[PATCH 1/2] KVM: arm64: Split kvm_pgtable_stage2_destroy()

[Raghavendra Rao Ananta]

Split kvm_pgtable_stage2_destroy() into two:
  - kvm_pgtable_stage2_destroy_range(), that performs the
    page-table walk and free the entries over a range of addresses.
  - kvm_pgtable_stage2_destroy_pgd(), that frees the PGD.

This refactoring enables subsequent patches to free large page-tables
in chunks, calling cond_resched() between each chunk, to yield the CPU
as necessary.

Direct callers of kvm_pgtable_stage2_destroy() will continue to walk
the entire range of the VM as before, ensuring no functional changes.

Also, add equivalent pkvm_pgtable_stage2_*() stubs to maintain 1:1
mapping of the page-table functions.

Signed-off-by: Raghavendra Rao Ananta <rananta at google.com>
---
 arch/arm64/include/asm/kvm_pgtable.h | 19 +++++++++++++++++++
 arch/arm64/include/asm/kvm_pkvm.h    |  3 +++
 arch/arm64/kvm/hyp/pgtable.c         | 23 ++++++++++++++++++++---
 arch/arm64/kvm/pkvm.c                | 11 +++++++++++
 4 files changed, 53 insertions(+), 3 deletions(-)

diff --git a/arch/arm64/include/asm/kvm_pgtable.h b/arch/arm64/include/asm/kvm_pgtable.h
index 2888b5d03757..20aea58eca18 100644
--- a/arch/arm64/include/asm/kvm_pgtable.h
+++ b/arch/arm64/include/asm/kvm_pgtable.h
@@ -542,6 +542,25 @@ static inline int kvm_pgtable_stage2_init(struct kvm_pgtable *pgt, struct kvm_s2
 	return __kvm_pgtable_stage2_init(pgt, mmu, mm_ops, 0, NULL);
 }
 
+/**
+ * kvm_pgtable_stage2_destroy_range() - Destroy the unlinked range of addresses.
+ * @pgt:	Page-table structure initialised by kvm_pgtable_stage2_init*().
+ * @addr:	Intermediate physical address at which to place the mapping.
+ * @size:	Size of the mapping.
+ *
+ * The page-table is assumed to be unreachable by any hardware walkers prior
+ * to freeing and therefore no TLB invalidation is performed.
+ */
+void kvm_pgtable_stage2_destroy_range(struct kvm_pgtable *pgt,
+				       u64 addr, u64 size);
+/**
+ * kvm_pgtable_stage2_destroy_pgd() - Destroy the PGD of guest stage-2 page-table.
+ * @pgt:	Page-table structure initialised by kvm_pgtable_stage2_init*().
+ *
+ * It is assumed that the rest of the page-table is freed before this operation.
+ */
+void kvm_pgtable_stage2_destroy_pgd(struct kvm_pgtable *pgt);
+
 /**
  * kvm_pgtable_stage2_destroy() - Destroy an unused guest stage-2 page-table.
  * @pgt:	Page-table structure initialised by kvm_pgtable_stage2_init*().
diff --git a/arch/arm64/include/asm/kvm_pkvm.h b/arch/arm64/include/asm/kvm_pkvm.h
index ea58282f59bb..ad32ea90639c 100644
--- a/arch/arm64/include/asm/kvm_pkvm.h
+++ b/arch/arm64/include/asm/kvm_pkvm.h
@@ -197,4 +197,7 @@ void pkvm_pgtable_stage2_free_unlinked(struct kvm_pgtable_mm_ops *mm_ops, void *
 kvm_pte_t *pkvm_pgtable_stage2_create_unlinked(struct kvm_pgtable *pgt, u64 phys, s8 level,
 					       enum kvm_pgtable_prot prot, void *mc,
 					       bool force_pte);
+void pkvm_pgtable_stage2_destroy_range(struct kvm_pgtable *pgt,
+					u64 addr, u64 size);
+void pkvm_pgtable_stage2_destroy_pgd(struct kvm_pgtable *pgt);
 #endif	/* __ARM64_KVM_PKVM_H__ */
diff --git a/arch/arm64/kvm/hyp/pgtable.c b/arch/arm64/kvm/hyp/pgtable.c
index c351b4abd5db..7fad791cf40b 100644
--- a/arch/arm64/kvm/hyp/pgtable.c
+++ b/arch/arm64/kvm/hyp/pgtable.c
@@ -1551,21 +1551,38 @@ static int stage2_free_walker(const struct kvm_pgtable_visit_ctx *ctx,
 	return 0;
 }
 
-void kvm_pgtable_stage2_destroy(struct kvm_pgtable *pgt)
+void kvm_pgtable_stage2_destroy_range(struct kvm_pgtable *pgt,
+				       u64 addr, u64 size)
 {
-	size_t pgd_sz;
 	struct kvm_pgtable_walker walker = {
 		.cb	= stage2_free_walker,
 		.flags	= KVM_PGTABLE_WALK_LEAF |
 			  KVM_PGTABLE_WALK_TABLE_POST,
 	};
 
-	WARN_ON(kvm_pgtable_walk(pgt, 0, BIT(pgt->ia_bits), &walker));
+	WARN_ON(kvm_pgtable_walk(pgt, addr, size, &walker));
+}
+
+void kvm_pgtable_stage2_destroy_pgd(struct kvm_pgtable *pgt)
+{
+	/*
+	 * We aren't doing a pgtable walk here, but the walker struct is needed
+	 * for kvm_dereference_pteref(), which only looks at the ->flags.
+	 */
+	struct kvm_pgtable_walker walker = {0};
+	size_t pgd_sz;
+
 	pgd_sz = kvm_pgd_pages(pgt->ia_bits, pgt->start_level) * PAGE_SIZE;
 	pgt->mm_ops->free_pages_exact(kvm_dereference_pteref(&walker, pgt->pgd), pgd_sz);
 	pgt->pgd = NULL;
 }
 
+void kvm_pgtable_stage2_destroy(struct kvm_pgtable *pgt)
+{
+	kvm_pgtable_stage2_destroy_range(pgt, 0, BIT(pgt->ia_bits));
+	kvm_pgtable_stage2_destroy_pgd(pgt);
+}
+
 void kvm_pgtable_stage2_free_unlinked(struct kvm_pgtable_mm_ops *mm_ops, void *pgtable, s8 level)
 {
 	kvm_pteref_t ptep = (kvm_pteref_t)pgtable;
diff --git a/arch/arm64/kvm/pkvm.c b/arch/arm64/kvm/pkvm.c
index fcd70bfe44fb..bf737717ccb4 100644
--- a/arch/arm64/kvm/pkvm.c
+++ b/arch/arm64/kvm/pkvm.c
@@ -450,3 +450,14 @@ int pkvm_pgtable_stage2_split(struct kvm_pgtable *pgt, u64 addr, u64 size,
 	WARN_ON_ONCE(1);
 	return -EINVAL;
 }
+
+void pkvm_pgtable_stage2_destroy_range(struct kvm_pgtable *pgt,
+					u64 addr, u64 size)
+{
+	WARN_ON_ONCE(1);
+}
+
+void pkvm_pgtable_stage2_destroy_pgd(struct kvm_pgtable *pgt)
+{
+	WARN_ON_ONCE(1);
+}
-- 
2.50.1.470.g6ba607880d-goog