KVM: arm64: Enable forcing page-level stage-2 mappings

Much of the stage-2 manipulation logic relies on being able to destroy
block mappings if e.g. installing a smaller mapping in the range. The
rationale for this behaviour is that stage-2 mappings can always be
re-created lazily. However, this gets more complicated when the stage-2
page-table is used to store metadata about the underlying pages. In such
cases, destroying a block mapping may lead to losing part of the state,
and confuse the user of those metadata (such as the hypervisor in nVHE
protected mode).

To avoid this, introduce a callback function in the pgtable struct which
is called during all map operations to determine whether the mappings
can use blocks, or should be forced to page granularity. This is used by
the hypervisor when creating the host stage-2 to force page-level
mappings when using non-default protection attributes.

Signed-off-by: Quentin Perret <qperret@google.com>
Reviewed-by: Fuad Tabba <tabba@google.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20210809152448.1810400-11-qperret@google.com

1 files changed, 41 insertions, 25 deletions

diff --git a/arch/arm64/include/asm/kvm_pgtable.h b/arch/arm64/include/asm/kvm_pgtable.h
index 8d6c710c1996..ca0c039547b5 100644
--- a/arch/arm64/include/asm/kvm_pgtable.h
+++ b/arch/arm64/include/asm/kvm_pgtable.h
@@ -116,25 +116,6 @@ enum kvm_pgtable_stage2_flags {
 };
 
 /**
- * struct kvm_pgtable - KVM page-table.
- * @ia_bits:		Maximum input address size, in bits.
- * @start_level:	Level at which the page-table walk starts.
- * @pgd:		Pointer to the first top-level entry of the page-table.
- * @mm_ops:		Memory management callbacks.
- * @mmu:		Stage-2 KVM MMU struct. Unused for stage-1 page-tables.
- */
-struct kvm_pgtable {
-	u32					ia_bits;
-	u32					start_level;
-	kvm_pte_t				*pgd;
-	struct kvm_pgtable_mm_ops		*mm_ops;
-
-	/* Stage-2 only */
-	struct kvm_s2_mmu			*mmu;
-	enum kvm_pgtable_stage2_flags		flags;
-};
-
-/**
  * enum kvm_pgtable_prot - Page-table permissions and attributes.
  * @KVM_PGTABLE_PROT_X:		Execute permission.
  * @KVM_PGTABLE_PROT_W:		Write permission.
@@ -149,11 +130,43 @@ enum kvm_pgtable_prot {
 	KVM_PGTABLE_PROT_DEVICE			= BIT(3),
 };
 
-#define PAGE_HYP		(KVM_PGTABLE_PROT_R | KVM_PGTABLE_PROT_W)
+#define KVM_PGTABLE_PROT_RW	(KVM_PGTABLE_PROT_R | KVM_PGTABLE_PROT_W)
+#define KVM_PGTABLE_PROT_RWX	(KVM_PGTABLE_PROT_RW | KVM_PGTABLE_PROT_X)
+
+#define PKVM_HOST_MEM_PROT	KVM_PGTABLE_PROT_RWX
+#define PKVM_HOST_MMIO_PROT	KVM_PGTABLE_PROT_RW
+
+#define PAGE_HYP		KVM_PGTABLE_PROT_RW
 #define PAGE_HYP_EXEC		(KVM_PGTABLE_PROT_R | KVM_PGTABLE_PROT_X)
 #define PAGE_HYP_RO		(KVM_PGTABLE_PROT_R)
 #define PAGE_HYP_DEVICE		(PAGE_HYP | KVM_PGTABLE_PROT_DEVICE)
 
+typedef bool (*kvm_pgtable_force_pte_cb_t)(u64 addr, u64 end,
+					   enum kvm_pgtable_prot prot);
+
+/**
+ * struct kvm_pgtable - KVM page-table.
+ * @ia_bits:		Maximum input address size, in bits.
+ * @start_level:	Level at which the page-table walk starts.
+ * @pgd:		Pointer to the first top-level entry of the page-table.
+ * @mm_ops:		Memory management callbacks.
+ * @mmu:		Stage-2 KVM MMU struct. Unused for stage-1 page-tables.
+ * @flags:		Stage-2 page-table flags.
+ * @force_pte_cb:	Function that returns true if page level mappings must
+ *			be used instead of block mappings.
+ */
+struct kvm_pgtable {
+	u32					ia_bits;
+	u32					start_level;
+	kvm_pte_t				*pgd;
+	struct kvm_pgtable_mm_ops		*mm_ops;
+
+	/* Stage-2 only */
+	struct kvm_s2_mmu			*mmu;
+	enum kvm_pgtable_stage2_flags		flags;
+	kvm_pgtable_force_pte_cb_t		force_pte_cb;
+};
+
 /**
  * enum kvm_pgtable_walk_flags - Flags to control a depth-first page-table walk.
  * @KVM_PGTABLE_WALK_LEAF:		Visit leaf entries, including invalid
@@ -246,21 +259,24 @@ int kvm_pgtable_hyp_map(struct kvm_pgtable *pgt, u64 addr, u64 size, u64 phys,
 u64 kvm_get_vtcr(u64 mmfr0, u64 mmfr1, u32 phys_shift);
 
 /**
- * kvm_pgtable_stage2_init_flags() - Initialise a guest stage-2 page-table.
+ * __kvm_pgtable_stage2_init() - Initialise a guest stage-2 page-table.
  * @pgt:	Uninitialised page-table structure to initialise.
  * @arch:	Arch-specific KVM structure representing the guest virtual
  *		machine.
  * @mm_ops:	Memory management callbacks.
  * @flags:	Stage-2 configuration flags.
+ * @force_pte_cb: Function that returns true if page level mappings must
+ *		be used instead of block mappings.
  *
  * Return: 0 on success, negative error code on failure.
  */
-int kvm_pgtable_stage2_init_flags(struct kvm_pgtable *pgt, struct kvm_arch *arch,
-				  struct kvm_pgtable_mm_ops *mm_ops,
-				  enum kvm_pgtable_stage2_flags flags);
+int __kvm_pgtable_stage2_init(struct kvm_pgtable *pgt, struct kvm_arch *arch,
+			      struct kvm_pgtable_mm_ops *mm_ops,
+			      enum kvm_pgtable_stage2_flags flags,
+			      kvm_pgtable_force_pte_cb_t force_pte_cb);
 
 #define kvm_pgtable_stage2_init(pgt, arch, mm_ops) \
-	kvm_pgtable_stage2_init_flags(pgt, arch, mm_ops, 0)
+	__kvm_pgtable_stage2_init(pgt, arch, mm_ops, 0, NULL)
 
 /**
  * kvm_pgtable_stage2_destroy() - Destroy an unused guest stage-2 page-table.