Merge branch kvm-arm64/s2-ptdump into kvmarm-master/next

* kvm-arm64/s2-ptdump:
  : .
  : Stage-2 page table dumper, reusing the main ptdump infrastructure,
  : courtesy of Sebastian Ene. From the cover letter:
  :
  : "This series extends the ptdump support to allow dumping the guest
  : stage-2 pagetables. When CONFIG_PTDUMP_STAGE2_DEBUGFS is enabled, ptdump
  : registers the new following files under debugfs:
  : - /sys/debug/kvm/<guest_id>/stage2_page_tables
  : - /sys/debug/kvm/<guest_id>/stage2_levels
  : - /sys/debug/kvm/<guest_id>/ipa_range
  :
  : This allows userspace tools (eg. cat) to dump the stage-2 pagetables by
  : reading the 'stage2_page_tables' file.
  : [...]"
  : .
  KVM: arm64: Register ptdump with debugfs on guest creation
  arm64: ptdump: Don't override the level when operating on the stage-2 tables
  arm64: ptdump: Use the ptdump description from a local context
  arm64: ptdump: Expose the attribute parsing functionality
  KVM: arm64: Move pagetable definitions to common header

Signed-off-by: Marc Zyngier <[email protected]>

Author: Marc Zyngier

arch/arm64/include/asm/kvm_mmu.h

@@ -352,5 +352,11 @@ static inline bool kvm_is_nested_s2_mmu(struct kvm *kvm, struct kvm_s2_mmu *mmu)
 	return &kvm->arch.mmu != mmu;
 }
 
+#ifdef CONFIG_PTDUMP_STAGE2_DEBUGFS
+void kvm_s2_ptdump_create_debugfs(struct kvm *kvm);
+#else
+static inline void kvm_s2_ptdump_create_debugfs(struct kvm *kvm) {}
+#endif /* CONFIG_PTDUMP_STAGE2_DEBUGFS */
+
 #endif /* __ASSEMBLY__ */
 #endif /* __ARM64_KVM_MMU_H__ */

arch/arm64/include/asm/kvm_pgtable.h

@@ -59,6 +59,48 @@ typedef u64 kvm_pte_t;
 
 #define KVM_PHYS_INVALID		(-1ULL)
 
+#define KVM_PTE_LEAF_ATTR_LO		GENMASK(11, 2)
+
+#define KVM_PTE_LEAF_ATTR_LO_S1_ATTRIDX	GENMASK(4, 2)
+#define KVM_PTE_LEAF_ATTR_LO_S1_AP	GENMASK(7, 6)
+#define KVM_PTE_LEAF_ATTR_LO_S1_AP_RO		\
+	({ cpus_have_final_cap(ARM64_KVM_HVHE) ? 2 : 3; })
+#define KVM_PTE_LEAF_ATTR_LO_S1_AP_RW		\
+	({ cpus_have_final_cap(ARM64_KVM_HVHE) ? 0 : 1; })
+#define KVM_PTE_LEAF_ATTR_LO_S1_SH	GENMASK(9, 8)
+#define KVM_PTE_LEAF_ATTR_LO_S1_SH_IS	3
+#define KVM_PTE_LEAF_ATTR_LO_S1_AF	BIT(10)
+
+#define KVM_PTE_LEAF_ATTR_LO_S2_MEMATTR	GENMASK(5, 2)
+#define KVM_PTE_LEAF_ATTR_LO_S2_S2AP_R	BIT(6)
+#define KVM_PTE_LEAF_ATTR_LO_S2_S2AP_W	BIT(7)
+#define KVM_PTE_LEAF_ATTR_LO_S2_SH	GENMASK(9, 8)
+#define KVM_PTE_LEAF_ATTR_LO_S2_SH_IS	3
+#define KVM_PTE_LEAF_ATTR_LO_S2_AF	BIT(10)
+
+#define KVM_PTE_LEAF_ATTR_HI		GENMASK(63, 50)
+
+#define KVM_PTE_LEAF_ATTR_HI_SW		GENMASK(58, 55)
+
+#define KVM_PTE_LEAF_ATTR_HI_S1_XN	BIT(54)
+
+#define KVM_PTE_LEAF_ATTR_HI_S2_XN	BIT(54)
+
+#define KVM_PTE_LEAF_ATTR_HI_S1_GP	BIT(50)
+
+#define KVM_PTE_LEAF_ATTR_S2_PERMS	(KVM_PTE_LEAF_ATTR_LO_S2_S2AP_R | \
+					 KVM_PTE_LEAF_ATTR_LO_S2_S2AP_W | \
+					 KVM_PTE_LEAF_ATTR_HI_S2_XN)
+
+#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)
+
 static inline bool kvm_pte_valid(kvm_pte_t pte)
 {
 	return pte & KVM_PTE_VALID;

arch/arm64/include/asm/ptdump.h

@@ -5,6 +5,8 @@
 #ifndef __ASM_PTDUMP_H
 #define __ASM_PTDUMP_H
 
+#include <linux/ptdump.h>
+
 #ifdef CONFIG_PTDUMP_CORE
 
 #include <linux/mm_types.h>
@@ -21,14 +23,53 @@ struct ptdump_info {
 	unsigned long			base_addr;
 };
 
+struct ptdump_prot_bits {
+	u64		mask;
+	u64		val;
+	const char	*set;
+	const char	*clear;
+};
+
+struct ptdump_pg_level {
+	const struct ptdump_prot_bits *bits;
+	char name[4];
+	int num;
+	u64 mask;
+};
+
+/*
+ * The page dumper groups page table entries of the same type into a single
+ * description. It uses pg_state to track the range information while
+ * iterating over the pte entries. When the continuity is broken it then
+ * dumps out a description of the range.
+ */
+struct ptdump_pg_state {
+	struct ptdump_state ptdump;
+	struct ptdump_pg_level *pg_level;
+	struct seq_file *seq;
+	const struct addr_marker *marker;
+	const struct mm_struct *mm;
+	unsigned long start_address;
+	int level;
+	u64 current_prot;
+	bool check_wx;
+	unsigned long wx_pages;
+	unsigned long uxn_pages;
+};
+
 void ptdump_walk(struct seq_file *s, struct ptdump_info *info);
+void note_page(struct ptdump_state *pt_st, unsigned long addr, int level,
+	       u64 val);
 #ifdef CONFIG_PTDUMP_DEBUGFS
 #define EFI_RUNTIME_MAP_END	DEFAULT_MAP_WINDOW_64
 void __init ptdump_debugfs_register(struct ptdump_info *info, const char *name);
 #else
 static inline void ptdump_debugfs_register(struct ptdump_info *info,
 					   const char *name) { }
-#endif
+#endif /* CONFIG_PTDUMP_DEBUGFS */
+#else
+static inline void note_page(struct ptdump_state *pt_st, unsigned long addr,
+			     int level, u64 val) { }
 #endif /* CONFIG_PTDUMP_CORE */
 
 #endif /* __ASM_PTDUMP_H */

arch/arm64/kvm/Kconfig

@@ -66,4 +66,21 @@ config PROTECTED_NVHE_STACKTRACE
 
 	  If unsure, or not using protected nVHE (pKVM), say N.
 
+config PTDUMP_STAGE2_DEBUGFS
+	bool "Present the stage-2 pagetables to debugfs"
+	depends on KVM
+	depends on DEBUG_KERNEL
+	depends on DEBUG_FS
+	depends on GENERIC_PTDUMP
+	select PTDUMP_CORE
+	default n
+	help
+	  Say Y here if you want to show the stage-2 kernel pagetables
+	  layout in a debugfs file. This information is only useful for kernel developers
+	  who are working in architecture specific areas of the kernel.
+	  It is probably not a good idea to enable this feature in a production
+	  kernel.
+
+	  If in doubt, say N.
+
 endif # VIRTUALIZATION

arch/arm64/kvm/Makefile

@@ -27,6 +27,7 @@ kvm-y += arm.o mmu.o mmio.o psci.o hypercalls.o pvtime.o \
 
 kvm-$(CONFIG_HW_PERF_EVENTS)  += pmu-emul.o pmu.o
 kvm-$(CONFIG_ARM64_PTR_AUTH)  += pauth.o
+kvm-$(CONFIG_PTDUMP_STAGE2_DEBUGFS) += ptdump.o
 
 always-y := hyp_constants.h hyp-constants.s
 

arch/arm64/kvm/arm.c

@@ -230,6 +230,7 @@ vm_fault_t kvm_arch_vcpu_fault(struct kvm_vcpu *vcpu, struct vm_fault *vmf)
 void kvm_arch_create_vm_debugfs(struct kvm *kvm)
 {
 	kvm_sys_regs_create_debugfs(kvm);
+	kvm_s2_ptdump_create_debugfs(kvm);
 }
 
 static void kvm_destroy_mpidr_data(struct kvm *kvm)

arch/arm64/kvm/hyp/pgtable.c

@@ -17,48 +17,6 @@
 #define KVM_PTE_TYPE_PAGE		1
 #define KVM_PTE_TYPE_TABLE		1
 
-#define KVM_PTE_LEAF_ATTR_LO		GENMASK(11, 2)
-
-#define KVM_PTE_LEAF_ATTR_LO_S1_ATTRIDX	GENMASK(4, 2)
-#define KVM_PTE_LEAF_ATTR_LO_S1_AP	GENMASK(7, 6)
-#define KVM_PTE_LEAF_ATTR_LO_S1_AP_RO		\
-	({ cpus_have_final_cap(ARM64_KVM_HVHE) ? 2 : 3; })
-#define KVM_PTE_LEAF_ATTR_LO_S1_AP_RW		\
-	({ cpus_have_final_cap(ARM64_KVM_HVHE) ? 0 : 1; })
-#define KVM_PTE_LEAF_ATTR_LO_S1_SH	GENMASK(9, 8)
-#define KVM_PTE_LEAF_ATTR_LO_S1_SH_IS	3
-#define KVM_PTE_LEAF_ATTR_LO_S1_AF	BIT(10)
-
-#define KVM_PTE_LEAF_ATTR_LO_S2_MEMATTR	GENMASK(5, 2)
-#define KVM_PTE_LEAF_ATTR_LO_S2_S2AP_R	BIT(6)
-#define KVM_PTE_LEAF_ATTR_LO_S2_S2AP_W	BIT(7)
-#define KVM_PTE_LEAF_ATTR_LO_S2_SH	GENMASK(9, 8)
-#define KVM_PTE_LEAF_ATTR_LO_S2_SH_IS	3
-#define KVM_PTE_LEAF_ATTR_LO_S2_AF	BIT(10)
-
-#define KVM_PTE_LEAF_ATTR_HI		GENMASK(63, 50)
-
-#define KVM_PTE_LEAF_ATTR_HI_SW		GENMASK(58, 55)
-
-#define KVM_PTE_LEAF_ATTR_HI_S1_XN	BIT(54)
-
-#define KVM_PTE_LEAF_ATTR_HI_S2_XN	BIT(54)
-
-#define KVM_PTE_LEAF_ATTR_HI_S1_GP	BIT(50)
-
-#define KVM_PTE_LEAF_ATTR_S2_PERMS	(KVM_PTE_LEAF_ATTR_LO_S2_S2AP_R | \
-					 KVM_PTE_LEAF_ATTR_LO_S2_S2AP_W | \
-					 KVM_PTE_LEAF_ATTR_HI_S2_XN)
-
-#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_walker	*walker;