Merge tag 'powerpc-5.15-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux

Pull powerpc updates from Michael Ellerman:

 - Convert pseries & powernv to use MSI IRQ domains.

 - Rework the pseries CPU numbering so that CPUs that are removed, and
   later re-added, are given a CPU number on the same node as
   previously, when possible.

 - Add support for a new more flexible device-tree format for specifying
   NUMA distances.

 - Convert powerpc to GENERIC_PTDUMP.

 - Retire sbc8548 and sbc8641d board support.

 - Various other small features and fixes.

Thanks to Alexey Kardashevskiy, Aneesh Kumar K.V, Anton Blanchard,
Cédric Le Goater, Christophe Leroy, Emmanuel Gil Peyrot, Fabiano Rosas,
Fangrui Song, Finn Thain, Gautham R.  Shenoy, Hari Bathini, Joel
Stanley, Jordan Niethe, Kajol Jain, Laurent Dufour, Leonardo Bras, Lukas
Bulwahn, Marc Zyngier, Masahiro Yamada, Michal Suchanek, Nathan
Chancellor, Nicholas Piggin, Parth Shah, Paul Gortmaker, Pratik R.
Sampat, Randy Dunlap, Sebastian Andrzej Siewior, Srikar Dronamraju, Wan
Jiabing, Xiongwei Song, and Zheng Yongjun.

* tag 'powerpc-5.15-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux: (154 commits)
  powerpc/bug: Cast to unsigned long before passing to inline asm
  powerpc/ptdump: Fix generic ptdump for 64-bit
  KVM: PPC: Fix clearing never mapped TCEs in realmode
  powerpc/pseries/iommu: Rename "direct window" to "dma window"
  powerpc/pseries/iommu: Make use of DDW for indirect mapping
  powerpc/pseries/iommu: Find existing DDW with given property name
  powerpc/pseries/iommu: Update remove_dma_window() to accept property name
  powerpc/pseries/iommu: Reorganize iommu_table_setparms*() with new helper
  powerpc/pseries/iommu: Add ddw_property_create() and refactor enable_ddw()
  powerpc/pseries/iommu: Allow DDW windows starting at 0x00
  powerpc/pseries/iommu: Add ddw_list_new_entry() helper
  powerpc/pseries/iommu: Add iommu_pseries_alloc_table() helper
  powerpc/kernel/iommu: Add new iommu_table_in_use() helper
  powerpc/pseries/iommu: Replace hard-coded page shift
  powerpc/numa: Update cpu_cpu_map on CPU online/offline
  powerpc/numa: Print debug statements only when required
  powerpc/numa: convert printk to pr_xxx
  powerpc/numa: Drop dbg in favour of pr_debug
  powerpc/smp: Enable CACHE domain for shared processor
  powerpc/smp: Update cpu_core_map on all PowerPc systems
  ...

19 files changed, 506 insertions, 325 deletions

diff --git a/arch/powerpc/mm/Makefile b/arch/powerpc/mm/Makefile
index eae4ec2988fc..df8172da2301 100644
--- a/arch/powerpc/mm/Makefile
+++ b/arch/powerpc/mm/Makefile
@@ -18,5 +18,5 @@ obj-$(CONFIG_PPC_MM_SLICES)	+= slice.o
 obj-$(CONFIG_HUGETLB_PAGE)	+= hugetlbpage.o
 obj-$(CONFIG_NOT_COHERENT_CACHE) += dma-noncoherent.o
 obj-$(CONFIG_PPC_COPRO_BASE)	+= copro_fault.o
-obj-$(CONFIG_PPC_PTDUMP)	+= ptdump/
+obj-$(CONFIG_PTDUMP_CORE)	+= ptdump/
 obj-$(CONFIG_KASAN)		+= kasan/
diff --git a/arch/powerpc/mm/book3s64/hash_native.c b/arch/powerpc/mm/book3s64/hash_native.c
index 52e170bd95ae..d8279bfe68ea 100644
--- a/arch/powerpc/mm/book3s64/hash_native.c
+++ b/arch/powerpc/mm/book3s64/hash_native.c
@@ -787,7 +787,7 @@ static void hpte_decode(struct hash_pte *hpte, unsigned long slot,
  * TODO: add batching support when enabled.  remember, no dynamic memory here,
  * although there is the control page available...
  */
-static void native_hpte_clear(void)
+static notrace void native_hpte_clear(void)
 {
 	unsigned long vpn = 0;
 	unsigned long slot, slots;
diff --git a/arch/powerpc/mm/book3s64/hash_utils.c b/arch/powerpc/mm/book3s64/hash_utils.c
index ac5720371c0d..c145776d3ae5 100644
--- a/arch/powerpc/mm/book3s64/hash_utils.c
+++ b/arch/powerpc/mm/book3s64/hash_utils.c
@@ -36,8 +36,8 @@
 #include <linux/hugetlb.h>
 #include <linux/cpu.h>
 #include <linux/pgtable.h>
+#include <linux/debugfs.h>
 
-#include <asm/debugfs.h>
 #include <asm/interrupt.h>
 #include <asm/processor.h>
 #include <asm/mmu.h>
@@ -2072,7 +2072,7 @@ DEFINE_DEBUGFS_ATTRIBUTE(fops_hpt_order, hpt_order_get, hpt_order_set, "%llu\n")
 
 static int __init hash64_debugfs(void)
 {
-	debugfs_create_file("hpt_order", 0600, powerpc_debugfs_root, NULL,
+	debugfs_create_file("hpt_order", 0600, arch_debugfs_dir, NULL,
 			    &fops_hpt_order);
 	return 0;
 }
diff --git a/arch/powerpc/mm/book3s64/pgtable.c b/arch/powerpc/mm/book3s64/pgtable.c
index 9ffa65074cb0..9e16c7b1a6c5 100644
--- a/arch/powerpc/mm/book3s64/pgtable.c
+++ b/arch/powerpc/mm/book3s64/pgtable.c
@@ -6,9 +6,9 @@
 #include <linux/sched.h>
 #include <linux/mm_types.h>
 #include <linux/memblock.h>
+#include <linux/debugfs.h>
 #include <misc/cxl-base.h>
 
-#include <asm/debugfs.h>
 #include <asm/pgalloc.h>
 #include <asm/tlb.h>
 #include <asm/trace.h>
@@ -172,8 +172,8 @@ pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot)
 }
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
 
-/* For use by kexec */
-void mmu_cleanup_all(void)
+/* For use by kexec, called with MMU off */
+notrace void mmu_cleanup_all(void)
 {
 	if (radix_enabled())
 		radix__mmu_cleanup_all();
@@ -520,7 +520,7 @@ static int __init pgtable_debugfs_setup(void)
 	 * invalidated as expected.
 	 */
 	debugfs_create_bool("tlbie_enabled", 0600,
-			powerpc_debugfs_root,
+			arch_debugfs_dir,
 			&tlbie_enabled);
 
 	return 0;
diff --git a/arch/powerpc/mm/book3s64/radix_pgtable.c b/arch/powerpc/mm/book3s64/radix_pgtable.c
index e50ddf129c15..ae20add7954a 100644
--- a/arch/powerpc/mm/book3s64/radix_pgtable.c
+++ b/arch/powerpc/mm/book3s64/radix_pgtable.c
@@ -679,7 +679,8 @@ void radix__early_init_mmu_secondary(void)
 	mtspr(SPRN_UAMOR, 0);
 }
 
-void radix__mmu_cleanup_all(void)
+/* Called during kexec sequence with MMU off */
+notrace void radix__mmu_cleanup_all(void)
 {
 	unsigned long lpcr;
 
diff --git a/arch/powerpc/mm/book3s64/radix_tlb.c b/arch/powerpc/mm/book3s64/radix_tlb.c
index aefc100d79a7..7724af19ed7e 100644
--- a/arch/powerpc/mm/book3s64/radix_tlb.c
+++ b/arch/powerpc/mm/book3s64/radix_tlb.c
@@ -10,6 +10,7 @@
 #include <linux/memblock.h>
 #include <linux/mmu_context.h>
 #include <linux/sched/mm.h>
+#include <linux/debugfs.h>
 
 #include <asm/ppc-opcode.h>
 #include <asm/tlb.h>
@@ -1106,8 +1107,8 @@ EXPORT_SYMBOL(radix__flush_tlb_kernel_range);
  * invalidating a full PID, so it has a far lower threshold to change from
  * individual page flushes to full-pid flushes.
  */
-static unsigned long tlb_single_page_flush_ceiling __read_mostly = 33;
-static unsigned long tlb_local_single_page_flush_ceiling __read_mostly = POWER9_TLB_SETS_RADIX * 2;
+static u32 tlb_single_page_flush_ceiling __read_mostly = 33;
+static u32 tlb_local_single_page_flush_ceiling __read_mostly = POWER9_TLB_SETS_RADIX * 2;
 
 static inline void __radix__flush_tlb_range(struct mm_struct *mm,
 					    unsigned long start, unsigned long end)
@@ -1524,3 +1525,14 @@ void do_h_rpt_invalidate_prt(unsigned long pid, unsigned long lpid,
 EXPORT_SYMBOL_GPL(do_h_rpt_invalidate_prt);
 
 #endif /* CONFIG_KVM_BOOK3S_HV_POSSIBLE */
+
+static int __init create_tlb_single_page_flush_ceiling(void)
+{
+	debugfs_create_u32("tlb_single_page_flush_ceiling", 0600,
+			   arch_debugfs_dir, &tlb_single_page_flush_ceiling);
+	debugfs_create_u32("tlb_local_single_page_flush_ceiling", 0600,
+			   arch_debugfs_dir, &tlb_local_single_page_flush_ceiling);
+	return 0;
+}
+late_initcall(create_tlb_single_page_flush_ceiling);
+
diff --git a/arch/powerpc/mm/book3s64/slb.c b/arch/powerpc/mm/book3s64/slb.c
index c91bd85eb90e..f0037bcc47a0 100644
--- a/arch/powerpc/mm/book3s64/slb.c
+++ b/arch/powerpc/mm/book3s64/slb.c
@@ -822,7 +822,7 @@ DEFINE_INTERRUPT_HANDLER_RAW(do_slb_fault)
 	/* IRQs are not reconciled here, so can't check irqs_disabled */
 	VM_WARN_ON(mfmsr() & MSR_EE);
 
-	if (unlikely(!(regs->msr & MSR_RI)))
+	if (regs_is_unrecoverable(regs))
 		return -EINVAL;
 
 	/*
diff --git a/arch/powerpc/mm/drmem.c b/arch/powerpc/mm/drmem.c
index 9af3832c9d8d..22197b18d85e 100644
--- a/arch/powerpc/mm/drmem.c
+++ b/arch/powerpc/mm/drmem.c
@@ -18,6 +18,7 @@ static int n_root_addr_cells, n_root_size_cells;
 
 static struct drmem_lmb_info __drmem_info;
 struct drmem_lmb_info *drmem_info = &__drmem_info;
+static bool in_drmem_update;
 
 u64 drmem_lmb_memory_max(void)
 {
@@ -178,6 +179,11 @@ int drmem_update_dt(void)
 	if (!memory)
 		return -1;
 
+	/*
+	 * Set in_drmem_update to prevent the notifier callback to process the
+	 * DT property back since the change is coming from the LMB tree.
+	 */
+	in_drmem_update = true;
 	prop = of_find_property(memory, "ibm,dynamic-memory", NULL);
 	if (prop) {
 		rc = drmem_update_dt_v1(memory, prop);
@@ -186,6 +192,7 @@ int drmem_update_dt(void)
 		if (prop)
 			rc = drmem_update_dt_v2(memory, prop);
 	}
+	in_drmem_update = false;
 
 	of_node_put(memory);
 	return rc;
@@ -307,6 +314,45 @@ int __init walk_drmem_lmbs_early(unsigned long node, void *data,
 	return ret;
 }
 
+/*
+ * Update the LMB associativity index.
+ */
+static int update_lmb(struct drmem_lmb *updated_lmb,
+		      __maybe_unused const __be32 **usm,
+		      __maybe_unused void *data)
+{
+	struct drmem_lmb *lmb;
+
+	for_each_drmem_lmb(lmb) {
+		if (lmb->drc_index != updated_lmb->drc_index)
+			continue;
+
+		lmb->aa_index = updated_lmb->aa_index;
+		break;
+	}
+	return 0;
+}
+
+/*
+ * Update the LMB associativity index.
+ *
+ * This needs to be called when the hypervisor is updating the
+ * dynamic-reconfiguration-memory node property.
+ */
+void drmem_update_lmbs(struct property *prop)
+{
+	/*
+	 * Don't update the LMBs if triggered by the update done in
+	 * drmem_update_dt(), the LMB values have been used to the update the DT
+	 * property in that case.
+	 */
+	if (in_drmem_update)
+		return;
+	if (!strcmp(prop->name, "ibm,dynamic-memory"))
+		__walk_drmem_v1_lmbs(prop->value, NULL, NULL, update_lmb);
+	else if (!strcmp(prop->name, "ibm,dynamic-memory-v2"))
+		__walk_drmem_v2_lmbs(prop->value, NULL, NULL, update_lmb);
+}
 #endif
 
 static int init_drmem_lmb_size(struct device_node *dn)
diff --git a/arch/powerpc/mm/mmu_decl.h b/arch/powerpc/mm/mmu_decl.h
index 7dac910c0b21..dd1cabc2ea0f 100644
--- a/arch/powerpc/mm/mmu_decl.h
+++ b/arch/powerpc/mm/mmu_decl.h
@@ -180,7 +180,7 @@ static inline void mmu_mark_rodata_ro(void) { }
 void __init mmu_mapin_immr(void);
 #endif
 
-#ifdef CONFIG_PPC_DEBUG_WX
+#ifdef CONFIG_DEBUG_WX
 void ptdump_check_wx(void);
 #else
 static inline void ptdump_check_wx(void) { }
diff --git a/arch/powerpc/mm/nohash/tlb_low.S b/arch/powerpc/mm/nohash/tlb_low.S
index 4613bf8e9aae..5add4a51e51f 100644
--- a/arch/powerpc/mm/nohash/tlb_low.S
+++ b/arch/powerpc/mm/nohash/tlb_low.S
@@ -199,7 +199,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_476_DD2)
  * Touch enough instruction cache lines to ensure cache hits
  */
 1:	mflr	r9
-	bl	2f
+	bcl	20,31,$+4
 2:	mflr	r6
 	li	r7,32
 	PPC_ICBT(0,R6,R7)		/* touch next cache line */
@@ -414,7 +414,7 @@ _GLOBAL(loadcam_multi)
 	 * Set up temporary TLB entry that is the same as what we're
 	 * running from, but in AS=1.
 	 */
-	bl	1f
+	bcl	20,31,$+4
 1:	mflr	r6
 	tlbsx	0,r8
 	mfspr	r6,SPRN_MAS1
diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c
index f2bf98bdcea2..6f14c8fb6359 100644
--- a/arch/powerpc/mm/numa.c
+++ b/arch/powerpc/mm/numa.c
@@ -40,9 +40,6 @@ static int numa_enabled = 1;
 
 static char *cmdline __initdata;
 
-static int numa_debug;
-#define dbg(args...) if (numa_debug) { printk(KERN_INFO args); }
-
 int numa_cpu_lookup_table[NR_CPUS];
 cpumask_var_t node_to_cpumask_map[MAX_NUMNODES];
 struct pglist_data *node_data[MAX_NUMNODES];
@@ -51,14 +48,22 @@ EXPORT_SYMBOL(numa_cpu_lookup_table);
 EXPORT_SYMBOL(node_to_cpumask_map);
 EXPORT_SYMBOL(node_data);
 
-static int min_common_depth;
+static int primary_domain_index;
 static int n_mem_addr_cells, n_mem_size_cells;
-static int form1_affinity;
+
+#define FORM0_AFFINITY 0
+#define FORM1_AFFINITY 1
+#define FORM2_AFFINITY 2
+static int affinity_form;
 
 #define MAX_DISTANCE_REF_POINTS 4
 static int distance_ref_points_depth;
 static const __be32 *distance_ref_points;
 static int distance_lookup_table[MAX_NUMNODES][MAX_DISTANCE_REF_POINTS];
+static int numa_distance_table[MAX_NUMNODES][MAX_NUMNODES] = {
+	[0 ... MAX_NUMNODES - 1] = { [0 ... MAX_NUMNODES - 1] = -1 }
+};
+static int numa_id_index_table[MAX_NUMNODES] = { [0 ... MAX_NUMNODES - 1] = NUMA_NO_NODE };
 
 /*
  * Allocate node_to_cpumask_map based on number of available nodes
@@ -79,7 +84,7 @@ static void __init setup_node_to_cpumask_map(void)
 		alloc_bootmem_cpumask_var(&node_to_cpumask_map[node]);
 
 	/* cpumask_of_node() will now work */
-	dbg("Node to cpumask map for %u nodes\n", nr_node_ids);
+	pr_debug("Node to cpumask map for %u nodes\n", nr_node_ids);
 }
 
 static int __init fake_numa_create_new_node(unsigned long end_pfn,
@@ -123,7 +128,7 @@ static int __init fake_numa_create_new_node(unsigned long end_pfn,
 		cmdline = p;
 		fake_nid++;
 		*nid = fake_nid;
-		dbg("created new fake_node with id %d\n", fake_nid);
+		pr_debug("created new fake_node with id %d\n", fake_nid);
 		return 1;
 	}
 	return 0;
@@ -137,33 +142,79 @@ static void reset_numa_cpu_lookup_table(void)
 		numa_cpu_lookup_table[cpu] = -1;
 }
 
-static void map_cpu_to_node(int cpu, int node)
+void map_cpu_to_node(int cpu, int node)
 {
 	update_numa_cpu_lookup_table(cpu, node);
 
-	dbg("adding cpu %d to node %d\n", cpu, node);
-
-	if (!(cpumask_test_cpu(cpu, node_to_cpumask_map[node])))
+	if (!(cpumask_test_cpu(cpu, node_to_cpumask_map[node]))) {
+		pr_debug("adding cpu %d to node %d\n", cpu, node);
 		cpumask_set_cpu(cpu, node_to_cpumask_map[node]);
+	}
 }
 
 #if defined(CONFIG_HOTPLUG_CPU) || defined(CONFIG_PPC_SPLPAR)
-static void unmap_cpu_from_node(unsigned long cpu)
+void unmap_cpu_from_node(unsigned long cpu)
 {
 	int node = numa_cpu_lookup_table[cpu];
 
-	dbg("removing cpu %lu from node %d\n", cpu, node);
-
 	if (cpumask_test_cpu(cpu, node_to_cpumask_map[node])) {
 		cpumask_clear_cpu(cpu, node_to_cpumask_map[node]);
+		pr_debug("removing cpu %lu from node %d\n", cpu, node);
 	} else {
-		printk(KERN_ERR "WARNING: cpu %lu not found in node %d\n",
-		       cpu, node);
+		pr_warn("Warning: cpu %lu not found in node %d\n", cpu, node);
 	}
 }
 #endif /* CONFIG_HOTPLUG_CPU || CONFIG_PPC_SPLPAR */
 
-int cpu_distance(__be32 *cpu1_assoc, __be32 *cpu2_assoc)
+static int __associativity_to_nid(const __be32 *associativity,
+				  int max_array_sz)
+{
+	int nid;
+	/*
+	 * primary_domain_index is 1 based array index.
+	 */
+	int index = primary_domain_index  - 1;
+
+	if (!numa_enabled || index >= max_array_sz)
+		return NUMA_NO_NODE;
+
+	nid = of_read_number(&associativity[index], 1);
+
+	/* POWER4 LPAR uses 0xffff as invalid node */
+	if (nid == 0xffff || nid >= nr_node_ids)
+		nid = NUMA_NO_NODE;
+	return nid;
+}
+/*
+ * Returns nid in the range [0..nr_node_ids], or -1 if no useful NUMA
+ * info is found.
+ */
+static int associativity_to_nid(const __be32 *associativity)
+{
+	int array_sz = of_read_number(associativity, 1);
+
+	/* Skip the first element in the associativity array */
+	return __associativity_to_nid((associativity + 1), array_sz);
+}
+
+static int __cpu_form2_relative_distance(__be32 *cpu1_assoc, __be32 *cpu2_assoc)
+{
+	int dist;
+	int node1, node2;
+
+	node1 = associativity_to_nid(cpu1_assoc);
+	node2 = associativity_to_nid(cpu2_assoc);
+
+	dist = numa_distance_table[node1][node2];
+	if (dist <= LOCAL_DISTANCE)
+		return 0;
+	else if (dist <= REMOTE_DISTANCE)
+		return 1;
+	else
+		return 2;
+}
+
+static int __cpu_form1_relative_distance(__be32 *cpu1_assoc, __be32 *cpu2_assoc)
 {
 	int dist = 0;
 
@@ -179,6 +230,15 @@ int cpu_distance(__be32 *cpu1_assoc, __be32 *cpu2_assoc)
 	return dist;
 }
 
+int cpu_relative_distance(__be32 *cpu1_assoc, __be32 *cpu2_assoc)
+{
+	/* We should not get called with FORM0 */
+	VM_WARN_ON(affinity_form == FORM0_AFFINITY);
+	if (affinity_form == FORM1_AFFINITY)
+		return __cpu_form1_relative_distance(cpu1_assoc, cpu2_assoc);
+	return __cpu_form2_relative_distance(cpu1_assoc, cpu2_assoc);
+}
+
 /* must hold reference to node during call */
 static const __be32 *of_get_associativity(struct device_node *dev)
 {
@@ -190,7 +250,9 @@ int __node_distance(int a, int b)
 	int i;
 	int distance = LOCAL_DISTANCE;
 
-	if (!form1_affinity)
+	if (affinity_form == FORM2_AFFINITY)
+		return numa_distance_table[a][b];
+	else if (affinity_form == FORM0_AFFINITY)
 		return ((a == b) ? LOCAL_DISTANCE : REMOTE_DISTANCE);
 
 	for (i = 0; i < distance_ref_points_depth; i++) {
@@ -205,52 +267,6 @@ int __node_distance(int a, int b)
 }
 EXPORT_SYMBOL(__node_distance);
 
-static void initialize_distance_lookup_table(int nid,
-		const __be32 *associativity)
-{
-	int i;
-
-	if (!form1_affinity)
-		return;
-
-	for (i = 0; i < distance_ref_points_depth; i++) {
-		const __be32 *entry;
-
-		entry = &associativity[be32_to_cpu(distance_ref_points[i]) - 1];
-		distance_lookup_table[nid][i] = of_read_number(entry, 1);
-	}
-}
-
-/*
- * Returns nid in the range [0..nr_node_ids], or -1 if no useful NUMA
- * info is found.
- */
-static int associativity_to_nid(const __be32 *associativity)
-{
-	int nid = NUMA_NO_NODE;
-
-	if (!numa_enabled)
-		goto out;
-
-	if (of_read_number(associativity, 1) >= min_common_depth)
-		nid = of_read_number(&associativity[min_common_depth], 1);
-
-	/* POWER4 LPAR uses 0xffff as invalid node */
-	if (nid == 0xffff || nid >= nr_node_ids)
-		nid = NUMA_NO_NODE;
-
-	if (nid > 0 &&
-		of_read_number(associativity, 1) >= distance_ref_points_depth) {
-		/*
-		 * Skip the length field and send start of associativity array
-		 */
-		initialize_distance_lookup_table(nid, associativity + 1);
-	}
-
-out:
-	return nid;
-}
-
 /* Returns the nid associated with the given device tree node,
  * or -1 if not found.
  */
@@ -284,11 +300,159 @@ int of_node_to_nid(struct device_node *device)
 }
 EXPORT_SYMBOL(of_node_to_nid);
 
-static int __init find_min_common_depth(void)
+static void __initialize_form1_numa_distance(const __be32 *associativity,
+					     int max_array_sz)
+{
+	int i, nid;
+
+	if (affinity_form != FORM1_AFFINITY)
+		return;
+
+	nid = __associativity_to_nid(associativity, max_array_sz);
+	if (nid != NUMA_NO_NODE) {
+		for (i = 0; i < distance_ref_points_depth; i++) {
+			const __be32 *entry;
+			int index = be32_to_cpu(distance_ref_points[i]) - 1;
+
+			/*
+			 * broken hierarchy, return with broken distance table
+			 */
+			if (WARN(index >= max_array_sz, "Broken ibm,associativity property"))
+				return;
+
+			entry = &associativity[index];
+			distance_lookup_table[nid][i] = of_read_number(entry, 1);
+		}
+	}
+}
+
+static void initialize_form1_numa_distance(const __be32 *associativity)
+{
+	int array_sz;
+
+	array_sz = of_read_number(associativity, 1);
+	/* Skip the first element in the associativity array */
+	__initialize_form1_numa_distance(associativity + 1, array_sz);
+}
+
+/*
+ * Used to update distance information w.r.t newly added node.
+ */
+void update_numa_distance(struct device_node *node)
 {
-	int depth;
+	int nid;
+
+	if (affinity_form == FORM0_AFFINITY)
+		return;
+	else if (affinity_form == FORM1_AFFINITY) {
+		const __be32 *associativity;
+
+		associativity = of_get_associativity(node);
+		if (!associativity)
+			return;
+
+		initialize_form1_numa_distance(associativity);
+		return;
+	}
+
+	/* FORM2 affinity  */
+	nid = of_node_to_nid_single(node);
+	if (nid == NUMA_NO_NODE)
+		return;
+
+	/*
+	 * With FORM2 we expect NUMA distance of all possible NUMA
+	 * nodes to be provided during boot.
+	 */
+	WARN(numa_distance_table[nid][nid] == -1,
+	     "NUMA distance details for node %d not provided\n", nid);
+}
+
+/*
+ * ibm,numa-lookup-index-table= {N, domainid1, domainid2, ..... domainidN}
+ * ibm,numa-distance-table = { N, 1, 2, 4, 5, 1, 6, .... N elements}
+ */
+static void initialize_form2_numa_distance_lookup_table(void)
+{
+	int i, j;
+	struct device_node *root;
+	const __u8 *numa_dist_table;
+	const __be32 *numa_lookup_index;
+	int numa_dist_table_length;
+	int max_numa_index, distance_index;
+
+	if (firmware_has_feature(FW_FEATURE_OPAL))
+		root = of_find_node_by_path("/ibm,opal");
+	else
+		root = of_find_node_by_path("/rtas");
+	if (!root)
+		root = of_find_node_by_path("/");
+
+	numa_lookup_index = of_get_property(root, "ibm,numa-lookup-index-table", NULL);
+	max_numa_index = of_read_number(&numa_lookup_index[0], 1);
+
+	/* first element of the array is the size and is encode-int */
+	numa_dist_table = of_get_property(root, "ibm,numa-distance-table", NULL);
+	numa_dist_table_length = of_read_number((const __be32 *)&numa_dist_table[0], 1);
+	/* Skip the size which is encoded int */
+	numa_dist_table += sizeof(__be32);
+
+	pr_debug("numa_dist_table_len = %d, numa_dist_indexes_len = %d\n",
+		 numa_dist_table_length, max_numa_index);
+
+	for (i = 0; i < max_numa_index; i++)
+		/* +1 skip the max_numa_index in the property */
+		numa_id_index_table[i] = of_read_number(&numa_lookup_index[i + 1], 1);
+
+
+	if (numa_dist_table_length != max_numa_index * max_numa_index) {
+		WARN(1, "Wrong NUMA distance information\n");
+		/* consider everybody else just remote. */
+		for (i = 0;  i < max_numa_index; i++) {
+			for (j = 0; j < max_numa_index; j++) {
+				int nodeA = numa_id_index_table[i];
+				int nodeB = numa_id_index_table[j];
+
+				if (nodeA == nodeB)
+					numa_distance_table[nodeA][nodeB] = LOCAL_DISTANCE;
+				else
+					numa_distance_table[nodeA][nodeB] = REMOTE_DISTANCE;
+			}
+		}
+	}
+
+	distance_index = 0;
+	for (i = 0;  i < max_numa_index; i++) {
+		for (j = 0; j < max_numa_index; j++) {
+			int nodeA = numa_id_index_table[i];
+			int nodeB = numa_id_index_table[j];
+
+			numa_distance_table[nodeA][nodeB] = numa_dist_table[distance_index++];
+			pr_debug("dist[%d][%d]=%d ", nodeA, nodeB, numa_distance_table[nodeA][nodeB]);
+		}
+	}
+	of_node_put(root);
+}
+
+static int __init find_primary_domain_index(void)
+{
+	int index;
 	struct device_node *root;
 
+	/*
+	 * Check for which form of affinity.
+	 */
+	if (firmware_has_feature(FW_FEATURE_OPAL)) {
+		affinity_form = FORM1_AFFINITY;
+	} else if (firmware_has_feature(FW_FEATURE_FORM2_AFFINITY)) {
+		pr_debug("Using form 2 affinity\n");
+		affinity_form = FORM2_AFFINITY;
+	} else if (firmware_has_feature(FW_FEATURE_FORM1_AFFINITY)) {
+		pr_debug("Using form 1 affinity\n");
+		affinity_form = FORM1_AFFINITY;
+	} else
+		affinity_form = FORM0_AFFINITY;
+
 	if (firmware_has_feature(FW_FEATURE_OPAL))
 		root = of_find_node_by_path("/ibm,opal");
 	else
@@ -313,42 +477,37 @@ static int __init find_min_common_depth(void)
 					&distance_ref_points_depth);
 
 	if (!distance_ref_points) {
-		dbg("NUMA: ibm,associativity-reference-points not found.\n");
+		pr_debug("ibm,associativity-reference-points not found.\n");
 		goto err;
 	}
 
 	distance_ref_points_depth /= sizeof(int);
-
-	if (firmware_has_feature(FW_FEATURE_OPAL) ||
-	    firmware_has_feature(FW_FEATURE_TYPE1_AFFINITY)) {
-		dbg("Using form 1 affinity\n");
-		form1_affinity = 1;
-	}
-
-	if (form1_affinity) {
-		depth = of_read_number(distance_ref_points, 1);
-	} else {
+	if (affinity_form == FORM0_AFFINITY) {
 		if (distance_ref_points_depth < 2) {
-			printk(KERN_WARNING "NUMA: "
-				"short ibm,associativity-reference-points\n");
+			pr_warn("short ibm,associativity-reference-points\n");
 			goto err;
 		}
 
-		depth = of_read_number(&distance_ref_points[1], 1);
+		index = of_read_number(&distance_ref_points[1], 1);
+	} else {
+		/*
+		 * Both FORM1 and FORM2 affinity find the primary domain details
+		 * at the same offset.
+		 */
+		index = of_read_number(distance_ref_points, 1);
 	}
-
 	/*
 	 * Warn and cap if the hardware supports more than
 	 * MAX_DISTANCE_REF_POINTS domains.
 	 */
 	if (distance_ref_points_depth > MAX_DISTANCE_REF_POINTS) {
-		printk(KERN_WARNING "NUMA: distance array capped at "
-			"%d entries\n", MAX_DISTANCE_REF_POINTS);
+		pr_warn("distance array capped at %d entries\n",
+			MAX_DISTANCE_REF_POINTS);
 		distance_ref_points_depth = MAX_DISTANCE_REF_POINTS;
 	}
 
 	of_node_put(root);
-	return depth;
+	return index;
 
 err:
 	of_node_put(root);
@@ -426,6 +585,38 @@ static int of_get_assoc_arrays(struct assoc_arrays *aa)
 	return 0;
 }
 
+static int get_nid_and_numa_distance(struct drmem_lmb *lmb)
+{
+	struct assoc_arrays aa = { .arrays = NULL };
+	int default_nid = NUMA_NO_NODE;
+	int nid = default_nid;
+	int rc, index;
+
+	if ((primary_domain_index < 0) || !numa_enabled)
+		return default_nid;
+
+	rc = of_get_assoc_arrays(&aa);
+	if (rc)
+		return default_nid;
+
+	if (primary_domain_index <= aa.array_sz &&
+	    !(lmb->flags & DRCONF_MEM_AI_INVALID) && lmb->aa_index < aa.n_arrays) {
+		const __be32 *associativity;
+
+		index = lmb->aa_index * aa.array_sz;
+		associativity = &aa.arrays[index];
+		nid = __associativity_to_nid(associativity, aa.array_sz);
+		if (nid > 0 && affinity_form == FORM1_AFFINITY) {
+			/*
+			 * lookup array associativity entries have
+			 * no length of the array as the first element.
+			 */
+			__initialize_form1_numa_distance(associativity, aa.array_sz);
+		}
+	}
+	return nid;
+}
+
 /*
  * This is like of_node_to_nid_single() for memory represented in the
  * ibm,dynamic-reconfiguration-memory node.
@@ -437,35 +628,28 @@ int of_drconf_to_nid_single(struct drmem_lmb *lmb)
 	int nid = default_nid;
 	int rc, index;
 
-	if ((min_common_depth < 0) || !numa_enabled)
+	if ((primary_domain_index < 0) || !numa_enabled)
 		return default_nid;
 
 	rc = of_get_assoc_arrays(&aa);
 	if (rc)
 		return default_nid;
 
-	if (min_common_depth <= aa.array_sz &&
+	if (primary_domain_index <= aa.array_sz &&
 	    !(lmb->flags & DRCONF_MEM_AI_INVALID) && lmb->aa_index < aa.n_arrays) {
-		index = lmb->aa_index * aa.array_sz + min_common_depth - 1;
-		nid = of_read_number(&aa.arrays[index], 1);
-
-		if (nid == 0xffff || nid >= nr_node_ids)
-			nid = default_nid;
+		const __be32 *associativity;
 
-		if (nid > 0) {
-			index = lmb->aa_index * aa.array_sz;
-			initialize_distance_lookup_table(nid,
-							&aa.arrays[index]);
-		}
+		index = lmb->aa_index * aa.array_sz;
+		associativity = &aa.arrays[index];
+		nid = __associativity_to_nid(associativity, aa.array_sz);
 	}
-
 	return nid;
 }
 
 #ifdef CONFIG_PPC_SPLPAR
-static int vphn_get_nid(long lcpu)
+
+static int __vphn_get_associativity(long lcpu, __be32 *associativity)
 {
-	__be32 associativity[VPHN_ASSOC_BUFSIZE] = {0};
 	long rc, hwid;
 
 	/*
@@ -485,12 +669,30 @@ static int vphn_get_nid(long lcpu)
 
 		rc = hcall_vphn(hwid, VPHN_FLAG_VCPU, associativity);
 		if (rc == H_SUCCESS)
-			return associativity_to_nid(associativity);
+			return 0;
 	}
 
+	return -1;
+}
+
+static int vphn_get_nid(long lcpu)
+{
+	__be32 associativity[VPHN_ASSOC_BUFSIZE] = {0};
+
+
+	if (!__vphn_get_associativity(lcpu, associativity))
+		return associativity_to_nid(associativity);
+
 	return NUMA_NO_NODE;
+
 }
 #else
+
+static int __vphn_get_associativity(long lcpu, __be32 *associativity)
+{
+	return -1;
+}
+
 static int vphn_get_nid(long unused)
 {
 	return NUMA_NO_NODE;
@@ -598,9 +800,6 @@ static int ppc_numa_cpu_prepare(unsigned int cpu)
 
 static int ppc_numa_cpu_dead(unsigned int cpu)
 {
-#ifdef CONFIG_HOTPLUG_CPU
-	unmap_cpu_from_node(cpu);
-#endif
 	return 0;
 }
 
@@ -685,7 +884,7 @@ static int __init numa_setup_drmem_lmb(struct drmem_lmb *lmb,
 			size = read_n_cells(n_mem_size_cells, usm);
 		}
 
-		nid = of_drconf_to_nid_single(lmb);
+		nid = get_nid_and_numa_distance(lmb);
 		fake_numa_create_new_node(((base + size) >> PAGE_SHIFT),
 					  &nid);
 		node_set_online(nid);
@@ -702,24 +901,31 @@ static int __init parse_numa_properties(void)
 	struct device_node *memory;
 	int default_nid = 0;
 	unsigned long i;
+	const __be32 *associativity;
 
 	if (numa_enabled == 0) {
-		printk(KERN_WARNING "NUMA disabled by user\n");
+		pr_warn("disabled by user\n");
 		return -1;
 	}
 
-	min_common_depth = find_min_common_depth();
+	primary_domain_index = find_primary_domain_index();
 
-	if (min_common_depth < 0) {
+	if (primary_domain_index < 0) {
 		/*
-		 * if we fail to parse min_common_depth from device tree
+		 * if we fail to parse primary_domain_index from device tree
 		 * mark the numa disabled, boot with numa disabled.
 		 */
 		numa_enabled = false;
-		return min_common_depth;
+		return primary_domain_index;
 	}
 
-	dbg("NUMA associativity depth for CPU/Memory: %d\n", min_common_depth);
+	pr_debug("associativity depth for CPU/Memory: %d\n", primary_domain_index);
+
+	/*
+	 * If it is FORM2 initialize the distance table here.
+	 */
+	if (affinity_form == FORM2_AFFINITY)
+		initialize_form2_numa_distance_lookup_table();
 
 	/*
 	 * Even though we connect cpus to numa domains later in SMP
@@ -727,18 +933,30 @@ static int __init parse_numa_properties(void)
 	 * each node to be onlined must have NODE_DATA etc backing it.
 	 */
 	for_each_present_cpu(i) {
+		__be32 vphn_assoc[VPHN_ASSOC_BUFSIZE];
 		struct device_node *cpu;
-		int nid = vphn_get_nid(i);
+		int nid = NUMA_NO_NODE;
 
-		/*
-		 * Don't fall back to default_nid yet -- we will plug
-		 * cpus into nodes once the memory scan has discovered
-		 * the topology.
-		 */
-		if (nid == NUMA_NO_NODE) {
+		memset(vphn_assoc, 0, VPHN_ASSOC_BUFSIZE * sizeof(__be32));
+
+		if (__vphn_get_associativity(i, vphn_assoc) == 0) {
+			nid = associativity_to_nid(vphn_assoc);
+			initialize_form1_numa_distance(vphn_assoc);
+		} else {
+
+			/*
+			 * Don't fall back to default_nid yet -- we will plug
+			 * cpus into nodes once the memory scan has discovered
+			 * the topology.
+			 */
 			cpu = of_get_cpu_node(i, NULL);
 			BUG_ON(!cpu);
-			nid = of_node_to_nid_single(cpu);
+
+			associativity = of_get_associativity(cpu);
+			if (associativity) {
+				nid = associativity_to_nid(associativity);
+				initialize_form1_numa_distance(associativity);
+			}
 			of_node_put(cpu);
 		}
 
@@ -774,8 +992,11 @@ new_range:
 		 * have associativity properties.  If none, then
 		 * everything goes to default_nid.
 		 */
-		nid = of_node_to_nid_single(memory);
-		if (nid < 0)
+		associativity = of_get_associativity(memory);
+		if (associativity) {
+			nid = associativity_to_nid(associativity);
+			initialize_form1_numa_distance(associativity);
+		} else
 			nid = default_nid;
 
 		fake_numa_create_new_node(((start + size) >> PAGE_SHIFT), &nid);
@@ -811,10 +1032,8 @@ static void __init setup_nonnuma(void)
 	unsigned int nid = 0;
 	int i;
 
-	printk(KERN_DEBUG "Top of RAM: 0x%lx, Total RAM: 0x%lx\n",
-	       top_of_ram, total_ram);
-	printk(KERN_DEBUG "Memory hole size: %ldMB\n",
-	       (top_of_ram - total_ram) >> 20);
+	pr_debug("Top of RAM: 0x%lx, Total RAM: 0x%lx\n", top_of_ram, total_ram);
+	pr_debug("Memory hole size: %ldMB\n", (top_of_ram - total_ram) >> 20);
 
 	for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn, NULL) {
 		fake_numa_create_new_node(end_pfn, &nid);
@@ -893,7 +1112,7 @@ static void __init setup_node_data(int nid, u64 start_pfn, u64 end_pfn)
 static void __init find_possible_nodes(void)
 {
 	struct device_node *rtas;
-	const __be32 *domains;
+	const __be32 *domains = NULL;
 	int prop_length, max_nodes;
 	u32 i;
 
@@ -909,9 +1128,14 @@ static void __init find_possible_nodes(void)
 	 * it doesn't exist, then fallback on ibm,max-associativity-domains.
 	 * Current denotes what the platform can support compared to max
 	 * which denotes what the Hypervisor can support.
+	 *
+	 * If the LPAR is migratable, new nodes might be activated after a LPM,
+	 * so we should consider the max number in that case.
 	 */
-	domains = of_get_property(rtas, "ibm,current-associativity-domains",
-					&prop_length);
+	if (!of_get_property(of_root, "ibm,migratable-partition", NULL))
+		domains = of_get_property(rtas,
+					  "ibm,current-associativity-domains",
+					  &prop_length);
 	if (!domains) {
 		domains = of_get_property(rtas, "ibm,max-associativity-domains",
 					&prop_length);
@@ -919,14 +1143,16 @@ static void __init find_possible_nodes(void)
 			goto out;
 	}
 
-	max_nodes = of_read_number(&domains[min_common_depth], 1);
+	max_nodes = of_read_number(&domains[primary_domain_index], 1);
+	pr_info("Partition configured for %d NUMA nodes.\n", max_nodes);
+
 	for (i = 0; i < max_nodes; i++) {
 		if (!node_possible(i))
 			node_set(i, node_possible_map);
 	}
 
 	prop_length /= sizeof(int);
-	if (prop_length > min_common_depth + 2)
+	if (prop_length > primary_domain_index + 2)
 		coregroup_enabled = 1;
 
 out:
@@ -1014,9 +1240,6 @@ static int __init early_numa(char *p)
 	if (strstr(p, "off"))
 		numa_enabled = 0;
 
-	if (strstr(p, "debug"))
-		numa_debug = 1;
-
 	p = strstr(p, "fake=");
 	if (p)
 		cmdline = p + strlen("fake=");
@@ -1179,7 +1402,7 @@ static long vphn_get_associativity(unsigned long cpu,
 
 	switch (rc) {
 	case H_SUCCESS:
-		dbg("VPHN hcall succeeded. Reset polling...\n");
+		pr_debug("VPHN hcall succeeded. Reset polling...\n");
 		goto out;
 
 	case H_FUNCTION:
@@ -1259,7 +1482,7 @@ int cpu_to_coregroup_id(int cpu)
 		goto out;
 
 	index = of_read_number(associativity, 1);
-	if (index > min_common_depth + 1)
+	if (index > primary_domain_index + 1)
 		return of_read_number(&associativity[index - 1], 1);
 
 out:
diff --git a/arch/powerpc/mm/ptdump/8xx.c b/arch/powerpc/mm/ptdump/8xx.c
index 86da2a669680..fac932eb8f9a 100644
--- a/arch/powerpc/mm/ptdump/8xx.c
+++ b/arch/powerpc/mm/ptdump/8xx.c
@@ -75,8 +75,10 @@ static const struct flag_info flag_array[] = {
 };
 
 struct pgtable_level pg_level[5] = {
-	{
-	}, { /* pgd */
+	{ /* pgd */
+		.flag	= flag_array,
+		.num	= ARRAY_SIZE(flag_array),
+	}, { /* p4d */
 		.flag	= flag_array,
 		.num	= ARRAY_SIZE(flag_array),
 	}, { /* pud */
diff --git a/arch/powerpc/mm/ptdump/Makefile b/arch/powerpc/mm/ptdump/Makefile
index 712762be3cb1..4050cbb55acf 100644
--- a/arch/powerpc/mm/ptdump/Makefile
+++ b/arch/powerpc/mm/ptdump/Makefile
@@ -5,5 +5,10 @@ obj-y	+= ptdump.o
 obj-$(CONFIG_4xx)		+= shared.o
 obj-$(CONFIG_PPC_8xx)		+= 8xx.o
 obj-$(CONFIG_PPC_BOOK3E_MMU)	+= shared.o
-obj-$(CONFIG_PPC_BOOK3S_32)	+= shared.o bats.o segment_regs.o
-obj-$(CONFIG_PPC_BOOK3S_64)	+= book3s64.o hashpagetable.o
+obj-$(CONFIG_PPC_BOOK3S_32)	+= shared.o
+obj-$(CONFIG_PPC_BOOK3S_64)	+= book3s64.o
+
+ifdef CONFIG_PTDUMP_DEBUGFS
+obj-$(CONFIG_PPC_BOOK3S_32)	+= bats.o segment_regs.o
+obj-$(CONFIG_PPC_BOOK3S_64)	+= hashpagetable.o
+endif
diff --git a/arch/powerpc/mm/ptdump/bats.c b/arch/powerpc/mm/ptdump/bats.c
index c4c628b03cf8..820c119013e4 100644
--- a/arch/powerpc/mm/ptdump/bats.c
+++ b/arch/powerpc/mm/ptdump/bats.c
@@ -7,7 +7,7 @@
  */
 
 #include <linux/pgtable.h>
-#include <asm/debugfs.h>
+#include <linux/debugfs.h>
 #include <asm/cpu_has_feature.h>
 
 #include "ptdump.h"
@@ -57,7 +57,7 @@ static void bat_show_603(struct seq_file *m, int idx, u32 lower, u32 upper, bool
 
 #define BAT_SHOW_603(_m, _n, _l, _u, _d) bat_show_603(_m, _n, mfspr(_l), mfspr(_u), _d)
 
-static int bats_show_603(struct seq_file *m, void *v)
+static int bats_show(struct seq_file *m, void *v)
 {
 	seq_puts(m, "---[ Instruction Block Address Translation ]---\n");
 
@@ -88,22 +88,12 @@ static int bats_show_603(struct seq_file *m, void *v)
 	return 0;
 }
 
-static int bats_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, bats_show_603, NULL);
-}
-
-static const struct file_operations bats_fops = {
-	.open		= bats_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
+DEFINE_SHOW_ATTRIBUTE(bats);
 
 static int __init bats_init(void)
 {
 	debugfs_create_file("block_address_translation", 0400,
-			    powerpc_debugfs_root, NULL, &bats_fops);
+			    arch_debugfs_dir, NULL, &bats_fops);
 	return 0;
 }
 device_initcall(bats_init);
diff --git a/arch/powerpc/mm/ptdump/book3s64.c b/arch/powerpc/mm/ptdump/book3s64.c
index 14f73868db66..5ad92d9dc5d1 100644
--- a/arch/powerpc/mm/ptdump/book3s64.c
+++ b/arch/powerpc/mm/ptdump/book3s64.c
@@ -103,8 +103,10 @@ static const struct flag_info flag_array[] = {
 };
 
 struct pgtable_level pg_level[5] = {
-	{
-	}, { /* pgd */
+	{ /* pgd */
+		.flag	= flag_array,
+		.num	= ARRAY_SIZE(flag_array),
+	}, { /* p4d */
 		.flag	= flag_array,
 		.num	= ARRAY_SIZE(flag_array),
 	}, { /* pud */
diff --git a/arch/powerpc/mm/ptdump/hashpagetable.c b/arch/powerpc/mm/ptdump/hashpagetable.c
index ad6df9a2e7c8..c7f824d294b2 100644
--- a/arch/powerpc/mm/ptdump/hashpagetable.c
+++ b/arch/powerpc/mm/ptdump/hashpagetable.c
@@ -526,17 +526,7 @@ static int ptdump_show(struct seq_file *m, void *v)
 	return 0;
 }
 
-static int ptdump_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, ptdump_show, NULL);
-}
-
-static const struct file_operations ptdump_fops = {
-	.open		= ptdump_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
+DEFINE_SHOW_ATTRIBUTE(ptdump);
 
 static int ptdump_init(void)
 {
diff --git a/arch/powerpc/mm/ptdump/ptdump.c b/arch/powerpc/mm/ptdump/ptdump.c
index 5062c58b1e5b..bf251191e78d 100644
--- a/arch/powerpc/mm/ptdump/ptdump.c
+++ b/arch/powerpc/mm/ptdump/ptdump.c
@@ -16,6 +16,7 @@
 #include <linux/io.h>
 #include <linux/mm.h>
 #include <linux/highmem.h>
+#include <linux/ptdump.h>
 #include <linux/sched.h>
 #include <linux/seq_file.h>
 #include <asm/fixmap.h>
@@ -54,11 +55,12 @@
  *
  */
 struct pg_state {
+	struct ptdump_state ptdump;
 	struct seq_file *seq;
 	const struct addr_marker *marker;
 	unsigned long start_address;
 	unsigned long start_pa;
-	unsigned int level;
+	int level;
 	u64 current_flags;
 	bool check_wx;
 	unsigned long wx_pages;
@@ -102,6 +104,11 @@ static struct addr_marker address_markers[] = {
 	{ -1,	NULL },
 };
 
+static struct ptdump_range ptdump_range[] __ro_after_init = {
+	{TASK_SIZE_MAX, ~0UL},
+	{0, 0}
+};
+
 #define pt_dump_seq_printf(m, fmt, args...)	\
 ({						\
 	if (m)					\
@@ -188,10 +195,9 @@ static void note_prot_wx(struct pg_state *st, unsigned long addr)
 	st->wx_pages += (addr - st->start_address) / PAGE_SIZE;
 }
 
-static void note_page_update_state(struct pg_state *st, unsigned long addr,
-				   unsigned int level, u64 val, unsigned long page_size)
+static void note_page_update_state(struct pg_state *st, unsigned long addr, int level, u64 val)
 {
-	u64 flag = val & pg_level[level].mask;
+	u64 flag = level >= 0 ? val & pg_level[level].mask : 0;
 	u64 pa = val & PTE_RPN_MASK;
 
 	st->level = level;
@@ -205,15 +211,15 @@ static void note_page_update_state(struct pg_state *st, unsigned long addr,
 	}
 }
 
-static void note_page(struct pg_state *st, unsigned long addr,
-	       unsigned int level, u64 val, unsigned long page_size)
+static void note_page(struct ptdump_state *pt_st, unsigned long addr, int level, u64 val)
 {
-	u64 flag = val & pg_level[level].mask;
+	u64 flag = level >= 0 ? val & pg_level[level].mask : 0;
+	struct pg_state *st = container_of(pt_st, struct pg_state, ptdump);
 
 	/* At first no level is set */
-	if (!st->level) {
+	if (st->level == -1) {
 		pt_dump_seq_printf(st->seq, "---[ %s ]---\n", st->marker->name);
-		note_page_update_state(st, addr, level, val, page_size);
+		note_page_update_state(st, addr, level, val);
 	/*
 	 * Dump the section of virtual memory when:
 	 *   - the PTE flags from one entry to the next differs.
@@ -242,95 +248,7 @@ static void note_page(struct pg_state *st, unsigned long addr,
 		 * Address indicates we have passed the end of the
 		 * current section of virtual memory
 		 */
-		note_page_update_state(st, addr, level, val, page_size);
-	}
-}
-
-static void walk_pte(struct pg_state *st, pmd_t *pmd, unsigned long start)
-{
-	pte_t *pte = pte_offset_kernel(pmd, 0);
-	unsigned long addr;
-	unsigned int i;
-
-	for (i = 0; i < PTRS_PER_PTE; i++, pte++) {
-		addr = start + i * PAGE_SIZE;
-		note_page(st, addr, 4, pte_val(*pte), PAGE_SIZE);
-
-	}
-}
-
-static void walk_hugepd(struct pg_state *st, hugepd_t *phpd, unsigned long start,
-			int pdshift, int level)
-{
-#ifdef CONFIG_ARCH_HAS_HUGEPD
-	unsigned int i;
-	int shift = hugepd_shift(*phpd);
-	int ptrs_per_hpd = pdshift - shift > 0 ? 1 << (pdshift - shift) : 1;
-
-	if (start & ((1 << shift) - 1))
-		return;
-
-	for (i = 0; i < ptrs_per_hpd; i++) {
-		unsigned long addr = start + (i << shift);
-		pte_t *pte = hugepte_offset(*phpd, addr, pdshift);
-
-		note_page(st, addr, level + 1, pte_val(*pte), 1 << shift);
-	}
-#endif
-}
-
-static void walk_pmd(struct pg_state *st, pud_t *pud, unsigned long start)
-{
-	pmd_t *pmd = pmd_offset(pud, 0);
-	unsigned long addr;
-	unsigned int i;
-
-	for (i = 0; i < PTRS_PER_PMD; i++, pmd++) {
-		addr = start + i * PMD_SIZE;
-		if (!pmd_none(*pmd) && !pmd_is_leaf(*pmd))
-			/* pmd exists */
-			walk_pte(st, pmd, addr);
-		else
-			note_page(st, addr, 3, pmd_val(*pmd), PMD_SIZE);
-	}
-}
-
-static void walk_pud(struct pg_state *st, p4d_t *p4d, unsigned long start)
-{
-	pud_t *pud = pud_offset(p4d, 0);
-	unsigned long addr;
-	unsigned int i;
-
-	for (i = 0; i < PTRS_PER_PUD; i++, pud++) {
-		addr = start + i * PUD_SIZE;
-		if (!pud_none(*pud) && !pud_is_leaf(*pud))
-			/* pud exists */
-			walk_pmd(st, pud, addr);
-		else
-			note_page(st, addr, 2, pud_val(*pud), PUD_SIZE);
-	}
-}
-
-static void walk_pagetables(struct pg_state *st)
-{
-	unsigned int i;
-	unsigned long addr = st->start_address & PGDIR_MASK;
-	pgd_t *pgd = pgd_offset_k(addr);
-
-	/*
-	 * Traverse the linux pagetable structure and dump pages that are in
-	 * the hash pagetable.
-	 */
-	for (i = pgd_index(addr); i < PTRS_PER_PGD; i++, pgd++, addr += PGDIR_SIZE) {
-		p4d_t *p4d = p4d_offset(pgd, 0);
-
-		if (p4d_none(*p4d) || p4d_is_leaf(*p4d))
-			note_page(st, addr, 1, p4d_val(*p4d), PGDIR_SIZE);
-		else if (is_hugepd(__hugepd(p4d_val(*p4d))))
-			walk_hugepd(st, (hugepd_t *)p4d, addr, PGDIR_SHIFT, 1);
-		else
-			/* p4d exists */
-			walk_pud(st, p4d, addr);
+		note_page_update_state(st, addr, level, val);
 	}
 }
 
@@ -383,32 +301,19 @@ static int ptdump_show(struct seq_file *m, void *v)
 	struct pg_state st = {
 		.seq = m,
 		.marker = address_markers,
-		.start_address = IS_ENABLED(CONFIG_PPC64) ? PAGE_OFFSET : TASK_SIZE,
+		.level = -1,
+		.ptdump = {
+			.note_page = note_page,
+			.range = ptdump_range,
+		}
 	};
 
-#ifdef CONFIG_PPC64
-	if (!radix_enabled())
-		st.start_address = KERN_VIRT_START;
-#endif
-
 	/* Traverse kernel page tables */
-	walk_pagetables(&st);
-	note_page(&st, 0, 0, 0, 0);
+	ptdump_walk_pgd(&st.ptdump, &init_mm, NULL);
 	return 0;
 }
 
-
-static int ptdump_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, ptdump_show, NULL);
-}
-
-static const struct file_operations ptdump_fops = {
-	.open		= ptdump_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
+DEFINE_SHOW_ATTRIBUTE(ptdump);
 
 static void build_pgtable_complete_mask(void)
 {
@@ -420,22 +325,24 @@ static void build_pgtable_complete_mask(void)
 				pg_level[i].mask |= pg_level[i].flag[j].mask;
 }
 
-#ifdef CONFIG_PPC_DEBUG_WX
+#ifdef CONFIG_DEBUG_WX
 void ptdump_check_wx(void)
 {
 	struct pg_state st = {
 		.seq = NULL,
-		.marker = address_markers,
+		.marker = (struct addr_marker[]) {
+			{ 0, NULL},
+			{ -1, NULL},
+		},
+		.level = -1,
 		.check_wx = true,
-		.start_address = IS_ENABLED(CONFIG_PPC64) ? PAGE_OFFSET : TASK_SIZE,
+		.ptdump = {
+			.note_page = note_page,
+			.range = ptdump_range,
+		}
 	};
 
-#ifdef CONFIG_PPC64
-	if (!radix_enabled())
-		st.start_address = KERN_VIRT_START;
-#endif
-
-	walk_pagetables(&st);
+	ptdump_walk_pgd(&st.ptdump, &init_mm, NULL);
 
 	if (st.wx_pages)
 		pr_warn("Checked W+X mappings: FAILED, %lu W+X pages found\n",
@@ -445,12 +352,23 @@ void ptdump_check_wx(void)
 }
 #endif
 
-static int ptdump_init(void)
+static int __init ptdump_init(void)
 {
+#ifdef CONFIG_PPC64
+	if (!radix_enabled())
+		ptdump_range[0].start = KERN_VIRT_START;
+	else
+		ptdump_range[0].start = PAGE_OFFSET;
+
+	ptdump_range[0].end = PAGE_OFFSET + (PGDIR_SIZE * PTRS_PER_PGD);
+#endif
+
 	populate_markers();
 	build_pgtable_complete_mask();
-	debugfs_create_file("kernel_page_tables", 0400, NULL, NULL,
-			    &ptdump_fops);
+
+	if (IS_ENABLED(CONFIG_PTDUMP_DEBUGFS))
+		debugfs_create_file("kernel_page_tables", 0400, NULL, NULL, &ptdump_fops);
+
 	return 0;
 }
 device_initcall(ptdump_init);
diff --git a/arch/powerpc/mm/ptdump/segment_regs.c b/arch/powerpc/mm/ptdump/segment_regs.c
index 565048a0c9be..9df3af8d481f 100644
--- a/arch/powerpc/mm/ptdump/segment_regs.c
+++ b/arch/powerpc/mm/ptdump/segment_regs.c
@@ -6,7 +6,7 @@
  * This dumps the content of Segment Registers
  */
 
-#include <asm/debugfs.h>
+#include <linux/debugfs.h>
 
 static void seg_show(struct seq_file *m, int i)
 {
@@ -41,21 +41,11 @@ static int sr_show(struct seq_file *m, void *v)
 	return 0;
 }
 
-static int sr_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, sr_show, NULL);
-}
-
-static const struct file_operations sr_fops = {
-	.open		= sr_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
+DEFINE_SHOW_ATTRIBUTE(sr);
 
 static int __init sr_init(void)
 {
-	debugfs_create_file("segment_registers", 0400, powerpc_debugfs_root,
+	debugfs_create_file("segment_registers", 0400, arch_debugfs_dir,
 			    NULL, &sr_fops);
 	return 0;
 }
diff --git a/arch/powerpc/mm/ptdump/shared.c b/arch/powerpc/mm/ptdump/shared.c
index c005fe041c18..03607ab90c66 100644
--- a/arch/powerpc/mm/ptdump/shared.c
+++ b/arch/powerpc/mm/ptdump/shared.c
@@ -68,8 +68,10 @@ static const struct flag_info flag_array[] = {
 };
 
 struct pgtable_level pg_level[5] = {
-	{
-	}, { /* pgd */
+	{ /* pgd */
+		.flag	= flag_array,
+		.num	= ARRAY_SIZE(flag_array),
+	}, { /* p4d */
 		.flag	= flag_array,
 		.num	= ARRAY_SIZE(flag_array),
 	}, { /* pud */