xref: /linux/arch/arm64/kvm/mmu.c (revision 29c925376df478c26415c46561c010d6ca514f8d)

// SPDX-License-Identifier: GPL-2.0-only
/*
 * Copyright (C) 2012 - Virtual Open Systems and Columbia University
 * Author: Christoffer Dall <c.dall@virtualopensystems.com>
 */

#include <linux/acpi.h>
#include <linux/cleanup.h>
#include <linux/mman.h>
#include <linux/kvm_host.h>
#include <linux/interval_tree.h>
#include <linux/io.h>
#include <linux/hugetlb.h>
#include <linux/sched/signal.h>
#include <trace/events/kvm.h>
#include <asm/acpi.h>
#include <asm/pgalloc.h>
#include <asm/cacheflush.h>
#include <asm/kvm_arm.h>
#include <asm/kvm_mmu.h>
#include <asm/kvm_pgtable.h>
#include <asm/kvm_pkvm.h>
#include <asm/kvm_asm.h>
#include <asm/kvm_emulate.h>
#include <asm/virt.h>

#include "trace.h"

static struct kvm_pgtable *hyp_pgtable;
static DEFINE_MUTEX(kvm_hyp_pgd_mutex);

static unsigned long __ro_after_init hyp_idmap_start;
static unsigned long __ro_after_init hyp_idmap_end;
static phys_addr_t __ro_after_init hyp_idmap_vector;

u32 __ro_after_init __hyp_va_bits;

static unsigned long __ro_after_init io_map_base;

#define KVM_PGT_FN(fn)		(!is_protected_kvm_enabled() ? fn : p ## fn)

static int kvm_vm_init_vm_s2_ops(struct kvm *kvm);

static phys_addr_t __stage2_range_addr_end(phys_addr_t addr, phys_addr_t end,
					   phys_addr_t size)
{
	phys_addr_t boundary = ALIGN_DOWN(addr + size, size);

	return (boundary - 1 < end - 1) ? boundary : end;
}

static phys_addr_t stage2_range_addr_end(phys_addr_t addr, phys_addr_t end)
{
	phys_addr_t size = kvm_granule_size(KVM_PGTABLE_MIN_BLOCK_LEVEL);

	return __stage2_range_addr_end(addr, end, size);
}

/*
 * Release kvm_mmu_lock periodically if the memory region is large. Otherwise,
 * we may see kernel panics with CONFIG_DETECT_HUNG_TASK,
 * CONFIG_LOCKUP_DETECTOR, CONFIG_LOCKDEP. Additionally, holding the lock too
 * long will also starve other vCPUs. We have to also make sure that the page
 * tables are not freed while we released the lock.
 */
static int stage2_apply_range(struct kvm_s2_mmu *mmu, phys_addr_t start,
			      phys_addr_t end,
			      int (*fn)(struct kvm_pgtable *, u64, u64),
			      bool resched)
{
	struct kvm *kvm = kvm_s2_mmu_to_kvm(mmu);
	bool lock_dropped = false;
	phys_addr_t addr = start;
	int ret;
	u64 next;

	do {
		struct kvm_pgtable *pgt = mmu->pgt;
		/*
		 * We may be raced on PGT teardown when we release the
		 * kvm->mmu_lock. That's fine as the PGT is legitimately no
		 * longer present.
		 */
		if (!pgt)
			return lock_dropped ? 0 : -EINVAL;

		next = stage2_range_addr_end(addr, end);
		ret = fn(pgt, addr, next - addr);
		if (ret)
			break;

		if (resched && next != end) {
			cond_resched_rwlock_write(&kvm->mmu_lock);
			lock_dropped = true;
		}
	} while (addr = next, addr != end);

	return ret;
}

#define stage2_apply_range_resched(mmu, addr, end, fn)			\
	stage2_apply_range(mmu, addr, end, fn, true)

/*
 * Get the maximum number of page-tables pages needed to split a range
 * of blocks into PAGE_SIZE PTEs. It assumes the range is already
 * mapped at level 2, or at level 1 if allowed.
 */
static int kvm_mmu_split_nr_page_tables(u64 range)
{
	int n = 0;

	if (KVM_PGTABLE_MIN_BLOCK_LEVEL < 2)
		n += DIV_ROUND_UP(range, PUD_SIZE);
	n += DIV_ROUND_UP(range, PMD_SIZE);
	return n;
}

static bool need_split_memcache_topup_or_resched(struct kvm *kvm)
{
	struct kvm_mmu_memory_cache *cache;
	u64 chunk_size, min;

	if (need_resched() || rwlock_needbreak(&kvm->mmu_lock))
		return true;

	chunk_size = kvm->arch.mmu.split_page_chunk_size;
	min = kvm_mmu_split_nr_page_tables(chunk_size);
	cache = &kvm->arch.mmu.split_page_cache;
	return kvm_mmu_memory_cache_nr_free_objects(cache) < min;
}

static int kvm_mmu_split_huge_pages(struct kvm *kvm, phys_addr_t addr,
				    phys_addr_t end)
{
	struct kvm_mmu_memory_cache *cache;
	struct kvm_pgtable *pgt;
	int ret, cache_capacity;
	u64 next, chunk_size;

	lockdep_assert_held_write(&kvm->mmu_lock);

	chunk_size = kvm->arch.mmu.split_page_chunk_size;
	cache_capacity = kvm_mmu_split_nr_page_tables(chunk_size);

	if (chunk_size == 0)
		return 0;

	cache = &kvm->arch.mmu.split_page_cache;

	do {
		if (need_split_memcache_topup_or_resched(kvm)) {
			write_unlock(&kvm->mmu_lock);
			cond_resched();
			/* Eager page splitting is best-effort. */
			ret = __kvm_mmu_topup_memory_cache(cache,
							   cache_capacity,
							   cache_capacity);
			write_lock(&kvm->mmu_lock);
			if (ret)
				break;
		}

		pgt = kvm->arch.mmu.pgt;
		if (!pgt)
			return -EINVAL;

		next = __stage2_range_addr_end(addr, end, chunk_size);
		ret = KVM_PGT_FN(kvm_pgtable_stage2_split)(pgt, addr, next - addr, cache);
		if (ret)
			break;
	} while (addr = next, addr != end);

	return ret;
}

static bool memslot_is_logging(struct kvm_memory_slot *memslot)
{
	return memslot->dirty_bitmap && !(memslot->flags & KVM_MEM_READONLY);
}

static int pkvm_flush_remote_tlbs(struct kvm *kvm)
{
	kvm_call_hyp_nvhe(__pkvm_tlb_flush_vmid, kvm->arch.pkvm.handle);
	return 0;
}

static int kvm_vm_flush_remote_tlbs(struct kvm *kvm)
{
	kvm_call_hyp(__kvm_tlb_flush_vmid, &kvm->arch.mmu);
	return 0;
}

/**
 * kvm_arch_flush_remote_tlbs() - flush all VM TLB entries for v7/8
 * @kvm:	pointer to kvm structure.
 *
 * Interface to HYP function to flush all VM TLB entries
 */
int kvm_arch_flush_remote_tlbs(struct kvm *kvm)
{
	return kvm->arch.vm_s2_ops->vm_flush_remote_tlbs(kvm);
}

static int pkvm_flush_remote_tlbs_range(struct kvm *kvm,
					gfn_t gfn, u64 nr_pages)
{
	return pkvm_flush_remote_tlbs(kvm);
}

static int kvm_vm_flush_remote_tlbs_range(struct kvm *kvm,
					 gfn_t gfn, u64 nr_pages)
{
	u64 size = nr_pages << PAGE_SHIFT;
	u64 addr = gfn << PAGE_SHIFT;

	kvm_tlb_flush_vmid_range(&kvm->arch.mmu, addr, size);
	return 0;
}

int kvm_arch_flush_remote_tlbs_range(struct kvm *kvm,
				     gfn_t gfn, u64 nr_pages)
{
	return kvm->arch.vm_s2_ops->vm_flush_remote_tlbs_range(kvm, gfn, nr_pages);
}

static void *stage2_memcache_zalloc_page(void *arg)
{
	struct kvm_mmu_memory_cache *mc = arg;
	void *virt;

	/* Allocated with __GFP_ZERO, so no need to zero */
	virt = kvm_mmu_memory_cache_alloc(mc);
	if (virt)
		kvm_account_pgtable_pages(virt, 1);
	return virt;
}

static void *kvm_host_zalloc_pages_exact(size_t size)
{
	return alloc_pages_exact(size, GFP_KERNEL_ACCOUNT | __GFP_ZERO);
}

static void *kvm_s2_zalloc_pages_exact(size_t size)
{
	void *virt = kvm_host_zalloc_pages_exact(size);

	if (virt)
		kvm_account_pgtable_pages(virt, (size >> PAGE_SHIFT));
	return virt;
}

static void kvm_s2_free_pages_exact(void *virt, size_t size)
{
	kvm_account_pgtable_pages(virt, -(size >> PAGE_SHIFT));
	free_pages_exact(virt, size);
}

static struct kvm_pgtable_mm_ops kvm_s2_mm_ops;

static void stage2_free_unlinked_table_rcu_cb(struct rcu_head *head)
{
	struct page *page = container_of(head, struct page, rcu_head);
	void *pgtable = page_to_virt(page);
	s8 level = page_private(page);

	KVM_PGT_FN(kvm_pgtable_stage2_free_unlinked)(&kvm_s2_mm_ops, pgtable, level);
}

static void stage2_free_unlinked_table(void *addr, s8 level)
{
	struct page *page = virt_to_page(addr);

	set_page_private(page, (unsigned long)level);
	call_rcu(&page->rcu_head, stage2_free_unlinked_table_rcu_cb);
}

static void kvm_host_get_page(void *addr)
{
	get_page(virt_to_page(addr));
}

static void kvm_host_put_page(void *addr)
{
	put_page(virt_to_page(addr));
}

static void kvm_s2_put_page(void *addr)
{
	struct page *p = virt_to_page(addr);
	/* Dropping last refcount, the page will be freed */
	if (page_count(p) == 1)
		kvm_account_pgtable_pages(addr, -1);
	put_page(p);
}

static int kvm_host_page_count(void *addr)
{
	return page_count(virt_to_page(addr));
}

static phys_addr_t kvm_host_pa(void *addr)
{
	return __pa(addr);
}

static void *kvm_host_va(phys_addr_t phys)
{
	return __va(phys);
}

static void clean_dcache_guest_page(void *va, size_t size)
{
	__clean_dcache_guest_page(va, size);
}

static void invalidate_icache_guest_page(void *va, size_t size)
{
	__invalidate_icache_guest_page(va, size);
}

static int kvm_pgtable_stage2_unmap_tracked(struct kvm_pgtable *pgt,
					    u64 addr, u64 size);

static void kvm_vm_stage2_unmap_range(struct kvm_s2_mmu *mmu,
				      phys_addr_t start,
				      u64 size, bool may_block)
{
	struct kvm *kvm = kvm_s2_mmu_to_kvm(mmu);
	int (*fn)(struct kvm_pgtable *, u64, u64);

	if (kvm_is_nested_s2_mmu(kvm, mmu))
		fn = kvm_pgtable_stage2_unmap_tracked;
	else
		fn = kvm_pgtable_stage2_unmap;

	WARN_ON(stage2_apply_range(mmu, start, start + size, fn, may_block));
}

static void pkvm_stage2_unmap_range(struct kvm_s2_mmu *mmu,
				    phys_addr_t start,
				    u64 size, bool may_block)
{
	WARN_ON(stage2_apply_range(mmu, start, start + size,
				   pkvm_pgtable_stage2_unmap, may_block));
}

static void no_stage2_unmap_range(struct kvm_s2_mmu *mmu,
				  phys_addr_t start, u64 size, bool may_block)
{
}

/*
 * Unmapping vs dcache management:
 *
 * If a guest maps certain memory pages as uncached, all writes will
 * bypass the data cache and go directly to RAM.  However, the CPUs
 * can still speculate reads (not writes) and fill cache lines with
 * data.
 *
 * Those cache lines will be *clean* cache lines though, so a
 * clean+invalidate operation is equivalent to an invalidate
 * operation, because no cache lines are marked dirty.
 *
 * Those clean cache lines could be filled prior to an uncached write
 * by the guest, and the cache coherent IO subsystem would therefore
 * end up writing old data to disk.
 *
 * This is why right after unmapping a page/section and invalidating
 * the corresponding TLBs, we flush to make sure the IO subsystem will
 * never hit in the cache.
 *
 * This is all avoided on systems that have ARM64_HAS_STAGE2_FWB, as
 * we then fully enforce cacheability of RAM, no matter what the guest
 * does.
 */

static int kvm_pgtable_stage2_unmap_tracked(struct kvm_pgtable *pgt, u64 addr, u64 size)
{
	int ret;

	ret = kvm_pgtable_stage2_unmap(pgt, addr, size);
	if (ret)
		return ret;

	kvm_remove_guest_s2_mappings(pgt->mmu, addr, size);
	return 0;
}

/**
 * kvm_stage2_unmap_range -- Clear stage2 page table entries to unmap a range
 * @mmu:   The KVM stage-2 MMU pointer
 * @start: The intermediate physical base address of the range to unmap
 * @size:  The size of the area to unmap
 * @may_block: Whether or not we are permitted to block
 *
 * Clear a range of stage-2 mappings, lowering the various ref-counts.  Must
 * be called while holding mmu_lock otherwise another faulting VCPU may
 * come in and mess with things behind our backs.
 */
void kvm_stage2_unmap_range(struct kvm_s2_mmu *mmu, phys_addr_t start,
			    u64 size, bool may_block)
{
	struct kvm *kvm = kvm_s2_mmu_to_kvm(mmu);

	lockdep_assert_held_write(&kvm->mmu_lock);
	WARN_ON(size & ~PAGE_MASK);

	kvm->arch.vm_s2_ops->vm_stage2_unmap_range(mmu, start, size, may_block);
}

void kvm_stage2_flush_range(struct kvm_s2_mmu *mmu, phys_addr_t addr, phys_addr_t end)
{
	stage2_apply_range_resched(mmu, addr, end, KVM_PGT_FN(kvm_pgtable_stage2_flush));
}

static void stage2_flush_memslot(struct kvm *kvm,
				 struct kvm_memory_slot *memslot)
{
	phys_addr_t addr = memslot->base_gfn << PAGE_SHIFT;
	phys_addr_t end = addr + PAGE_SIZE * memslot->npages;

	kvm_stage2_flush_range(&kvm->arch.mmu, addr, end);
}

/**
 * stage2_flush_vm - Invalidate cache for pages mapped in stage 2
 * @kvm: The struct kvm pointer
 *
 * Go through the stage 2 page tables and invalidate any cache lines
 * backing memory already mapped to the VM.
 */
static void stage2_flush_vm(struct kvm *kvm)
{
	struct kvm_memslots *slots;
	struct kvm_memory_slot *memslot;
	int idx, bkt;

	idx = srcu_read_lock(&kvm->srcu);
	write_lock(&kvm->mmu_lock);

	slots = kvm_memslots(kvm);
	kvm_for_each_memslot(memslot, bkt, slots)
		stage2_flush_memslot(kvm, memslot);

	kvm_nested_s2_flush(kvm);

	write_unlock(&kvm->mmu_lock);
	srcu_read_unlock(&kvm->srcu, idx);
}

/**
 * free_hyp_pgds - free Hyp-mode page tables
 */
void __init free_hyp_pgds(void)
{
	mutex_lock(&kvm_hyp_pgd_mutex);
	if (hyp_pgtable) {
		kvm_pgtable_hyp_destroy(hyp_pgtable);
		kfree(hyp_pgtable);
		hyp_pgtable = NULL;
	}
	mutex_unlock(&kvm_hyp_pgd_mutex);
}

static bool kvm_host_owns_hyp_mappings(void)
{
	if (is_kernel_in_hyp_mode())
		return false;

	if (static_branch_likely(&kvm_protected_mode_initialized))
		return false;

	/*
	 * This can happen at boot time when __create_hyp_mappings() is called
	 * after the hyp protection has been enabled, but the static key has
	 * not been flipped yet.
	 */
	if (!hyp_pgtable && is_protected_kvm_enabled())
		return false;

	WARN_ON(!hyp_pgtable);

	return true;
}

int __create_hyp_mappings(unsigned long start, unsigned long size,
			  unsigned long phys, enum kvm_pgtable_prot prot)
{
	int err;

	if (WARN_ON(!kvm_host_owns_hyp_mappings()))
		return -EINVAL;

	mutex_lock(&kvm_hyp_pgd_mutex);
	err = kvm_pgtable_hyp_map(hyp_pgtable, start, size, phys, prot);
	mutex_unlock(&kvm_hyp_pgd_mutex);

	return err;
}

static phys_addr_t kvm_kaddr_to_phys(void *kaddr)
{
	if (!is_vmalloc_addr(kaddr)) {
		BUG_ON(!virt_addr_valid(kaddr));
		return __pa(kaddr);
	} else {
		return page_to_phys(vmalloc_to_page(kaddr)) +
		       offset_in_page(kaddr);
	}
}

struct hyp_shared_pfn {
	u64 pfn;
	int count;
	struct rb_node node;
};

static DEFINE_MUTEX(hyp_shared_pfns_lock);
static struct rb_root hyp_shared_pfns = RB_ROOT;

static struct hyp_shared_pfn *find_shared_pfn(u64 pfn, struct rb_node ***node,
					      struct rb_node **parent)
{
	struct hyp_shared_pfn *this;

	*node = &hyp_shared_pfns.rb_node;
	*parent = NULL;
	while (**node) {
		this = container_of(**node, struct hyp_shared_pfn, node);
		*parent = **node;
		if (this->pfn < pfn)
			*node = &((**node)->rb_left);
		else if (this->pfn > pfn)
			*node = &((**node)->rb_right);
		else
			return this;
	}

	return NULL;
}

static int share_pfn_hyp(u64 pfn)
{
	struct rb_node **node, *parent;
	struct hyp_shared_pfn *this;
	int ret = 0;

	mutex_lock(&hyp_shared_pfns_lock);
	this = find_shared_pfn(pfn, &node, &parent);
	if (this) {
		this->count++;
		goto unlock;
	}

	this = kzalloc_obj(*this);
	if (!this) {
		ret = -ENOMEM;
		goto unlock;
	}

	this->pfn = pfn;
	this->count = 1;
	rb_link_node(&this->node, parent, node);
	rb_insert_color(&this->node, &hyp_shared_pfns);
	ret = kvm_call_hyp_nvhe(__pkvm_host_share_hyp, pfn);
	if (ret) {
		rb_erase(&this->node, &hyp_shared_pfns);
		kfree(this);
	}
unlock:
	mutex_unlock(&hyp_shared_pfns_lock);

	return ret;
}

static int unshare_pfn_hyp(u64 pfn)
{
	struct rb_node **node, *parent;
	struct hyp_shared_pfn *this;
	int ret = 0;

	mutex_lock(&hyp_shared_pfns_lock);
	this = find_shared_pfn(pfn, &node, &parent);
	if (WARN_ON(!this)) {
		ret = -ENOENT;
		goto unlock;
	}

	if (this->count > 1) {
		this->count--;
		goto unlock;
	}

	ret = kvm_call_hyp_nvhe(__pkvm_host_unshare_hyp, pfn);
	if (ret)
		goto unlock;

	rb_erase(&this->node, &hyp_shared_pfns);
	kfree(this);
unlock:
	mutex_unlock(&hyp_shared_pfns_lock);

	return ret;
}

int kvm_share_hyp(void *from, void *to)
{
	phys_addr_t start, end, cur;
	int ret = 0;
	u64 pfn;

	if (is_kernel_in_hyp_mode())
		return 0;

	/*
	 * The share hcall maps things in the 'fixed-offset' region of the hyp
	 * VA space, so we can only share physically contiguous data-structures
	 * for now.
	 */
	if (is_vmalloc_or_module_addr(from) || is_vmalloc_or_module_addr(to))
		return -EINVAL;

	if (kvm_host_owns_hyp_mappings())
		return create_hyp_mappings(from, to, PAGE_HYP);

	start = ALIGN_DOWN(__pa(from), PAGE_SIZE);
	end = PAGE_ALIGN(__pa(to));
	for (cur = start; cur < end; cur += PAGE_SIZE) {
		pfn = __phys_to_pfn(cur);
		ret = share_pfn_hyp(pfn);
		if (ret)
			break;
	}

	if (!ret)
		return 0;

	/*
	 * Roll back the pages shared by this call. A failed unshare leaks
	 * the page (it stays shared with the hypervisor and is no longer
	 * reusable for pKVM) but breaks no isolation guarantee, so warn and
	 * continue. Not expected in practice.
	 */
	for (end = cur, cur = start; cur < end; cur += PAGE_SIZE) {
		pfn = __phys_to_pfn(cur);
		WARN_ON(unshare_pfn_hyp(pfn));
	}

	return ret;
}

void kvm_unshare_hyp(void *from, void *to)
{
	phys_addr_t start, end, cur;
	u64 pfn;

	if (is_kernel_in_hyp_mode() || kvm_host_owns_hyp_mappings() || !from)
		return;

	start = ALIGN_DOWN(__pa(from), PAGE_SIZE);
	end = PAGE_ALIGN(__pa(to));
	for (cur = start; cur < end; cur += PAGE_SIZE) {
		pfn = __phys_to_pfn(cur);
		/*
		 * A failed unshare leaks the page: it stays shared with the
		 * hypervisor and is no longer reusable for pKVM. No isolation
		 * guarantee is broken, and this is not expected in practice.
		 */
		WARN_ON(unshare_pfn_hyp(pfn));
	}
}

/**
 * create_hyp_mappings - duplicate a kernel virtual address range in Hyp mode
 * @from:	The virtual kernel start address of the range
 * @to:		The virtual kernel end address of the range (exclusive)
 * @prot:	The protection to be applied to this range
 *
 * The same virtual address as the kernel virtual address is also used
 * in Hyp-mode mapping (modulo HYP_PAGE_OFFSET) to the same underlying
 * physical pages.
 */
int create_hyp_mappings(void *from, void *to, enum kvm_pgtable_prot prot)
{
	phys_addr_t phys_addr;
	unsigned long virt_addr;
	unsigned long start = kern_hyp_va((unsigned long)from);
	unsigned long end = kern_hyp_va((unsigned long)to);

	if (is_kernel_in_hyp_mode())
		return 0;

	if (!kvm_host_owns_hyp_mappings())
		return -EPERM;

	start = start & PAGE_MASK;
	end = PAGE_ALIGN(end);

	for (virt_addr = start; virt_addr < end; virt_addr += PAGE_SIZE) {
		int err;

		phys_addr = kvm_kaddr_to_phys(from + virt_addr - start);
		err = __create_hyp_mappings(virt_addr, PAGE_SIZE, phys_addr,
					    prot);
		if (err)
			return err;
	}

	return 0;
}

static int __hyp_alloc_private_va_range(unsigned long base)
{
	lockdep_assert_held(&kvm_hyp_pgd_mutex);

	if (!PAGE_ALIGNED(base))
		return -EINVAL;

	/*
	 * Verify that BIT(VA_BITS - 1) hasn't been flipped by
	 * allocating the new area, as it would indicate we've
	 * overflowed the idmap/IO address range.
	 */
	if ((base ^ io_map_base) & BIT(VA_BITS - 1))
		return -ENOMEM;

	io_map_base = base;

	return 0;
}

/**
 * hyp_alloc_private_va_range - Allocates a private VA range.
 * @size:	The size of the VA range to reserve.
 * @haddr:	The hypervisor virtual start address of the allocation.
 *
 * The private virtual address (VA) range is allocated below io_map_base
 * and aligned based on the order of @size.
 *
 * Return: 0 on success or negative error code on failure.
 */
int hyp_alloc_private_va_range(size_t size, unsigned long *haddr)
{
	unsigned long base;
	int ret = 0;

	mutex_lock(&kvm_hyp_pgd_mutex);

	/*
	 * This assumes that we have enough space below the idmap
	 * page to allocate our VAs. If not, the check in
	 * __hyp_alloc_private_va_range() will kick. A potential
	 * alternative would be to detect that overflow and switch
	 * to an allocation above the idmap.
	 *
	 * The allocated size is always a multiple of PAGE_SIZE.
	 */
	size = PAGE_ALIGN(size);
	base = io_map_base - size;
	ret = __hyp_alloc_private_va_range(base);

	mutex_unlock(&kvm_hyp_pgd_mutex);

	if (!ret)
		*haddr = base;

	return ret;
}

static int __create_hyp_private_mapping(phys_addr_t phys_addr, size_t size,
					unsigned long *haddr,
					enum kvm_pgtable_prot prot)
{
	unsigned long addr;
	int ret = 0;

	if (!kvm_host_owns_hyp_mappings()) {
		addr = kvm_call_hyp_nvhe(__pkvm_create_private_mapping,
					 phys_addr, size, prot);
		if (IS_ERR_VALUE(addr))
			return addr;
		*haddr = addr;

		return 0;
	}

	size = PAGE_ALIGN(size + offset_in_page(phys_addr));
	ret = hyp_alloc_private_va_range(size, &addr);
	if (ret)
		return ret;

	ret = __create_hyp_mappings(addr, size, phys_addr, prot);
	if (ret)
		return ret;

	*haddr = addr + offset_in_page(phys_addr);
	return ret;
}

int create_hyp_stack(phys_addr_t phys_addr, unsigned long *haddr)
{
	unsigned long base;
	size_t size;
	int ret;

	mutex_lock(&kvm_hyp_pgd_mutex);
	/*
	 * Efficient stack verification using the NVHE_STACK_SHIFT bit implies
	 * an alignment of our allocation on the order of the size.
	 */
	size = NVHE_STACK_SIZE * 2;
	base = ALIGN_DOWN(io_map_base - size, size);

	ret = __hyp_alloc_private_va_range(base);

	mutex_unlock(&kvm_hyp_pgd_mutex);

	if (ret) {
		kvm_err("Cannot allocate hyp stack guard page\n");
		return ret;
	}

	/*
	 * Since the stack grows downwards, map the stack to the page
	 * at the higher address and leave the lower guard page
	 * unbacked.
	 *
	 * Any valid stack address now has the NVHE_STACK_SHIFT bit as 1
	 * and addresses corresponding to the guard page have the
	 * NVHE_STACK_SHIFT bit as 0 - this is used for overflow detection.
	 */
	ret = __create_hyp_mappings(base + NVHE_STACK_SIZE, NVHE_STACK_SIZE,
				    phys_addr, PAGE_HYP);
	if (ret)
		kvm_err("Cannot map hyp stack\n");

	*haddr = base + size;

	return ret;
}

/**
 * create_hyp_io_mappings - Map IO into both kernel and HYP
 * @phys_addr:	The physical start address which gets mapped
 * @size:	Size of the region being mapped
 * @kaddr:	Kernel VA for this mapping
 * @haddr:	HYP VA for this mapping
 */
int create_hyp_io_mappings(phys_addr_t phys_addr, size_t size,
			   void __iomem **kaddr,
			   void __iomem **haddr)
{
	unsigned long addr;
	int ret;

	if (is_protected_kvm_enabled())
		return -EPERM;

	*kaddr = ioremap(phys_addr, size);
	if (!*kaddr)
		return -ENOMEM;

	if (is_kernel_in_hyp_mode()) {
		*haddr = *kaddr;
		return 0;
	}

	ret = __create_hyp_private_mapping(phys_addr, size,
					   &addr, PAGE_HYP_DEVICE);
	if (ret) {
		iounmap(*kaddr);
		*kaddr = NULL;
		*haddr = NULL;
		return ret;
	}

	*haddr = (void __iomem *)addr;
	return 0;
}

/**
 * create_hyp_exec_mappings - Map an executable range into HYP
 * @phys_addr:	The physical start address which gets mapped
 * @size:	Size of the region being mapped
 * @haddr:	HYP VA for this mapping
 */
int create_hyp_exec_mappings(phys_addr_t phys_addr, size_t size,
			     void **haddr)
{
	unsigned long addr;
	int ret;

	BUG_ON(is_kernel_in_hyp_mode());

	ret = __create_hyp_private_mapping(phys_addr, size,
					   &addr, PAGE_HYP_EXEC);
	if (ret) {
		*haddr = NULL;
		return ret;
	}

	*haddr = (void *)addr;
	return 0;
}

static struct kvm_pgtable_mm_ops kvm_user_mm_ops = {
	/* We shouldn't need any other callback to walk the PT */
	.phys_to_virt		= kvm_host_va,
};

static int get_user_mapping_size(struct kvm *kvm, u64 addr)
{
	struct kvm_pgtable pgt = {
		.pgd		= (kvm_pteref_t)kvm->mm->pgd,
		.ia_bits	= vabits_actual,
		.start_level	= (KVM_PGTABLE_LAST_LEVEL -
				   ARM64_HW_PGTABLE_LEVELS(pgt.ia_bits) + 1),
		.mm_ops		= &kvm_user_mm_ops,
	};
	unsigned long flags;
	kvm_pte_t pte = 0;	/* Keep GCC quiet... */
	s8 level = S8_MAX;
	int ret;

	/*
	 * Disable IRQs so that we hazard against a concurrent
	 * teardown of the userspace page tables (which relies on
	 * IPI-ing threads).
	 */
	local_irq_save(flags);
	ret = kvm_pgtable_get_leaf(&pgt, addr, &pte, &level, 0);
	local_irq_restore(flags);

	if (ret)
		return ret;

	/*
	 * Not seeing an error, but not updating level? Something went
	 * deeply wrong...
	 */
	if (WARN_ON(level > KVM_PGTABLE_LAST_LEVEL))
		return -EFAULT;
	if (WARN_ON(level < KVM_PGTABLE_FIRST_LEVEL))
		return -EFAULT;

	/* Oops, the userspace PTs are gone... Replay the fault */
	if (!kvm_pte_valid(pte))
		return -EAGAIN;

	return BIT(ARM64_HW_PGTABLE_LEVEL_SHIFT(level));
}

static struct kvm_pgtable_mm_ops kvm_s2_mm_ops = {
	.zalloc_page		= stage2_memcache_zalloc_page,
	.zalloc_pages_exact	= kvm_s2_zalloc_pages_exact,
	.free_pages_exact	= kvm_s2_free_pages_exact,
	.free_unlinked_table	= stage2_free_unlinked_table,
	.get_page		= kvm_host_get_page,
	.put_page		= kvm_s2_put_page,
	.page_count		= kvm_host_page_count,
	.phys_to_virt		= kvm_host_va,
	.virt_to_phys		= kvm_host_pa,
	.dcache_clean_inval_poc	= clean_dcache_guest_page,
	.icache_inval_pou	= invalidate_icache_guest_page,
};

static int kvm_init_ipa_range(struct kvm_s2_mmu *mmu, unsigned long type)
{
	u32 kvm_ipa_limit = get_kvm_ipa_limit();
	u64 mmfr0, mmfr1;
	u32 phys_shift;

	phys_shift = KVM_VM_TYPE_ARM_IPA_SIZE(type);
	if (is_protected_kvm_enabled()) {
		phys_shift = kvm_ipa_limit;
	} else if (phys_shift) {
		if (phys_shift > kvm_ipa_limit ||
		    phys_shift < ARM64_MIN_PARANGE_BITS)
			return -EINVAL;
	} else {
		phys_shift = KVM_PHYS_SHIFT;
		if (phys_shift > kvm_ipa_limit) {
			pr_warn_once("%s using unsupported default IPA limit, upgrade your VMM\n",
				     current->comm);
			return -EINVAL;
		}
	}

	mmfr0 = read_sanitised_ftr_reg(SYS_ID_AA64MMFR0_EL1);
	mmfr1 = read_sanitised_ftr_reg(SYS_ID_AA64MMFR1_EL1);
	mmu->vtcr = kvm_get_vtcr(mmfr0, mmfr1, phys_shift);

	return 0;
}

/*
 * Assume that @pgt is valid and unlinked from the KVM MMU to free the
 * page-table without taking the kvm_mmu_lock and without performing any
 * TLB invalidations.
 *
 * Also, the range of addresses can be large enough to cause need_resched
 * warnings, for instance on CONFIG_PREEMPT_NONE kernels. Hence, invoke
 * cond_resched() periodically to prevent hogging the CPU for a long time
 * and schedule something else, if required.
 */
static void stage2_destroy_range(struct kvm_pgtable *pgt, phys_addr_t addr,
				   phys_addr_t end)
{
	u64 next;

	do {
		next = stage2_range_addr_end(addr, end);
		KVM_PGT_FN(kvm_pgtable_stage2_destroy_range)(pgt, addr,
							     next - addr);
		if (next != end)
			cond_resched();
	} while (addr = next, addr != end);
}

static void kvm_stage2_destroy(struct kvm_pgtable *pgt)
{
	unsigned int ia_bits = VTCR_EL2_IPA(pgt->mmu->vtcr);

	stage2_destroy_range(pgt, 0, BIT(ia_bits));
	KVM_PGT_FN(kvm_pgtable_stage2_destroy_pgd)(pgt);
}

/**
 * kvm_init_stage2_mmu - Initialise a S2 MMU structure
 * @kvm:	The pointer to the KVM structure
 * @mmu:	The pointer to the s2 MMU structure
 * @type:	The machine type of the virtual machine
 *
 * Allocates only the stage-2 HW PGD level table(s).
 * Note we don't need locking here as this is only called in two cases:
 *
 * - when the VM is created, which can't race against anything
 *
 * - when secondary kvm_s2_mmu structures are initialised for NV
 *   guests, and the caller must hold kvm->lock as this is called on a
 *   per-vcpu basis.
 */
int kvm_init_stage2_mmu(struct kvm *kvm, struct kvm_s2_mmu *mmu, unsigned long type)
{
	int cpu, err;
	struct kvm_pgtable *pgt;

	/* Initialize the VM ops for the VM instance for the first time */
	if (mmu == &kvm->arch.mmu) {
		err = kvm_vm_init_vm_s2_ops(kvm);
		if (err)
			return err;
	}
	/*
	 * If we already have our page tables in place, and that the
	 * MMU context is the canonical one, we have a bug somewhere,
	 * as this is only supposed to ever happen once per VM.
	 *
	 * Otherwise, we're building nested page tables, and that's
	 * probably because userspace called KVM_ARM_VCPU_INIT more
	 * than once on the same vcpu. Since that's actually legal,
	 * don't kick a fuss and leave gracefully.
	 */
	if (mmu->pgt != NULL) {
		if (kvm_is_nested_s2_mmu(kvm, mmu))
			return 0;

		kvm_err("kvm_arch already initialized?\n");
		return -EINVAL;
	}

	err = kvm_init_ipa_range(mmu, type);
	if (err)
		return err;

	pgt = kzalloc_obj(*pgt, GFP_KERNEL_ACCOUNT);
	if (!pgt)
		return -ENOMEM;

	mmu->arch = &kvm->arch;
	err = KVM_PGT_FN(kvm_pgtable_stage2_init)(pgt, mmu, &kvm_s2_mm_ops);
	if (err)
		goto out_free_pgtable;

	mmu->pgt = pgt;
	if (is_protected_kvm_enabled())
		return 0;

	mmu->last_vcpu_ran = alloc_percpu(typeof(*mmu->last_vcpu_ran));
	if (!mmu->last_vcpu_ran) {
		err = -ENOMEM;
		goto out_destroy_pgtable;
	}

	for_each_possible_cpu(cpu)
		*per_cpu_ptr(mmu->last_vcpu_ran, cpu) = -1;

	 /* The eager page splitting is disabled by default */
	mmu->split_page_chunk_size = KVM_ARM_EAGER_SPLIT_CHUNK_SIZE_DEFAULT;
	mmu->split_page_cache.gfp_zero = __GFP_ZERO;

	mmu->pgd_phys = __pa(pgt->pgd);

	mmu->guest_s2_mappings = RB_ROOT_CACHED;

	if (kvm_is_nested_s2_mmu(kvm, mmu))
		kvm_init_nested_s2_mmu(mmu);

	return 0;

out_destroy_pgtable:
	kvm_stage2_destroy(pgt);
	mmu->pgt = NULL;
out_free_pgtable:
	kfree(pgt);
	return err;
}

void kvm_uninit_stage2_mmu(struct kvm *kvm)
{
	kvm_free_stage2_pgd(&kvm->arch.mmu);
	kvm_mmu_free_memory_cache(&kvm->arch.mmu.split_page_cache);
}

static void stage2_unmap_memslot(struct kvm *kvm,
				 struct kvm_memory_slot *memslot)
{
	hva_t hva = memslot->userspace_addr;
	phys_addr_t addr = memslot->base_gfn << PAGE_SHIFT;
	phys_addr_t size = PAGE_SIZE * memslot->npages;
	hva_t reg_end = hva + size;

	/*
	 * A memory region could potentially cover multiple VMAs, and any holes
	 * between them, so iterate over all of them to find out if we should
	 * unmap any of them.
	 *
	 *     +--------------------------------------------+
	 * +---------------+----------------+   +----------------+
	 * |   : VMA 1     |      VMA 2     |   |    VMA 3  :    |
	 * +---------------+----------------+   +----------------+
	 *     |               memory region                |
	 *     +--------------------------------------------+
	 */
	do {
		struct vm_area_struct *vma;
		hva_t vm_start, vm_end;

		vma = find_vma_intersection(current->mm, hva, reg_end);
		if (!vma)
			break;

		/*
		 * Take the intersection of this VMA with the memory region
		 */
		vm_start = max(hva, vma->vm_start);
		vm_end = min(reg_end, vma->vm_end);

		if (!(vma->vm_flags & VM_PFNMAP)) {
			gpa_t gpa = addr + (vm_start - memslot->userspace_addr);
			kvm_stage2_unmap_range(&kvm->arch.mmu, gpa, vm_end - vm_start, true);
		}
		hva = vm_end;
	} while (hva < reg_end);
}

/**
 * stage2_unmap_vm - Unmap Stage-2 RAM mappings
 * @kvm: The struct kvm pointer
 *
 * Go through the memregions and unmap any regular RAM
 * backing memory already mapped to the VM.
 */
void stage2_unmap_vm(struct kvm *kvm)
{
	struct kvm_memslots *slots;
	struct kvm_memory_slot *memslot;
	int idx, bkt;

	idx = srcu_read_lock(&kvm->srcu);
	mmap_read_lock(current->mm);
	write_lock(&kvm->mmu_lock);

	slots = kvm_memslots(kvm);
	kvm_for_each_memslot(memslot, bkt, slots)
		stage2_unmap_memslot(kvm, memslot);

	kvm_nested_s2_unmap(kvm, true);

	write_unlock(&kvm->mmu_lock);
	mmap_read_unlock(current->mm);
	srcu_read_unlock(&kvm->srcu, idx);
}

static void guest_s2_tracking_destroy(struct rb_root_cached *tree)
{
	struct kvm_guest_s2_mapping *mapping;
	struct interval_tree_node *node;

	while ((node = interval_tree_iter_first(tree, 0, ULONG_MAX))) {
		interval_tree_remove(node, tree);
		mapping = container_of(node, struct kvm_guest_s2_mapping,
				       canonical);
		kfree(mapping);
		cond_resched();
	}
}

void kvm_free_stage2_pgd(struct kvm_s2_mmu *mmu)
{
	struct kvm *kvm = kvm_s2_mmu_to_kvm(mmu);
	struct kvm_pgtable *pgt = NULL;
	struct rb_root_cached mappings_tree;

	write_lock(&kvm->mmu_lock);
	pgt = mmu->pgt;
	if (pgt) {
		mmu->pgd_phys = 0;
		mmu->pgt = NULL;
		free_percpu(mmu->last_vcpu_ran);
	}

	if (kvm_is_nested_s2_mmu(kvm, mmu))
		kvm_init_nested_s2_mmu(mmu);

	mappings_tree = mmu->guest_s2_mappings;
	mmu->guest_s2_mappings = RB_ROOT_CACHED;

	write_unlock(&kvm->mmu_lock);

	if (pgt) {
		kvm_stage2_destroy(pgt);
		kfree(pgt);
	}

	if (!kvm_is_nested_s2_mmu(kvm, mmu))
		guest_s2_tracking_destroy(&mappings_tree);
}

static void hyp_mc_free_fn(void *addr, void *mc)
{
	struct kvm_hyp_memcache *memcache = mc;

	if (memcache->flags & HYP_MEMCACHE_ACCOUNT_STAGE2)
		kvm_account_pgtable_pages(addr, -1);

	free_page((unsigned long)addr);
}

static void *hyp_mc_alloc_fn(void *mc)
{
	struct kvm_hyp_memcache *memcache = mc;
	void *addr;
	gfp_t gfp;

	gfp = memcache->flags & HYP_MEMCACHE_ACCOUNT_KMEMCG ? GFP_KERNEL_ACCOUNT : GFP_KERNEL;
	addr = (void *)__get_free_page(gfp);
	if (addr && memcache->flags & HYP_MEMCACHE_ACCOUNT_STAGE2)
		kvm_account_pgtable_pages(addr, 1);

	return addr;
}

void free_hyp_memcache(struct kvm_hyp_memcache *mc)
{
	if (!is_protected_kvm_enabled())
		return;

	kfree(mc->mapping);
	__free_hyp_memcache(mc, hyp_mc_free_fn, kvm_host_va, mc);
}

int topup_hyp_memcache(struct kvm_hyp_memcache *mc, unsigned long min_pages)
{
	if (!is_protected_kvm_enabled())
		return 0;

	if (!mc->mapping) {
		mc->mapping = kzalloc_obj(struct pkvm_mapping,
					  GFP_KERNEL_ACCOUNT);
		if (!mc->mapping)
			return -ENOMEM;
	}

	return __topup_hyp_memcache(mc, min_pages, hyp_mc_alloc_fn,
				    kvm_host_pa, mc);
}

/**
 * kvm_phys_addr_ioremap - map a device range to guest IPA
 *
 * @kvm:	The KVM pointer
 * @guest_ipa:	The IPA at which to insert the mapping
 * @pa:		The physical address of the device
 * @size:	The size of the mapping
 * @writable:   Whether or not to create a writable mapping
 */
int kvm_phys_addr_ioremap(struct kvm *kvm, phys_addr_t guest_ipa,
			  phys_addr_t pa, unsigned long size, bool writable)
{
	phys_addr_t addr;
	int ret = 0;
	struct kvm_mmu_memory_cache cache = { .gfp_zero = __GFP_ZERO };
	struct kvm_s2_mmu *mmu = &kvm->arch.mmu;
	struct kvm_pgtable *pgt = mmu->pgt;
	enum kvm_pgtable_prot prot = KVM_PGTABLE_PROT_DEVICE |
				     KVM_PGTABLE_PROT_R |
				     (writable ? KVM_PGTABLE_PROT_W : 0);

	if (kvm_vm_hyp_is_distrusting(kvm))
		return -EPERM;

	size += offset_in_page(guest_ipa);
	guest_ipa &= PAGE_MASK;

	for (addr = guest_ipa; addr < guest_ipa + size; addr += PAGE_SIZE) {
		ret = kvm_mmu_topup_memory_cache(&cache,
						 kvm_mmu_cache_min_pages(mmu));
		if (ret)
			break;

		write_lock(&kvm->mmu_lock);
		ret = KVM_PGT_FN(kvm_pgtable_stage2_map)(pgt, addr, PAGE_SIZE,
				 pa, prot, &cache, 0);
		write_unlock(&kvm->mmu_lock);
		if (ret)
			break;

		pa += PAGE_SIZE;
	}

	kvm_mmu_free_memory_cache(&cache);
	return ret;
}

/**
 * kvm_stage2_wp_range() - write protect stage2 memory region range
 * @mmu:        The KVM stage-2 MMU pointer
 * @addr:	Start address of range
 * @end:	End address of range
 */
void kvm_stage2_wp_range(struct kvm_s2_mmu *mmu, phys_addr_t addr, phys_addr_t end)
{
	stage2_apply_range_resched(mmu, addr, end, KVM_PGT_FN(kvm_pgtable_stage2_wrprotect));
}

/**
 * kvm_mmu_wp_memory_region() - write protect stage 2 entries for memory slot
 * @kvm:	The KVM pointer
 * @slot:	The memory slot to write protect
 *
 * Called to start logging dirty pages after memory region
 * KVM_MEM_LOG_DIRTY_PAGES operation is called. After this function returns
 * all present PUD, PMD and PTEs are write protected in the memory region.
 * Afterwards read of dirty page log can be called.
 *
 * Acquires kvm_mmu_lock. Called with kvm->slots_lock mutex acquired,
 * serializing operations for VM memory regions.
 */
static void kvm_mmu_wp_memory_region(struct kvm *kvm, int slot)
{
	struct kvm_memslots *slots = kvm_memslots(kvm);
	struct kvm_memory_slot *memslot = id_to_memslot(slots, slot);
	phys_addr_t start, end;

	if (WARN_ON_ONCE(!memslot))
		return;

	start = memslot->base_gfn << PAGE_SHIFT;
	end = (memslot->base_gfn + memslot->npages) << PAGE_SHIFT;

	write_lock(&kvm->mmu_lock);
	kvm_stage2_wp_range(&kvm->arch.mmu, start, end);
	kvm_nested_s2_wp(kvm);
	write_unlock(&kvm->mmu_lock);
	kvm_flush_remote_tlbs_memslot(kvm, memslot);
}

/**
 * kvm_mmu_split_memory_region() - split the stage 2 blocks into PAGE_SIZE
 *				   pages for memory slot
 * @kvm:	The KVM pointer
 * @slot:	The memory slot to split
 *
 * Acquires kvm->mmu_lock. Called with kvm->slots_lock mutex acquired,
 * serializing operations for VM memory regions.
 */
static void kvm_mmu_split_memory_region(struct kvm *kvm, int slot)
{
	struct kvm_memslots *slots;
	struct kvm_memory_slot *memslot;
	phys_addr_t start, end;

	lockdep_assert_held(&kvm->slots_lock);

	slots = kvm_memslots(kvm);
	memslot = id_to_memslot(slots, slot);

	start = memslot->base_gfn << PAGE_SHIFT;
	end = (memslot->base_gfn + memslot->npages) << PAGE_SHIFT;

	write_lock(&kvm->mmu_lock);
	kvm_mmu_split_huge_pages(kvm, start, end);
	write_unlock(&kvm->mmu_lock);
}

/*
 * kvm_arch_mmu_enable_log_dirty_pt_masked() - enable dirty logging for selected pages.
 * @kvm:	The KVM pointer
 * @slot:	The memory slot associated with mask
 * @gfn_offset:	The gfn offset in memory slot
 * @mask:	The mask of pages at offset 'gfn_offset' in this memory
 *		slot to enable dirty logging on
 *
 * Writes protect selected pages to enable dirty logging, and then
 * splits them to PAGE_SIZE. Caller must acquire kvm->mmu_lock.
 */
void kvm_arch_mmu_enable_log_dirty_pt_masked(struct kvm *kvm,
		struct kvm_memory_slot *slot,
		gfn_t gfn_offset, unsigned long mask)
{
	phys_addr_t base_gfn = slot->base_gfn + gfn_offset;
	phys_addr_t start = (base_gfn +  __ffs(mask)) << PAGE_SHIFT;
	phys_addr_t end = (base_gfn + __fls(mask) + 1) << PAGE_SHIFT;

	lockdep_assert_held_write(&kvm->mmu_lock);

	kvm_stage2_wp_range(&kvm->arch.mmu, start, end);

	/*
	 * Eager-splitting is done when manual-protect is set.  We
	 * also check for initially-all-set because we can avoid
	 * eager-splitting if initially-all-set is false.
	 * Initially-all-set equal false implies that huge-pages were
	 * already split when enabling dirty logging: no need to do it
	 * again.
	 */
	if (kvm_dirty_log_manual_protect_and_init_set(kvm))
		kvm_mmu_split_huge_pages(kvm, start, end);

	kvm_nested_s2_wp(kvm);
}

static void kvm_send_hwpoison_signal(unsigned long address, short lsb)
{
	send_sig_mceerr(BUS_MCEERR_AR, (void __user *)address, lsb, current);
}

struct kvm_s2_fault_desc {
	struct kvm_vcpu		*vcpu;
	phys_addr_t		fault_ipa;
	struct kvm_s2_trans	*nested;
	struct kvm_memory_slot	*memslot;
	unsigned long		hva;
	unsigned long		esr;
	struct kvm_s2_mmu	*mmu;
};

struct kvm_s2_fault_vma_info {
	unsigned long	mmu_seq;
	long		vma_pagesize;
	vm_flags_t	vm_flags;
	unsigned long	max_map_size;
	struct page	*page;
	kvm_pfn_t	pfn;
	gfn_t		gfn;
	bool		device;
	bool		mte_allowed;
	bool		is_vma_cacheable;
	bool		map_writable;
	bool		map_non_cacheable;
};

struct kvm_s2_fault_result {
	unsigned long mapping_size;
};

static bool fault_supports_stage2_huge_mapping(const struct kvm_s2_fault_desc *s2fd,
					       unsigned long map_size)
{
	struct kvm_memory_slot *memslot = s2fd->memslot;
	unsigned long hva = s2fd->hva;
	hva_t uaddr_start, uaddr_end;
	gpa_t gpa_start;
	size_t size;

	/* The memslot and the VMA are guaranteed to be aligned to PAGE_SIZE */
	if (map_size == PAGE_SIZE)
		return true;

	/* pKVM only supports PMD_SIZE huge-mappings for non-protected VMs */
	if (is_protected_kvm_enabled()) {
		if (vcpu_is_protected(s2fd->vcpu) || map_size != PMD_SIZE)
			return false;
	}

	size = memslot->npages * PAGE_SIZE;

	gpa_start = memslot->base_gfn << PAGE_SHIFT;

	uaddr_start = memslot->userspace_addr;
	uaddr_end = uaddr_start + size;

	/*
	 * Pages belonging to memslots that don't have the same alignment
	 * within a PMD/PUD for userspace and IPA cannot be mapped with stage-2
	 * PMD/PUD entries, because we'll end up mapping the wrong pages.
	 *
	 * Consider a layout like the following:
	 *
	 *    memslot->userspace_addr:
	 *    +-----+--------------------+--------------------+---+
	 *    |abcde|fgh  Stage-1 block  |    Stage-1 block tv|xyz|
	 *    +-----+--------------------+--------------------+---+
	 *
	 *    memslot->base_gfn << PAGE_SHIFT:
	 *      +---+--------------------+--------------------+-----+
	 *      |abc|def  Stage-2 block  |    Stage-2 block   |tvxyz|
	 *      +---+--------------------+--------------------+-----+
	 *
	 * If we create those stage-2 blocks, we'll end up with this incorrect
	 * mapping:
	 *   d -> f
	 *   e -> g
	 *   f -> h
	 */
	if ((gpa_start & (map_size - 1)) != (uaddr_start & (map_size - 1)))
		return false;

	/*
	 * Next, let's make sure we're not trying to map anything not covered
	 * by the memslot. This means we have to prohibit block size mappings
	 * for the beginning and end of a non-block aligned and non-block sized
	 * memory slot (illustrated by the head and tail parts of the
	 * userspace view above containing pages 'abcde' and 'xyz',
	 * respectively).
	 *
	 * Note that it doesn't matter if we do the check using the
	 * userspace_addr or the base_gfn, as both are equally aligned (per
	 * the check above) and equally sized.
	 */
	return (hva & ~(map_size - 1)) >= uaddr_start &&
	       (hva & ~(map_size - 1)) + map_size <= uaddr_end;
}

/*
 * Check if the given hva is backed by a transparent huge page (THP) and
 * whether it can be mapped using block mapping in stage2. If so, adjust
 * the stage2 PFN and IPA accordingly. Only PMD_SIZE THPs are currently
 * supported. This will need to be updated to support other THP sizes.
 *
 * Returns the size of the mapping.
 */
static long
transparent_hugepage_adjust(const struct kvm_s2_fault_desc *s2fd, kvm_pfn_t *pfnp, gfn_t *gfnp)
{
	struct kvm *kvm = s2fd->vcpu->kvm;
	kvm_pfn_t pfn = *pfnp;
	gfn_t gfn = *gfnp;

	/*
	 * Make sure the adjustment is done only for THP pages. Also make
	 * sure that the HVA and IPA are sufficiently aligned and that the
	 * block map is contained within the memslot.
	 */
	if (fault_supports_stage2_huge_mapping(s2fd, PMD_SIZE)) {
		int sz = get_user_mapping_size(kvm, s2fd->hva);

		if (sz < 0)
			return sz;

		if (sz < PMD_SIZE)
			return PAGE_SIZE;

		gfn &= ~(PTRS_PER_PMD - 1);
		*gfnp = gfn;
		pfn &= ~(PTRS_PER_PMD - 1);
		*pfnp = pfn;

		return PMD_SIZE;
	}

	/* Use page mapping if we cannot use block mapping. */
	return PAGE_SIZE;
}

static int get_vma_page_shift(struct vm_area_struct *vma)
{
	if (is_vm_hugetlb_page(vma))
		return huge_page_shift(hstate_vma(vma));

	return PAGE_SHIFT;
}

/*
 * The page will be mapped in stage 2 as Normal Cacheable, so the VM will be
 * able to see the page's tags and therefore they must be initialised first. If
 * PG_mte_tagged is set, tags have already been initialised.
 *
 * Must be called with kvm->mmu_lock held to ensure the memory remains mapped
 * while the tags are zeroed.
 */
static void sanitise_mte_tags(struct kvm *kvm, kvm_pfn_t pfn,
			      unsigned long size)
{
	unsigned long i, nr_pages = size >> PAGE_SHIFT;
	struct page *page = pfn_to_page(pfn);
	struct folio *folio = page_folio(page);

	if (!kvm_has_mte(kvm))
		return;

	if (is_zero_pfn(pfn)) {
		WARN_ON_ONCE(nr_pages != 1);
		return;
	}

	if (folio_test_hugetlb(folio)) {
		/* Hugetlb has MTE flags set on head page only */
		if (folio_try_hugetlb_mte_tagging(folio)) {
			for (i = 0; i < nr_pages; i++, page++)
				mte_clear_page_tags(page_address(page));
			folio_set_hugetlb_mte_tagged(folio);
		}
		return;
	}

	for (i = 0; i < nr_pages; i++, page++) {
		if (try_page_mte_tagging(page)) {
			mte_clear_page_tags(page_address(page));
			set_page_mte_tagged(page);
		}
	}
}

static bool kvm_vma_mte_allowed(struct vm_area_struct *vma)
{
	return vma->vm_flags & VM_MTE_ALLOWED;
}

static bool kvm_vma_is_cacheable(struct vm_area_struct *vma)
{
	switch (FIELD_GET(PTE_ATTRINDX_MASK, pgprot_val(vma->vm_page_prot))) {
	case MT_NORMAL_NC:
	case MT_DEVICE_nGnRnE:
	case MT_DEVICE_nGnRE:
		return false;
	default:
		return true;
	}
}

static void *get_mmu_memcache(struct kvm_vcpu *vcpu)
{
	if (!is_protected_kvm_enabled())
		return &vcpu->arch.mmu_page_cache;
	else
		return &vcpu->arch.stage2_mc;
}

static int topup_mmu_memcache(struct kvm_s2_mmu *mmu, void *memcache)
{
	int min_pages = kvm_mmu_cache_min_pages(mmu);

	if (!is_protected_kvm_enabled())
		return kvm_mmu_topup_memory_cache(memcache, min_pages);

	return topup_hyp_memcache(memcache, min_pages);
}

/*
 * Potentially reduce shadow S2 permissions to match the guest's own S2. For
 * exec faults, we'd only reach this point if the guest actually allowed it (see
 * kvm_s2_handle_perm_fault).
 *
 * Also encode the level of the original translation in the SW bits of the leaf
 * entry as a proxy for the span of that translation. This will be retrieved on
 * TLB invalidation from the guest and used to limit the invalidation scope if a
 * TTL hint or a range isn't provided.
 */
static enum kvm_pgtable_prot adjust_nested_fault_perms(struct kvm_s2_trans *nested,
						       enum kvm_pgtable_prot prot)
{
	if (!kvm_s2_trans_writable(nested))
		prot &= ~KVM_PGTABLE_PROT_W;
	if (!kvm_s2_trans_readable(nested))
		prot &= ~KVM_PGTABLE_PROT_R;

	return prot | kvm_encode_nested_level(nested);
}

static enum kvm_pgtable_prot adjust_nested_exec_perms(struct kvm *kvm,
						      struct kvm_s2_trans *nested,
						      enum kvm_pgtable_prot prot)
{
	if (!kvm_s2_trans_exec_el0(kvm, nested))
		prot &= ~KVM_PGTABLE_PROT_UX;
	if (!kvm_s2_trans_exec_el1(kvm, nested))
		prot &= ~KVM_PGTABLE_PROT_PX;

	return prot;
}

static bool kvm_s2_fault_is_perm(const struct kvm_s2_fault_desc *s2fd)
{
	return esr_fsc_is_permission_fault(s2fd->esr);
}

static bool kvm_s2_fault_is_exec(const struct kvm_s2_fault_desc *s2fd)
{
	return esr_abt_is_exec_fault(s2fd->esr);
}

static bool kvm_s2_fault_is_write(const struct kvm_s2_fault_desc *s2fd)
{
	return esr_abt_is_write_fault(s2fd->esr);
}

static u64 kvm_s2_perm_fault_granule(const struct kvm_s2_fault_desc *s2fd)
{
	u64 level;

	if (!kvm_s2_fault_is_perm(s2fd))
		return 0;
	level = s2fd->esr & ESR_ELx_FSC_LEVEL;
	return BIT(ARM64_HW_PGTABLE_LEVEL_SHIFT(level));
}

static int kvm_s2_fault_get_vma_info(const struct kvm_s2_fault_desc *s2fd,
				     struct kvm_s2_fault_vma_info *s2vi);

static gfn_t get_canonical_gfn(const struct kvm_s2_fault_desc *s2fd,
			       const struct kvm_s2_fault_vma_info *s2vi);

static int gmem_abort(const struct kvm_s2_fault_desc *s2fd,
		      struct kvm_s2_fault_result *result)
{
	bool write_fault, exec_fault;
	bool perm_fault = kvm_s2_fault_is_perm(s2fd);
	enum kvm_pgtable_walk_flags flags = KVM_PGTABLE_WALK_SHARED;
	enum kvm_pgtable_prot prot = KVM_PGTABLE_PROT_R;
	struct kvm_pgtable *pgt = s2fd->mmu->pgt;
	struct kvm_guest_s2_mapping *mapping = NULL;
	struct kvm_s2_fault_vma_info s2vi = {};
	struct kvm *kvm = s2fd->vcpu->kvm;
	void *memcache = NULL;
	gfn_t canonical_gfn;
	int ret;

	if (!perm_fault) {
		memcache = get_mmu_memcache(s2fd->vcpu);
		ret = topup_mmu_memcache(s2fd->mmu, memcache);
		if (ret)
			return ret;
		if (kvm_is_nested_s2_mmu(kvm, pgt->mmu)) {
			mapping = kmalloc_obj(struct kvm_guest_s2_mapping, GFP_KERNEL_ACCOUNT);
			if (!mapping)
				return -ENOMEM;
		}
	}

	s2vi.vma_pagesize = PAGE_SIZE;
	s2vi.gfn = ALIGN_DOWN(s2fd->fault_ipa, s2vi.vma_pagesize) >> PAGE_SHIFT;
	canonical_gfn = get_canonical_gfn(s2fd, &s2vi);

	write_fault = kvm_s2_fault_is_write(s2fd);
	exec_fault = kvm_s2_fault_is_exec(s2fd);

	VM_WARN_ON_ONCE(write_fault && exec_fault);

	s2vi.mmu_seq = kvm->mmu_invalidate_seq;
	/* Pairs with the smp_wmb() in kvm_mmu_invalidate_end(). */
	smp_rmb();

	ret = kvm_gmem_get_pfn(kvm, s2fd->memslot, canonical_gfn, &s2vi.pfn, NULL);
	if (ret) {
		/* If result is non-NULL this is a synthetic fault. */
		if (!result)
			kvm_prepare_memory_fault_exit(s2fd->vcpu, gfn_to_gpa(canonical_gfn),
						      s2vi.vma_pagesize, write_fault, exec_fault,
						      false);
		kfree(mapping);
	}

	if (!(s2fd->memslot->flags & KVM_MEM_READONLY))
		prot |= KVM_PGTABLE_PROT_W;

	if (s2fd->nested)
		prot = adjust_nested_fault_perms(s2fd->nested, prot);

	if (exec_fault || cpus_have_final_cap(ARM64_HAS_CACHE_DIC))
		prot |= KVM_PGTABLE_PROT_X;

	if (s2fd->nested)
		prot = adjust_nested_exec_perms(kvm, s2fd->nested, prot);

	kvm_fault_lock(kvm);
	if (mmu_invalidate_retry(kvm, s2vi.mmu_seq)) {
		ret = -EAGAIN;
		goto out_unlock;
	}

	if (perm_fault) {
		/*
		 * Drop the SW bits in favour of those stored in the
		 * PTE, which will be preserved.
		 */
		prot &= ~KVM_NV_GUEST_MAP_SZ;
		ret = KVM_PGT_FN(kvm_pgtable_stage2_relax_perms)(pgt, gfn_to_gpa(s2vi.gfn),
								 prot, flags);
	} else {
		ret = KVM_PGT_FN(kvm_pgtable_stage2_map)(pgt, gfn_to_gpa(s2vi.gfn),
							 s2vi.vma_pagesize,
							 __pfn_to_phys(s2vi.pfn), prot,
							 memcache, flags);
		/*
		 * -EAGAIN from kvm_pgtable_stage2_map() can install mappings.
		 * We don't know which subrange is installed, track the whole
		 * thing.
		 */
		if ((ret == 0 || ret == -EAGAIN) && kvm_is_nested_s2_mmu(kvm, pgt->mmu)) {
			kvm_record_guest_s2_mapping(pgt->mmu, canonical_gfn << PAGE_SHIFT,
						    s2fd->fault_ipa, s2vi.vma_pagesize, mapping);
			mapping = NULL;
		}
	}

out_unlock:
	kvm_fault_unlock(kvm);
	kfree(mapping);

	if ((prot & KVM_PGTABLE_PROT_W) && !ret)
		mark_page_dirty_in_slot(kvm, s2fd->memslot, canonical_gfn);

	if (ret == -EAGAIN)
		return result ? ret : 0;

	if (result && !ret)
		result->mapping_size = s2vi.vma_pagesize;

	return ret;
}

static int protected_pkvm_mem_abort(const struct kvm_s2_fault_desc *s2fd)
{
	unsigned int flags = FOLL_HWPOISON | FOLL_LONGTERM | FOLL_WRITE;
	struct kvm_s2_fault_vma_info s2vi = {};
	struct kvm_vcpu *vcpu = s2fd->vcpu;
	struct kvm_pgtable *pgt = s2fd->mmu->pgt;
	struct mm_struct *mm = current->mm;
	struct kvm *kvm = vcpu->kvm;
	void *hyp_memcache;
	int ret;

	hyp_memcache = get_mmu_memcache(vcpu);
	ret = topup_mmu_memcache(s2fd->mmu, hyp_memcache);
	if (ret)
		return -ENOMEM;

	ret = kvm_s2_fault_get_vma_info(s2fd, &s2vi);
	if (ret)
		return ret;

	ret = account_locked_vm(mm, 1, true);
	if (ret)
		return ret;

	mmap_read_lock(mm);
	ret = pin_user_pages(s2fd->hva, 1, flags, &s2vi.page);
	mmap_read_unlock(mm);

	if (ret == -EHWPOISON) {
		kvm_send_hwpoison_signal(s2fd->hva, PAGE_SHIFT);
		ret = 0;
		goto dec_account;
	} else if (ret != 1) {
		ret = -EFAULT;
		goto dec_account;
	} else if (!folio_test_swapbacked(page_folio(s2vi.page))) {
		/*
		 * We really can't deal with page-cache pages returned by GUP
		 * because (a) we may trigger writeback of a page for which we
		 * no longer have access and (b) page_mkclean() won't find the
		 * stage-2 mapping in the rmap so we can get out-of-whack with
		 * the filesystem when marking the page dirty during unpinning
		 * (see cc5095747edf ("ext4: don't BUG if someone dirty pages
		 * without asking ext4 first")).
		 *
		 * Ideally we'd just restrict ourselves to anonymous pages, but
		 * we also want to allow memfd (i.e. shmem) pages, so check for
		 * pages backed by swap in the knowledge that the GUP pin will
		 * prevent try_to_unmap() from succeeding.
		 */
		ret = -EIO;
		goto unpin;
	}

	write_lock(&kvm->mmu_lock);
	ret = pkvm_pgtable_stage2_map(pgt, gfn_to_gpa(s2vi.gfn), PAGE_SIZE,
				      page_to_phys(s2vi.page), KVM_PGTABLE_PROT_RWX,
				      hyp_memcache, 0);
	write_unlock(&kvm->mmu_lock);
	if (ret) {
		if (ret == -EAGAIN)
			ret = 0;
		goto unpin;
	}

	return 0;
unpin:
	unpin_user_page(s2vi.page);
dec_account:
	account_locked_vm(mm, 1, false);
	return ret;
}

static short kvm_s2_resolve_vma_size(const struct kvm_s2_fault_desc *s2fd,
				     struct kvm_s2_fault_vma_info *s2vi,
				     struct vm_area_struct *vma)
{
	short vma_shift;

	if (memslot_is_logging(s2fd->memslot)) {
		s2vi->max_map_size = PAGE_SIZE;
		vma_shift = PAGE_SHIFT;
	} else {
		s2vi->max_map_size = PUD_SIZE;
		vma_shift = get_vma_page_shift(vma);
	}

	switch (vma_shift) {
#ifndef __PAGETABLE_PMD_FOLDED
	case PUD_SHIFT:
		if (fault_supports_stage2_huge_mapping(s2fd, PUD_SIZE))
			break;
		fallthrough;
#endif
	case CONT_PMD_SHIFT:
		vma_shift = PMD_SHIFT;
		fallthrough;
	case PMD_SHIFT:
		if (fault_supports_stage2_huge_mapping(s2fd, PMD_SIZE))
			break;
		fallthrough;
	case CONT_PTE_SHIFT:
		vma_shift = PAGE_SHIFT;
		s2vi->max_map_size = PAGE_SIZE;
		fallthrough;
	case PAGE_SHIFT:
		break;
	default:
		WARN_ONCE(1, "Unknown vma_shift %d", vma_shift);
	}

	if (s2fd->nested) {
		unsigned long max_map_size;

		max_map_size = min(s2vi->max_map_size, PUD_SIZE);

		/*
		 * If we're about to create a shadow stage 2 entry, then we
		 * can only create a block mapping if the guest stage 2 page
		 * table uses at least as big a mapping.
		 */
		max_map_size = min(kvm_s2_trans_size(s2fd->nested), max_map_size);

		/*
		 * Be careful that if the mapping size falls between
		 * two host sizes, take the smallest of the two.
		 */
		if (max_map_size >= PMD_SIZE && max_map_size < PUD_SIZE)
			max_map_size = PMD_SIZE;
		else if (max_map_size >= PAGE_SIZE && max_map_size < PMD_SIZE)
			max_map_size = PAGE_SIZE;

		s2vi->max_map_size = max_map_size;
		vma_shift = min_t(short, vma_shift, __ffs(max_map_size));
	}

	return vma_shift;
}

static int kvm_s2_fault_get_vma_info(const struct kvm_s2_fault_desc *s2fd,
				     struct kvm_s2_fault_vma_info *s2vi)
{
	struct vm_area_struct *vma;
	struct kvm *kvm = s2fd->vcpu->kvm;

	mmap_read_lock(current->mm);
	vma = vma_lookup(current->mm, s2fd->hva);
	if (unlikely(!vma)) {
		kvm_err("Failed to find VMA for hva 0x%lx\n", s2fd->hva);
		mmap_read_unlock(current->mm);
		return -EFAULT;
	}

	s2vi->vma_pagesize = BIT(kvm_s2_resolve_vma_size(s2fd, s2vi, vma));

	/*
	 * Both the canonical IPA and fault IPA must be aligned to the
	 * mapping size to ensure we find the right PFN and lay down the
	 * mapping in the right place.
	 */
	s2vi->gfn = ALIGN_DOWN(s2fd->fault_ipa, s2vi->vma_pagesize) >> PAGE_SHIFT;

	s2vi->mte_allowed = kvm_vma_mte_allowed(vma);

	s2vi->vm_flags = vma->vm_flags;

	s2vi->is_vma_cacheable = kvm_vma_is_cacheable(vma);

	/*
	 * Read mmu_invalidate_seq so that KVM can detect if the results of
	 * vma_lookup() or __kvm_faultin_pfn() become stale prior to
	 * acquiring kvm->mmu_lock.
	 *
	 * Rely on mmap_read_unlock() for an implicit smp_rmb(), which pairs
	 * with the smp_wmb() in kvm_mmu_invalidate_end().
	 */
	s2vi->mmu_seq = kvm->mmu_invalidate_seq;
	mmap_read_unlock(current->mm);

	return 0;
}

static gfn_t get_canonical_gfn(const struct kvm_s2_fault_desc *s2fd,
			       const struct kvm_s2_fault_vma_info *s2vi)
{
	phys_addr_t ipa;

	if (!s2fd->nested)
		return s2vi->gfn;

	ipa = kvm_s2_trans_output(s2fd->nested);
	return ALIGN_DOWN(ipa, s2vi->vma_pagesize) >> PAGE_SHIFT;
}

static int kvm_s2_fault_pin_pfn(const struct kvm_s2_fault_desc *s2fd,
				struct kvm_s2_fault_vma_info *s2vi)
{
	int ret;

	ret = kvm_s2_fault_get_vma_info(s2fd, s2vi);
	if (ret)
		return ret;

	s2vi->pfn = __kvm_faultin_pfn(s2fd->memslot, get_canonical_gfn(s2fd, s2vi),
				      kvm_s2_fault_is_write(s2fd) ? FOLL_WRITE : 0,
				      &s2vi->map_writable, &s2vi->page);
	if (unlikely(is_error_noslot_pfn(s2vi->pfn))) {
		if (s2vi->pfn == KVM_PFN_ERR_HWPOISON)
			return -EHWPOISON;
		return -EFAULT;
	}

	/*
	 * Check if this is non-struct page memory PFN, and cannot support
	 * CMOs. It could potentially be unsafe to access as cacheable.
	 */
	if (s2vi->vm_flags & (VM_PFNMAP | VM_MIXEDMAP) && !pfn_is_map_memory(s2vi->pfn)) {
		if (s2vi->is_vma_cacheable) {
			/*
			 * Whilst the VMA owner expects cacheable mapping to this
			 * PFN, hardware also has to support the FWB and CACHE DIC
			 * features.
			 *
			 * ARM64 KVM relies on kernel VA mapping to the PFN to
			 * perform cache maintenance as the CMO instructions work on
			 * virtual addresses. VM_PFNMAP region are not necessarily
			 * mapped to a KVA and hence the presence of hardware features
			 * S2FWB and CACHE DIC are mandatory to avoid the need for
			 * cache maintenance.
			 */
			if (!kvm_supports_cacheable_pfnmap()) {
				kvm_release_faultin_page(s2fd->vcpu->kvm, s2vi->page, true, false);
				return -EFAULT;
			}
		} else {
			s2vi->map_non_cacheable = true;
		}

		s2vi->device = true;
	}

	return 1;
}

static int kvm_s2_fault_compute_prot(const struct kvm_s2_fault_desc *s2fd,
				     const struct kvm_s2_fault_vma_info *s2vi,
				     enum kvm_pgtable_prot *prot)
{
	struct kvm *kvm = s2fd->vcpu->kvm;

	if (kvm_s2_fault_is_exec(s2fd) && s2vi->map_non_cacheable)
		return -ENOEXEC;

	/*
	 * Guest performs atomic/exclusive operations on memory with unsupported
	 * attributes (e.g. ld64b/st64b on normal memory when no FEAT_LS64WB)
	 * and trigger the exception here. Since the memslot is valid, inject
	 * the fault back to the guest.
	 */
	if (esr_fsc_is_excl_atomic_fault(s2fd->esr)) {
		kvm_inject_dabt_excl_atomic(s2fd->vcpu, kvm_vcpu_get_hfar(s2fd->vcpu));
		return 1;
	}

	*prot = KVM_PGTABLE_PROT_R;

	if (s2vi->map_writable && (s2vi->device ||
				   !memslot_is_logging(s2fd->memslot) ||
				   kvm_s2_fault_is_write(s2fd)))
		*prot |= KVM_PGTABLE_PROT_W;

	if (s2fd->nested)
		*prot = adjust_nested_fault_perms(s2fd->nested, *prot);

	if (kvm_s2_fault_is_exec(s2fd))
		*prot |= KVM_PGTABLE_PROT_X;

	if (s2vi->map_non_cacheable)
		*prot |= (s2vi->vm_flags & VM_ALLOW_ANY_UNCACHED) ?
			KVM_PGTABLE_PROT_NORMAL_NC : KVM_PGTABLE_PROT_DEVICE;
	else if (cpus_have_final_cap(ARM64_HAS_CACHE_DIC))
		*prot |= KVM_PGTABLE_PROT_X;

	if (s2fd->nested)
		*prot = adjust_nested_exec_perms(kvm, s2fd->nested, *prot);

	if (!kvm_s2_fault_is_perm(s2fd) && !s2vi->map_non_cacheable && kvm_has_mte(kvm)) {
		/* Check the VMM hasn't introduced a new disallowed VMA */
		if (!s2vi->mte_allowed)
			return -EFAULT;
	}

	return 0;
}

static int kvm_s2_fault_map(const struct kvm_s2_fault_desc *s2fd,
			    const struct kvm_s2_fault_vma_info *s2vi,
			    enum kvm_pgtable_prot prot,
			    void *memcache,
			    struct kvm_s2_fault_result *result)
{
	enum kvm_pgtable_walk_flags flags = KVM_PGTABLE_WALK_SHARED;
	struct kvm_guest_s2_mapping *mapping = NULL;
	bool writable = prot & KVM_PGTABLE_PROT_W;
	struct kvm *kvm = s2fd->vcpu->kvm;
	phys_addr_t canonical_ipa;
	struct kvm_pgtable *pgt;
	long perm_fault_granule;
	long mapping_size;
	kvm_pfn_t pfn;
	gfn_t gfn;
	int ret;

	if (kvm_is_nested_s2_mmu(kvm, s2fd->mmu)) {
		mapping = kmalloc_obj(struct kvm_guest_s2_mapping,
				      GFP_KERNEL_ACCOUNT);
		if (!mapping) {
			kvm_release_page_unused(s2vi->page);
			return -ENOMEM;
		}
	}

	kvm_fault_lock(kvm);
	pgt = s2fd->mmu->pgt;
	ret = -EAGAIN;
	if (mmu_invalidate_retry(kvm, s2vi->mmu_seq))
		goto out_unlock;

	perm_fault_granule = kvm_s2_perm_fault_granule(s2fd);
	mapping_size = s2vi->vma_pagesize;
	pfn = s2vi->pfn;
	gfn = s2vi->gfn;
	canonical_ipa = gfn_to_gpa(get_canonical_gfn(s2fd, s2vi));

	/*
	 * If we are not forced to use page mapping, check if we are
	 * backed by a huge stage-1 mapping and thus use block mapping if
	 * possible.
	 */
	if (mapping_size == PAGE_SIZE && s2vi->max_map_size != PAGE_SIZE) {
		if (perm_fault_granule > PAGE_SIZE) {
			mapping_size = perm_fault_granule;
		} else {
			mapping_size = transparent_hugepage_adjust(s2fd, &pfn, &gfn);
			if (mapping_size < 0) {
				ret = mapping_size;
				goto out_unlock;
			}
		}
		canonical_ipa = ALIGN_DOWN(canonical_ipa, mapping_size);
	}

	if (!perm_fault_granule && !s2vi->map_non_cacheable && kvm_has_mte(kvm))
		sanitise_mte_tags(kvm, pfn, mapping_size);

	/*
	 * Under the premise of getting a FSC_PERM fault, we just need to relax
	 * permissions only if mapping_size equals perm_fault_granule. Otherwise,
	 * kvm_pgtable_stage2_map() should be called to change block size.
	 */
	if (mapping_size == perm_fault_granule) {
		/*
		 * Drop the SW bits in favour of those stored in the
		 * PTE, which will be preserved.
		 */
		prot &= ~KVM_NV_GUEST_MAP_SZ;
		ret = KVM_PGT_FN(kvm_pgtable_stage2_relax_perms)(pgt, gfn_to_gpa(gfn),
								 prot, flags);
	} else {
		ret = KVM_PGT_FN(kvm_pgtable_stage2_map)(pgt, gfn_to_gpa(gfn), mapping_size,
							 __pfn_to_phys(pfn), prot,
							 memcache, flags);
		/*
		 * -EAGAIN from kvm_pgtable_stage2_map() can install mappings.
		 * We don't know which subrange is installed, track the whole
		 * thing.
		 */
		if ((ret == 0 || ret == -EAGAIN) && kvm_is_nested_s2_mmu(kvm, pgt->mmu)) {
			kvm_record_guest_s2_mapping(pgt->mmu, canonical_ipa,
						    gfn_to_gpa(gfn), mapping_size, mapping);
			mapping = NULL;
		}
	}

out_unlock:
	kvm_release_faultin_page(kvm, s2vi->page, !!ret, writable);
	kvm_fault_unlock(kvm);
	kfree(mapping);

	/*
	 * Mark the page dirty only if the fault is handled successfully,
	 * making sure we adjust the canonical IPA if the mapping size has
	 * been updated (via a THP upgrade, for example).
	 */
	if (writable && !ret)
		mark_page_dirty_in_slot(kvm, s2fd->memslot,
					gpa_to_gfn(canonical_ipa));

	if (ret == -EAGAIN)
		return result ? ret : 0;

	if (result && !ret)
		result->mapping_size = mapping_size;

	return ret;
}

static int user_mem_abort(const struct kvm_s2_fault_desc *s2fd,
			  struct kvm_s2_fault_result *result)
{
	bool perm_fault = kvm_s2_fault_is_perm(s2fd);
	struct kvm_s2_fault_vma_info s2vi = {};
	enum kvm_pgtable_prot prot;
	void *memcache;
	int ret;

	/*
	 * Permission faults just need to update the existing leaf entry,
	 * and so normally don't require allocations from the memcache. The
	 * only exception to this is when dirty logging is enabled at runtime
	 * and a fault needs to collapse a block entry into a table.
	 * Under pKVM a permission fault can also collapse pages into a block,
	 * which needs a fresh mapping object, and the hypervisor requires the
	 * min-pages memcache even when the install allocates nothing.
	 */
	memcache = get_mmu_memcache(s2fd->vcpu);
	if (!perm_fault || memslot_is_logging(s2fd->memslot) ||
	    is_protected_kvm_enabled()) {
		ret = topup_mmu_memcache(s2fd->mmu, memcache);
		if (ret)
			return ret;
	}

	ret = kvm_s2_fault_pin_pfn(s2fd, &s2vi);
	if (ret == -EHWPOISON) {
		/* If result is specified, let the caller handle this. */
		if (result)
			return -EHWPOISON;
		kvm_send_hwpoison_signal(s2fd->hva, __ffs(s2vi.vma_pagesize));
		return 0;
	}
	if (ret != 1)
		return ret;

	ret = kvm_s2_fault_compute_prot(s2fd, &s2vi, &prot);
	if (ret) {
		kvm_release_page_unused(s2vi.page);
		return ret;
	}

	return kvm_s2_fault_map(s2fd, &s2vi, prot, memcache, result);
}

static int kvm_vm_mem_abort(const struct kvm_s2_fault_desc *s2fd)
{
	VM_WARN_ON_ONCE(kvm_s2_fault_is_perm(s2fd) &&
			!esr_abt_is_write_fault(s2fd->esr) &&
			!kvm_s2_fault_is_exec(s2fd));

	if (kvm_slot_has_gmem(s2fd->memslot))
		return gmem_abort(s2fd, NULL);
	else
		return user_mem_abort(s2fd, NULL);
}

/* Resolve the access fault by making the page young again. */
static void handle_access_fault(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa)
{
	enum kvm_pgtable_walk_flags flags = KVM_PGTABLE_WALK_SHARED;
	struct kvm_s2_mmu *mmu;

	trace_kvm_access_fault(fault_ipa);

	read_lock(&vcpu->kvm->mmu_lock);
	mmu = vcpu->arch.hw_mmu;
	KVM_PGT_FN(kvm_pgtable_stage2_mkyoung)(mmu->pgt, fault_ipa, flags);
	read_unlock(&vcpu->kvm->mmu_lock);
}

/*
 * Returns true if the SEA should be handled locally within KVM if the abort
 * is caused by a kernel memory allocation (e.g. stage-2 table memory).
 */
static bool host_owns_sea(struct kvm_vcpu *vcpu, u64 esr)
{
	/*
	 * Without FEAT_RAS HCR_EL2.TEA is RES0, meaning any external abort
	 * taken from a guest EL to EL2 is due to a host-imposed access (e.g.
	 * stage-2 PTW).
	 */
	if (!cpus_have_final_cap(ARM64_HAS_RAS_EXTN))
		return true;

	/* KVM owns the VNCR when the vCPU isn't in a nested context. */
	if (is_hyp_ctxt(vcpu) && !kvm_vcpu_trap_is_iabt(vcpu) && (esr & ESR_ELx_VNCR))
		return true;

	/*
	 * Determining if an external abort during a table walk happened at
	 * stage-2 is only possible with S1PTW is set. Otherwise, since KVM
	 * sets HCR_EL2.TEA, SEAs due to a stage-1 walk (i.e. accessing the
	 * PA of the stage-1 descriptor) can reach here and are reported
	 * with a TTW ESR value.
	 */
	return (esr_fsc_is_sea_ttw(esr) && (esr & ESR_ELx_S1PTW));
}

int kvm_handle_guest_sea(struct kvm_vcpu *vcpu)
{
	struct kvm *kvm = vcpu->kvm;
	struct kvm_run *run = vcpu->run;
	u64 esr = kvm_vcpu_get_esr(vcpu);
	u64 esr_mask = ESR_ELx_EC_MASK	|
		       ESR_ELx_IL	|
		       ESR_ELx_FnV	|
		       ESR_ELx_EA	|
		       ESR_ELx_CM	|
		       ESR_ELx_WNR	|
		       ESR_ELx_FSC;
	u64 ipa;

	/*
	 * Give APEI the opportunity to claim the abort before handling it
	 * within KVM. apei_claim_sea() expects to be called with IRQs enabled.
	 */
	lockdep_assert_irqs_enabled();
	if (apei_claim_sea(NULL) == 0)
		return 1;

	if (host_owns_sea(vcpu, esr) ||
	    !test_bit(KVM_ARCH_FLAG_EXIT_SEA, &vcpu->kvm->arch.flags))
		return kvm_inject_serror(vcpu);

	/* ESR_ELx.SET is RES0 when FEAT_RAS isn't implemented. */
	if (kvm_has_ras(kvm))
		esr_mask |= ESR_ELx_SET_MASK;

	/*
	 * Exit to userspace, and provide faulting guest virtual and physical
	 * addresses in case userspace wants to emulate SEA to guest by
	 * writing to FAR_ELx and HPFAR_ELx registers.
	 */
	memset(&run->arm_sea, 0, sizeof(run->arm_sea));
	run->exit_reason = KVM_EXIT_ARM_SEA;
	run->arm_sea.esr = esr & esr_mask;

	if (!(esr & ESR_ELx_FnV))
		run->arm_sea.gva = kvm_vcpu_get_hfar(vcpu);

	ipa = kvm_vcpu_get_fault_ipa(vcpu);
	if (ipa != INVALID_GPA) {
		run->arm_sea.flags |= KVM_EXIT_ARM_SEA_FLAG_GPA_VALID;
		run->arm_sea.gpa = ipa;
	}

	return 0;
}

/**
 * kvm_handle_guest_abort - handles all 2nd stage aborts
 * @vcpu:	the VCPU pointer
 *
 * Any abort that gets to the host is almost guaranteed to be caused by a
 * missing second stage translation table entry, which can mean that either the
 * guest simply needs more memory and we must allocate an appropriate page or it
 * can mean that the guest tried to access I/O memory, which is emulated by user
 * space. The distinction is based on the IPA causing the fault and whether this
 * memory region has been registered as standard RAM by user space.
 */
int kvm_handle_guest_abort(struct kvm_vcpu *vcpu)
{
	struct kvm_s2_trans nested_trans, *nested = NULL;
	unsigned long esr = kvm_vcpu_get_esr(vcpu);
	struct kvm_s2_mmu *mmu = vcpu->arch.hw_mmu;
	struct kvm *kvm = vcpu->kvm;
	phys_addr_t fault_ipa; /* The address we faulted on */
	phys_addr_t ipa; /* Always the IPA in the L1 guest phys space */
	struct kvm_memory_slot *memslot;
	unsigned long hva;
	bool is_iabt, write_fault, writable;
	gfn_t gfn;
	int ret, idx;

	if (esr_abt_is_sea(esr))
		return kvm_handle_guest_sea(vcpu);

	/*
	 * The fault IPA should be reliable at this point as we're not dealing
	 * with an SEA.
	 */
	ipa = fault_ipa = kvm_vcpu_get_fault_ipa(vcpu);
	if (KVM_BUG_ON(ipa == INVALID_GPA, kvm))
		return -EFAULT;

	is_iabt = esr_trap_is_iabt(esr);

	if (esr_fsc_is_translation_fault(esr)) {
		/* Beyond sanitised PARange (which is the IPA limit) */
		if (fault_ipa >= BIT_ULL(get_kvm_ipa_limit())) {
			kvm_inject_size_fault(vcpu);
			return 1;
		}

		/* Falls between the IPA range and the PARange? */
		if (fault_ipa >= BIT_ULL(VTCR_EL2_IPA(mmu->vtcr))) {
			fault_ipa |= FAR_TO_FIPA_OFFSET(kvm_vcpu_get_hfar(vcpu));

			return kvm_inject_sea(vcpu, is_iabt, fault_ipa);
		}
	}

	trace_kvm_guest_fault(*vcpu_pc(vcpu), esr,
			      kvm_vcpu_get_hfar(vcpu), fault_ipa);

	/* Check the stage-2 fault is trans. fault or write fault */
	if (!esr_fsc_is_translation_fault(esr) &&
	    !esr_fsc_is_permission_fault(esr) &&
	    !esr_fsc_is_access_flag_fault(esr) &&
	    !esr_fsc_is_excl_atomic_fault(esr)) {
		kvm_err("Unsupported FSC: EC=%#lx xFSC=%#lx ESR_EL2=%#lx\n",
			ESR_ELx_EC(esr),
			(unsigned long)(esr & ESR_ELx_FSC),
			(unsigned long)esr);
		return -EFAULT;
	}

	idx = srcu_read_lock(&kvm->srcu);

	/*
	 * We may have faulted on a shadow stage 2 page table if we are
	 * running a nested guest.  In this case, we have to resolve the L2
	 * IPA to the L1 IPA first, before knowing what kind of memory should
	 * back the L1 IPA.
	 *
	 * If the shadow stage 2 page table walk faults, then we simply inject
	 * this to the guest and carry on.
	 *
	 * If there are no shadow S2 PTs because S2 is disabled, there is
	 * nothing to walk and we treat it as a 1:1 before going through the
	 * canonical translation.
	 */
	if (kvm_is_nested_s2_mmu(kvm, mmu) && mmu->nested_stage2_enabled) {
		u32 esr;

		ret = kvm_walk_nested_s2(vcpu, fault_ipa, &nested_trans);
		if (ret == -EAGAIN) {
			ret = 1;
			goto out_unlock;
		}

		if (ret) {
			esr = kvm_s2_trans_esr(&nested_trans);
			kvm_inject_s2_fault(vcpu, esr);
			goto out_unlock;
		}

		ret = kvm_s2_handle_perm_fault(vcpu, &nested_trans);
		if (ret) {
			esr = kvm_s2_trans_esr(&nested_trans);
			kvm_inject_s2_fault(vcpu, esr);
			goto out_unlock;
		}

		ipa = kvm_s2_trans_output(&nested_trans);
		nested = &nested_trans;
	}

	gfn = ipa >> PAGE_SHIFT;
	memslot = gfn_to_memslot(kvm, gfn);
	hva = gfn_to_hva_memslot_prot(memslot, gfn, &writable);
	write_fault = esr_abt_is_write_fault(esr);
	if (kvm_is_error_hva(hva) || (write_fault && !writable)) {
		/*
		 * The guest has put either its instructions or its page-tables
		 * somewhere it shouldn't have. Userspace won't be able to do
		 * anything about this (there's no syndrome for a start), so
		 * re-inject the abort back into the guest.
		 */
		if (is_iabt) {
			ret = -ENOEXEC;
			goto out;
		}

		if (esr_abt_is_s1ptw(esr)) {
			ret = kvm_inject_sea_dabt(vcpu, kvm_vcpu_get_hfar(vcpu));
			goto out_unlock;
		}

		/*
		 * Check for a cache maintenance operation. Since we
		 * ended-up here, we know it is outside of any memory
		 * slot. But we can't find out if that is for a device,
		 * or if the guest is just being stupid. The only thing
		 * we know for sure is that this range cannot be cached.
		 *
		 * So let's assume that the guest is just being
		 * cautious, and skip the instruction.
		 */
		if (kvm_is_error_hva(hva) && esr_dabt_is_cm(esr)) {
			kvm_incr_pc(vcpu);
			ret = 1;
			goto out_unlock;
		}

		/*
		 * The IPA is reported as [MAX:12], so we need to
		 * complement it with the bottom 12 bits from the
		 * faulting VA. This is always 12 bits, irrespective
		 * of the page size.
		 */
		ipa |= FAR_TO_FIPA_OFFSET(kvm_vcpu_get_hfar(vcpu));
		ret = io_mem_abort(vcpu, ipa);
		goto out_unlock;
	}

	/* Userspace should not be able to register out-of-bounds IPAs */
	VM_BUG_ON(ipa >= kvm_phys_size(mmu));

	if (esr_fsc_is_access_flag_fault(esr)) {
		handle_access_fault(vcpu, fault_ipa);
		ret = 1;
		goto out_unlock;
	}

	const struct kvm_s2_fault_desc s2fd = {
		.vcpu		= vcpu,
		.fault_ipa	= fault_ipa,
		.nested		= nested,
		.memslot	= memslot,
		.hva		= hva,
		.esr		= esr,
		.mmu		= mmu,
	};

	ret = kvm->arch.vm_s2_ops->vm_mem_abort(&s2fd);
	if (ret == 0)
		ret = 1;
out:
	if (ret == -ENOEXEC)
		ret = kvm_inject_sea_iabt(vcpu, kvm_vcpu_get_hfar(vcpu));
out_unlock:
	srcu_read_unlock(&kvm->srcu, idx);
	return ret;
}

bool kvm_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range)
{
	gpa_t gpa = range->start << PAGE_SHIFT;
	size_t size = (range->end - range->start) << PAGE_SHIFT;
	bool may_block = range->may_block;

	if (!kvm->arch.mmu.pgt)
		return false;

	kvm_stage2_unmap_range(&kvm->arch.mmu, gpa, size, may_block);
	kvm_nested_unmap_cipa_range(kvm, gpa, size, may_block);

	return false;
}

static bool kvm_vm_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range)
{
	u64 size = (range->end - range->start) << PAGE_SHIFT;

	return kvm_pgtable_stage2_test_clear_young(kvm->arch.mmu.pgt,
						   range->start << PAGE_SHIFT,
						   size, true);
}

static bool pkvm_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range)
{
	u64 size = (range->end - range->start) << PAGE_SHIFT;

	return pkvm_pgtable_stage2_test_clear_young(kvm->arch.mmu.pgt,
						    range->start << PAGE_SHIFT,
						    size, true);
}

static bool no_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range)
{
	/* The hypervisor doesn't support aging */
	return false;
}

bool kvm_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range)
{
	if (!kvm->arch.mmu.pgt)
		return false;

	return kvm->arch.vm_s2_ops->vm_age_gfn(kvm, range);
	/*
	 * TODO: Handle nested_mmu structures here using the reverse mapping in
	 * a later version of patch series.
	 */
}

static bool kvm_vm_test_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range)
{
	u64 size = (range->end - range->start) << PAGE_SHIFT;

	return kvm_pgtable_stage2_test_clear_young(kvm->arch.mmu.pgt,
						   range->start << PAGE_SHIFT,
						   size, false);
}

static bool pkvm_test_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range)
{
	u64 size = (range->end - range->start) << PAGE_SHIFT;

	return pkvm_pgtable_stage2_test_clear_young(kvm->arch.mmu.pgt,
						    range->start << PAGE_SHIFT,
						    size, false);
}

bool kvm_test_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range)
{
	if (!kvm->arch.mmu.pgt)
		return false;

	return kvm->arch.vm_s2_ops->vm_test_age_gfn(kvm, range);
}

phys_addr_t kvm_mmu_get_httbr(void)
{
	return __pa(hyp_pgtable->pgd);
}

phys_addr_t kvm_get_idmap_vector(void)
{
	return hyp_idmap_vector;
}

static int kvm_map_idmap_text(void)
{
	unsigned long size = hyp_idmap_end - hyp_idmap_start;
	int err = __create_hyp_mappings(hyp_idmap_start, size, hyp_idmap_start,
					PAGE_HYP_EXEC);
	if (err)
		kvm_err("Failed to idmap %lx-%lx\n",
			hyp_idmap_start, hyp_idmap_end);

	return err;
}

static void *kvm_hyp_zalloc_page(void *arg)
{
	return (void *)get_zeroed_page(GFP_KERNEL);
}

static struct kvm_pgtable_mm_ops kvm_hyp_mm_ops = {
	.zalloc_page		= kvm_hyp_zalloc_page,
	.get_page		= kvm_host_get_page,
	.put_page		= kvm_host_put_page,
	.phys_to_virt		= kvm_host_va,
	.virt_to_phys		= kvm_host_pa,
};

int __init kvm_mmu_init(u32 hyp_va_bits)
{
	int err;

	hyp_idmap_start = __pa_symbol(__hyp_idmap_text_start);
	hyp_idmap_start = ALIGN_DOWN(hyp_idmap_start, PAGE_SIZE);
	hyp_idmap_end = __pa_symbol(__hyp_idmap_text_end);
	hyp_idmap_end = ALIGN(hyp_idmap_end, PAGE_SIZE);
	hyp_idmap_vector = __pa_symbol(__kvm_hyp_init);

	/*
	 * We rely on the linker script to ensure at build time that the HYP
	 * init code does not cross a page boundary.
	 */
	BUG_ON((hyp_idmap_start ^ (hyp_idmap_end - 1)) & PAGE_MASK);

	kvm_debug("Using %u-bit virtual addresses at EL2\n", hyp_va_bits);
	kvm_debug("IDMAP page: %lx\n", hyp_idmap_start);
	kvm_debug("HYP VA range: %lx:%lx\n",
		  kern_hyp_va(PAGE_OFFSET),
		  kern_hyp_va((unsigned long)high_memory - 1));

	if (hyp_idmap_start >= kern_hyp_va(PAGE_OFFSET) &&
	    hyp_idmap_start <  kern_hyp_va((unsigned long)high_memory - 1) &&
	    hyp_idmap_start != (unsigned long)__hyp_idmap_text_start) {
		/*
		 * The idmap page is intersecting with the VA space,
		 * it is not safe to continue further.
		 */
		kvm_err("IDMAP intersecting with HYP VA, unable to continue\n");
		err = -EINVAL;
		goto out;
	}

	hyp_pgtable = kzalloc_obj(*hyp_pgtable);
	if (!hyp_pgtable) {
		kvm_err("Hyp mode page-table not allocated\n");
		err = -ENOMEM;
		goto out;
	}

	err = kvm_pgtable_hyp_init(hyp_pgtable, hyp_va_bits, &kvm_hyp_mm_ops);
	if (err)
		goto out_free_pgtable;

	err = kvm_map_idmap_text();
	if (err)
		goto out_destroy_pgtable;

	io_map_base = hyp_idmap_start;
	__hyp_va_bits = hyp_va_bits;
	return 0;

out_destroy_pgtable:
	kvm_pgtable_hyp_destroy(hyp_pgtable);
out_free_pgtable:
	kfree(hyp_pgtable);
	hyp_pgtable = NULL;
out:
	return err;
}

void kvm_arch_commit_memory_region(struct kvm *kvm,
				   struct kvm_memory_slot *old,
				   const struct kvm_memory_slot *new,
				   enum kvm_mr_change change)
{
	bool log_dirty_pages = new && new->flags & KVM_MEM_LOG_DIRTY_PAGES;

	/*
	 * At this point memslot has been committed and there is an
	 * allocated dirty_bitmap[], dirty pages will be tracked while the
	 * memory slot is write protected.
	 */
	if (log_dirty_pages) {

		if (change == KVM_MR_DELETE)
			return;

		/*
		 * Huge and normal pages are write-protected and split
		 * on either of these two cases:
		 *
		 * 1. with initial-all-set: gradually with CLEAR ioctls,
		 */
		if (kvm_dirty_log_manual_protect_and_init_set(kvm))
			return;
		/*
		 * or
		 * 2. without initial-all-set: all in one shot when
		 *    enabling dirty logging.
		 */
		kvm_mmu_wp_memory_region(kvm, new->id);
		kvm_mmu_split_memory_region(kvm, new->id);
	} else {
		/*
		 * Free any leftovers from the eager page splitting cache. Do
		 * this when deleting, moving, disabling dirty logging, or
		 * creating the memslot (a nop). Doing it for deletes makes
		 * sure we don't leak memory, and there's no need to keep the
		 * cache around for any of the other cases.
		 */
		kvm_mmu_free_memory_cache(&kvm->arch.mmu.split_page_cache);
	}
}

int kvm_arch_prepare_memory_region(struct kvm *kvm,
				   const struct kvm_memory_slot *old,
				   struct kvm_memory_slot *new,
				   enum kvm_mr_change change)
{
	hva_t hva, reg_end;
	int ret = 0;

	if (kvm_vm_is_protected(kvm)) {
		/* Cannot modify memslots once a pVM has run. */
		if (pkvm_hyp_vm_is_created(kvm) &&
		    (change == KVM_MR_DELETE || change == KVM_MR_MOVE)) {
			return -EPERM;
		}

		if (new &&
		    new->flags & (KVM_MEM_LOG_DIRTY_PAGES | KVM_MEM_READONLY)) {
			return -EPERM;
		}
	}

	if (change != KVM_MR_CREATE && change != KVM_MR_MOVE &&
			change != KVM_MR_FLAGS_ONLY)
		return 0;

	/*
	 * Prevent userspace from creating a memory region outside of the IPA
	 * space addressable by the KVM guest IPA space.
	 */
	if ((new->base_gfn + new->npages) > (kvm_phys_size(&kvm->arch.mmu) >> PAGE_SHIFT))
		return -EFAULT;

	/*
	 * Only support guest_memfd backed memslots with mappable memory, since
	 * there aren't any CoCo VMs that support only private memory on arm64.
	 */
	if (kvm_slot_has_gmem(new) && !kvm_memslot_is_gmem_only(new))
		return -EINVAL;

	/* guest_memfd is incompatible with MTE. */
	if (kvm_slot_has_gmem(new) && kvm_has_mte(kvm))
		return -EINVAL;

	hva = new->userspace_addr;
	reg_end = hva + (new->npages << PAGE_SHIFT);

	mmap_read_lock(current->mm);
	/*
	 * A memory region could potentially cover multiple VMAs, and any holes
	 * between them, so iterate over all of them.
	 *
	 *     +--------------------------------------------+
	 * +---------------+----------------+   +----------------+
	 * |   : VMA 1     |      VMA 2     |   |    VMA 3  :    |
	 * +---------------+----------------+   +----------------+
	 *     |               memory region                |
	 *     +--------------------------------------------+
	 */
	do {
		struct vm_area_struct *vma;

		vma = find_vma_intersection(current->mm, hva, reg_end);
		if (!vma)
			break;

		if (kvm_has_mte(kvm) && !kvm_vma_mte_allowed(vma)) {
			ret = -EINVAL;
			break;
		}

		if (vma->vm_flags & VM_PFNMAP) {
			/* IO region dirty page logging not allowed */
			if (new->flags & KVM_MEM_LOG_DIRTY_PAGES) {
				ret = -EINVAL;
				break;
			}

			/*
			 * Cacheable PFNMAP is allowed only if the hardware
			 * supports it.
			 */
			if (kvm_vma_is_cacheable(vma) && !kvm_supports_cacheable_pfnmap()) {
				ret = -EINVAL;
				break;
			}
		}
		hva = min(reg_end, vma->vm_end);
	} while (hva < reg_end);

	mmap_read_unlock(current->mm);
	return ret;
}

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

void kvm_arch_memslots_updated(struct kvm *kvm, u64 gen)
{
}

void kvm_arch_flush_shadow_memslot(struct kvm *kvm,
				   struct kvm_memory_slot *slot)
{
	gpa_t gpa = slot->base_gfn << PAGE_SHIFT;
	phys_addr_t size = slot->npages << PAGE_SHIFT;

	write_lock(&kvm->mmu_lock);
	kvm_stage2_unmap_range(&kvm->arch.mmu, gpa, size, true);
	kvm_nested_unmap_cipa_range(kvm, gpa, size, true);
	write_unlock(&kvm->mmu_lock);
}

/*
 * See note at ARMv7 ARM B1.14.4 (TL;DR: S/W ops are not easily virtualized).
 *
 * Main problems:
 * - S/W ops are local to a CPU (not broadcast)
 * - We have line migration behind our back (speculation)
 * - System caches don't support S/W at all (damn!)
 *
 * In the face of the above, the best we can do is to try and convert
 * S/W ops to VA ops. Because the guest is not allowed to infer the
 * S/W to PA mapping, it can only use S/W to nuke the whole cache,
 * which is a rather good thing for us.
 *
 * Also, it is only used when turning caches on/off ("The expected
 * usage of the cache maintenance instructions that operate by set/way
 * is associated with the cache maintenance instructions associated
 * with the powerdown and powerup of caches, if this is required by
 * the implementation.").
 *
 * We use the following policy:
 *
 * - If we trap a S/W operation, we enable VM trapping to detect
 *   caches being turned on/off, and do a full clean.
 *
 * - We flush the caches on both caches being turned on and off.
 *
 * - Once the caches are enabled, we stop trapping VM ops.
 */
void kvm_set_way_flush(struct kvm_vcpu *vcpu)
{
	unsigned long hcr = *vcpu_hcr(vcpu);

	/*
	 * If this is the first time we do a S/W operation
	 * (i.e. HCR_TVM not set) flush the whole memory, and set the
	 * VM trapping.
	 *
	 * Otherwise, rely on the VM trapping to wait for the MMU +
	 * Caches to be turned off. At that point, we'll be able to
	 * clean the caches again.
	 */
	if (!(hcr & HCR_TVM)) {
		trace_kvm_set_way_flush(*vcpu_pc(vcpu),
					vcpu_has_cache_enabled(vcpu));
		stage2_flush_vm(vcpu->kvm);
		*vcpu_hcr(vcpu) = hcr | HCR_TVM;
	}
}

void kvm_toggle_cache(struct kvm_vcpu *vcpu, bool was_enabled)
{
	bool now_enabled = vcpu_has_cache_enabled(vcpu);

	/*
	 * If switching the MMU+caches on, need to invalidate the caches.
	 * If switching it off, need to clean the caches.
	 * Clean + invalidate does the trick always.
	 */
	if (now_enabled != was_enabled)
		stage2_flush_vm(vcpu->kvm);

	/* Caches are now on, stop trapping VM ops (until a S/W op) */
	if (now_enabled)
		*vcpu_hcr(vcpu) &= ~HCR_TVM;

	trace_kvm_toggle_cache(*vcpu_pc(vcpu), was_enabled, now_enabled);
}

/*
 * Try to walk to the specified GPA in canonical mmu - if unmapped returns 0, if
 * mapped returns the granule size, otherwise returns an error.
 */
static long kvm_walk_s2(struct kvm_pgtable *pgt,
			gpa_t gpa, s8 *level)
{
	struct kvm *kvm = kvm_s2_mmu_to_kvm(pgt->mmu);
	kvm_pte_t pte;
	long ret;

	guard(read_lock)(&kvm->mmu_lock);

	ret = kvm_pgtable_get_leaf(pgt, gpa, &pte, level,
				   KVM_PGTABLE_WALK_SHARED);
	if (ret)
		return ret;
	/* Unpopulated, must fault. */
	if (!kvm_pte_valid(pte))
		return 0;
	return kvm_granule_size(*level);
}

/* Synthesised data abort at specified page table level. */
#define PRE_FAULT_ESR(level)				\
	 ((ESR_ELx_EC_DABT_LOW << ESR_ELx_EC_SHIFT) |	\
	  ESR_ELx_IL | ESR_ELx_FSC_FAULT_L(level))

/* Retrieve either a read-only or a read/write hva. */
static hva_t gfn_to_hva_memslot_read(struct kvm_memory_slot *slot, gfn_t gfn)
{
	return gfn_to_hva_memslot_prot(slot, gfn, /*writable=*/NULL);
}

static long __pre_fault_s2(struct kvm_s2_mmu *mmu, struct kvm_vcpu *vcpu,
			   gpa_t gpa, struct kvm_memory_slot *memslot, s8 level)
{
	const bool is_gmem = kvm_slot_has_gmem(memslot);
	const gfn_t gfn = gpa_to_gfn(gpa);
	const hva_t hva = is_gmem ? 0 : gfn_to_hva_memslot_read(memslot, gfn);
	const struct kvm_s2_fault_desc s2fd = {
		.vcpu		= vcpu,
		.fault_ipa	= gpa,
		.nested		= NULL,
		.memslot	= memslot,
		.hva		= hva,
		.esr		= PRE_FAULT_ESR(level),
		.mmu		= mmu,
	};
	struct kvm_s2_fault_result result = {};
	long ret;

	if (kvm_is_error_hva(hva))
		return -EFAULT;

	if (is_gmem)
		ret = gmem_abort(&s2fd, &result);
	else
		ret = user_mem_abort(&s2fd, &result);
	if (IS_ERR_VALUE(ret))
		return ret;
	return result.mapping_size;
}

static long pre_fault_s2(struct kvm_s2_mmu *mmu, struct kvm_vcpu *vcpu,
			 gpa_t gpa, struct kvm_memory_slot *memslot)
{
	s8 level;
	long ret;

	/* Try a walk first. */
	ret = kvm_walk_s2(mmu->pgt, gpa, &level);
	if (ret)
		return ret;
	/* OK, have to fault page in. */
	return __pre_fault_s2(mmu, vcpu, gpa, memslot, level);
}

static unsigned long
pre_fault_bytes_consumed(gpa_t gpa, unsigned long granule_size,
			 unsigned long bytes_remaining)
{
	/* Granules are always a power-of-2. */
	const unsigned long granule_bytes_remaining =
		granule_size - (gpa % granule_size);

	return min(granule_bytes_remaining, bytes_remaining);
}

/* If you lose the race this many times, time to give up. */
#define MAX_PRE_FAULT_RETRIES 3

int kvm_arch_pre_fault_allowed(struct kvm_vcpu *vcpu)
{
	if (is_protected_kvm_enabled())
		return -EOPNOTSUPP;
	if (!kvm_vcpu_initialized(vcpu))
		return -ENOEXEC;

	return 0;
}

/**
 * kvm_arch_vcpu_pre_fault_memory - pre-fault stage-2 page tables for the
 * specified GPA.
 * @vcpu:	The VCPU pointer
 * @range:	{gpa, size, flags} tuple
 *
 * The mapping performed is always best-effort - faulting in is necessarily
 * racey. The ranges faulted in are canonical, nested page tables are ignored.
 *
 * @range->gpa specifies the GPA to pre-fault, @range->size specifies how many
 * bytes remain to be pre-faulted and @range->flags is reserved and must be 0.
 *
 * Returns: the number of bytes the pre-fault consumed, or an error.
 */
long kvm_arch_vcpu_pre_fault_memory(struct kvm_vcpu *vcpu,
				    struct kvm_pre_fault_memory *range)
{
	struct kvm *kvm = vcpu->kvm;
	const u64 bytes_remaining = range->size;
	struct kvm_s2_mmu *mmu = &kvm->arch.mmu; /* Canonical. */
	struct kvm_memory_slot *memslot;
	const gpa_t gpa = range->gpa;
	int num_retries = 0;
	long ret;

	memslot = gfn_to_memslot(kvm, gpa_to_gfn(gpa));
	if (!memslot)
		return -ENOENT;
	/* SRCU must be released for progress and only userland can do that. */
	if (memslot->flags & KVM_MEMSLOT_INVALID)
		return -EAGAIN;

	do {
		ret = pre_fault_s2(mmu, vcpu, gpa, memslot);
	} while (ret == -EAGAIN && num_retries++ < MAX_PRE_FAULT_RETRIES);

	if (IS_ERR_VALUE(ret))
		return ret;
	return pre_fault_bytes_consumed(gpa, ret, bytes_remaining);
}

static const struct kvm_vm_s2_ops protected_pkvm_vm_s2_ops = {
	.vm_flush_remote_tlbs		= pkvm_flush_remote_tlbs,
	.vm_flush_remote_tlbs_range	= pkvm_flush_remote_tlbs_range,
	.vm_age_gfn			= no_age_gfn,
	.vm_test_age_gfn		= no_age_gfn,
	.vm_stage2_unmap_range		= no_stage2_unmap_range,
	.vm_mem_abort			= protected_pkvm_mem_abort,
};

static const struct kvm_vm_s2_ops pkvm_vm_s2_ops = {
	.vm_flush_remote_tlbs		= pkvm_flush_remote_tlbs,
	.vm_flush_remote_tlbs_range	= pkvm_flush_remote_tlbs_range,
	.vm_age_gfn			= pkvm_age_gfn,
	.vm_test_age_gfn		= pkvm_test_age_gfn,
	.vm_stage2_unmap_range		= pkvm_stage2_unmap_range,
	.vm_mem_abort			= kvm_vm_mem_abort,
};

static const struct kvm_vm_s2_ops kvm_default_vm_s2_ops = {
	.vm_flush_remote_tlbs		= kvm_vm_flush_remote_tlbs,
	.vm_flush_remote_tlbs_range	= kvm_vm_flush_remote_tlbs_range,
	.vm_age_gfn			= kvm_vm_age_gfn,
	.vm_test_age_gfn		= kvm_vm_test_age_gfn,
	.vm_stage2_unmap_range		= kvm_vm_stage2_unmap_range,
	.vm_mem_abort			= kvm_vm_mem_abort,
};

#define KVM_VM_S2_OPS(flavor, ops)		\
		[(flavor)] = &(ops)

static const struct kvm_vm_s2_ops *arm64_vm_s2_ops[] = {
	KVM_VM_S2_OPS(VM_VHE, kvm_default_vm_s2_ops),
	KVM_VM_S2_OPS(VM_NVHE, kvm_default_vm_s2_ops),
	KVM_VM_S2_OPS(VM_PKVM, pkvm_vm_s2_ops),
	KVM_VM_S2_OPS(VM_PROTECTED_PKVM, protected_pkvm_vm_s2_ops),
};

static int kvm_vm_init_vm_s2_ops(struct kvm *kvm)
{
	BUILD_BUG_ON(ARRAY_SIZE(arm64_vm_s2_ops) != VM_FLAVOR_MAX);

	kvm->arch.vm_s2_ops = arm64_vm_s2_ops[kvm->arch.vm_flavor];
	if (WARN_ON(!kvm->arch.vm_s2_ops))
		return -EINVAL;
	return 0;
}