diff mbox series

[v2,11/22] KVM: arm64: Add support for stage-2 page-aging in generic page-table

Message ID 20200818132818.16065-12-will@kernel.org (mailing list archive)
State New, archived
Headers show
Series KVM: arm64: Rewrite page-table code and fault handling | expand

Commit Message

Will Deacon Aug. 18, 2020, 1:28 p.m. UTC
Add stage-2 mkyoung(), mkold() and is_young() operations to the generic
page-table code.

Cc: Marc Zyngier <maz@kernel.org>
Cc: Quentin Perret <qperret@google.com>
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/include/asm/kvm_pgtable.h | 38 ++++++++++++
 arch/arm64/kvm/hyp/pgtable.c         | 86 ++++++++++++++++++++++++++++
 2 files changed, 124 insertions(+)
diff mbox series

Patch

diff --git a/arch/arm64/include/asm/kvm_pgtable.h b/arch/arm64/include/asm/kvm_pgtable.h
index 8ab0d5f43817..ae56534f87a0 100644
--- a/arch/arm64/include/asm/kvm_pgtable.h
+++ b/arch/arm64/include/asm/kvm_pgtable.h
@@ -173,6 +173,44 @@  int kvm_pgtable_stage2_map(struct kvm_pgtable *pgt, u64 addr, u64 size,
  */
 int kvm_pgtable_stage2_unmap(struct kvm_pgtable *pgt, u64 addr, u64 size);
 
+/**
+ * kvm_pgtable_stage2_mkyoung() - Set 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.
+ *
+ * If there is a valid, leaf page-table entry used to translate @addr, then
+ * set the access flag in that entry.
+ *
+ * Return: The old page-table entry prior to setting the flag, 0 on failure.
+ */
+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.
+ * @pgt:	Page-table structure initialised by kvm_pgtable_stage2_init().
+ * @addr:	Intermediate physical address to identify the page-table entry.
+ *
+ * If there is a valid, leaf page-table entry used to translate @addr, then
+ * clear the access flag in that entry.
+ *
+ * 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.
+ */
+kvm_pte_t kvm_pgtable_stage2_mkold(struct kvm_pgtable *pgt, u64 addr);
+
+/**
+ * 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.
+ *
+ * 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_walk() - Walk a page-table.
  * @pgt:	Page-table structure initialised by kvm_pgtable_*_init().
diff --git a/arch/arm64/kvm/hyp/pgtable.c b/arch/arm64/kvm/hyp/pgtable.c
index 6f65d3841ec9..30713eb773e0 100644
--- a/arch/arm64/kvm/hyp/pgtable.c
+++ b/arch/arm64/kvm/hyp/pgtable.c
@@ -670,6 +670,92 @@  int kvm_pgtable_stage2_unmap(struct kvm_pgtable *pgt, u64 addr, u64 size)
 	return kvm_pgtable_walk(pgt, addr, size, &walker);
 }
 
+struct stage2_attr_data {
+	kvm_pte_t	attr_set;
+	kvm_pte_t	attr_clr;
+	kvm_pte_t	pte;
+};
+
+static int stage2_attr_walker(u64 addr, u64 end, u32 level, kvm_pte_t *ptep,
+			      enum kvm_pgtable_walk_flags flag,
+			      void * const arg)
+{
+	kvm_pte_t pte = *ptep;
+	struct stage2_attr_data *data = arg;
+
+	if (!kvm_pte_valid(pte))
+		return 0;
+
+	data->pte = pte;
+	pte &= ~data->attr_clr;
+	pte |= data->attr_set;
+
+	/*
+	 * We may race with the CPU trying to set the access flag here,
+	 * but worst-case the access flag update gets lost and will be
+	 * set on the next access instead.
+	 */
+	if (data->pte != pte)
+		WRITE_ONCE(*ptep, pte);
+
+	return 0;
+}
+
+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)
+{
+	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,
+	};
+	struct kvm_pgtable_walker walker = {
+		.cb		= stage2_attr_walker,
+		.arg		= &data,
+		.flags		= KVM_PGTABLE_WALK_LEAF,
+	};
+
+	ret = kvm_pgtable_walk(pgt, addr, size, &walker);
+	if (ret)
+		return ret;
+
+	if (orig_pte)
+		*orig_pte = data.pte;
+	return 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);
+	dsb(ishst);
+	return pte;
+}
+
+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);
+	/*
+	 * "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;
+}
+
+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);
+	return pte & KVM_PTE_LEAF_ATTR_LO_S2_AF;
+}
+
 int kvm_pgtable_stage2_init(struct kvm_pgtable *pgt, struct kvm *kvm)
 {
 	size_t pgd_sz;