1 files changed, 343 insertions, 309 deletions

diff --git a/arch/arm64/kvm/hyp/pgtable.c b/arch/arm64/kvm/hyp/pgtable.c
index cdf8e76b0be1..b11cf2c618a6 100644
--- a/arch/arm64/kvm/hyp/pgtable.c
+++ b/arch/arm64/kvm/hyp/pgtable.c
@@ -49,35 +49,38 @@
 #define KVM_INVALID_PTE_OWNER_MASK	GENMASK(9, 2)
 #define KVM_MAX_OWNER_ID		1
 
+/*
+ * Used to indicate a pte for which a 'break-before-make' sequence is in
+ * progress.
+ */
+#define KVM_INVALID_PTE_LOCKED		BIT(10)
+
 struct kvm_pgtable_walk_data {
-	struct kvm_pgtable		*pgt;
 	struct kvm_pgtable_walker	*walker;
 
 	u64				addr;
 	u64				end;
 };
 
-#define KVM_PHYS_INVALID (-1ULL)
-
 static bool kvm_phys_is_valid(u64 phys)
 {
 	return phys < BIT(id_aa64mmfr0_parange_to_phys_shift(ID_AA64MMFR0_EL1_PARANGE_MAX));
 }
 
-static bool kvm_block_mapping_supported(u64 addr, u64 end, u64 phys, u32 level)
+static bool kvm_block_mapping_supported(const struct kvm_pgtable_visit_ctx *ctx, u64 phys)
 {
-	u64 granule = kvm_granule_size(level);
+	u64 granule = kvm_granule_size(ctx->level);
 
-	if (!kvm_level_supports_block_mapping(level))
+	if (!kvm_level_supports_block_mapping(ctx->level))
 		return false;
 
-	if (granule > (end - addr))
+	if (granule > (ctx->end - ctx->addr))
 		return false;
 
 	if (kvm_phys_is_valid(phys) && !IS_ALIGNED(phys, granule))
 		return false;
 
-	return IS_ALIGNED(addr, granule);
+	return IS_ALIGNED(ctx->addr, granule);
 }
 
 static u32 kvm_pgtable_idx(struct kvm_pgtable_walk_data *data, u32 level)
@@ -88,7 +91,7 @@ static u32 kvm_pgtable_idx(struct kvm_pgtable_walk_data *data, u32 level)
 	return (data->addr >> shift) & mask;
 }
 
-static u32 __kvm_pgd_page_idx(struct kvm_pgtable *pgt, u64 addr)
+static u32 kvm_pgd_page_idx(struct kvm_pgtable *pgt, u64 addr)
 {
 	u64 shift = kvm_granule_shift(pgt->start_level - 1); /* May underflow */
 	u64 mask = BIT(pgt->ia_bits) - 1;
@@ -96,11 +99,6 @@ static u32 __kvm_pgd_page_idx(struct kvm_pgtable *pgt, u64 addr)
 	return (addr & mask) >> shift;
 }
 
-static u32 kvm_pgd_page_idx(struct kvm_pgtable_walk_data *data)
-{
-	return __kvm_pgd_page_idx(data->pgt, data->addr);
-}
-
 static u32 kvm_pgd_pages(u32 ia_bits, u32 start_level)
 {
 	struct kvm_pgtable pgt = {
@@ -108,7 +106,7 @@ static u32 kvm_pgd_pages(u32 ia_bits, u32 start_level)
 		.start_level	= start_level,
 	};
 
-	return __kvm_pgd_page_idx(&pgt, -1ULL) + 1;
+	return kvm_pgd_page_idx(&pgt, -1ULL) + 1;
 }
 
 static bool kvm_pte_table(kvm_pte_t pte, u32 level)
@@ -122,16 +120,6 @@ static bool kvm_pte_table(kvm_pte_t pte, u32 level)
 	return FIELD_GET(KVM_PTE_TYPE, pte) == KVM_PTE_TYPE_TABLE;
 }
 
-static kvm_pte_t kvm_phys_to_pte(u64 pa)
-{
-	kvm_pte_t pte = pa & KVM_PTE_ADDR_MASK;
-
-	if (PAGE_SHIFT == 16)
-		pte |= FIELD_PREP(KVM_PTE_ADDR_51_48, pa >> 48);
-
-	return pte;
-}
-
 static kvm_pte_t *kvm_pte_follow(kvm_pte_t pte, struct kvm_pgtable_mm_ops *mm_ops)
 {
 	return mm_ops->phys_to_virt(kvm_pte_to_phys(pte));
@@ -142,16 +130,13 @@ static void kvm_clear_pte(kvm_pte_t *ptep)
 	WRITE_ONCE(*ptep, 0);
 }
 
-static void kvm_set_table_pte(kvm_pte_t *ptep, kvm_pte_t *childp,
-			      struct kvm_pgtable_mm_ops *mm_ops)
+static kvm_pte_t kvm_init_table_pte(kvm_pte_t *childp, struct kvm_pgtable_mm_ops *mm_ops)
 {
-	kvm_pte_t old = *ptep, pte = kvm_phys_to_pte(mm_ops->virt_to_phys(childp));
+	kvm_pte_t pte = kvm_phys_to_pte(mm_ops->virt_to_phys(childp));
 
 	pte |= FIELD_PREP(KVM_PTE_TYPE, KVM_PTE_TYPE_TABLE);
 	pte |= KVM_PTE_VALID;
-
-	WARN_ON(kvm_pte_valid(old));
-	smp_store_release(ptep, pte);
+	return pte;
 }
 
 static kvm_pte_t kvm_init_valid_leaf_pte(u64 pa, kvm_pte_t attr, u32 level)
@@ -172,36 +157,47 @@ static kvm_pte_t kvm_init_invalid_leaf_owner(u8 owner_id)
 	return FIELD_PREP(KVM_INVALID_PTE_OWNER_MASK, owner_id);
 }
 
-static int kvm_pgtable_visitor_cb(struct kvm_pgtable_walk_data *data, u64 addr,
-				  u32 level, kvm_pte_t *ptep,
-				  enum kvm_pgtable_walk_flags flag)
+static int kvm_pgtable_visitor_cb(struct kvm_pgtable_walk_data *data,
+				  const struct kvm_pgtable_visit_ctx *ctx,
+				  enum kvm_pgtable_walk_flags visit)
 {
 	struct kvm_pgtable_walker *walker = data->walker;
-	return walker->cb(addr, data->end, level, ptep, flag, walker->arg);
+
+	/* Ensure the appropriate lock is held (e.g. RCU lock for stage-2 MMU) */
+	WARN_ON_ONCE(kvm_pgtable_walk_shared(ctx) && !kvm_pgtable_walk_lock_held());
+	return walker->cb(ctx, visit);
 }
 
 static int __kvm_pgtable_walk(struct kvm_pgtable_walk_data *data,
-			      kvm_pte_t *pgtable, u32 level);
+			      struct kvm_pgtable_mm_ops *mm_ops, kvm_pteref_t pgtable, u32 level);
 
 static inline int __kvm_pgtable_visit(struct kvm_pgtable_walk_data *data,
-				      kvm_pte_t *ptep, u32 level)
+				      struct kvm_pgtable_mm_ops *mm_ops,
+				      kvm_pteref_t pteref, u32 level)
 {
-	int ret = 0;
-	u64 addr = data->addr;
-	kvm_pte_t *childp, pte = *ptep;
-	bool table = kvm_pte_table(pte, level);
 	enum kvm_pgtable_walk_flags flags = data->walker->flags;
+	kvm_pte_t *ptep = kvm_dereference_pteref(data->walker, pteref);
+	struct kvm_pgtable_visit_ctx ctx = {
+		.ptep	= ptep,
+		.old	= READ_ONCE(*ptep),
+		.arg	= data->walker->arg,
+		.mm_ops	= mm_ops,
+		.addr	= data->addr,
+		.end	= data->end,
+		.level	= level,
+		.flags	= flags,
+	};
+	int ret = 0;
+	kvm_pteref_t childp;
+	bool table = kvm_pte_table(ctx.old, level);
 
-	if (table && (flags & KVM_PGTABLE_WALK_TABLE_PRE)) {
-		ret = kvm_pgtable_visitor_cb(data, addr, level, ptep,
-					     KVM_PGTABLE_WALK_TABLE_PRE);
-	}
+	if (table && (ctx.flags & KVM_PGTABLE_WALK_TABLE_PRE))
+		ret = kvm_pgtable_visitor_cb(data, &ctx, KVM_PGTABLE_WALK_TABLE_PRE);
 
-	if (!table && (flags & KVM_PGTABLE_WALK_LEAF)) {
-		ret = kvm_pgtable_visitor_cb(data, addr, level, ptep,
-					     KVM_PGTABLE_WALK_LEAF);
-		pte = *ptep;
-		table = kvm_pte_table(pte, level);
+	if (!table && (ctx.flags & KVM_PGTABLE_WALK_LEAF)) {
+		ret = kvm_pgtable_visitor_cb(data, &ctx, KVM_PGTABLE_WALK_LEAF);
+		ctx.old = READ_ONCE(*ptep);
+		table = kvm_pte_table(ctx.old, level);
 	}
 
 	if (ret)
@@ -213,22 +209,20 @@ static inline int __kvm_pgtable_visit(struct kvm_pgtable_walk_data *data,
 		goto out;
 	}
 
-	childp = kvm_pte_follow(pte, data->pgt->mm_ops);
-	ret = __kvm_pgtable_walk(data, childp, level + 1);
+	childp = (kvm_pteref_t)kvm_pte_follow(ctx.old, mm_ops);
+	ret = __kvm_pgtable_walk(data, mm_ops, childp, level + 1);
 	if (ret)
 		goto out;
 
-	if (flags & KVM_PGTABLE_WALK_TABLE_POST) {
-		ret = kvm_pgtable_visitor_cb(data, addr, level, ptep,
-					     KVM_PGTABLE_WALK_TABLE_POST);
-	}
+	if (ctx.flags & KVM_PGTABLE_WALK_TABLE_POST)
+		ret = kvm_pgtable_visitor_cb(data, &ctx, KVM_PGTABLE_WALK_TABLE_POST);
 
 out:
 	return ret;
 }
 
 static int __kvm_pgtable_walk(struct kvm_pgtable_walk_data *data,
-			      kvm_pte_t *pgtable, u32 level)
+			      struct kvm_pgtable_mm_ops *mm_ops, kvm_pteref_t pgtable, u32 level)
 {
 	u32 idx;
 	int ret = 0;
@@ -237,12 +231,12 @@ static int __kvm_pgtable_walk(struct kvm_pgtable_walk_data *data,
 		return -EINVAL;
 
 	for (idx = kvm_pgtable_idx(data, level); idx < PTRS_PER_PTE; ++idx) {
-		kvm_pte_t *ptep = &pgtable[idx];
+		kvm_pteref_t pteref = &pgtable[idx];
 
 		if (data->addr >= data->end)
 			break;
 
-		ret = __kvm_pgtable_visit(data, ptep, level);
+		ret = __kvm_pgtable_visit(data, mm_ops, pteref, level);
 		if (ret)
 			break;
 	}
@@ -250,11 +244,10 @@ static int __kvm_pgtable_walk(struct kvm_pgtable_walk_data *data,
 	return ret;
 }
 
-static int _kvm_pgtable_walk(struct kvm_pgtable_walk_data *data)
+static int _kvm_pgtable_walk(struct kvm_pgtable *pgt, struct kvm_pgtable_walk_data *data)
 {
 	u32 idx;
 	int ret = 0;
-	struct kvm_pgtable *pgt = data->pgt;
 	u64 limit = BIT(pgt->ia_bits);
 
 	if (data->addr > limit || data->end > limit)
@@ -263,10 +256,10 @@ static int _kvm_pgtable_walk(struct kvm_pgtable_walk_data *data)
 	if (!pgt->pgd)
 		return -EINVAL;
 
-	for (idx = kvm_pgd_page_idx(data); data->addr < data->end; ++idx) {
-		kvm_pte_t *ptep = &pgt->pgd[idx * PTRS_PER_PTE];
+	for (idx = kvm_pgd_page_idx(pgt, data->addr); data->addr < data->end; ++idx) {
+		kvm_pteref_t pteref = &pgt->pgd[idx * PTRS_PER_PTE];
 
-		ret = __kvm_pgtable_walk(data, ptep, pgt->start_level);
+		ret = __kvm_pgtable_walk(data, pgt->mm_ops, pteref, pgt->start_level);
 		if (ret)
 			break;
 	}
@@ -278,13 +271,20 @@ int kvm_pgtable_walk(struct kvm_pgtable *pgt, u64 addr, u64 size,
 		     struct kvm_pgtable_walker *walker)
 {
 	struct kvm_pgtable_walk_data walk_data = {
-		.pgt	= pgt,
 		.addr	= ALIGN_DOWN(addr, PAGE_SIZE),
 		.end	= PAGE_ALIGN(walk_data.addr + size),
 		.walker	= walker,
 	};
+	int r;
 
-	return _kvm_pgtable_walk(&walk_data);
+	r = kvm_pgtable_walk_begin(walker);
+	if (r)
+		return r;
+
+	r = _kvm_pgtable_walk(pgt, &walk_data);
+	kvm_pgtable_walk_end(walker);
+
+	return r;
 }
 
 struct leaf_walk_data {
@@ -292,13 +292,13 @@ struct leaf_walk_data {
 	u32		level;
 };
 
-static int leaf_walker(u64 addr, u64 end, u32 level, kvm_pte_t *ptep,
-		       enum kvm_pgtable_walk_flags flag, void * const arg)
+static int leaf_walker(const struct kvm_pgtable_visit_ctx *ctx,
+		       enum kvm_pgtable_walk_flags visit)
 {
-	struct leaf_walk_data *data = arg;
+	struct leaf_walk_data *data = ctx->arg;
 
-	data->pte   = *ptep;
-	data->level = level;
+	data->pte   = ctx->old;
+	data->level = ctx->level;
 
 	return 0;
 }
@@ -329,7 +329,6 @@ int kvm_pgtable_get_leaf(struct kvm_pgtable *pgt, u64 addr,
 struct hyp_map_data {
 	u64				phys;
 	kvm_pte_t			attr;
-	struct kvm_pgtable_mm_ops	*mm_ops;
 };
 
 static int hyp_set_prot_attr(enum kvm_pgtable_prot prot, kvm_pte_t *ptep)
@@ -383,47 +382,49 @@ enum kvm_pgtable_prot kvm_pgtable_hyp_pte_prot(kvm_pte_t pte)
 	return prot;
 }
 
-static bool hyp_map_walker_try_leaf(u64 addr, u64 end, u32 level,
-				    kvm_pte_t *ptep, struct hyp_map_data *data)
+static bool hyp_map_walker_try_leaf(const struct kvm_pgtable_visit_ctx *ctx,
+				    struct hyp_map_data *data)
 {
-	kvm_pte_t new, old = *ptep;
-	u64 granule = kvm_granule_size(level), phys = data->phys;
+	kvm_pte_t new;
+	u64 granule = kvm_granule_size(ctx->level), phys = data->phys;
 
-	if (!kvm_block_mapping_supported(addr, end, phys, level))
+	if (!kvm_block_mapping_supported(ctx, phys))
 		return false;
 
 	data->phys += granule;
-	new = kvm_init_valid_leaf_pte(phys, data->attr, level);
-	if (old == new)
+	new = kvm_init_valid_leaf_pte(phys, data->attr, ctx->level);
+	if (ctx->old == new)
 		return true;
-	if (!kvm_pte_valid(old))
-		data->mm_ops->get_page(ptep);
-	else if (WARN_ON((old ^ new) & ~KVM_PTE_LEAF_ATTR_HI_SW))
+	if (!kvm_pte_valid(ctx->old))
+		ctx->mm_ops->get_page(ctx->ptep);
+	else if (WARN_ON((ctx->old ^ new) & ~KVM_PTE_LEAF_ATTR_HI_SW))
 		return false;
 
-	smp_store_release(ptep, new);
+	smp_store_release(ctx->ptep, new);
 	return true;
 }
 
-static int hyp_map_walker(u64 addr, u64 end, u32 level, kvm_pte_t *ptep,
-			  enum kvm_pgtable_walk_flags flag, void * const arg)
+static int hyp_map_walker(const struct kvm_pgtable_visit_ctx *ctx,
+			  enum kvm_pgtable_walk_flags visit)
 {
-	kvm_pte_t *childp;
-	struct hyp_map_data *data = arg;
-	struct kvm_pgtable_mm_ops *mm_ops = data->mm_ops;
+	kvm_pte_t *childp, new;
+	struct hyp_map_data *data = ctx->arg;
+	struct kvm_pgtable_mm_ops *mm_ops = ctx->mm_ops;
 
-	if (hyp_map_walker_try_leaf(addr, end, level, ptep, arg))
+	if (hyp_map_walker_try_leaf(ctx, data))
 		return 0;
 
-	if (WARN_ON(level == KVM_PGTABLE_MAX_LEVELS - 1))
+	if (WARN_ON(ctx->level == KVM_PGTABLE_MAX_LEVELS - 1))
 		return -EINVAL;
 
 	childp = (kvm_pte_t *)mm_ops->zalloc_page(NULL);
 	if (!childp)
 		return -ENOMEM;
 
-	kvm_set_table_pte(ptep, childp, mm_ops);
-	mm_ops->get_page(ptep);
+	new = kvm_init_table_pte(childp, mm_ops);
+	mm_ops->get_page(ctx->ptep);
+	smp_store_release(ctx->ptep, new);
+
 	return 0;
 }
 
@@ -433,7 +434,6 @@ int kvm_pgtable_hyp_map(struct kvm_pgtable *pgt, u64 addr, u64 size, u64 phys,
 	int ret;
 	struct hyp_map_data map_data = {
 		.phys	= ALIGN_DOWN(phys, PAGE_SIZE),
-		.mm_ops	= pgt->mm_ops,
 	};
 	struct kvm_pgtable_walker walker = {
 		.cb	= hyp_map_walker,
@@ -451,44 +451,39 @@ int kvm_pgtable_hyp_map(struct kvm_pgtable *pgt, u64 addr, u64 size, u64 phys,
 	return ret;
 }
 
-struct hyp_unmap_data {
-	u64				unmapped;
-	struct kvm_pgtable_mm_ops	*mm_ops;
-};
-
-static int hyp_unmap_walker(u64 addr, u64 end, u32 level, kvm_pte_t *ptep,
-			    enum kvm_pgtable_walk_flags flag, void * const arg)
+static int hyp_unmap_walker(const struct kvm_pgtable_visit_ctx *ctx,
+			    enum kvm_pgtable_walk_flags visit)
 {
-	kvm_pte_t pte = *ptep, *childp = NULL;
-	u64 granule = kvm_granule_size(level);
-	struct hyp_unmap_data *data = arg;
-	struct kvm_pgtable_mm_ops *mm_ops = data->mm_ops;
+	kvm_pte_t *childp = NULL;
+	u64 granule = kvm_granule_size(ctx->level);
+	u64 *unmapped = ctx->arg;
+	struct kvm_pgtable_mm_ops *mm_ops = ctx->mm_ops;
 
-	if (!kvm_pte_valid(pte))
+	if (!kvm_pte_valid(ctx->old))
 		return -EINVAL;
 
-	if (kvm_pte_table(pte, level)) {
-		childp = kvm_pte_follow(pte, mm_ops);
+	if (kvm_pte_table(ctx->old, ctx->level)) {
+		childp = kvm_pte_follow(ctx->old, mm_ops);
 
 		if (mm_ops->page_count(childp) != 1)
 			return 0;
 
-		kvm_clear_pte(ptep);
+		kvm_clear_pte(ctx->ptep);
 		dsb(ishst);
-		__tlbi_level(vae2is, __TLBI_VADDR(addr, 0), level);
+		__tlbi_level(vae2is, __TLBI_VADDR(ctx->addr, 0), ctx->level);
 	} else {
-		if (end - addr < granule)
+		if (ctx->end - ctx->addr < granule)
 			return -EINVAL;
 
-		kvm_clear_pte(ptep);
+		kvm_clear_pte(ctx->ptep);
 		dsb(ishst);
-		__tlbi_level(vale2is, __TLBI_VADDR(addr, 0), level);
-		data->unmapped += granule;
+		__tlbi_level(vale2is, __TLBI_VADDR(ctx->addr, 0), ctx->level);
+		*unmapped += granule;
 	}
 
 	dsb(ish);
 	isb();
-	mm_ops->put_page(ptep);
+	mm_ops->put_page(ctx->ptep);
 
 	if (childp)
 		mm_ops->put_page(childp);
@@ -498,12 +493,10 @@ static int hyp_unmap_walker(u64 addr, u64 end, u32 level, kvm_pte_t *ptep,
 
 u64 kvm_pgtable_hyp_unmap(struct kvm_pgtable *pgt, u64 addr, u64 size)
 {
-	struct hyp_unmap_data unmap_data = {
-		.mm_ops	= pgt->mm_ops,
-	};
+	u64 unmapped = 0;
 	struct kvm_pgtable_walker walker = {
 		.cb	= hyp_unmap_walker,
-		.arg	= &unmap_data,
+		.arg	= &unmapped,
 		.flags	= KVM_PGTABLE_WALK_LEAF | KVM_PGTABLE_WALK_TABLE_POST,
 	};
 
@@ -511,7 +504,7 @@ u64 kvm_pgtable_hyp_unmap(struct kvm_pgtable *pgt, u64 addr, u64 size)
 		return 0;
 
 	kvm_pgtable_walk(pgt, addr, size, &walker);
-	return unmap_data.unmapped;
+	return unmapped;
 }
 
 int kvm_pgtable_hyp_init(struct kvm_pgtable *pgt, u32 va_bits,
@@ -519,7 +512,7 @@ int kvm_pgtable_hyp_init(struct kvm_pgtable *pgt, u32 va_bits,
 {
 	u64 levels = ARM64_HW_PGTABLE_LEVELS(va_bits);
 
-	pgt->pgd = (kvm_pte_t *)mm_ops->zalloc_page(NULL);
+	pgt->pgd = (kvm_pteref_t)mm_ops->zalloc_page(NULL);
 	if (!pgt->pgd)
 		return -ENOMEM;
 
@@ -532,19 +525,18 @@ int kvm_pgtable_hyp_init(struct kvm_pgtable *pgt, u32 va_bits,
 	return 0;
 }
 
-static int hyp_free_walker(u64 addr, u64 end, u32 level, kvm_pte_t *ptep,
-			   enum kvm_pgtable_walk_flags flag, void * const arg)
+static int hyp_free_walker(const struct kvm_pgtable_visit_ctx *ctx,
+			   enum kvm_pgtable_walk_flags visit)
 {
-	struct kvm_pgtable_mm_ops *mm_ops = arg;
-	kvm_pte_t pte = *ptep;
+	struct kvm_pgtable_mm_ops *mm_ops = ctx->mm_ops;
 
-	if (!kvm_pte_valid(pte))
+	if (!kvm_pte_valid(ctx->old))
 		return 0;
 
-	mm_ops->put_page(ptep);
+	mm_ops->put_page(ctx->ptep);
 
-	if (kvm_pte_table(pte, level))
-		mm_ops->put_page(kvm_pte_follow(pte, mm_ops));
+	if (kvm_pte_table(ctx->old, ctx->level))
+		mm_ops->put_page(kvm_pte_follow(ctx->old, mm_ops));
 
 	return 0;
 }
@@ -554,11 +546,10 @@ void kvm_pgtable_hyp_destroy(struct kvm_pgtable *pgt)
 	struct kvm_pgtable_walker walker = {
 		.cb	= hyp_free_walker,
 		.flags	= KVM_PGTABLE_WALK_LEAF | KVM_PGTABLE_WALK_TABLE_POST,
-		.arg	= pgt->mm_ops,
 	};
 
 	WARN_ON(kvm_pgtable_walk(pgt, 0, BIT(pgt->ia_bits), &walker));
-	pgt->mm_ops->put_page(pgt->pgd);
+	pgt->mm_ops->put_page(kvm_dereference_pteref(&walker, pgt->pgd));
 	pgt->pgd = NULL;
 }
 
@@ -573,8 +564,6 @@ struct stage2_map_data {
 	struct kvm_s2_mmu		*mmu;
 	void				*memcache;
 
-	struct kvm_pgtable_mm_ops	*mm_ops;
-
 	/* Force mappings to page granularity */
 	bool				force_pte;
 };
@@ -682,19 +671,92 @@ static bool stage2_pte_is_counted(kvm_pte_t pte)
 	return !!pte;
 }
 
-static void stage2_put_pte(kvm_pte_t *ptep, struct kvm_s2_mmu *mmu, u64 addr,
-			   u32 level, struct kvm_pgtable_mm_ops *mm_ops)
+static bool stage2_pte_is_locked(kvm_pte_t pte)
+{
+	return !kvm_pte_valid(pte) && (pte & KVM_INVALID_PTE_LOCKED);
+}
+
+static bool stage2_try_set_pte(const struct kvm_pgtable_visit_ctx *ctx, kvm_pte_t new)
+{
+	if (!kvm_pgtable_walk_shared(ctx)) {
+		WRITE_ONCE(*ctx->ptep, new);
+		return true;
+	}
+
+	return cmpxchg(ctx->ptep, ctx->old, new) == ctx->old;
+}
+
+/**
+ * stage2_try_break_pte() - Invalidates a pte according to the
+ *			    'break-before-make' requirements of the
+ *			    architecture.
+ *
+ * @ctx: context of the visited pte.
+ * @mmu: stage-2 mmu
+ *
+ * Returns: true if the pte was successfully broken.
+ *
+ * If the removed pte was valid, performs the necessary serialization and TLB
+ * invalidation for the old value. For counted ptes, drops the reference count
+ * on the containing table page.
+ */
+static bool stage2_try_break_pte(const struct kvm_pgtable_visit_ctx *ctx,
+				 struct kvm_s2_mmu *mmu)
+{
+	struct kvm_pgtable_mm_ops *mm_ops = ctx->mm_ops;
+
+	if (stage2_pte_is_locked(ctx->old)) {
+		/*
+		 * Should never occur if this walker has exclusive access to the
+		 * page tables.
+		 */
+		WARN_ON(!kvm_pgtable_walk_shared(ctx));
+		return false;
+	}
+
+	if (!stage2_try_set_pte(ctx, KVM_INVALID_PTE_LOCKED))
+		return false;
+
+	/*
+	 * Perform the appropriate TLB invalidation based on the evicted pte
+	 * value (if any).
+	 */
+	if (kvm_pte_table(ctx->old, ctx->level))
+		kvm_call_hyp(__kvm_tlb_flush_vmid, mmu);
+	else if (kvm_pte_valid(ctx->old))
+		kvm_call_hyp(__kvm_tlb_flush_vmid_ipa, mmu, ctx->addr, ctx->level);
+
+	if (stage2_pte_is_counted(ctx->old))
+		mm_ops->put_page(ctx->ptep);
+
+	return true;
+}
+
+static void stage2_make_pte(const struct kvm_pgtable_visit_ctx *ctx, kvm_pte_t new)
+{
+	struct kvm_pgtable_mm_ops *mm_ops = ctx->mm_ops;
+
+	WARN_ON(!stage2_pte_is_locked(*ctx->ptep));
+
+	if (stage2_pte_is_counted(new))
+		mm_ops->get_page(ctx->ptep);
+
+	smp_store_release(ctx->ptep, new);
+}
+
+static void stage2_put_pte(const struct kvm_pgtable_visit_ctx *ctx, struct kvm_s2_mmu *mmu,
+			   struct kvm_pgtable_mm_ops *mm_ops)
 {
 	/*
 	 * Clear the existing PTE, and perform break-before-make with
 	 * TLB maintenance if it was valid.
 	 */
-	if (kvm_pte_valid(*ptep)) {
-		kvm_clear_pte(ptep);
-		kvm_call_hyp(__kvm_tlb_flush_vmid_ipa, mmu, addr, level);
+	if (kvm_pte_valid(ctx->old)) {
+		kvm_clear_pte(ctx->ptep);
+		kvm_call_hyp(__kvm_tlb_flush_vmid_ipa, mmu, ctx->addr, ctx->level);
 	}
 
-	mm_ops->put_page(ptep);
+	mm_ops->put_page(ctx->ptep);
 }
 
 static bool stage2_pte_cacheable(struct kvm_pgtable *pgt, kvm_pte_t pte)
@@ -708,44 +770,42 @@ static bool stage2_pte_executable(kvm_pte_t pte)
 	return !(pte & KVM_PTE_LEAF_ATTR_HI_S2_XN);
 }
 
-static bool stage2_leaf_mapping_allowed(u64 addr, u64 end, u32 level,
+static bool stage2_leaf_mapping_allowed(const struct kvm_pgtable_visit_ctx *ctx,
 					struct stage2_map_data *data)
 {
-	if (data->force_pte && (level < (KVM_PGTABLE_MAX_LEVELS - 1)))
+	if (data->force_pte && (ctx->level < (KVM_PGTABLE_MAX_LEVELS - 1)))
 		return false;
 
-	return kvm_block_mapping_supported(addr, end, data->phys, level);
+	return kvm_block_mapping_supported(ctx, data->phys);
 }
 
-static int stage2_map_walker_try_leaf(u64 addr, u64 end, u32 level,
-				      kvm_pte_t *ptep,
+static int stage2_map_walker_try_leaf(const struct kvm_pgtable_visit_ctx *ctx,
 				      struct stage2_map_data *data)
 {
-	kvm_pte_t new, old = *ptep;
-	u64 granule = kvm_granule_size(level), phys = data->phys;
+	kvm_pte_t new;
+	u64 granule = kvm_granule_size(ctx->level), phys = data->phys;
 	struct kvm_pgtable *pgt = data->mmu->pgt;
-	struct kvm_pgtable_mm_ops *mm_ops = data->mm_ops;
+	struct kvm_pgtable_mm_ops *mm_ops = ctx->mm_ops;
 
-	if (!stage2_leaf_mapping_allowed(addr, end, level, data))
+	if (!stage2_leaf_mapping_allowed(ctx, data))
 		return -E2BIG;
 
 	if (kvm_phys_is_valid(phys))
-		new = kvm_init_valid_leaf_pte(phys, data->attr, level);
+		new = kvm_init_valid_leaf_pte(phys, data->attr, ctx->level);
 	else
 		new = kvm_init_invalid_leaf_owner(data->owner_id);
 
-	if (stage2_pte_is_counted(old)) {
-		/*
-		 * Skip updating the PTE if we are trying to recreate the exact
-		 * same mapping or only change the access permissions. Instead,
-		 * the vCPU will exit one more time from guest if still needed
-		 * and then go through the path of relaxing permissions.
-		 */
-		if (!stage2_pte_needs_update(old, new))
-			return -EAGAIN;
+	/*
+	 * Skip updating the PTE if we are trying to recreate the exact
+	 * same mapping or only change the access permissions. Instead,
+	 * the vCPU will exit one more time from guest if still needed
+	 * and then go through the path of relaxing permissions.
+	 */
+	if (!stage2_pte_needs_update(ctx->old, new))
+		return -EAGAIN;
 
-		stage2_put_pte(ptep, data->mmu, addr, level, mm_ops);
-	}
+	if (!stage2_try_break_pte(ctx, data->mmu))
+		return -EAGAIN;
 
 	/* Perform CMOs before installation of the guest stage-2 PTE */
 	if (mm_ops->dcache_clean_inval_poc && stage2_pte_cacheable(pgt, new))
@@ -755,56 +815,43 @@ static int stage2_map_walker_try_leaf(u64 addr, u64 end, u32 level,
 	if (mm_ops->icache_inval_pou && stage2_pte_executable(new))
 		mm_ops->icache_inval_pou(kvm_pte_follow(new, mm_ops), granule);
 
-	smp_store_release(ptep, new);
-	if (stage2_pte_is_counted(new))
-		mm_ops->get_page(ptep);
+	stage2_make_pte(ctx, new);
+
 	if (kvm_phys_is_valid(phys))
 		data->phys += granule;
 	return 0;
 }
 
-static int stage2_map_walk_table_pre(u64 addr, u64 end, u32 level,
-				     kvm_pte_t *ptep,
+static int stage2_map_walk_table_pre(const struct kvm_pgtable_visit_ctx *ctx,
 				     struct stage2_map_data *data)
 {
-	if (data->anchor)
-		return 0;
+	struct kvm_pgtable_mm_ops *mm_ops = ctx->mm_ops;
+	kvm_pte_t *childp = kvm_pte_follow(ctx->old, mm_ops);
+	int ret;
 
-	if (!stage2_leaf_mapping_allowed(addr, end, level, data))
+	if (!stage2_leaf_mapping_allowed(ctx, data))
 		return 0;
 
-	data->childp = kvm_pte_follow(*ptep, data->mm_ops);
-	kvm_clear_pte(ptep);
+	ret = stage2_map_walker_try_leaf(ctx, data);
+	if (ret)
+		return ret;
 
-	/*
-	 * Invalidate the whole stage-2, as we may have numerous leaf
-	 * entries below us which would otherwise need invalidating
-	 * individually.
-	 */
-	kvm_call_hyp(__kvm_tlb_flush_vmid, data->mmu);
-	data->anchor = ptep;
+	mm_ops->free_removed_table(childp, ctx->level);
 	return 0;
 }
 
-static int stage2_map_walk_leaf(u64 addr, u64 end, u32 level, kvm_pte_t *ptep,
+static int stage2_map_walk_leaf(const struct kvm_pgtable_visit_ctx *ctx,
 				struct stage2_map_data *data)
 {
-	struct kvm_pgtable_mm_ops *mm_ops = data->mm_ops;
-	kvm_pte_t *childp, pte = *ptep;
+	struct kvm_pgtable_mm_ops *mm_ops = ctx->mm_ops;
+	kvm_pte_t *childp, new;
 	int ret;
 
-	if (data->anchor) {
-		if (stage2_pte_is_counted(pte))
-			mm_ops->put_page(ptep);
-
-		return 0;
-	}
-
-	ret = stage2_map_walker_try_leaf(addr, end, level, ptep, data);
+	ret = stage2_map_walker_try_leaf(ctx, data);
 	if (ret != -E2BIG)
 		return ret;
 
-	if (WARN_ON(level == KVM_PGTABLE_MAX_LEVELS - 1))
+	if (WARN_ON(ctx->level == KVM_PGTABLE_MAX_LEVELS - 1))
 		return -EINVAL;
 
 	if (!data->memcache)
@@ -814,99 +861,62 @@ static int stage2_map_walk_leaf(u64 addr, u64 end, u32 level, kvm_pte_t *ptep,
 	if (!childp)
 		return -ENOMEM;
 
+	if (!stage2_try_break_pte(ctx, data->mmu)) {
+		mm_ops->put_page(childp);
+		return -EAGAIN;
+	}
+
 	/*
 	 * If we've run into an existing block mapping then replace it with
 	 * a table. Accesses beyond 'end' that fall within the new table
 	 * will be mapped lazily.
 	 */
-	if (stage2_pte_is_counted(pte))
-		stage2_put_pte(ptep, data->mmu, addr, level, mm_ops);
-
-	kvm_set_table_pte(ptep, childp, mm_ops);
-	mm_ops->get_page(ptep);
+	new = kvm_init_table_pte(childp, mm_ops);
+	stage2_make_pte(ctx, new);
 
 	return 0;
 }
 
-static int stage2_map_walk_table_post(u64 addr, u64 end, u32 level,
-				      kvm_pte_t *ptep,
-				      struct stage2_map_data *data)
-{
-	struct kvm_pgtable_mm_ops *mm_ops = data->mm_ops;
-	kvm_pte_t *childp;
-	int ret = 0;
-
-	if (!data->anchor)
-		return 0;
-
-	if (data->anchor == ptep) {
-		childp = data->childp;
-		data->anchor = NULL;
-		data->childp = NULL;
-		ret = stage2_map_walk_leaf(addr, end, level, ptep, data);
-	} else {
-		childp = kvm_pte_follow(*ptep, mm_ops);
-	}
-
-	mm_ops->put_page(childp);
-	mm_ops->put_page(ptep);
-
-	return ret;
-}
-
 /*
- * This is a little fiddly, as we use all three of the walk flags. The idea
- * is that the TABLE_PRE callback runs for table entries on the way down,
- * looking for table entries which we could conceivably replace with a
- * block entry for this mapping. If it finds one, then it sets the 'anchor'
- * field in 'struct stage2_map_data' to point at the table entry, before
- * clearing the entry to zero and descending into the now detached table.
+ * The TABLE_PRE callback runs for table entries on the way down, looking
+ * for table entries which we could conceivably replace with a block entry
+ * for this mapping. If it finds one it replaces the entry and calls
+ * kvm_pgtable_mm_ops::free_removed_table() to tear down the detached table.
  *
- * The behaviour of the LEAF callback then depends on whether or not the
- * anchor has been set. If not, then we're not using a block mapping higher
- * up the table and we perform the mapping at the existing leaves instead.
- * If, on the other hand, the anchor _is_ set, then we drop references to
- * all valid leaves so that the pages beneath the anchor can be freed.
- *
- * Finally, the TABLE_POST callback does nothing if the anchor has not
- * been set, but otherwise frees the page-table pages while walking back up
- * the page-table, installing the block entry when it revisits the anchor
- * pointer and clearing the anchor to NULL.
+ * Otherwise, the LEAF callback performs the mapping at the existing leaves
+ * instead.
  */
-static int stage2_map_walker(u64 addr, u64 end, u32 level, kvm_pte_t *ptep,
-			     enum kvm_pgtable_walk_flags flag, void * const arg)
+static int stage2_map_walker(const struct kvm_pgtable_visit_ctx *ctx,
+			     enum kvm_pgtable_walk_flags visit)
 {
-	struct stage2_map_data *data = arg;
+	struct stage2_map_data *data = ctx->arg;
 
-	switch (flag) {
+	switch (visit) {
 	case KVM_PGTABLE_WALK_TABLE_PRE:
-		return stage2_map_walk_table_pre(addr, end, level, ptep, data);
+		return stage2_map_walk_table_pre(ctx, data);
 	case KVM_PGTABLE_WALK_LEAF:
-		return stage2_map_walk_leaf(addr, end, level, ptep, data);
-	case KVM_PGTABLE_WALK_TABLE_POST:
-		return stage2_map_walk_table_post(addr, end, level, ptep, data);
+		return stage2_map_walk_leaf(ctx, data);
+	default:
+		return -EINVAL;
 	}
-
-	return -EINVAL;
 }
 
 int kvm_pgtable_stage2_map(struct kvm_pgtable *pgt, u64 addr, u64 size,
 			   u64 phys, enum kvm_pgtable_prot prot,
-			   void *mc)
+			   void *mc, enum kvm_pgtable_walk_flags flags)
 {
 	int ret;
 	struct stage2_map_data map_data = {
 		.phys		= ALIGN_DOWN(phys, PAGE_SIZE),
 		.mmu		= pgt->mmu,
 		.memcache	= mc,
-		.mm_ops		= pgt->mm_ops,
 		.force_pte	= pgt->force_pte_cb && pgt->force_pte_cb(addr, addr + size, prot),
 	};
 	struct kvm_pgtable_walker walker = {
 		.cb		= stage2_map_walker,
-		.flags		= KVM_PGTABLE_WALK_TABLE_PRE |
-				  KVM_PGTABLE_WALK_LEAF |
-				  KVM_PGTABLE_WALK_TABLE_POST,
+		.flags		= flags |
+				  KVM_PGTABLE_WALK_TABLE_PRE |
+				  KVM_PGTABLE_WALK_LEAF,
 		.arg		= &map_data,
 	};
 
@@ -930,15 +940,13 @@ int kvm_pgtable_stage2_set_owner(struct kvm_pgtable *pgt, u64 addr, u64 size,
 		.phys		= KVM_PHYS_INVALID,
 		.mmu		= pgt->mmu,
 		.memcache	= mc,
-		.mm_ops		= pgt->mm_ops,
 		.owner_id	= owner_id,
 		.force_pte	= true,
 	};
 	struct kvm_pgtable_walker walker = {
 		.cb		= stage2_map_walker,
 		.flags		= KVM_PGTABLE_WALK_TABLE_PRE |
-				  KVM_PGTABLE_WALK_LEAF |
-				  KVM_PGTABLE_WALK_TABLE_POST,
+				  KVM_PGTABLE_WALK_LEAF,
 		.arg		= &map_data,
 	};
 
@@ -949,30 +957,29 @@ int kvm_pgtable_stage2_set_owner(struct kvm_pgtable *pgt, u64 addr, u64 size,
 	return ret;
 }
 
-static int stage2_unmap_walker(u64 addr, u64 end, u32 level, kvm_pte_t *ptep,
-			       enum kvm_pgtable_walk_flags flag,
-			       void * const arg)
+static int stage2_unmap_walker(const struct kvm_pgtable_visit_ctx *ctx,
+			       enum kvm_pgtable_walk_flags visit)
 {
-	struct kvm_pgtable *pgt = arg;
+	struct kvm_pgtable *pgt = ctx->arg;
 	struct kvm_s2_mmu *mmu = pgt->mmu;
-	struct kvm_pgtable_mm_ops *mm_ops = pgt->mm_ops;
-	kvm_pte_t pte = *ptep, *childp = NULL;
+	struct kvm_pgtable_mm_ops *mm_ops = ctx->mm_ops;
+	kvm_pte_t *childp = NULL;
 	bool need_flush = false;
 
-	if (!kvm_pte_valid(pte)) {
-		if (stage2_pte_is_counted(pte)) {
-			kvm_clear_pte(ptep);
-			mm_ops->put_page(ptep);
+	if (!kvm_pte_valid(ctx->old)) {
+		if (stage2_pte_is_counted(ctx->old)) {
+			kvm_clear_pte(ctx->ptep);
+			mm_ops->put_page(ctx->ptep);
 		}
 		return 0;
 	}
 
-	if (kvm_pte_table(pte, level)) {
-		childp = kvm_pte_follow(pte, mm_ops);
+	if (kvm_pte_table(ctx->old, ctx->level)) {
+		childp = kvm_pte_follow(ctx->old, mm_ops);
 
 		if (mm_ops->page_count(childp) != 1)
 			return 0;
-	} else if (stage2_pte_cacheable(pgt, pte)) {
+	} else if (stage2_pte_cacheable(pgt, ctx->old)) {
 		need_flush = !stage2_has_fwb(pgt);
 	}
 
@@ -981,11 +988,11 @@ static int stage2_unmap_walker(u64 addr, u64 end, u32 level, kvm_pte_t *ptep,
 	 * block entry and rely on the remaining portions being faulted
 	 * back lazily.
 	 */
-	stage2_put_pte(ptep, mmu, addr, level, mm_ops);
+	stage2_put_pte(ctx, mmu, mm_ops);
 
 	if (need_flush && mm_ops->dcache_clean_inval_poc)
-		mm_ops->dcache_clean_inval_poc(kvm_pte_follow(pte, mm_ops),
-					       kvm_granule_size(level));
+		mm_ops->dcache_clean_inval_poc(kvm_pte_follow(ctx->old, mm_ops),
+					       kvm_granule_size(ctx->level));
 
 	if (childp)
 		mm_ops->put_page(childp);
@@ -1009,21 +1016,19 @@ struct stage2_attr_data {
 	kvm_pte_t			attr_clr;
 	kvm_pte_t			pte;
 	u32				level;
-	struct kvm_pgtable_mm_ops	*mm_ops;
 };
 
-static int stage2_attr_walker(u64 addr, u64 end, u32 level, kvm_pte_t *ptep,
-			      enum kvm_pgtable_walk_flags flag,
-			      void * const arg)
+static int stage2_attr_walker(const struct kvm_pgtable_visit_ctx *ctx,
+			      enum kvm_pgtable_walk_flags visit)
 {
-	kvm_pte_t pte = *ptep;
-	struct stage2_attr_data *data = arg;
-	struct kvm_pgtable_mm_ops *mm_ops = data->mm_ops;
+	kvm_pte_t pte = ctx->old;
+	struct stage2_attr_data *data = ctx->arg;
+	struct kvm_pgtable_mm_ops *mm_ops = ctx->mm_ops;
 
-	if (!kvm_pte_valid(pte))
+	if (!kvm_pte_valid(ctx->old))
 		return 0;
 
-	data->level = level;
+	data->level = ctx->level;
 	data->pte = pte;
 	pte &= ~data->attr_clr;
 	pte |= data->attr_set;
@@ -1039,10 +1044,12 @@ static int stage2_attr_walker(u64 addr, u64 end, u32 level, kvm_pte_t *ptep,
 		 * stage-2 PTE if we are going to add executable permission.
 		 */
 		if (mm_ops->icache_inval_pou &&
-		    stage2_pte_executable(pte) && !stage2_pte_executable(*ptep))
+		    stage2_pte_executable(pte) && !stage2_pte_executable(ctx->old))
 			mm_ops->icache_inval_pou(kvm_pte_follow(pte, mm_ops),
-						  kvm_granule_size(level));
-		WRITE_ONCE(*ptep, pte);
+						  kvm_granule_size(ctx->level));
+
+		if (!stage2_try_set_pte(ctx, pte))
+			return -EAGAIN;
 	}
 
 	return 0;
@@ -1051,19 +1058,18 @@ static int stage2_attr_walker(u64 addr, u64 end, u32 level, kvm_pte_t *ptep,
 static int stage2_update_leaf_attrs(struct kvm_pgtable *pgt, u64 addr,
 				    u64 size, kvm_pte_t attr_set,
 				    kvm_pte_t attr_clr, kvm_pte_t *orig_pte,
-				    u32 *level)
+				    u32 *level, enum kvm_pgtable_walk_flags flags)
 {
 	int ret;
 	kvm_pte_t attr_mask = KVM_PTE_LEAF_ATTR_LO | KVM_PTE_LEAF_ATTR_HI;
 	struct stage2_attr_data data = {
 		.attr_set	= attr_set & attr_mask,
 		.attr_clr	= attr_clr & attr_mask,
-		.mm_ops		= pgt->mm_ops,
 	};
 	struct kvm_pgtable_walker walker = {
 		.cb		= stage2_attr_walker,
 		.arg		= &data,
-		.flags		= KVM_PGTABLE_WALK_LEAF,
+		.flags		= flags | KVM_PGTABLE_WALK_LEAF,
 	};
 
 	ret = kvm_pgtable_walk(pgt, addr, size, &walker);
@@ -1082,14 +1088,14 @@ int kvm_pgtable_stage2_wrprotect(struct kvm_pgtable *pgt, u64 addr, u64 size)
 {
 	return stage2_update_leaf_attrs(pgt, addr, size, 0,
 					KVM_PTE_LEAF_ATTR_LO_S2_S2AP_W,
-					NULL, NULL);
+					NULL, NULL, 0);
 }
 
 kvm_pte_t kvm_pgtable_stage2_mkyoung(struct kvm_pgtable *pgt, u64 addr)
 {
 	kvm_pte_t pte = 0;
 	stage2_update_leaf_attrs(pgt, addr, 1, KVM_PTE_LEAF_ATTR_LO_S2_AF, 0,
-				 &pte, NULL);
+				 &pte, NULL, 0);
 	dsb(ishst);
 	return pte;
 }
@@ -1098,7 +1104,7 @@ kvm_pte_t kvm_pgtable_stage2_mkold(struct kvm_pgtable *pgt, u64 addr)
 {
 	kvm_pte_t pte = 0;
 	stage2_update_leaf_attrs(pgt, addr, 1, 0, KVM_PTE_LEAF_ATTR_LO_S2_AF,
-				 &pte, NULL);
+				 &pte, NULL, 0);
 	/*
 	 * "But where's the TLBI?!", you scream.
 	 * "Over in the core code", I sigh.
@@ -1111,7 +1117,7 @@ kvm_pte_t kvm_pgtable_stage2_mkold(struct kvm_pgtable *pgt, u64 addr)
 bool kvm_pgtable_stage2_is_young(struct kvm_pgtable *pgt, u64 addr)
 {
 	kvm_pte_t pte = 0;
-	stage2_update_leaf_attrs(pgt, addr, 1, 0, 0, &pte, NULL);
+	stage2_update_leaf_attrs(pgt, addr, 1, 0, 0, &pte, NULL, 0);
 	return pte & KVM_PTE_LEAF_ATTR_LO_S2_AF;
 }
 
@@ -1134,26 +1140,25 @@ int kvm_pgtable_stage2_relax_perms(struct kvm_pgtable *pgt, u64 addr,
 	if (prot & KVM_PGTABLE_PROT_X)
 		clr |= KVM_PTE_LEAF_ATTR_HI_S2_XN;
 
-	ret = stage2_update_leaf_attrs(pgt, addr, 1, set, clr, NULL, &level);
+	ret = stage2_update_leaf_attrs(pgt, addr, 1, set, clr, NULL, &level,
+				       KVM_PGTABLE_WALK_SHARED);
 	if (!ret)
 		kvm_call_hyp(__kvm_tlb_flush_vmid_ipa, pgt->mmu, addr, level);
 	return ret;
 }
 
-static int stage2_flush_walker(u64 addr, u64 end, u32 level, kvm_pte_t *ptep,
-			       enum kvm_pgtable_walk_flags flag,
-			       void * const arg)
+static int stage2_flush_walker(const struct kvm_pgtable_visit_ctx *ctx,
+			       enum kvm_pgtable_walk_flags visit)
 {
-	struct kvm_pgtable *pgt = arg;
+	struct kvm_pgtable *pgt = ctx->arg;
 	struct kvm_pgtable_mm_ops *mm_ops = pgt->mm_ops;
-	kvm_pte_t pte = *ptep;
 
-	if (!kvm_pte_valid(pte) || !stage2_pte_cacheable(pgt, pte))
+	if (!kvm_pte_valid(ctx->old) || !stage2_pte_cacheable(pgt, ctx->old))
 		return 0;
 
 	if (mm_ops->dcache_clean_inval_poc)
-		mm_ops->dcache_clean_inval_poc(kvm_pte_follow(pte, mm_ops),
-					       kvm_granule_size(level));
+		mm_ops->dcache_clean_inval_poc(kvm_pte_follow(ctx->old, mm_ops),
+					       kvm_granule_size(ctx->level));
 	return 0;
 }
 
@@ -1184,7 +1189,7 @@ int __kvm_pgtable_stage2_init(struct kvm_pgtable *pgt, struct kvm_s2_mmu *mmu,
 	u32 start_level = VTCR_EL2_TGRAN_SL0_BASE - sl0;
 
 	pgd_sz = kvm_pgd_pages(ia_bits, start_level) * PAGE_SIZE;
-	pgt->pgd = mm_ops->zalloc_pages_exact(pgd_sz);
+	pgt->pgd = (kvm_pteref_t)mm_ops->zalloc_pages_exact(pgd_sz);
 	if (!pgt->pgd)
 		return -ENOMEM;
 
@@ -1200,20 +1205,27 @@ int __kvm_pgtable_stage2_init(struct kvm_pgtable *pgt, struct kvm_s2_mmu *mmu,
 	return 0;
 }
 
-static int stage2_free_walker(u64 addr, u64 end, u32 level, kvm_pte_t *ptep,
-			      enum kvm_pgtable_walk_flags flag,
-			      void * const arg)
+size_t kvm_pgtable_stage2_pgd_size(u64 vtcr)
+{
+	u32 ia_bits = VTCR_EL2_IPA(vtcr);
+	u32 sl0 = FIELD_GET(VTCR_EL2_SL0_MASK, vtcr);
+	u32 start_level = VTCR_EL2_TGRAN_SL0_BASE - sl0;
+
+	return kvm_pgd_pages(ia_bits, start_level) * PAGE_SIZE;
+}
+
+static int stage2_free_walker(const struct kvm_pgtable_visit_ctx *ctx,
+			      enum kvm_pgtable_walk_flags visit)
 {
-	struct kvm_pgtable_mm_ops *mm_ops = arg;
-	kvm_pte_t pte = *ptep;
+	struct kvm_pgtable_mm_ops *mm_ops = ctx->mm_ops;
 
-	if (!stage2_pte_is_counted(pte))
+	if (!stage2_pte_is_counted(ctx->old))
 		return 0;
 
-	mm_ops->put_page(ptep);
+	mm_ops->put_page(ctx->ptep);
 
-	if (kvm_pte_table(pte, level))
-		mm_ops->put_page(kvm_pte_follow(pte, mm_ops));
+	if (kvm_pte_table(ctx->old, ctx->level))
+		mm_ops->put_page(kvm_pte_follow(ctx->old, mm_ops));
 
 	return 0;
 }
@@ -1225,11 +1237,33 @@ void kvm_pgtable_stage2_destroy(struct kvm_pgtable *pgt)
 		.cb	= stage2_free_walker,
 		.flags	= KVM_PGTABLE_WALK_LEAF |
 			  KVM_PGTABLE_WALK_TABLE_POST,
-		.arg	= pgt->mm_ops,
 	};
 
 	WARN_ON(kvm_pgtable_walk(pgt, 0, BIT(pgt->ia_bits), &walker));
 	pgd_sz = kvm_pgd_pages(pgt->ia_bits, pgt->start_level) * PAGE_SIZE;
-	pgt->mm_ops->free_pages_exact(pgt->pgd, pgd_sz);
+	pgt->mm_ops->free_pages_exact(kvm_dereference_pteref(&walker, pgt->pgd), pgd_sz);
 	pgt->pgd = NULL;
 }
+
+void kvm_pgtable_stage2_free_removed(struct kvm_pgtable_mm_ops *mm_ops, void *pgtable, u32 level)
+{
+	kvm_pteref_t ptep = (kvm_pteref_t)pgtable;
+	struct kvm_pgtable_walker walker = {
+		.cb	= stage2_free_walker,
+		.flags	= KVM_PGTABLE_WALK_LEAF |
+			  KVM_PGTABLE_WALK_TABLE_POST,
+	};
+	struct kvm_pgtable_walk_data data = {
+		.walker	= &walker,
+
+		/*
+		 * At this point the IPA really doesn't matter, as the page
+		 * table being traversed has already been removed from the stage
+		 * 2. Set an appropriate range to cover the entire page table.
+		 */
+		.addr	= 0,
+		.end	= kvm_granule_size(level),
+	};
+
+	WARN_ON(__kvm_pgtable_walk(&data, mm_ops, ptep, level + 1));
+}