KVM: arm64: Correctly handle page aging notifiers for unaligned memslot

Userspace is allowed to select any PAGE_SIZE aligned hva to back guest
memory. This is even the case with hugepages, although it is a rather
suboptimal configuration as PTE level mappings are used at stage-2.

The arm64 page aging handlers have an assumption that the specified
range is exactly one page/block of memory, which in the aforementioned
case is not necessarily true. All together this leads to the WARN() in
kvm_age_gfn() firing.

However, the WARN is only part of the issue as the table walkers visit
at most a single leaf PTE. For hugepage-backed memory in a memslot that
isn't hugepage-aligned, page aging entirely misses accesses to the
hugepage beyond the first page in the memslot.

Add a new walker dedicated to handling page aging MMU notifiers capable
of walking a range of PTEs. Convert kvm(_test)_age_gfn() over to the new
walker and drop the WARN that caught the issue in the first place. The
implementation of this walker was inspired by the test_clear_young()
implementation by Yu Zhao [*], but repurposed to address a bug in the
existing aging implementation.

Cc: [email protected] # v5.15
Fixes: 056aad6 ("kvm: arm/arm64: Rework gpa callback handlers")
Link: https://lore.kernel.org/kvmarm/[email protected]/
Co-developed-by: Yu Zhao <[email protected]>
Signed-off-by: Yu Zhao <[email protected]>
Reported-by: Reiji Watanabe <[email protected]>
Reviewed-by: Marc Zyngier <[email protected]>
Reviewed-by: Shaoqin Huang <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Oliver Upton <[email protected]>

Author: oupton

arch/arm64/include/asm/kvm_pgtable.h

@@ -608,22 +608,26 @@ int kvm_pgtable_stage2_wrprotect(struct kvm_pgtable *pgt, u64 addr, u64 size);
 kvm_pte_t kvm_pgtable_stage2_mkyoung(struct kvm_pgtable *pgt, u64 addr);
 
 /**
- * kvm_pgtable_stage2_mkold() - Clear the access flag in a page-table entry.
+ * kvm_pgtable_stage2_test_clear_young() - Test and optionally clear the access
+ *					   flag in a page-table entry.
  * @pgt:	Page-table structure initialised by kvm_pgtable_stage2_init*().
  * @addr:	Intermediate physical address to identify the page-table entry.
+ * @size:	Size of the address range to visit.
+ * @mkold:	True if the access flag should be cleared.
  *
  * The offset of @addr within a page is ignored.
  *
- * If there is a valid, leaf page-table entry used to translate @addr, then
- * clear the access flag in that entry.
+ * Tests and conditionally clears the access flag for every valid, leaf
+ * page-table entry used to translate the range [@addr, @addr + @size).
  *
  * Note that it is the caller's responsibility to invalidate the TLB after
  * calling this function to ensure that the updated permissions are visible
  * to the CPUs.
  *
- * Return: The old page-table entry prior to clearing the flag, 0 on failure.
+ * Return: True if any of the visited PTEs had the access flag set.
  */
-kvm_pte_t kvm_pgtable_stage2_mkold(struct kvm_pgtable *pgt, u64 addr);
+bool kvm_pgtable_stage2_test_clear_young(struct kvm_pgtable *pgt, u64 addr,
+					 u64 size, bool mkold);
 
 /**
  * kvm_pgtable_stage2_relax_perms() - Relax the permissions enforced by a
@@ -645,18 +649,6 @@ kvm_pte_t kvm_pgtable_stage2_mkold(struct kvm_pgtable *pgt, u64 addr);
 int kvm_pgtable_stage2_relax_perms(struct kvm_pgtable *pgt, u64 addr,
 				   enum kvm_pgtable_prot prot);
 
-/**
- * kvm_pgtable_stage2_is_young() - Test whether a page-table entry has the
- *				   access flag set.
- * @pgt:	Page-table structure initialised by kvm_pgtable_stage2_init*().
- * @addr:	Intermediate physical address to identify the page-table entry.
- *
- * The offset of @addr within a page is ignored.
- *
- * Return: True if the page-table entry has the access flag set, false otherwise.
- */
-bool kvm_pgtable_stage2_is_young(struct kvm_pgtable *pgt, u64 addr);
-
 /**
  * kvm_pgtable_stage2_flush_range() - Clean and invalidate data cache to Point
  * 				      of Coherency for guest stage-2 address

arch/arm64/kvm/hyp/pgtable.c

@@ -1195,25 +1195,54 @@ kvm_pte_t kvm_pgtable_stage2_mkyoung(struct kvm_pgtable *pgt, u64 addr)
 	return pte;
 }
 
-kvm_pte_t kvm_pgtable_stage2_mkold(struct kvm_pgtable *pgt, u64 addr)
+struct stage2_age_data {
+	bool	mkold;
+	bool	young;
+};
+
+static int stage2_age_walker(const struct kvm_pgtable_visit_ctx *ctx,
+			     enum kvm_pgtable_walk_flags visit)
 {
-	kvm_pte_t pte = 0;
-	stage2_update_leaf_attrs(pgt, addr, 1, 0, KVM_PTE_LEAF_ATTR_LO_S2_AF,
-				 &pte, NULL, 0);
+	kvm_pte_t new = ctx->old & ~KVM_PTE_LEAF_ATTR_LO_S2_AF;
+	struct stage2_age_data *data = ctx->arg;
+
+	if (!kvm_pte_valid(ctx->old) || new == ctx->old)
+		return 0;
+
+	data->young = true;
+
+	/*
+	 * stage2_age_walker() is always called while holding the MMU lock for
+	 * write, so this will always succeed. Nonetheless, this deliberately
+	 * follows the race detection pattern of the other stage-2 walkers in
+	 * case the locking mechanics of the MMU notifiers is ever changed.
+	 */
+	if (data->mkold && !stage2_try_set_pte(ctx, new))
+		return -EAGAIN;
+
 	/*
 	 * "But where's the TLBI?!", you scream.
 	 * "Over in the core code", I sigh.
 	 *
 	 * See the '->clear_flush_young()' callback on the KVM mmu notifier.
 	 */
-	return pte;
+	return 0;
 }
 
-bool kvm_pgtable_stage2_is_young(struct kvm_pgtable *pgt, u64 addr)
+bool kvm_pgtable_stage2_test_clear_young(struct kvm_pgtable *pgt, u64 addr,
+					 u64 size, bool mkold)
 {
-	kvm_pte_t pte = 0;
-	stage2_update_leaf_attrs(pgt, addr, 1, 0, 0, &pte, NULL, 0);
-	return pte & KVM_PTE_LEAF_ATTR_LO_S2_AF;
+	struct stage2_age_data data = {
+		.mkold		= mkold,
+	};
+	struct kvm_pgtable_walker walker = {
+		.cb		= stage2_age_walker,
+		.arg		= &data,
+		.flags		= KVM_PGTABLE_WALK_LEAF,
+	};
+
+	WARN_ON(kvm_pgtable_walk(pgt, addr, size, &walker));
+	return data.young;
 }
 
 int kvm_pgtable_stage2_relax_perms(struct kvm_pgtable *pgt, u64 addr,

arch/arm64/kvm/mmu.c

@@ -1756,27 +1756,25 @@ bool kvm_set_spte_gfn(struct kvm *kvm, struct kvm_gfn_range *range)
 bool kvm_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range)
 {
 	u64 size = (range->end - range->start) << PAGE_SHIFT;
-	kvm_pte_t kpte;
-	pte_t pte;
 
 	if (!kvm->arch.mmu.pgt)
 		return false;
 
-	WARN_ON(size != PAGE_SIZE && size != PMD_SIZE && size != PUD_SIZE);
-
-	kpte = kvm_pgtable_stage2_mkold(kvm->arch.mmu.pgt,
-					range->start << PAGE_SHIFT);
-	pte = __pte(kpte);
-	return pte_valid(pte) && pte_young(pte);
+	return kvm_pgtable_stage2_test_clear_young(kvm->arch.mmu.pgt,
+						   range->start << PAGE_SHIFT,
+						   size, true);
 }
 
 bool kvm_test_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range)
 {
+	u64 size = (range->end - range->start) << PAGE_SHIFT;
+
 	if (!kvm->arch.mmu.pgt)
 		return false;
 
-	return kvm_pgtable_stage2_is_young(kvm->arch.mmu.pgt,
-					   range->start << PAGE_SHIFT);
+	return kvm_pgtable_stage2_test_clear_young(kvm->arch.mmu.pgt,
+						   range->start << PAGE_SHIFT,
+						   size, false);
 }
 
 phys_addr_t kvm_mmu_get_httbr(void)