Merge branch 'akpm' (patches from Andrew)

Merge more updates from Andrew Morton:
 "The rest of MM and the rest of everything else: hotfixes, ipc, misc,
  procfs, lib, cleanups, arm"

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (67 commits)
  ARM: dma-api: fix max_pfn off-by-one error in __dma_supported()
  treewide: remove redundant IS_ERR() before error code check
  include/linux/cpumask.h: don't calculate length of the input string
  lib: new testcases for bitmap_parse{_user}
  lib: rework bitmap_parse()
  lib: make bitmap_parse_user a wrapper on bitmap_parse
  lib: add test for bitmap_parse()
  bitops: more BITS_TO_* macros
  lib/string: add strnchrnul()
  proc: convert everything to "struct proc_ops"
  proc: decouple proc from VFS with "struct proc_ops"
  asm-generic/tlb: provide MMU_GATHER_TABLE_FREE
  asm-generic/tlb: rename HAVE_MMU_GATHER_NO_GATHER
  asm-generic/tlb: rename HAVE_MMU_GATHER_PAGE_SIZE
  asm-generic/tlb: rename HAVE_RCU_TABLE_FREE
  asm-generic/tlb: add missing CONFIG symbol
  asm-gemeric/tlb: remove stray function declarations
  asm-generic/tlb: avoid potential double flush
  mm/mmu_gather: invalidate TLB correctly on batch allocation failure and flush
  powerpc/mmu_gather: enable RCU_TABLE_FREE even for !SMP case
  ...

15 files changed, 514 insertions, 252 deletions

diff --git a/mm/Kconfig.debug b/mm/Kconfig.debug
index 327b3ebf23bf..0271b22e063f 100644
--- a/mm/Kconfig.debug
+++ b/mm/Kconfig.debug
@@ -117,3 +117,24 @@ config DEBUG_RODATA_TEST
     depends on STRICT_KERNEL_RWX
     ---help---
       This option enables a testcase for the setting rodata read-only.
+
+config GENERIC_PTDUMP
+	bool
+
+config PTDUMP_CORE
+	bool
+
+config PTDUMP_DEBUGFS
+	bool "Export kernel pagetable layout to userspace via debugfs"
+	depends on DEBUG_KERNEL
+	depends on DEBUG_FS
+	depends on GENERIC_PTDUMP
+	select PTDUMP_CORE
+	help
+	  Say Y here if you want to show the kernel pagetable 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.
diff --git a/mm/Makefile b/mm/Makefile
index 32f08e22e824..272e66039e70 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -109,3 +109,4 @@ obj-$(CONFIG_ZONE_DEVICE) += memremap.o
 obj-$(CONFIG_HMM_MIRROR) += hmm.o
 obj-$(CONFIG_MEMFD_CREATE) += memfd.o
 obj-$(CONFIG_MAPPING_DIRTY_HELPERS) += mapping_dirty_helpers.o
+obj-$(CONFIG_PTDUMP_CORE) += ptdump.o
diff --git a/mm/gup.c b/mm/gup.c
index e13f4d211475..1b521e0ac1de 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -1792,7 +1792,7 @@ EXPORT_SYMBOL(get_user_pages_unlocked);
  * Before activating this code, please be aware that the following assumptions
  * are currently made:
  *
- *  *) Either HAVE_RCU_TABLE_FREE is enabled, and tlb_remove_table() is used to
+ *  *) Either MMU_GATHER_RCU_TABLE_FREE is enabled, and tlb_remove_table() is used to
  *  free pages containing page tables or TLB flushing requires IPI broadcast.
  *
  *  *) ptes can be read atomically by the architecture.
diff --git a/mm/hmm.c b/mm/hmm.c
index d379cb6496ae..72e5a6d9a417 100644
--- a/mm/hmm.c
+++ b/mm/hmm.c
@@ -186,7 +186,7 @@ static void hmm_range_need_fault(const struct hmm_vma_walk *hmm_vma_walk,
 }
 
 static int hmm_vma_walk_hole(unsigned long addr, unsigned long end,
-			     struct mm_walk *walk)
+			     __always_unused int depth, struct mm_walk *walk)
 {
 	struct hmm_vma_walk *hmm_vma_walk = walk->private;
 	struct hmm_range *range = hmm_vma_walk->range;
@@ -380,7 +380,7 @@ static int hmm_vma_walk_pmd(pmd_t *pmdp,
 again:
 	pmd = READ_ONCE(*pmdp);
 	if (pmd_none(pmd))
-		return hmm_vma_walk_hole(start, end, walk);
+		return hmm_vma_walk_hole(start, end, -1, walk);
 
 	if (thp_migration_supported() && is_pmd_migration_entry(pmd)) {
 		bool fault, write_fault;
@@ -474,23 +474,32 @@ static int hmm_vma_walk_pud(pud_t *pudp, unsigned long start, unsigned long end,
 {
 	struct hmm_vma_walk *hmm_vma_walk = walk->private;
 	struct hmm_range *range = hmm_vma_walk->range;
-	unsigned long addr = start, next;
-	pmd_t *pmdp;
+	unsigned long addr = start;
 	pud_t pud;
-	int ret;
+	int ret = 0;
+	spinlock_t *ptl = pud_trans_huge_lock(pudp, walk->vma);
+
+	if (!ptl)
+		return 0;
+
+	/* Normally we don't want to split the huge page */
+	walk->action = ACTION_CONTINUE;
 
-again:
 	pud = READ_ONCE(*pudp);
-	if (pud_none(pud))
-		return hmm_vma_walk_hole(start, end, walk);
+	if (pud_none(pud)) {
+		ret = hmm_vma_walk_hole(start, end, -1, walk);
+		goto out_unlock;
+	}
 
 	if (pud_huge(pud) && pud_devmap(pud)) {
 		unsigned long i, npages, pfn;
 		uint64_t *pfns, cpu_flags;
 		bool fault, write_fault;
 
-		if (!pud_present(pud))
-			return hmm_vma_walk_hole(start, end, walk);
+		if (!pud_present(pud)) {
+			ret = hmm_vma_walk_hole(start, end, -1, walk);
+			goto out_unlock;
+		}
 
 		i = (addr - range->start) >> PAGE_SHIFT;
 		npages = (end - addr) >> PAGE_SHIFT;
@@ -499,16 +508,20 @@ again:
 		cpu_flags = pud_to_hmm_pfn_flags(range, pud);
 		hmm_range_need_fault(hmm_vma_walk, pfns, npages,
 				     cpu_flags, &fault, &write_fault);
-		if (fault || write_fault)
-			return hmm_vma_walk_hole_(addr, end, fault,
-						write_fault, walk);
+		if (fault || write_fault) {
+			ret = hmm_vma_walk_hole_(addr, end, fault,
+						 write_fault, walk);
+			goto out_unlock;
+		}
 
 		pfn = pud_pfn(pud) + ((addr & ~PUD_MASK) >> PAGE_SHIFT);
 		for (i = 0; i < npages; ++i, ++pfn) {
 			hmm_vma_walk->pgmap = get_dev_pagemap(pfn,
 					      hmm_vma_walk->pgmap);
-			if (unlikely(!hmm_vma_walk->pgmap))
-				return -EBUSY;
+			if (unlikely(!hmm_vma_walk->pgmap)) {
+				ret = -EBUSY;
+				goto out_unlock;
+			}
 			pfns[i] = hmm_device_entry_from_pfn(range, pfn) |
 				  cpu_flags;
 		}
@@ -517,22 +530,15 @@ again:
 			hmm_vma_walk->pgmap = NULL;
 		}
 		hmm_vma_walk->last = end;
-		return 0;
+		goto out_unlock;
 	}
 
-	split_huge_pud(walk->vma, pudp, addr);
-	if (pud_none(*pudp))
-		goto again;
+	/* Ask for the PUD to be split */
+	walk->action = ACTION_SUBTREE;
 
-	pmdp = pmd_offset(pudp, addr);
-	do {
-		next = pmd_addr_end(addr, end);
-		ret = hmm_vma_walk_pmd(pmdp, addr, next, walk);
-		if (ret)
-			return ret;
-	} while (pmdp++, addr = next, addr != end);
-
-	return 0;
+out_unlock:
+	spin_unlock(ptl);
+	return ret;
 }
 #else
 #define hmm_vma_walk_pud	NULL
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 36d80915ddc2..0a54ffac8c68 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -355,7 +355,7 @@ static unsigned long find_smallest_section_pfn(int nid, struct zone *zone,
 		if (unlikely(pfn_to_nid(start_pfn) != nid))
 			continue;
 
-		if (zone && zone != page_zone(pfn_to_page(start_pfn)))
+		if (zone != page_zone(pfn_to_page(start_pfn)))
 			continue;
 
 		return start_pfn;
@@ -380,7 +380,7 @@ static unsigned long find_biggest_section_pfn(int nid, struct zone *zone,
 		if (unlikely(pfn_to_nid(pfn) != nid))
 			continue;
 
-		if (zone && zone != page_zone(pfn_to_page(pfn)))
+		if (zone != page_zone(pfn_to_page(pfn)))
 			continue;
 
 		return pfn;
@@ -392,14 +392,11 @@ static unsigned long find_biggest_section_pfn(int nid, struct zone *zone,
 static void shrink_zone_span(struct zone *zone, unsigned long start_pfn,
 			     unsigned long end_pfn)
 {
-	unsigned long zone_start_pfn = zone->zone_start_pfn;
-	unsigned long z = zone_end_pfn(zone); /* zone_end_pfn namespace clash */
-	unsigned long zone_end_pfn = z;
 	unsigned long pfn;
 	int nid = zone_to_nid(zone);
 
 	zone_span_writelock(zone);
-	if (zone_start_pfn == start_pfn) {
+	if (zone->zone_start_pfn == start_pfn) {
 		/*
 		 * If the section is smallest section in the zone, it need
 		 * shrink zone->zone_start_pfn and zone->zone_spanned_pages.
@@ -407,50 +404,30 @@ static void shrink_zone_span(struct zone *zone, unsigned long start_pfn,
 		 * for shrinking zone.
 		 */
 		pfn = find_smallest_section_pfn(nid, zone, end_pfn,
-						zone_end_pfn);
+						zone_end_pfn(zone));
 		if (pfn) {
+			zone->spanned_pages = zone_end_pfn(zone) - pfn;
 			zone->zone_start_pfn = pfn;
-			zone->spanned_pages = zone_end_pfn - pfn;
+		} else {
+			zone->zone_start_pfn = 0;
+			zone->spanned_pages = 0;
 		}
-	} else if (zone_end_pfn == end_pfn) {
+	} else if (zone_end_pfn(zone) == end_pfn) {
 		/*
 		 * If the section is biggest section in the zone, it need
 		 * shrink zone->spanned_pages.
 		 * In this case, we find second biggest valid mem_section for
 		 * shrinking zone.
 		 */
-		pfn = find_biggest_section_pfn(nid, zone, zone_start_pfn,
+		pfn = find_biggest_section_pfn(nid, zone, zone->zone_start_pfn,
 					       start_pfn);
 		if (pfn)
-			zone->spanned_pages = pfn - zone_start_pfn + 1;
-	}
-
-	/*
-	 * The section is not biggest or smallest mem_section in the zone, it
-	 * only creates a hole in the zone. So in this case, we need not
-	 * change the zone. But perhaps, the zone has only hole data. Thus
-	 * it check the zone has only hole or not.
-	 */
-	pfn = zone_start_pfn;
-	for (; pfn < zone_end_pfn; pfn += PAGES_PER_SUBSECTION) {
-		if (unlikely(!pfn_to_online_page(pfn)))
-			continue;
-
-		if (page_zone(pfn_to_page(pfn)) != zone)
-			continue;
-
-		/* Skip range to be removed */
-		if (pfn >= start_pfn && pfn < end_pfn)
-			continue;
-
-		/* If we find valid section, we have nothing to do */
-		zone_span_writeunlock(zone);
-		return;
+			zone->spanned_pages = pfn - zone->zone_start_pfn + 1;
+		else {
+			zone->zone_start_pfn = 0;
+			zone->spanned_pages = 0;
+		}
 	}
-
-	/* The zone has no valid section */
-	zone->zone_start_pfn = 0;
-	zone->spanned_pages = 0;
 	zone_span_writeunlock(zone);
 }
 
@@ -490,6 +467,9 @@ void __ref remove_pfn_range_from_zone(struct zone *zone,
 	struct pglist_data *pgdat = zone->zone_pgdat;
 	unsigned long flags;
 
+	/* Poison struct pages because they are now uninitialized again. */
+	page_init_poison(pfn_to_page(start_pfn), sizeof(struct page) * nr_pages);
+
 #ifdef CONFIG_ZONE_DEVICE
 	/*
 	 * Zone shrinking code cannot properly deal with ZONE_DEVICE. So
@@ -536,25 +516,20 @@ static void __remove_section(unsigned long pfn, unsigned long nr_pages,
 void __remove_pages(unsigned long pfn, unsigned long nr_pages,
 		    struct vmem_altmap *altmap)
 {
+	const unsigned long end_pfn = pfn + nr_pages;
+	unsigned long cur_nr_pages;
 	unsigned long map_offset = 0;
-	unsigned long nr, start_sec, end_sec;
 
 	map_offset = vmem_altmap_offset(altmap);
 
 	if (check_pfn_span(pfn, nr_pages, "remove"))
 		return;
 
-	start_sec = pfn_to_section_nr(pfn);
-	end_sec = pfn_to_section_nr(pfn + nr_pages - 1);
-	for (nr = start_sec; nr <= end_sec; nr++) {
-		unsigned long pfns;
-
+	for (; pfn < end_pfn; pfn += cur_nr_pages) {
 		cond_resched();
-		pfns = min(nr_pages, PAGES_PER_SECTION
-				- (pfn & ~PAGE_SECTION_MASK));
-		__remove_section(pfn, pfns, map_offset, altmap);
-		pfn += pfns;
-		nr_pages -= pfns;
+		/* Select all remaining pages up to the next section boundary */
+		cur_nr_pages = min(end_pfn - pfn, -(pfn | PAGE_SECTION_MASK));
+		__remove_section(pfn, cur_nr_pages, map_offset, altmap);
 		map_offset = 0;
 	}
 }
@@ -1197,14 +1172,13 @@ bool is_mem_section_removable(unsigned long start_pfn, unsigned long nr_pages)
 }
 
 /*
- * Confirm all pages in a range [start, end) belong to the same zone.
- * When true, return its valid [start, end).
+ * Confirm all pages in a range [start, end) belong to the same zone (skipping
+ * memory holes). When true, return the zone.
  */
-int test_pages_in_a_zone(unsigned long start_pfn, unsigned long end_pfn,
-			 unsigned long *valid_start, unsigned long *valid_end)
+struct zone *test_pages_in_a_zone(unsigned long start_pfn,
+				  unsigned long end_pfn)
 {
 	unsigned long pfn, sec_end_pfn;
-	unsigned long start, end;
 	struct zone *zone = NULL;
 	struct page *page;
 	int i;
@@ -1225,24 +1199,15 @@ int test_pages_in_a_zone(unsigned long start_pfn, unsigned long end_pfn,
 				continue;
 			/* Check if we got outside of the zone */
 			if (zone && !zone_spans_pfn(zone, pfn + i))
-				return 0;
+				return NULL;
 			page = pfn_to_page(pfn + i);
 			if (zone && page_zone(page) != zone)
-				return 0;
-			if (!zone)
-				start = pfn + i;
+				return NULL;
 			zone = page_zone(page);
-			end = pfn + MAX_ORDER_NR_PAGES;
 		}
 	}
 
-	if (zone) {
-		*valid_start = start;
-		*valid_end = min(end, end_pfn);
-		return 1;
-	} else {
-		return 0;
-	}
+	return zone;
 }
 
 /*
@@ -1487,7 +1452,6 @@ static int __ref __offline_pages(unsigned long start_pfn,
 	unsigned long offlined_pages = 0;
 	int ret, node, nr_isolate_pageblock;
 	unsigned long flags;
-	unsigned long valid_start, valid_end;
 	struct zone *zone;
 	struct memory_notify arg;
 	char *reason;
@@ -1512,14 +1476,12 @@ static int __ref __offline_pages(unsigned long start_pfn,
 
 	/* This makes hotplug much easier...and readable.
 	   we assume this for now. .*/
-	if (!test_pages_in_a_zone(start_pfn, end_pfn, &valid_start,
-				  &valid_end)) {
+	zone = test_pages_in_a_zone(start_pfn, end_pfn);
+	if (!zone) {
 		ret = -EINVAL;
 		reason = "multizone range";
 		goto failed_removal;
 	}
-
-	zone = page_zone(pfn_to_page(valid_start));
 	node = zone_to_nid(zone);
 
 	/* set above range as isolated */
diff --git a/mm/memremap.c b/mm/memremap.c
index 4c723d2049d5..09b5b7adc773 100644
--- a/mm/memremap.c
+++ b/mm/memremap.c
@@ -120,6 +120,8 @@ void memunmap_pages(struct dev_pagemap *pgmap)
 	nid = page_to_nid(first_page);
 
 	mem_hotplug_begin();
+	remove_pfn_range_from_zone(page_zone(first_page), PHYS_PFN(res->start),
+				   PHYS_PFN(resource_size(res)));
 	if (pgmap->type == MEMORY_DEVICE_PRIVATE) {
 		__remove_pages(PHYS_PFN(res->start),
 			       PHYS_PFN(resource_size(res)), NULL);
diff --git a/mm/migrate.c b/mm/migrate.c
index edf42ed90030..b1092876e537 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -2151,6 +2151,7 @@ out_unlock:
 #ifdef CONFIG_DEVICE_PRIVATE
 static int migrate_vma_collect_hole(unsigned long start,
 				    unsigned long end,
+				    __always_unused int depth,
 				    struct mm_walk *walk)
 {
 	struct migrate_vma *migrate = walk->private;
@@ -2195,7 +2196,7 @@ static int migrate_vma_collect_pmd(pmd_t *pmdp,
 
 again:
 	if (pmd_none(*pmdp))
-		return migrate_vma_collect_hole(start, end, walk);
+		return migrate_vma_collect_hole(start, end, -1, walk);
 
 	if (pmd_trans_huge(*pmdp)) {
 		struct page *page;
@@ -2228,7 +2229,7 @@ again:
 				return migrate_vma_collect_skip(start, end,
 								walk);
 			if (pmd_none(*pmdp))
-				return migrate_vma_collect_hole(start, end,
+				return migrate_vma_collect_hole(start, end, -1,
 								walk);
 		}
 	}
diff --git a/mm/mincore.c b/mm/mincore.c
index 49b6fa2f6aa1..0e6dd9948f1a 100644
--- a/mm/mincore.c
+++ b/mm/mincore.c
@@ -112,6 +112,7 @@ static int __mincore_unmapped_range(unsigned long addr, unsigned long end,
 }
 
 static int mincore_unmapped_range(unsigned long addr, unsigned long end,
+				   __always_unused int depth,
 				   struct mm_walk *walk)
 {
 	walk->private += __mincore_unmapped_range(addr, end,
diff --git a/mm/mmu_gather.c b/mm/mmu_gather.c
index 7d70e5c78f97..a3538cb2bcbe 100644
--- a/mm/mmu_gather.c
+++ b/mm/mmu_gather.c
@@ -11,7 +11,7 @@
 #include <asm/pgalloc.h>
 #include <asm/tlb.h>
 
-#ifndef CONFIG_HAVE_MMU_GATHER_NO_GATHER
+#ifndef CONFIG_MMU_GATHER_NO_GATHER
 
 static bool tlb_next_batch(struct mmu_gather *tlb)
 {
@@ -69,7 +69,7 @@ bool __tlb_remove_page_size(struct mmu_gather *tlb, struct page *page, int page_
 
 	VM_BUG_ON(!tlb->end);
 
-#ifdef CONFIG_HAVE_MMU_GATHER_PAGE_SIZE
+#ifdef CONFIG_MMU_GATHER_PAGE_SIZE
 	VM_WARN_ON(tlb->page_size != page_size);
 #endif
 
@@ -89,58 +89,108 @@ bool __tlb_remove_page_size(struct mmu_gather *tlb, struct page *page, int page_
 	return false;
 }
 
-#endif /* HAVE_MMU_GATHER_NO_GATHER */
+#endif /* MMU_GATHER_NO_GATHER */
 
-#ifdef CONFIG_HAVE_RCU_TABLE_FREE
+#ifdef CONFIG_MMU_GATHER_TABLE_FREE
 
-/*
- * See the comment near struct mmu_table_batch.
- */
+static void __tlb_remove_table_free(struct mmu_table_batch *batch)
+{
+	int i;
+
+	for (i = 0; i < batch->nr; i++)
+		__tlb_remove_table(batch->tables[i]);
+
+	free_page((unsigned long)batch);
+}
+
+#ifdef CONFIG_MMU_GATHER_RCU_TABLE_FREE
 
 /*
- * If we want tlb_remove_table() to imply TLB invalidates.
+ * Semi RCU freeing of the page directories.
+ *
+ * This is needed by some architectures to implement software pagetable walkers.
+ *
+ * gup_fast() and other software pagetable walkers do a lockless page-table
+ * walk and therefore needs some synchronization with the freeing of the page
+ * directories. The chosen means to accomplish that is by disabling IRQs over
+ * the walk.
+ *
+ * Architectures that use IPIs to flush TLBs will then automagically DTRT,
+ * since we unlink the page, flush TLBs, free the page. Since the disabling of
+ * IRQs delays the completion of the TLB flush we can never observe an already
+ * freed page.
+ *
+ * Architectures that do not have this (PPC) need to delay the freeing by some
+ * other means, this is that means.
+ *
+ * What we do is batch the freed directory pages (tables) and RCU free them.
+ * We use the sched RCU variant, as that guarantees that IRQ/preempt disabling
+ * holds off grace periods.
+ *
+ * However, in order to batch these pages we need to allocate storage, this
+ * allocation is deep inside the MM code and can thus easily fail on memory
+ * pressure. To guarantee progress we fall back to single table freeing, see
+ * the implementation of tlb_remove_table_one().
+ *
  */
-static inline void tlb_table_invalidate(struct mmu_gather *tlb)
-{
-#ifndef CONFIG_HAVE_RCU_TABLE_NO_INVALIDATE
-	/*
-	 * Invalidate page-table caches used by hardware walkers. Then we still
-	 * need to RCU-sched wait while freeing the pages because software
-	 * walkers can still be in-flight.
-	 */
-	tlb_flush_mmu_tlbonly(tlb);
-#endif
-}
 
 static void tlb_remove_table_smp_sync(void *arg)
 {
 	/* Simply deliver the interrupt */
 }
 
-static void tlb_remove_table_one(void *table)
+static void tlb_remove_table_sync_one(void)
 {
 	/*
 	 * This isn't an RCU grace period and hence the page-tables cannot be
 	 * assumed to be actually RCU-freed.
 	 *
 	 * It is however sufficient for software page-table walkers that rely on
-	 * IRQ disabling. See the comment near struct mmu_table_batch.
+	 * IRQ disabling.
 	 */
 	smp_call_function(tlb_remove_table_smp_sync, NULL, 1);
-	__tlb_remove_table(table);
 }
 
 static void tlb_remove_table_rcu(struct rcu_head *head)
 {
-	struct mmu_table_batch *batch;
-	int i;
+	__tlb_remove_table_free(container_of(head, struct mmu_table_batch, rcu));
+}
+
+static void tlb_remove_table_free(struct mmu_table_batch *batch)
+{
+	call_rcu(&batch->rcu, tlb_remove_table_rcu);
+}
 
-	batch = container_of(head, struct mmu_table_batch, rcu);
+#else /* !CONFIG_MMU_GATHER_RCU_TABLE_FREE */
 
-	for (i = 0; i < batch->nr; i++)
-		__tlb_remove_table(batch->tables[i]);
+static void tlb_remove_table_sync_one(void) { }
 
-	free_page((unsigned long)batch);
+static void tlb_remove_table_free(struct mmu_table_batch *batch)
+{
+	__tlb_remove_table_free(batch);
+}
+
+#endif /* CONFIG_MMU_GATHER_RCU_TABLE_FREE */
+
+/*
+ * If we want tlb_remove_table() to imply TLB invalidates.
+ */
+static inline void tlb_table_invalidate(struct mmu_gather *tlb)
+{
+	if (tlb_needs_table_invalidate()) {
+		/*
+		 * Invalidate page-table caches used by hardware walkers. Then
+		 * we still need to RCU-sched wait while freeing the pages
+		 * because software walkers can still be in-flight.
+		 */
+		tlb_flush_mmu_tlbonly(tlb);
+	}
+}
+
+static void tlb_remove_table_one(void *table)
+{
+	tlb_remove_table_sync_one();
+	__tlb_remove_table(table);
 }
 
 static void tlb_table_flush(struct mmu_gather *tlb)
@@ -149,7 +199,7 @@ static void tlb_table_flush(struct mmu_gather *tlb)
 
 	if (*batch) {
 		tlb_table_invalidate(tlb);
-		call_rcu(&(*batch)->rcu, tlb_remove_table_rcu);
+		tlb_remove_table_free(*batch);
 		*batch = NULL;
 	}
 }
@@ -173,14 +223,22 @@ void tlb_remove_table(struct mmu_gather *tlb, void *table)
 		tlb_table_flush(tlb);
 }
 
-#endif /* CONFIG_HAVE_RCU_TABLE_FREE */
+static inline void tlb_table_init(struct mmu_gather *tlb)
+{
+	tlb->batch = NULL;
+}
+
+#else /* !CONFIG_MMU_GATHER_TABLE_FREE */
+
+static inline void tlb_table_flush(struct mmu_gather *tlb) { }
+static inline void tlb_table_init(struct mmu_gather *tlb) { }
+
+#endif /* CONFIG_MMU_GATHER_TABLE_FREE */
 
 static void tlb_flush_mmu_free(struct mmu_gather *tlb)
 {
-#ifdef CONFIG_HAVE_RCU_TABLE_FREE
 	tlb_table_flush(tlb);
-#endif
-#ifndef CONFIG_HAVE_MMU_GATHER_NO_GATHER
+#ifndef CONFIG_MMU_GATHER_NO_GATHER
 	tlb_batch_pages_flush(tlb);
 #endif
 }
@@ -211,7 +269,7 @@ void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm,
 	/* Is it from 0 to ~0? */
 	tlb->fullmm     = !(start | (end+1));
 
-#ifndef CONFIG_HAVE_MMU_GATHER_NO_GATHER
+#ifndef CONFIG_MMU_GATHER_NO_GATHER
 	tlb->need_flush_all = 0;
 	tlb->local.next = NULL;
 	tlb->local.nr   = 0;
@@ -220,10 +278,8 @@ void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm,
 	tlb->batch_count = 0;
 #endif
 
-#ifdef CONFIG_HAVE_RCU_TABLE_FREE
-	tlb->batch = NULL;
-#endif
-#ifdef CONFIG_HAVE_MMU_GATHER_PAGE_SIZE
+	tlb_table_init(tlb);
+#ifdef CONFIG_MMU_GATHER_PAGE_SIZE
 	tlb->page_size = 0;
 #endif
 
@@ -271,7 +327,7 @@ void tlb_finish_mmu(struct mmu_gather *tlb,
 
 	tlb_flush_mmu(tlb);
 
-#ifndef CONFIG_HAVE_MMU_GATHER_NO_GATHER
+#ifndef CONFIG_MMU_GATHER_NO_GATHER
 	tlb_batch_list_free(tlb);
 #endif
 	dec_tlb_flush_pending(tlb->mm);
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 15e908ad933b..3c4eb750a199 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -5852,18 +5852,11 @@ overlap_memmap_init(unsigned long zone, unsigned long *pfn)
 /* Skip PFNs that belong to non-present sections */
 static inline __meminit unsigned long next_pfn(unsigned long pfn)
 {
-	unsigned long section_nr;
+	const unsigned long section_nr = pfn_to_section_nr(++pfn);
 
-	section_nr = pfn_to_section_nr(++pfn);
 	if (present_section_nr(section_nr))
 		return pfn;
-
-	while (++section_nr <= __highest_present_section_nr) {
-		if (present_section_nr(section_nr))
-			return section_nr_to_pfn(section_nr);
-	}
-
-	return -1;
+	return section_nr_to_pfn(next_present_section_nr(section_nr));
 }
 #else
 static inline __meminit unsigned long next_pfn(unsigned long pfn)
@@ -5905,18 +5898,20 @@ void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone,
 	}
 #endif
 
-	for (pfn = start_pfn; pfn < end_pfn; pfn++) {
+	for (pfn = start_pfn; pfn < end_pfn; ) {
 		/*
 		 * There can be holes in boot-time mem_map[]s handed to this
 		 * function.  They do not exist on hotplugged memory.
 		 */
 		if (context == MEMMAP_EARLY) {
 			if (!early_pfn_valid(pfn)) {
-				pfn = next_pfn(pfn) - 1;
+				pfn = next_pfn(pfn);
 				continue;
 			}
-			if (!early_pfn_in_nid(pfn, nid))
+			if (!early_pfn_in_nid(pfn, nid)) {
+				pfn++;
 				continue;
+			}
 			if (overlap_memmap_init(zone, &pfn))
 				continue;
 			if (defer_init(nid, pfn, end_pfn))
@@ -5944,16 +5939,17 @@ void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone,
 			set_pageblock_migratetype(page, MIGRATE_MOVABLE);
 			cond_resched();
 		}
+		pfn++;
 	}
 }
 
 #ifdef CONFIG_ZONE_DEVICE
 void __ref memmap_init_zone_device(struct zone *zone,
 				   unsigned long start_pfn,
-				   unsigned long size,
+				   unsigned long nr_pages,
 				   struct dev_pagemap *pgmap)
 {
-	unsigned long pfn, end_pfn = start_pfn + size;
+	unsigned long pfn, end_pfn = start_pfn + nr_pages;
 	struct pglist_data *pgdat = zone->zone_pgdat;
 	struct vmem_altmap *altmap = pgmap_altmap(pgmap);
 	unsigned long zone_idx = zone_idx(zone);
@@ -5970,7 +5966,7 @@ void __ref memmap_init_zone_device(struct zone *zone,
 	 */
 	if (altmap) {
 		start_pfn = altmap->base_pfn + vmem_altmap_offset(altmap);
-		size = end_pfn - start_pfn;
+		nr_pages = end_pfn - start_pfn;
 	}
 
 	for (pfn = start_pfn; pfn < end_pfn; pfn++) {
@@ -6017,7 +6013,7 @@ void __ref memmap_init_zone_device(struct zone *zone,
 	}
 
 	pr_info("%s initialised %lu pages in %ums\n", __func__,
-		size, jiffies_to_msecs(jiffies - start));
+		nr_pages, jiffies_to_msecs(jiffies - start));
 }
 
 #endif
@@ -6916,10 +6912,10 @@ void __init free_area_init_node(int nid, unsigned long *zones_size,
 
 #if !defined(CONFIG_FLAT_NODE_MEM_MAP)
 /*
- * Zero all valid struct pages in range [spfn, epfn), return number of struct
- * pages zeroed
+ * Initialize all valid struct pages in the range [spfn, epfn) and mark them
+ * PageReserved(). Return the number of struct pages that were initialized.
  */
-static u64 zero_pfn_range(unsigned long spfn, unsigned long epfn)
+static u64 __init init_unavailable_range(unsigned long spfn, unsigned long epfn)
 {
 	unsigned long pfn;
 	u64 pgcnt = 0;
@@ -6930,7 +6926,13 @@ static u64 zero_pfn_range(unsigned long spfn, unsigned long epfn)
 				+ pageblock_nr_pages - 1;
 			continue;
 		}
-		mm_zero_struct_page(pfn_to_page(pfn));
+		/*
+		 * Use a fake node/zone (0) for now. Some of these pages
+		 * (in memblock.reserved but not in memblock.memory) will
+		 * get re-initialized via reserve_bootmem_region() later.
+		 */
+		__init_single_page(pfn_to_page(pfn), pfn, 0, 0);
+		__SetPageReserved(pfn_to_page(pfn));
 		pgcnt++;
 	}
 
@@ -6942,14 +6944,15 @@ static u64 zero_pfn_range(unsigned long spfn, unsigned long epfn)
  * initialized by going through __init_single_page(). But, there are some
  * struct pages which are reserved in memblock allocator and their fields
  * may be accessed (for example page_to_pfn() on some configuration accesses
- * flags). We must explicitly zero those struct pages.
+ * flags). We must explicitly initialize those struct pages.
  *
  * This function also addresses a similar issue where struct pages are left
  * uninitialized because the physical address range is not covered by
  * memblock.memory or memblock.reserved. That could happen when memblock
- * layout is manually configured via memmap=.
+ * layout is manually configured via memmap=, or when the highest physical
+ * address (max_pfn) does not end on a section boundary.
  */
-void __init zero_resv_unavail(void)
+static void __init init_unavailable_mem(void)
 {
 	phys_addr_t start, end;
 	u64 i, pgcnt;
@@ -6962,10 +6965,20 @@ void __init zero_resv_unavail(void)
 	for_each_mem_range(i, &memblock.memory, NULL,
 			NUMA_NO_NODE, MEMBLOCK_NONE, &start, &end, NULL) {
 		if (next < start)
-			pgcnt += zero_pfn_range(PFN_DOWN(next), PFN_UP(start));
+			pgcnt += init_unavailable_range(PFN_DOWN(next),
+							PFN_UP(start));
 		next = end;
 	}
-	pgcnt += zero_pfn_range(PFN_DOWN(next), max_pfn);
+
+	/*
+	 * Early sections always have a fully populated memmap for the whole
+	 * section - see pfn_valid(). If the last section has holes at the
+	 * end and that section is marked "online", the memmap will be
+	 * considered initialized. Make sure that memmap has a well defined
+	 * state.
+	 */
+	pgcnt += init_unavailable_range(PFN_DOWN(next),
+					round_up(max_pfn, PAGES_PER_SECTION));
 
 	/*
 	 * Struct pages that do not have backing memory. This could be because
@@ -6974,6 +6987,10 @@ void __init zero_resv_unavail(void)
 	if (pgcnt)
 		pr_info("Zeroed struct page in unavailable ranges: %lld pages", pgcnt);
 }
+#else
+static inline void __init init_unavailable_mem(void)
+{
+}
 #endif /* !CONFIG_FLAT_NODE_MEM_MAP */
 
 #ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
@@ -7403,7 +7420,7 @@ void __init free_area_init_nodes(unsigned long *max_zone_pfn)
 	/* Initialise every node */
 	mminit_verify_pageflags_layout();
 	setup_nr_node_ids();
-	zero_resv_unavail();
+	init_unavailable_mem();
 	for_each_online_node(nid) {
 		pg_data_t *pgdat = NODE_DATA(nid);
 		free_area_init_node(nid, NULL,
@@ -7598,7 +7615,7 @@ void __init set_dma_reserve(unsigned long new_dma_reserve)
 
 void __init free_area_init(unsigned long *zones_size)
 {
-	zero_resv_unavail();
+	init_unavailable_mem();
 	free_area_init_node(0, zones_size,
 			__pa(PAGE_OFFSET) >> PAGE_SHIFT, NULL);
 }
diff --git a/mm/pagewalk.c b/mm/pagewalk.c
index ea0b9e606ad1..928df1638c30 100644
--- a/mm/pagewalk.c
+++ b/mm/pagewalk.c
@@ -4,26 +4,57 @@
 #include <linux/sched.h>
 #include <linux/hugetlb.h>
 
-static int walk_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
-			  struct mm_walk *walk)
+/*
+ * We want to know the real level where a entry is located ignoring any
+ * folding of levels which may be happening. For example if p4d is folded then
+ * a missing entry found at level 1 (p4d) is actually at level 0 (pgd).
+ */
+static int real_depth(int depth)
+{
+	if (depth == 3 && PTRS_PER_PMD == 1)
+		depth = 2;
+	if (depth == 2 && PTRS_PER_PUD == 1)
+		depth = 1;
+	if (depth == 1 && PTRS_PER_P4D == 1)
+		depth = 0;
+	return depth;
+}
+
+static int walk_pte_range_inner(pte_t *pte, unsigned long addr,
+				unsigned long end, struct mm_walk *walk)
 {
-	pte_t *pte;
-	int err = 0;
 	const struct mm_walk_ops *ops = walk->ops;
-	spinlock_t *ptl;
+	int err = 0;
 
-	pte = pte_offset_map_lock(walk->mm, pmd, addr, &ptl);
 	for (;;) {
 		err = ops->pte_entry(pte, addr, addr + PAGE_SIZE, walk);
 		if (err)
 		       break;
-		addr += PAGE_SIZE;
-		if (addr == end)
+		if (addr >= end - PAGE_SIZE)
 			break;
+		addr += PAGE_SIZE;
 		pte++;
 	}
+	return err;
+}
+
+static int walk_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
+			  struct mm_walk *walk)
+{
+	pte_t *pte;
+	int err = 0;
+	spinlock_t *ptl;
+
+	if (walk->no_vma) {
+		pte = pte_offset_map(pmd, addr);
+		err = walk_pte_range_inner(pte, addr, end, walk);
+		pte_unmap(pte);
+	} else {
+		pte = pte_offset_map_lock(walk->mm, pmd, addr, &ptl);
+		err = walk_pte_range_inner(pte, addr, end, walk);
+		pte_unmap_unlock(pte, ptl);
+	}
 
-	pte_unmap_unlock(pte, ptl);
 	return err;
 }
 
@@ -34,18 +65,22 @@ static int walk_pmd_range(pud_t *pud, unsigned long addr, unsigned long end,
 	unsigned