARM64_HAS_STAGE2_FWB))
		return;

	__apply_guest_page(va, size, __clean_dcache_guest_page);
}

static void invalidate_icache_guest_page(void *va, size_t size)
{
	if (alternative_has_cap_unlikely(ARM64_HAS_CACHE_DIC))
		return;

	__apply_guest_page(va, size, __invalidate_icache_guest_page);
}

int kvm_guest_prepare_stage2(struct pkvm_hyp_vm *vm, void *pgd)
{
	struct kvm_s2_mmu *mmu = &vm->kvm.arch.mmu;
	unsigned long nr_pages;
	int ret;

	nr_pages = kvm_pgtable_stage2_pgd_size(mmu->vtcr) >> PAGE_SHIFT;
	ret = hyp_pool_init(&vm->pool, hyp_virt_to_pfn(pgd), nr_pages, 0);
	if (ret)
		return ret;

	hyp_spin_lock_init(&vm->lock);
	vm->mm_ops = (struct kvm_pgtable_mm_ops) {
		.zalloc_pages_exact	= guest_s2_zalloc_pages_exact,
		.free_pages_exact	= guest_s2_free_pages_exact,
		.zalloc_page		= guest_s2_zalloc_page,
		.phys_to_virt		= hyp_phys_to_virt,
		.virt_to_phys		= hyp_virt_to_phys,
		.page_count		= hyp_page_count,
		.get_page		= guest_s2_get_page,
		.put_page		= guest_s2_put_page,
		.dcache_clean_inval_poc	= clean_dcache_guest_page,
		.icache_inval_pou	= invalidate_icache_guest_page,
	};

	guest_lock_component(vm);
	ret = __kvm_pgtable_stage2_init(mmu->pgt, mmu, &vm->mm_ops, 0, NULL);
	guest_unlock_component(vm);
	if (ret)
		return ret;

	vm->kvm.arch.mmu.pgd_phys = __hyp_pa(vm->pgt.pgd);

	return 0;
}

void kvm_guest_destroy_stage2(struct pkvm_hyp_vm *vm)
{
	guest_lock_component(vm);
	kvm_pgtable_stage2_destroy(&vm->pgt);
	vm->kvm.arch.mmu.pgd_phys = 0ULL;
	guest_unlock_component(vm);
}

void reclaim_pgtable_pages(struct pkvm_hyp_vm *vm, struct kvm_hyp_memcache *mc)
{
	struct hyp_page *page;
	void *addr;

	/* Dump all pgtable pages in the hyp_pool */
	kvm_guest_destroy_stage2(vm);

	/* Drain the hyp_pool into the memcache */
	addr = hyp_alloc_pages(&vm->pool, 0);
	while (addr) {
		page = hyp_virt_to_page(addr);
		page->refcount = 0;
		push_hyp_memcache(mc, addr, hyp_virt_to_phys);
		WARN_ON(__pkvm_hyp_donate_host(hyp_virt_to_pfn(addr), 1));
		addr = hyp_alloc_pages(&vm->pool, 0);
	}
}

int __pkvm_prot_finalize(void)
{
	struct kvm_s2_mmu *mmu = &host_mmu.arch.mmu;
	struct kvm_nvhe_init_params *params = this_cpu_ptr(&kvm_init_params);

	if (params->hcr_el2 & HCR_VM)
		return -EPERM;

	params->vttbr = kvm_get_vttbr(mmu);
	params->vtcr = mmu->vtcr;
	params->hcr_el2 |= HCR_VM;
	if (cpus_have_final_cap(ARM64_HAS_STAGE2_FWB))
		params->hcr_el2 |= HCR_FWB;

	/*
	 * The CMO below not only cleans the updated params to the
	 * PoC, but also provides the DSB that ensures ongoing
	 * page-table walks that have started before we trapped to EL2
	 * have completed.
	 */
	kvm_flush_dcache_to_poc(params, sizeof(*params));

	write_sysreg_hcr(params->hcr_el2);
	__load_stage2(&host_mmu.arch.mmu);

	/*
	 * Make sure to have an ISB before the TLB maintenance below but only
	 * when __load_stage2() doesn't include one already.
	 */
	asm(ALTERNATIVE("isb", "nop", ARM64_WORKAROUND_SPECULATIVE_AT));

	/* Invalidate stale HCR bits that may be cached in TLBs */
	__tlbi(vmalls12e1);
	dsb(nsh);
	isb();

	return 0;
}

static int host_stage2_unmap_dev_all(void)
{
	struct kvm_pgtable *pgt = &host_mmu.pgt;
	struct memblock_region *reg;
	u64 addr = 0;
	int i, ret;

	/* Unmap all non-memory regions to recycle the pages */
	for (i = 0; i < hyp_memblock_nr; i++, addr = reg->base + reg->size) {
		reg = &hyp_memory[i];
		ret = kvm_pgtable_stage2_unmap(pgt, addr, reg->base - addr);
		if (ret)
			return ret;
	}
	return kvm_pgtable_stage2_unmap(pgt, addr, BIT(pgt->ia_bits) - addr);
}

/*
 * Ensure the PFN range is contained within PA-range.
 *
 * This check is also robust to overflows and is therefore a requirement before
 * using a pfn/nr_pages pair from an untrusted source.
 */
static bool pfn_range_is_valid(u64 pfn, u64 nr_pages)
{
	u64 limit = BIT(kvm_phys_shift(&host_mmu.arch.mmu) - PAGE_SHIFT);

	return pfn < limit && ((limit - pfn) >= nr_pages);
}

struct kvm_mem_range {
	u64 start;
	u64 end;
};

static struct memblock_region *find_mem_range(phys_addr_t addr, struct kvm_mem_range *range)
{
	int cur, left = 0, right = hyp_memblock_nr;
	struct memblock_region *reg;
	phys_addr_t end;

	range->start = 0;
	range->end = ULONG_MAX;

	/* The list of memblock regions is sorted, binary search it */
	while (left < right) {
		cur = (left + right) >> 1;
		reg = &hyp_memory[cur];
		end = reg->base + reg->size;
		if (addr < reg->base) {
			right = cur;
			range->end = reg->base;
		} else if (addr >= end) {
			left = cur + 1;
			range->start = end;
		} else {
			range->start = reg->base;
			range->end = end;
			return reg;
		}
	}

	return NULL;
}

bool addr_is_memory(phys_addr_t phys)
{
	struct kvm_mem_range range;

	return !!find_mem_range(phys, &range);
}

bool addr_is_hyp_text(phys_addr_t phys)
{
	phys_addr_t start = ALIGN_DOWN(__hyp_pa(__hyp_text_start), PAGE_SIZE);
	phys_addr_t end = PAGE_ALIGN(__hyp_pa(__hyp_text_end));

	return phys >= start && phys < end;
}

static bool is_in_mem_range(u64 addr, struct kvm_mem_range *range)
{
	return range->start <= addr && addr < range->end;
}

static int check_range_allowed_memory(u64 start, u64 end)
{
	struct memblock_region *reg;
	struct kvm_mem_range range;

	/*
	 * Callers can't check the state of a range that overlaps memory and
	 * MMIO regions, so ensure [start, end[ is in the same kvm_mem_range.
	 */
	reg = find_mem_range(start, &range);
	if (!is_in_mem_range(end - 1, &range))
		return -EINVAL;

	if (!reg || reg->flags & MEMBLOCK_NOMAP)
		return -EPERM;

	return 0;
}

static bool range_is_memory(u64 start, u64 end)
{
	struct kvm_mem_range r;

	if (!find_mem_range(start, &r))
		return false;

	return is_in_mem_range(end - 1, &r);
}

static inline int __host_stage2_idmap(u64 start, u64 end,
				      enum kvm_pgtable_prot prot)
{
	/*
	 * We don't make permission changes to the host idmap after
	 * initialisation, so we can squash -EAGAIN to save callers
	 * having to treat it like success in the case that they try to
	 * map something that is already mapped.
	 */
	return kvm_pgtable_stage2_map(&host_mmu.pgt, start, end - start, start,
				      prot, &host_s2_pool,
				      KVM_PGTABLE_WALK_IGNORE_EAGAIN);
}

/*
 * The pool has been provided with enough pages to cover all of memory with
 * page granularity, but it is difficult to know how much of the MMIO range
 * we will need to cover upfront, so we may need to 'recycle' the pages if we
 * run out.
 */
#define host_stage2_try(fn, ...)					\
	({								\
		int __ret;						\
		hyp_assert_lock_held(&host_mmu.lock);			\
		__ret = fn(__VA_ARGS__);				\
		if (__ret == -ENOMEM) {					\
			__ret = host_stage2_unmap_dev_all();		\
			if (!__ret)					\
				__ret = fn(__VA_ARGS__);		\
		}							\
		__ret;							\
	 })

static inline bool range_included(struct kvm_mem_range *child,
				  struct kvm_mem_range *parent)
{
	return parent->start <= child->start && child->end <= parent->end;
}

static int host_stage2_adjust_range(u64 addr, struct kvm_mem_range *range)
{
	struct kvm_mem_range cur;
	kvm_pte_t pte;
	u64 granule;
	s8 level;
	int ret;

	hyp_assert_lock_held(&host_mmu.lock);
	ret = kvm_pgtable_get_leaf(&host_mmu.pgt, addr, &pte, &level, 0);
	if (ret)
		return ret;

	if (kvm_pte_valid(pte))
		return -EEXIST;

	if (pte) {
		WARN_ON(addr_is_memory(addr) &&
			get_host_state(hyp_phys_to_page(addr)) != PKVM_NOPAGE);
		return -EPERM;
	}

	for (; level <= KVM_PGTABLE_LAST_LEVEL; level++) {
		if (!kvm_level_supports_block_mapping(level))
			continue;
		granule = kvm_granule_size(level);
		cur.start = ALIGN_DOWN(addr, granule);
		cur.end = cur.start + granule;
		if (!range_included(&cur, range) && level < KVM_PGTABLE_LAST_LEVEL)
			continue;
		*range = cur;
		return 0;
	}

	WARN_ON(1);

	return -EINVAL;
}

int host_stage2_idmap_locked(phys_addr_t addr, u64 size,
			     enum kvm_pgtable_prot prot)
{
	return host_stage2_try(__host_stage2_idmap, addr, addr + size, prot);
}

static void __host_update_page_state(phys_addr_t addr, u64 size, enum pkvm_page_state state)
{
	for_each_hyp_page(page, addr, size)
		set_host_state(page, state);
}

#define KVM_HOST_DONATION_PTE_OWNER_MASK	GENMASK(3, 1)
#define KVM_HOST_DONATION_PTE_EXTRA_MASK	GENMASK(59, 4)
static int host_stage2_set_owner_metadata_locked(phys_addr_t addr, u64 size,
						 u8 owner_id, u64 meta)
{
	kvm_pte_t annotation;
	int ret;

	if (owner_id == PKVM_ID_HOST)
		return -EINVAL;

	if (!range_is_memory(addr, addr + size))
		return -EPERM;

	if (!FIELD_FIT(KVM_HOST_DONATION_PTE_OWNER_MASK, owner_id))
		return -EINVAL;

	if (!FIELD_FIT(KVM_HOST_DONATION_PTE_EXTRA_MASK, meta))
		return -EINVAL;

	annotation = FIELD_PREP(KVM_HOST_DONATION_PTE_OWNER_MASK, owner_id) |
		     FIELD_PREP(KVM_HOST_DONATION_PTE_EXTRA_MASK, meta);
	ret = host_stage2_try(kvm_pgtable_stage2_annotate, &host_mmu.pgt,
			      addr, size, &host_s2_pool,
			      KVM_HOST_INVALID_PTE_TYPE_DONATION, annotation);
	if (!ret) {
		/*
		 * After stage2 maintenance has happened, but before the page
		 * owner has changed.
		 */
		pkvm_sme_dvmsync_fw_call();
		__host_update_page_state(addr, size, PKVM_NOPAGE);
	}

	return ret;
}

int host_stage2_set_owner_locked(phys_addr_t addr, u64 size, u8 owner_id)
{
	int ret = -EINVAL;

	switch (owner_id) {
	case PKVM_ID_HOST:
		if (!range_is_memory(addr, addr + size))
			return -EPERM;

		ret = host_stage2_idmap_locked(addr, size, PKVM_HOST_MEM_PROT);
		if (!ret)
			__host_update_page_state(addr, size, PKVM_PAGE_OWNED);
		break;
	case PKVM_ID_HYP:
		ret = host_stage2_set_owner_metadata_locked(addr, size,
							    owner_id, 0);
		break;
	}

	return ret;
}

bool host_stage2_pte_is_hyp_owned(kvm_pte_t pte)
{
	if (kvm_pte_valid(pte))
		return false;

	if (FIELD_GET(KVM_INVALID_PTE_TYPE_MASK, pte) !=
	    KVM_HOST_INVALID_PTE_TYPE_DONATION)
		return false;

	return FIELD_GET(KVM_HOST_DONATION_PTE_OWNER_MASK, pte) == PKVM_ID_HYP;
}

#define KVM_HOST_PTE_OWNER_GUEST_HANDLE_MASK	GENMASK(15, 0)
/* We need 40 bits for the GFN to cover a 52-bit IPA with 4k pages and LPA2 */
#define KVM_HOST_PTE_OWNER_GUEST_GFN_MASK	GENMASK(55, 16)
static u64 host_stage2_encode_gfn_meta(struct pkvm_hyp_vm *vm, u64 gfn)
{
	pkvm_handle_t handle = vm->kvm.arch.pkvm.handle;

	BUILD_BUG_ON((pkvm_handle_t)-1 > KVM_HOST_PTE_OWNER_GUEST_HANDLE_MASK);
	WARN_ON(!FIELD_FIT(KVM_HOST_PTE_OWNER_GUEST_GFN_MASK, gfn));

	return FIELD_PREP(KVM_HOST_PTE_OWNER_GUEST_HANDLE_MASK, handle) |
	       FIELD_PREP(KVM_HOST_PTE_OWNER_GUEST_GFN_MASK, gfn);
}

static int host_stage2_decode_gfn_meta(kvm_pte_t pte, struct pkvm_hyp_vm **vm,
				       u64 *gfn)
{
	pkvm_handle_t handle;
	u64 meta;

	if (WARN_ON(kvm_pte_valid(pte)))
		return -EINVAL;

	if (FIELD_GET(KVM_INVALID_PTE_TYPE_MASK, pte) !=
	    KVM_HOST_INVALID_PTE_TYPE_DONATION) {
		return -EINVAL;
	}

	if (FIELD_GET(KVM_HOST_DONATION_PTE_OWNER_MASK, pte) != PKVM_ID_GUEST)
		return -EPERM;

	meta = FIELD_GET(KVM_HOST_DONATION_PTE_EXTRA_MASK, pte);
	handle = FIELD_GET(KVM_HOST_PTE_OWNER_GUEST_HANDLE_MASK, meta);
	*vm = get_vm_by_handle(handle);
	if (!*vm) {
		/* We probably raced with teardown; try again */
		return -EAGAIN;
	}

	*gfn = FIELD_GET(KVM_HOST_PTE_OWNER_GUEST_GFN_MASK, meta);
	return 0;
}

static bool host_stage2_force_pte_cb(u64 addr, u64 end, enum kvm_pgtable_prot prot)
{
	/*
	 * Block mappings must be used with care in the host stage-2 as a
	 * kvm_pgtable_stage2_map() operation targeting a page in the range of
	 * an existing block will delete the block under the assumption that
	 * mappings in the rest of the block range can always be rebuilt lazily.
	 * That assumption is correct for the host stage-2 with RWX mappings
	 * targeting memory or RW mappings targeting MMIO ranges (see
	 * host_stage2_idmap() below which implements some of the host memory
	 * abort logic). However, this is not safe for any other mappings where
	 * the host stage-2 page-table is in fact the only place where this
	 * state is stored. In all those cases, it is safer to use page-level
	 * mappings, hence avoiding to lose the state because of side-effects in
	 * kvm_pgtable_stage2_map().
	 */
	if (range_is_memory(addr, end))
		return prot != PKVM_HOST_MEM_PROT;
	else
		return prot != PKVM_HOST_MMIO_PROT;
}

static int host_stage2_idmap(u64 addr)
{
	struct kvm_mem_range range;
	bool is_memory = !!find_mem_range(addr, &range);
	enum kvm_pgtable_prot prot;
	int ret;

	prot = is_memory ? PKVM_HOST_MEM_PROT : PKVM_HOST_MMIO_PROT;

	host_lock_component();
	ret = host_stage2_adjust_range(addr, &range);
	if (ret)
		goto unlock;

	ret = host_stage2_idmap_locked(range.start, range.end - range.start, prot);
unlock:
	host_unlock_component();

	return ret;
}

static void host_inject_mem_abort(struct kvm_cpu_context *host_ctxt)
{
	u64 ec, esr, spsr;

	esr = read_sysreg_el2(SYS_ESR);
	spsr = read_sysreg_el2(SYS_SPSR);

	/* Repaint the ESR to report a same-level fault if taken from EL1 */
	if ((spsr & PSR_MODE_MASK) != PSR_MODE_EL0t) {
		ec = ESR_ELx_EC(esr);
		if (ec == ESR_ELx_EC_DABT_LOW)
			ec = ESR_ELx_EC_DABT_CUR;
		else if (ec == ESR_ELx_EC_IABT_LOW)
			ec = ESR_ELx_EC_IABT_CUR;
		else
			WARN_ON(1);
		esr &= ~ESR_ELx_EC_MASK;
		esr |= ec << ESR_ELx_EC_SHIFT;
	}

	/*
	 * Since S1PTW should only ever be set for stage-2 faults, we're pretty
	 * much guaranteed that it won't be set in ESR_EL1 by the hardware. So,
	 * let's use that bit to allow the host abort handler to differentiate
	 * this abort from normal userspace faults.
	 *
	 * Note: although S1PTW is RES0 at EL1, it is guaranteed by the
	 * architecture to be backed by flops, so it should be safe to use.
	 */
	esr |= ESR_ELx_S1PTW;
	inject_host_exception(esr);
}

void handle_host_mem_abort(struct kvm_cpu_context *host_ctxt)
{
	struct kvm_vcpu_fault_info fault;
	u64 esr, addr;

	esr = read_sysreg_el2(SYS_ESR);
	if (!__get_fault_info(esr, &fault)) {
		/*
		 * We've presumably raced with a page-table change which caused
		 * AT to fail, try again.
		 */
		return;
	}


	/*
	 * Yikes, we couldn't resolve the fault IPA. This should reinject an
	 * abort into the host when we figure out how to do that.
	 */
	BUG_ON(!(fault.hpfar_el2 & HPFAR_EL2_NS));
	addr = FIELD_GET(HPFAR_EL2_FIPA, fault.hpfar_el2) << 12;

	switch (host_stage2_idmap(addr)) {
	case -EPERM:
		host_inject_mem_abort(host_ctxt);
		fallthrough;
	case -EEXIST:
	case 0:
		break;
	default:
		BUG();
	}
}

struct check_walk_data {
	enum pkvm_page_state	desired;
	enum pkvm_page_state	(*get_page_state)(kvm_pte_t pte, u64 addr);
};

static int __check_page_state_visitor(const struct kvm_pgtable_visit_ctx *ctx,
				      enum kvm_pgtable_walk_flags visit)
{
	struct check_walk_data *d = ctx->arg;

	return d->get_page_state(ctx->old, ctx->addr) == d->desired ? 0 : -EPERM;
}

static int check_page_state_range(struct kvm_pgtable *pgt, u64 addr, u64 size,
				  struct check_walk_data *data)
{
	struct kvm_pgtable_walker walker = {
		.cb	= __check_page_state_visitor,
		.arg	= data,
		.flags	= KVM_PGTABLE_WALK_LEAF,
	};

	return kvm_pgtable_walk(pgt, addr, size, &walker);
}

static int __host_check_page_state_range(u64 addr, u64 size,
					 enum pkvm_page_state state)
{
	int ret;

	ret = check_range_allowed_memory(addr, addr + size);
	if (ret)
		return ret;

	hyp_assert_lock_held(&host_mmu.lock);

	for_each_hyp_page(page, addr, size) {
		if (get_host_state(page) != state)
			return -EPERM;
	}

	return 0;
}

static int __host_set_page_state_range(u64 addr, u64 size,
				       enum pkvm_page_state state)
{
	if (get_host_state(hyp_phys_to_page(addr)) == PKVM_NOPAGE) {
		int ret = host_stage2_idmap_locked(addr, size, PKVM_HOST_MEM_PROT);

		if (ret)
			return ret;
	}

	__host_update_page_state(addr, size, state);

	return 0;
}

static void __hyp_set_page_state_range(phys_addr_t phys, u64 size, enum pkvm_page_state state)
{
	for_each_hyp_page(page, phys, size)
		set_hyp_state(page, state);
}

static int __hyp_check_page_state_range(phys_addr_t phys, u64 size, enum pkvm_page_state state)
{
	for_each_hyp_page(page, phys, size) {
		if (get_hyp_state(page) != state)
			return -EPERM;
	}

	return 0;
}

static int __hyp_check_page_count_range(phys_addr_t phys, u64 size)
{
	for_each_hyp_page(page, phys, size) {
		if (page->refcount)
			return -EBUSY;
	}

	return 0;
}

static bool guest_pte_is_poisoned(kvm_pte_t pte)
{
	if (kvm_pte_valid(pte))
		return false;

	return FIELD_GET(KVM_INVALID_PTE_TYPE_MASK, pte) ==
	       KVM_GUEST_INVALID_PTE_TYPE_POISONED;
}

static enum pkvm_page_state guest_get_page_state(kvm_pte_t pte, u64 addr)
{
	if (guest_pte_is_poisoned(pte))
		return PKVM_POISON;

	if (!kvm_pte_valid(pte))
		return PKVM_NOPAGE;

	return pkvm_getstate(kvm_pgtable_stage2_pte_prot(pte));
}

static int __guest_check_page_state_range(struct pkvm_hyp_vm *vm, u64 addr,
					  u64 size, enum pkvm_page_state state)
{
	struct check_walk_data d = {
		.desired	= state,
		.get_page_state	= guest_get_page_state,
	};

	hyp_assert_lock_held(&vm->lock);
	return check_page_state_range(&vm->pgt, addr, size, &d);
}

static int get_valid_guest_pte(struct pkvm_hyp_vm *vm, u64 ipa, kvm_pte_t *ptep, u64 *physp)
{
	kvm_pte_t pte;
	u64 phys;
	s8 level;
	int ret;

	ret = kvm_pgtable_get_leaf(&vm->pgt, ipa, &pte, &level, 0);
	if (ret)
		return ret;
	if (guest_pte_is_poisoned(pte))
		return -EHWPOISON;
	if (!kvm_pte_valid(pte))
		return -ENOENT;
	if (level != KVM_PGTABLE_LAST_LEVEL)
		return -E2BIG;

	phys = kvm_pte_to_phys(pte);
	ret = check_range_allowed_memory(phys, phys + PAGE_SIZE);
	if (WARN_ON(ret))
		return ret;

	*ptep = pte;
	*physp = phys;

	return 0;
}

int __pkvm_vcpu_in_poison_fault(struct pkvm_hyp_vcpu *hyp_vcpu)
{
	struct pkvm_hyp_vm *vm = pkvm_hyp_vcpu_to_hyp_vm(hyp_vcpu);
	kvm_pte_t pte;
	s8 level;
	u64 ipa;
	int ret;

	switch (kvm_vcpu_trap_get_class(&hyp_vcpu->vcpu)) {
	case ESR_ELx_EC_DABT_LOW:
	case ESR_ELx_EC_IABT_LOW:
		if (kvm_vcpu_trap_is_translation_fault(&hyp_vcpu->vcpu))
			break;
		fallthrough;
	default:
		return -EINVAL;
	}

	/*
	 * The host has the faulting IPA when it calls us from the guest
	 * fault handler but we retrieve it ourselves from the FAR so as
	 * to avoid exposing an "oracle" that could reveal data access
	 * patterns of the guest after initial donation of its pages.
	 */
	ipa = kvm_vcpu_get_fault_ipa(&hyp_vcpu->vcpu);
	ipa |= FAR_TO_FIPA_OFFSET(kvm_vcpu_get_hfar(&hyp_vcpu->vcpu));

	guest_lock_component(vm);
	ret = kvm_pgtable_get_leaf(&vm->pgt, ipa, &pte, &level, 0);
	if (ret)
		goto unlock;

	if (level != KVM_PGTABLE_LAST_LEVEL) {
		ret = -EINVAL;
		goto unlock;
	}

	ret = guest_pte_is_poisoned(pte);
unlock:
	guest_unlock_component(vm);
	return ret;
}

int __pkvm_host_share_hyp(u64 pfn)
{
	u64 phys = hyp_pfn_to_phys(pfn);
	u64 size = PAGE_SIZE;
	int ret;

	host_lock_component();
	hyp_lock_component();

	ret = __host_check_page_state_range(phys, size, PKVM_PAGE_OWNED);
	if (ret)
		goto unlock;
	ret = __hyp_check_page_state_range(phys, size, PKVM_NOPAGE);
	if (ret)
		goto unlock;

	__hyp_set_page_state_range(phys, size, PKVM_PAGE_SHARED_BORROWED);
	WARN_ON(__host_set_page_state_range(phys, size, PKVM_PAGE_SHARED_OWNED));

unlock:
	hyp_unlock_component();
	host_unlock_component();

	return ret;
}

int __pkvm_guest_share_host(struct pkvm_hyp_vcpu *vcpu, u64 gfn)
{
	struct pkvm_hyp_vm *vm = pkvm_hyp_vcpu_to_hyp_vm(vcpu);
	u64 phys, ipa = hyp_pfn_to_phys(gfn);
	kvm_pte_t pte;
	int ret;

	host_lock_component();
	guest_lock_component(vm);

	ret = get_valid_guest_pte(vm, ipa, &pte, &phys);
	if (ret)
		goto unlock;

	ret = -EPERM;
	if (pkvm_getstate(kvm_pgtable_stage2_pte_prot(pte)) != PKVM_PAGE_OWNED)
		goto unlock;
	if (__host_check_page_state_range(phys, PAGE_SIZE, PKVM_NOPAGE))
		goto unlock;

	ret = 0;
	WARN_ON(kvm_pgtable_stage2_map(&vm->pgt, ipa, PAGE_SIZE, phys,
				       pkvm_mkstate(KVM_PGTABLE_PROT_RWX, PKVM_PAGE_SHARED_OWNED),
				       &vcpu->vcpu.arch.stage2_mc, 0));
	WARN_ON(__host_set_page_state_range(phys, PAGE_SIZE, PKVM_PAGE_SHARED_BORROWED));
unlock:
	guest_unlock_component(vm);
	host_unlock_component();

	return ret;
}

int __pkvm_guest_unshare_host(struct pkvm_hyp_vcpu *vcpu, u64 gfn)
{
	struct pkvm_hyp_vm *vm = pkvm_hyp_vcpu_to_hyp_vm(vcpu);
	u64 meta, phys, ipa = hyp_pfn_to_phys(gfn);
	kvm_pte_t pte;
	int ret;

	host_lock_component();
	guest_lock_component(vm);

	ret = get_valid_guest_pte(vm, ipa, &pte, &phys);
	if (ret)
		goto unlock;

	ret = -EPERM;
	if (pkvm_getstate(kvm_pgtable_stage2_pte_prot(pte)) != PKVM_PAGE_SHARED_OWNED)
		goto unlock;
	if (__host_check_page_state_range(phys, PAGE_SIZE, PKVM_PAGE_SHARED_BORROWED))
		goto unlock;

	ret = 0;
	meta = host_stage2_encode_gfn_meta(vm, gfn);
	WARN_ON(host_stage2_set_owner_metadata_locked(phys, PAGE_SIZE,
						      PKVM_ID_GUEST, meta));
	WARN_ON(kvm_pgtable_stage2_map(&vm->pgt, ipa, PAGE_SIZE, phys,
				       pkvm_mkstate(KVM_PGTABLE_PROT_RWX, PKVM_PAGE_OWNED),
				       &vcpu->vcpu.arch.stage2_mc, 0));
unlock:
	guest_unlock_component(vm);
	host_unlock_component();

	return ret;
}

int __pkvm_host_unshare_hyp(u64 pfn)
{
	u64 phys = hyp_pfn_to_phys(pfn);
	u64 size = PAGE_SIZE;
	int ret;

	host_lock_component();
	hyp_lock_component();

	ret = __host_check_page_state_range(phys, size, PKVM_PAGE_SHARED_OWNED);
	if (ret)
		goto unlock;
	ret = __hyp_check_page_state_range(phys, size, PKVM_PAGE_SHARED_BORROWED);
	if (ret)
		goto unlock;
	ret = __hyp_check_page_count_range(phys, size);
	if (ret)
		goto unlock;

	__hyp_set_page_state_range(phys, size, PKVM_NOPAGE);
	WARN_ON(__host_set_page_state_range(phys, size, PKVM_PAGE_OWNED));

unlock:
	hyp_unlock_component();
	host_unlock_component();

	return ret;
}

int __pkvm_host_donate_hyp(u64 pfn, u64 nr_pages)
{
	u64 phys = hyp_pfn_to_phys(pfn);
	u64 size = PAGE_SIZE * nr_pages;
	void *virt = __hyp_va(phys);
	int ret;

	if (!pfn_range_is_valid(pfn, nr_pages))
		return -EINVAL;

	host_lock_component();
	hyp_lock_component();

	ret = __host_check_page_state_range(phys, size, PKVM_PAGE_OWNED);
	if (ret)
		goto unlock;
	ret = __hyp_check_page_state_range(phys, size, PKVM_NOPAGE);
	if (ret)
		goto unlock;

	__hyp_set_page_state_range(phys, size, PKVM_PAGE_OWNED);
	WARN_ON(pkvm_create_mappings_locked(virt, virt + size, PAGE_HYP));
	WARN_ON(host_stage2_set_owner_locked(phys, size, PKVM_ID_HYP));

unlock:
	hyp_unlock_component();
	host_unlock_component();

	return ret;
}

int __pkvm_hyp_donate_host(u64 pfn, u64 nr_pages)
{
	u64 phys = hyp_pfn_to_phys(pfn);
	u64 size = PAGE_SIZE * nr_pages;
	u64 virt = (u64)__hyp_va(phys);
	int ret;

	if (!pfn_range_is_valid(pfn, nr_pages))
		return -EINVAL;

	host_lock_component();
	hyp_lock_component();

	ret = __hyp_check_page_state_range(phys, size, PKVM_PAGE_OWNED);
	if (ret)
		goto unlock;
	ret = __host_check_page_state_range(phys, size, PKVM_NOPAGE);
	if (ret)
		goto unlock;

	ret = __hyp_check_page_count_range(phys, size);
	if (ret)
		goto unlock;

	__hyp_set_page_state_range(phys, size, PKVM_NOPAGE);
	WARN_ON(kvm_pgtable_hyp_unmap(&pkvm_pgtable, virt, size) != size);
	WARN_ON(host_stage2_set_owner_locked(phys, size, PKVM_ID_HOST));

unlock:
	hyp_unlock_component();
	host_unlock_component();

	return ret;
}

int hyp_pin_shared_mem(void *from, void *to)
{
	u64 cur, start = ALIGN_DOWN((u64)from, PAGE_SIZE);
	u64 end = PAGE_ALIGN((u64)to);
	u64 phys = __hyp_pa(start);
	u64 size = end - start;
	struct hyp_page *p;
	int ret;

	host_lock_component();
	hyp_lock_component();

	ret = __host_check_page_state_range(phys, size, PKVM_PAGE_SHARED_OWNED);
	if (ret)
		goto unlock;

	ret = __hyp_check_page_state_range(phys, size, PKVM_PAGE_SHARED_BORROWED);
	if (ret)
		goto unlock;

	for (cur = start; cur < end; cur += PAGE_SIZE) {
		p = hyp_virt_to_page(cur);
		hyp_page_ref_inc(p);
		if (p->refcount == 1)
			WARN_ON(pkvm_create_mappings_locked((void *)cur,
							    (void *)cur + PAGE_SIZE,
							    PAGE_HYP));
	}

unlock:
	hyp_unlock_component();
	host_unlock_component();

	return ret;
}

void hyp_unpin_shared_mem(void *from, void *to)
{
	u64 cur, start = ALIGN_DOWN((u64)from, PAGE_SIZE);
	u64 end = PAGE_ALIGN((u64)to);
	struct hyp_page *p;

	host_lock_component();
	hyp_lock_component();

	for (cur = start; cur < end; cur += PAGE_SIZE) {
		p = hyp_virt_to_page(cur);
		if (p->refcount == 1)
			WARN_ON(kvm_pgtable_hyp_unmap(&pkvm_pgtable, cur, PAGE_SIZE) != PAGE_SIZE);
		hyp_page_ref_dec(p);
	}

	hyp_unlock_component();
	host_unlock_component();
}

int __pkvm_host_share_ffa(u64 pfn, u64 nr_pages)
{
	u64 phys = hyp_pfn_to_phys(pfn);
	u64 size = PAGE_SIZE * nr_pages;
	int ret;

	if (!pfn_range_is_valid(pfn, nr_pages))
		return -EINVAL;

	host_lock_component();
	ret = __host_check_page_state_range(phys, size, PKVM_PAGE_OWNED);
	if (!ret)
		ret = __host_set_page_state_range(phys, size, PKVM_PAGE_SHARED_OWNED);
	host_unlock_component();

	return ret;
}

int __pkvm_host_unshare_ffa(u64 pfn, u64 nr_pages)
{
	u64 phys = hyp_pfn_to_phys(pfn);
	u64 size = PAGE_SIZE * nr_pages;
	int ret;

	if (!pfn_range_is_valid(pfn, nr_pages))
		return -EINVAL;

	host_lock_component();
	ret = __host_check_page_state_range(phys, size, PKVM_PAGE_SHARED_OWNED);
	if (!ret)
		ret = __host_set_page_state_range(phys, size, PKVM_PAGE_OWNED);
	host_unlock_component();

	return ret;
}

static int __guest_check_transition_size(u64 phys, u64 ipa, u64 nr_pages, u64 *size)
{
	size_t block_size;

	if (nr_pages == 1) {
		*size = PAGE_SIZE;
		return 0;
	}

	/* We solely support second to last level huge mapping */
	block_size = kvm_granule_size(KVM_PGTABLE_LAST_LEVEL - 1);

	if (nr_pages != block_size >> PAGE_SHIFT)
		return -EINVAL;

	if (!IS_ALIGNED(phys | ipa, block_size))
		return -EINVAL;

	*size = block_size;
	return 0;
}

static void hyp_poison_page(phys_addr_t phys)
{
	void *addr = hyp_fixmap_map(phys);

	memset(addr, 0, PAGE_SIZE);
	/*
	 * Prefer kvm_flush_dcache_to_poc() over __clean_dcache_guest_page()
	 * here as the latter may elide the CMO under the assumption that FWB
	 * will be enabled on CPUs that support it. This is incorrect for the
	 * host stage-2 and would otherwise lead to a malicious host potentially
	 * being able to read the contents of newly reclaimed guest pages.
	 */
	kvm_flush_dcache_to_poc(addr, PAGE_SIZE);
	hyp_fixmap_unmap();
}

static int host_stage2_get_guest_info(phys_addr_t phys, struct pkvm_hyp_vm **vm,
				      u64 *gfn)
{
	enum pkvm_page_state state;
	kvm_pte_t pte;
	s8 level;
	int ret;

	if (!addr_is_memory(phys))
		return -EFAULT;

	state = get_host_state(hyp_phys_to_page(phys));
	switch (state) {
	case PKVM_PAGE_OWNED:
	case PKVM_PAGE_SHARED_OWNED:
	case PKVM_PAGE_SHARED_BORROWED:
		/* The access should no longer fault; try again. */
		return -EAGAIN;
	case PKVM_NOPAGE:
		break;
	default:
		return -EPERM;
	}

	ret = kvm_pgtable_get_leaf(&host_mmu.pgt, phys, &pte, &level, 0);
	if (ret)
		return ret;

	if (WARN_ON(level != KVM_PGTABLE_LAST_LEVEL))
		return -EINVAL;

	return host_stage2_decode_gfn_meta(pte, vm, gfn);
}

int __pkvm_host_force_reclaim_page_guest(phys_addr_t phys)
{
	struct pkvm_hyp_vm *vm;
	u64 gfn, ipa, pa;
	kvm_pte_t pte;
	int ret;

	phys &= PAGE_MASK;

	hyp_spin_lock(&vm_table_lock);
	host_lock_component();

	ret = host_stage2_get_guest_info(phys, &vm, &gfn);
	if (ret)
		goto unlock_host;

	ipa = hyp_pfn_to_phys(gfn);
	guest_lock_component(vm);
	ret = get_valid_guest_pte(vm, ipa, &pte, &pa);
	if (ret)
		goto unlock_guest;

	WARN_ON(pa != phys);
	if (guest_get_page_state(pte, ipa) != PKVM_PAGE_OWNED) {
		ret = -EPERM;
		goto unlock_guest;
	}

	/* We really shouldn't be allocating, so don't pass a memcache */
	ret = kvm_pgtable_stage2_annotate(&vm->pgt, ipa, PAGE_SIZE, NULL,
					  KVM_GUEST_INVALID_PTE_TYPE_POISONED,
					  0);
	if (ret)
		goto unlock_guest;

	hyp_poison_page(phys);
	WARN_ON(host_stage2_set_owner_locked(phys, PAGE_SIZE, PKVM_ID_HOST));
unlock_guest:
	guest_unlock_component(vm);
unlock_host:
	host_unlock_component();
	hyp_spin_unlock(&vm_table_lock);

	return ret;
}

int __pkvm_host_reclaim_page_guest(u64 gfn, struct pkvm_hyp_vm *vm)
{
	u64 ipa = hyp_pfn_to_phys(gfn);
	kvm_pte_t pte;
	u64 phys;
	int ret;

	host_lock_component();
	guest_lock_component(vm);

	ret = get_valid_guest_pte(vm, ipa, &pte, &phys);
	if (ret)
		goto unlock;

	switch (guest_get_page_state(pte, ipa)) {
	case PKVM_PAGE_OWNED:
		WARN_ON(__host_check_page_state_range(phys, PAGE_SIZE, PKVM_NOPAGE));
		hyp_poison_page(phys);
		break;
	case PKVM_PAGE_SHARED_OWNED:
		WARN_ON(__host_check_page_state_range(phys, PAGE_SIZE, PKVM_PAGE_SHARED_BORROWED));
		break;
	default:
		ret = -EPERM;
		goto unlock;
	}

	WARN_ON(kvm_pgtable_stage2_unmap(&vm->pgt, ipa, PAGE_SIZE));
	WARN_ON(host_stage2_set_owner_locked(phys, PAGE_SIZE, PKVM_ID_HOST));

unlock:
	guest_unlock_component(vm);
	host_unlock_component();

	/*
	 * -EHWPOISON implies that the page was forcefully reclaimed already
	 * so return success for the GUP pin to be dropped.
	 */
	return ret && ret != -EHWPOISON ? ret : 0;
}

/*
 * share/donate install at most one stage-2 leaf (PAGE_SIZE, or one
 * KVM_PGTABLE_LAST_LEVEL - 1 block for share). kvm_mmu_cache_min_pages()
 * bounds the worst-case allocation: exact for the PAGE_SIZE leaf,
 * conservative by one for the block.
 */
static int __guest_check_pgtable_memcache(struct pkvm_hyp_vcpu *vcpu)
{
	struct pkvm_hyp_vm *vm = pkvm_hyp_vcpu_to_hyp_vm(vcpu);

	if (vcpu->vcpu.arch.stage2_mc.nr_pages < kvm_mmu_cache_min_pages(vm->pgt.mmu))
		return -ENOMEM;

	return 0;
}

int __pkvm_host_donate_guest(u64 pfn, u64 gfn, struct pkvm_hyp_vcpu *vcpu)
{
	struct pkvm_hyp_vm *vm = pkvm_hyp_vcpu_to_hyp_vm(vcpu);
	u64 phys = hyp_pfn_to_phys(pfn);
	u64 ipa = hyp_pfn_to_phys(gfn);
	u64 meta;
	int ret;

	host_lock_component();
	guest_lock_component(vm);

	ret = __host_check_page_state_range(phys, PAGE_SIZE, PKVM_PAGE_OWNED);
	if (ret)
		goto unlock;

	ret = __guest_check_page_state_range(vm, ipa, PAGE_SIZE, PKVM_NOPAGE);
	if (ret)
		goto unlock;

	ret = __guest_check_pgtable_memcache(vcpu);
	if (ret)
		goto unlock;

	meta = host_stage2_encode_gfn_meta(vm, gfn);
	WARN_ON(host_stage2_set_owner_metadata_locked(phys, PAGE_SIZE,
						      PKVM_ID_GUEST, meta));
	WARN_ON(kvm_pgtable_stage2_map(&vm->pgt, ipa, PAGE_SIZE, phys,
				       pkvm_mkstate(KVM_PGTABLE_PROT_RWX, PKVM_PAGE_OWNED),
				       &vcpu->vcpu.arch.stage2_mc, 0));

unlock:
	guest_unlock_component(vm);
	host_unlock_component();

	return ret;
}

int __pkvm_host_share_guest(u64 pfn, u64 gfn, u64 nr_pages, struct pkvm_hyp_vcpu *vcpu,
			    enum kvm_pgtable_prot prot)
{
	struct pkvm_hyp_vm *vm = pkvm_hyp_vcpu_to_hyp_vm(vcpu);
	u64 phys = hyp_pfn_to_phys(pfn);
	u64 ipa = hyp_pfn_to_phys(gfn);
	u64 size;
	int ret;

	if (prot & ~KVM_PGTABLE_PROT_RWX)
		return -EINVAL;

	if (!pfn_range_is_valid(pfn, nr_pages))
		return -EINVAL;

	ret = __guest_check_transition_size(phys, ipa, nr_pages, &size);
	if (ret)
		return ret;

	ret = check_range_allowed_memory(phys, phys + size);
	if (ret)
		return ret;

	host_lock_component();
	guest_lock_component(vm);

	ret = __guest_check_page_state_range(vm, ipa, size, PKVM_NOPAGE);
	if (ret)
		goto unlock;

	for_each_hyp_page(page, phys, size) {
		switch (get_host_state(page)) {
		case PKVM_PAGE_OWNED:
			continue;
		case PKVM_PAGE_SHARED_OWNED:
			if (page->host_share_guest_count == U32_MAX) {
				ret = -EBUSY;
				goto unlock;
			}

			/* Only host to np-guest multi-sharing is tolerated */
			if (page->host_share_guest_count)
				continue;

			fallthrough;
		default:
			ret = -EPERM;
			goto unlock;
		}
	}

	ret = __guest_check_pgtable_memcache(vcpu);
	if (ret)
		goto unlock;

	for_each_hyp_page(page, phys, size) {
		set_host_state(page, PKVM_PAGE_SHARED_OWNED);
		page->host_share_guest_count++;
	}

	WARN_ON(kvm_pgtable_stage2_map(&vm->pgt, ipa, size, phys,
				       pkvm_mkstate(prot, PKVM_PAGE_SHARED_BORROWED),
				       &vcpu->vcpu.arch.stage2_mc, 0));

unlock:
	guest_unlock_component(vm);
	host_unlock_component();

	return ret;
}

static int __check_host_shared_guest(struct pkvm_hyp_vm *vm, u64 *__phys, u64 ipa, u64 size)
{
	enum pkvm_page_state state;
	kvm_pte_t pte;
	u64 phys;
	s8 level;
	int ret;

	ret = kvm_pgtable_get_leaf(&vm->pgt, ipa, &pte, &level, 0);
	if (ret)
		return ret;
	if (!kvm_pte_valid(pte))
		return -ENOENT;
	if (size && kvm_granule_size(level) != size)
		return -E2BIG;

	if (!size)
		size = kvm_granule_size(level);

	state = guest_get_page_state(pte, ipa);
	if (state != PKVM_PAGE_SHARED_BORROWED)
		return -EPERM;

	phys = kvm_pte_to_phys(pte);
	ret = check_range_allowed_memory(phys, phys + size);
	if (WARN_ON(ret))
		return ret;

	for_each_hyp_page(page, phys, size) {
		if (get_host_state(page) != PKVM_PAGE_SHARED_OWNED)
			return -EPERM;
		if (WARN_ON(!page->host_share_guest_count))
			return -EINVAL;
	}

	*__phys = phys;

	return 0;
}

int __pkvm_host_unshare_guest(u64 gfn, u64 nr_pages, struct pkvm_hyp_vm *vm)
{
	u64 ipa = hyp_pfn_to_phys(gfn);
	u64 size, phys;
	int ret;

	ret = __guest_check_transition_size(0, ipa, nr_pages, &size);
	if (ret)
		return ret;

	host_lock_component();
	guest_lock_component(vm);

	ret = __check_host_shared_guest(vm, &phys, ipa, size);
	if (ret)
		goto unlock;

	ret = kvm_pgtable_stage2_unmap(&vm->pgt, ipa, size);
	if (ret)
		goto unlock;

	for_each_hyp_page(page, phys, size) {
		/* __check_host_shared_guest() protects against underflow */
		page->host_share_guest_count--;
		if (!page->host_share_guest_count)
			set_host_state(page, PKVM_PAGE_OWNED);
	}

unlock:
	guest_unlock_component(vm);
	host_unlock_component();

	return ret;
}

static void assert_host_shared_guest(struct pkvm_hyp_vm *vm, u64 ipa, u64 size)
{
	u64 phys;
	int ret;

	if (!IS_ENABLED(CONFIG_NVHE_EL2_DEBUG))
		return;

	host_lock_component();
	guest_lock_component(vm);

	ret = __check_host_shared_guest(vm, &phys, ipa, size);

	guest_unlock_component(vm);
	host_unlock_component();

	WARN_ON(ret && ret != -ENOENT);
}

int __pkvm_host_relax_perms_guest(u64 gfn, struct pkvm_hyp_vcpu *vcpu, enum kvm_pgtable_prot prot)
{
	struct pkvm_hyp_vm *vm = pkvm_hyp_vcpu_to_hyp_vm(vcpu);
	u64 ipa = hyp_pfn_to_phys(gfn);
	int ret;

	if (pkvm_hyp_vm_is_protected(vm))
		return -EPERM;

	if (prot & ~KVM_PGTABLE_PROT_RWX)
		return -EINVAL;

	assert_host_shared_guest(vm, ipa, 0);
	guest_lock_component(vm);
	ret = kvm_pgtable_stage2_relax_perms(&vm->pgt, ipa, prot, 0);
	guest_unlock_component(vm);

	return ret;
}

int __pkvm_host_wrprotect_guest(u64 gfn, u64 nr_pages, struct pkvm_hyp_vm *vm)
{
	u64 size, ipa = hyp_pfn_to_phys(gfn);
	int ret;

	if (pkvm_hyp_vm_is_protected(vm))
		return -EPERM;

	ret = __guest_check_transition_size(0, ipa, nr_pages, &size);
	if (ret)
		return ret;

	assert_host_shared_guest(vm, ipa, size);
	guest_lock_component(vm);
	ret = kvm_pgtable_stage2_wrprotect(&vm->pgt, ipa, size);
	guest_unlock_component(vm);

	return ret;
}

int __pkvm_host_test_clear_young_guest(u64 gfn, u64 nr_pages, bool mkold, struct pkvm_hyp_vm *vm)
{
	u64 size, ipa = hyp_pfn_to_phys(gfn);
	int ret;

	if (pkvm_hyp_vm_is_protected(vm))
		return -EPERM;

	ret = __guest_check_transition_size(0, ipa, nr_pages, &size);
	if (ret)
		return ret;

	assert_host_shared_guest(vm, ipa, size);
	guest_lock_component(vm);
	ret = kvm_pgtable_stage2_test_clear_young(&vm->pgt, ipa, size, mkold);
	guest_unlock_component(vm);

	return ret;
}

int __pkvm_host_mkyoung_guest(u64 gfn, struct pkvm_hyp_vcpu *vcpu)
{
	struct pkvm_hyp_vm *vm = pkvm_hyp_vcpu_to_hyp_vm(vcpu);
	u64 ipa = hyp_pfn_to_phys(gfn);

	if (pkvm_hyp_vm_is_protected(vm))
		return -EPERM;

	assert_host_shared_guest(vm, ipa, 0);
	guest_lock_component(vm);
	kvm_pgtable_stage2_mkyoung(&vm->pgt, ipa, 0);
	guest_unlock_component(vm);

	return 0;
}

#ifdef CONFIG_NVHE_EL2_DEBUG
struct pkvm_expected_state {
	enum pkvm_page_state host;
	enum pkvm_page_state hyp;
	enum pkvm_page_state guest[2]; /* [ gfn, gfn + 1 ] */
};

static struct pkvm_expected_state selftest_state;
static struct hyp_page *selftest_page;
static struct pkvm_hyp_vcpu *selftest_vcpu;

static u64 selftest_ipa(void)
{
	return BIT(selftest_vcpu->vcpu.arch.hw_mmu->pgt->ia_bits - 1);
}

static void assert_page_state(void)
{
	void *virt = hyp_page_to_virt(selftest_page);
	u64 size = PAGE_SIZE << selftest_page->order;
	struct pkvm_hyp_vcpu *vcpu = selftest_vcpu;
	u64 phys = hyp_virt_to_phys(virt);
	u64 ipa[2] = { selftest_ipa(), selftest_ipa() + PAGE_SIZE };
	struct pkvm_hyp_vm *vm;

	vm = pkvm_hyp_vcpu_to_hyp_vm(vcpu);

	host_lock_component();
	WARN_ON(__host_check_page_state_range(phys, size, selftest_state.host));
	host_unlock_component();

	hyp_lock_component();
	WARN_ON(__hyp_check_page_state_range(phys, size, selftest_state.hyp));
	hyp_unlock_component();

	guest_lock_component(vm);
	WARN_ON(__guest_check_page_state_range(vm, ipa[0], size, selftest_state.guest[0]));
	WARN_ON(__guest_check_page_state_range(vm, ipa[1], size, selftest_state.guest[1]));
	guest_unlock_component(vm);
}

#define assert_transition_res(res, fn, ...)		\
	do {						\
		WARN_ON(fn(__VA_ARGS__) != res);	\
		assert_page_state();			\
	} while (0)

void pkvm_ownership_selftest(void *base)
{
	enum kvm_pgtable_prot prot = KVM_PGTABLE_PROT_RWX;
	void *virt = hyp_alloc_pages(&host_s2_pool, 0);
	struct pkvm_hyp_vcpu *vcpu;
	u64 phys, size, pfn, gfn;
	struct pkvm_hyp_vm *vm;

	WARN_ON(!virt);
	selftest_page = hyp_virt_to_page(virt);
	selftest_page->refcount = 0;
	selftest_vcpu = vcpu = init_selftest_vm(base);
	vm = pkvm_hyp_vcpu_to_hyp_vm(vcpu);

	size = PAGE_SIZE << selftest_page->order;
	phys = hyp_virt_to_phys(virt);
	pfn = hyp_phys_to_pfn(phys);
	gfn = hyp_phys_to_pfn(selftest_ipa());

	selftest_state.host = PKVM_NOPAGE;
	selftest_state.hyp = PKVM_PAGE_OWNED;
	selftest_state.guest[0] = selftest_state.guest[1] = PKVM_NOPAGE;
	assert_page_state();
	assert_transition_res(-EPERM,	__pkvm_host_donate_hyp, pfn, 1);
	assert_transition_res(-EPERM,	__pkvm_host_share_hyp, pfn);
	assert_transition_res(-EPERM,	__pkvm_host_unshare_hyp, pfn);
	assert_transition_res(-EPERM,	__pkvm_host_share_ffa, pfn, 1);
	assert_transition_res(-EPERM,	__pkvm_host_unshare_ffa, pfn, 1);
	assert_transition_res(-EPERM,	hyp_pin_shared_mem, virt, virt + size);
	assert_transition_res(-EPERM,	__pkvm_host_share_guest, pfn, gfn, 1, vcpu, prot);
	assert_transition_res(-ENOENT,	__pkvm_host_unshare_guest, gfn, 1, vm);
	assert_transition_res(-EPERM,   __pkvm_host_donate_guest, pfn, gfn, vcpu);

	selftest_state.host = PKVM_PAGE_OWNED;
	selftest_state.hyp = PKVM_NOPAGE;
	assert_transition_res(0,	__pkvm_hyp_donate_host, pfn, 1);
	assert_transition_res(-EPERM,	__pkvm_hyp_donate_host, pfn, 1);
	assert_transition_res(-EPERM,	__pkvm_host_unshare_hyp, pfn);
	assert_transition_res(-EPERM,	__pkvm_host_unshare_ffa, pfn, 1);
	assert_transition_res(-ENOENT,	__pkvm_host_unshare_guest, gfn, 1, vm);
	assert_transition_res(-EPERM,	hyp_pin_shared_mem, virt, virt + size);

	selftest_state.host = PKVM_PAGE_SHARED_OWNED;
	selftest_state.hyp = PKVM_PAGE_SHARED_BORROWED;
	assert_transition_res(0,	__pkvm_host_share_hyp, pfn);
	assert_transition_res(-EPERM,	__pkvm_host_share_hyp, pfn);
	assert_transition_res(-EPERM,	__pkvm_host_donate_hyp, pfn, 1);
	assert_transition_res(-EPERM,	__pkvm_host_share_ffa, pfn, 1);
	assert_transition_res(-EPERM,	__pkvm_hyp_donate_host, pfn, 1);
	assert_transition_res(-EPERM,	__pkvm_host_share_guest, pfn, gfn, 1, vcpu, prot);
	assert_transition_res(-ENOENT,	__pkvm_host_unshare_guest, gfn, 1, vm);
	assert_transition_res(-EPERM,   __pkvm_host_donate_guest, pfn, gfn, vcpu);

	assert_transition_res(0,	hyp_pin_shared_mem, virt, virt + size);
	assert_transition_res(0,	hyp_pin_shared_mem, virt, virt + size);
	hyp_unpin_shared_mem(virt, virt + size);
	WARN_ON(hyp_page_count(virt) != 1);
	assert_transition_res(-EBUSY,	__pkvm_host_unshare_hyp, pfn);
	assert_transition_res(-EPERM,	__pkvm_host_share_hyp, pfn);
	assert_transition_res(-EPERM,	__pkvm_host_donate_hyp, pfn, 1);
	assert_transition_res(-EPERM,	__pkvm_host_share_ffa, pfn, 1);
	assert_transition_res(-EPERM,	__pkvm_hyp_donate_host, pfn, 1);
	assert_transition_res(-EPERM,	__pkvm_host_share_guest, pfn, gfn, 1, vcpu, prot);
	assert_transition_res(-ENOENT,	__pkvm_host_unshare_guest, gfn, 1, vm);
	assert_transition_res(-EPERM,   __pkvm_host_donate_guest, pfn, gfn, vcpu);

	hyp_unpin_shared_mem(virt, virt + size);
	assert_page_state();
	WARN_ON(hyp_page_count(virt));

	selftest_state.host = PKVM_PAGE_OWNED;
	selftest_state.hyp = PKVM_NOPAGE;
	assert_transition_res(0,	__pkvm_host_unshare_hyp, pfn);

	selftest_state.host = PKVM_PAGE_SHARED_OWNED;
	selftest_state.hyp = PKVM_NOPAGE;
	assert_transition_res(0,	__pkvm_host_share_ffa, pfn, 1);
	assert_transition_res(-EPERM,	__pkvm_host_share_ffa, pfn, 1);
	assert_transition_res(-EPERM,	__pkvm_host_donate_hyp, pfn, 1);
	assert_transition_res(-EPERM,	__pkvm_host_share_hyp, pfn);
	assert_transition_res(-EPERM,	__pkvm_host_unshare_hyp, pfn);
	assert_transition_res(-EPERM,	__pkvm_hyp_donate_host, pfn, 1);
	assert_transition_res(-EPERM,	__pkvm_host_share_guest, pfn, gfn, 1, vcpu, prot);
	assert_transition_res(-ENOENT,	__pkvm_host_unshare_guest, gfn, 1, vm);
	assert_transition_res(-EPERM,   __pkvm_host_donate_guest, pfn, gfn, vcpu);
	assert_transition_res(-EPERM,	hyp_pin_shared_mem, virt, virt + size);

	selftest_state.host = PKVM_PAGE_OWNED;
	selftest_state.hyp = PKVM_NOPAGE;
	assert_transition_res(0,	__pkvm_host_unshare_ffa, pfn, 1);
	assert_transition_res(-EPERM,	__pkvm_host_unshare_ffa, pfn, 1);

	selftest_state.host = PKVM_PAGE_SHARED_OWNED;
	selftest_state.guest[0] = PKVM_PAGE_SHARED_BORROWED;
	assert_transition_res(0,	__pkvm_host_share_guest, pfn, gfn, 1, vcpu, prot);
	assert_transition_res(-EPERM,	__pkvm_host_share_guest, pfn, gfn, 1, vcpu, prot);
	assert_transition_res(-EPERM,	__pkvm_host_share_ffa, pfn, 1);
	assert_transition_res(-EPERM,	__pkvm_host_donate_hyp, pfn, 1);
	assert_transition_res(-EPERM,	__pkvm_host_share_hyp, pfn);
	assert_transition_res(-EPERM,	__pkvm_host_unshare_hyp, pfn);
	assert_transition_res(-EPERM,	__pkvm_hyp_donate_host, pfn, 1);
	assert_transition_res(-EPERM,   __pkvm_host_donate_guest, pfn, gfn, vcpu);
	assert_transition_res(-EPERM,	hyp_pin_shared_mem, virt, virt + size);

	selftest_state.guest[1] = PKVM_PAGE_SHARED_BORROWED;
	assert_transition_res(0,	__pkvm_host_share_guest, pfn, gfn + 1, 1, vcpu, prot);
	WARN_ON(hyp_virt_to_page(virt)->host_share_guest_count != 2);

	selftest_state.guest[0] = PKVM_NOPAGE;
	assert_transition_res(0,	__pkvm_host_unshare_guest, gfn, 1, vm);

	selftest_state.guest[1] = PKVM_NOPAGE;
	selftest_state.host = PKVM_PAGE_OWNED;
	assert_transition_res(0,	__pkvm_host_unshare_guest, gfn + 1, 1, vm);

	selftest_state.host = PKVM_NOPAGE;
	selftest_state.guest[0] = PKVM_PAGE_OWNED;
	assert_transition_res(0,	__pkvm_host_donate_guest, pfn, gfn, vcpu);
	assert_transition_res(-EPERM,	__pkvm_host_donate_guest, pfn, gfn, vcpu);
	assert_transition_res(-EPERM,	__pkvm_host_donate_guest, pfn, gfn + 1, vcpu);
	assert_transition_res(-EPERM,	__pkvm_host_share_guest, pfn, gfn, 1, vcpu, prot);
	assert_transition_res(-EPERM,	__pkvm_host_share_guest, pfn, gfn + 1, 1, vcpu, prot);
	assert_transition_res(-EPERM,	__pkvm_host_share_ffa, pfn, 1);
	assert_transition_res(-EPERM,	__pkvm_host_donate_hyp, pfn, 1);
	assert_transition_res(-EPERM,	__pkvm_host_share_hyp, pfn);
	assert_transition_res(-EPERM,	__pkvm_host_unshare_hyp, pfn);
	assert_transition_res(-EPERM,	__pkvm_hyp_donate_host, pfn, 1);

	selftest_state.host = PKVM_PAGE_SHARED_BORROWED;
	selftest_state.guest[0] = PKVM_PAGE_SHARED_OWNED;
	assert_transition_res(0,	__pkvm_guest_share_host, vcpu, gfn);
	assert_transition_res(-EPERM,	__pkvm_guest_share_host, vcpu, gfn);
	assert_transition_res(-EPERM,	__pkvm_host_donate_guest, pfn, gfn, vcpu);
	assert_transition_res(-EPERM,	__pkvm_host_donate_guest, pfn, gfn + 1, vcpu);
	assert_transition_res(-EPERM,	__pkvm_host_share_guest, pfn, gfn, 1, vcpu, prot);
	assert_transition_res(-EPERM,	__pkvm_host_share_guest, pfn, gfn + 1, 1, vcpu, prot);
	assert_transition_res(-EPERM,	__pkvm_host_share_ffa, pfn, 1);
	assert_transition_res(-EPERM,	__pkvm_host_donate_hyp, pfn, 1);
	assert_transition_res(-EPERM,	__pkvm_host_share_hyp, pfn);
	assert_transition_res(-EPERM,	__pkvm_host_unshare_hyp, pfn);
	assert_transition_res(-EPERM,	__pkvm_hyp_donate_host, pfn, 1);

	selftest_state.host = PKVM_NOPAGE;
	selftest_state.guest[0] = PKVM_PAGE_OWNED;
	assert_transition_res(0,	__pkvm_guest_unshare_host, vcpu, gfn);
	assert_transition_res(-EPERM,	__pkvm_guest_unshare_host, vcpu, gfn);
	assert_transition_res(-EPERM,	__pkvm_host_donate_guest, pfn, gfn, vcpu);
	assert_transition_res(-EPERM,	__pkvm_host_donate_guest, pfn, gfn + 1, vcpu);
	assert_transition_res(-EPERM,	__pkvm_host_share_guest, pfn, gfn, 1, vcpu, prot);
	assert_transition_res(-EPERM,	__pkvm_host_share_guest, pfn, gfn + 1, 1, vcpu, prot);
	assert_transition_res(-EPERM,	__pkvm_host_share_ffa, pfn, 1);
	assert_transition_res(-EPERM,	__pkvm_host_donate_hyp, pfn, 1);
	assert_transition_res(-EPERM,	__pkvm_host_share_hyp, pfn);
	assert_transition_res(-EPERM,	__pkvm_host_unshare_hyp, pfn);
	assert_transition_res(-EPERM,	__pkvm_hyp_donate_host, pfn, 1);

	selftest_state.host = PKVM_PAGE_OWNED;
	selftest_state.guest[0] = PKVM_POISON;
	assert_transition_res(0,	__pkvm_host_force_reclaim_page_guest, phys);
	assert_transition_res(-EPERM,	__pkvm_host_donate_guest, pfn, gfn, vcpu);
	assert_transition_res(-EPERM,	__pkvm_host_share_guest, pfn, gfn, 1, vcpu, prot);
	assert_transition_res(-EHWPOISON, __pkvm_guest_share_host, vcpu, gfn);
	assert_transition_res(-EHWPOISON, __pkvm_guest_unshare_host, vcpu, gfn);

	selftest_state.host = PKVM_NOPAGE;
	selftest_state.guest[1] = PKVM_PAGE_OWNED;
	assert_transition_res(0,	__pkvm_host_donate_guest, pfn, gfn + 1, vcpu);

	selftest_state.host = PKVM_PAGE_OWNED;
	selftest_state.guest[1] = PKVM_NOPAGE;
	assert_transition_res(0,	__pkvm_host_reclaim_page_guest, gfn + 1, vm);
	assert_transition_res(-EPERM,	__pkvm_host_donate_guest, pfn, gfn, vcpu);
	assert_transition_res(-EPERM,	__pkvm_host_share_guest, pfn, gfn, 1, vcpu, prot);

	selftest_state.host = PKVM_NOPAGE;
	selftest_state.hyp = PKVM_PAGE_OWNED;
	assert_transition_res(0,	__pkvm_host_donate_hyp, pfn, 1);

	teardown_selftest_vm();
	selftest_page->refcount = 1;
	hyp_put_page(&host_s2_pool, virt);
}
#endif