Merge branch 'akpm' (patches from Andrew)

Merge updates from Andrew Morton:

 - fsnotify updates

 - ocfs2 updates

 - all of MM

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (127 commits)
  console: don't prefer first registered if DT specifies stdout-path
  cred: simpler, 1D supplementary groups
  CREDITS: update Pavel's information, add GPG key, remove snail mail address
  mailmap: add Johan Hovold
  .gitattributes: set git diff driver for C source code files
  uprobes: remove function declarations from arch/{mips,s390}
  spelling.txt: "modeled" is spelt correctly
  nmi_backtrace: generate one-line reports for idle cpus
  arch/tile: adopt the new nmi_backtrace framework
  nmi_backtrace: do a local dump_stack() instead of a self-NMI
  nmi_backtrace: add more trigger_*_cpu_backtrace() methods
  min/max: remove sparse warnings when they're nested
  Documentation/filesystems/proc.txt: add more description for maps/smaps
  mm, proc: fix region lost in /proc/self/smaps
  proc: fix timerslack_ns CAP_SYS_NICE check when adjusting self
  proc: add LSM hook checks to /proc/<tid>/timerslack_ns
  proc: relax /proc/<tid>/timerslack_ns capability requirements
  meminfo: break apart a very long seq_printf with #ifdefs
  seq/proc: modify seq_put_decimal_[u]ll to take a const char *, not char
  proc: faster /proc/*/status
  ...

34 files changed, 1250 insertions, 873 deletions

diff --git a/mm/bootmem.c b/mm/bootmem.c
index 0aa7dda52402..a869f84f44d3 100644
--- a/mm/bootmem.c
+++ b/mm/bootmem.c
@@ -11,15 +11,12 @@
 #include <linux/init.h>
 #include <linux/pfn.h>
 #include <linux/slab.h>
-#include <linux/bootmem.h>
 #include <linux/export.h>
 #include <linux/kmemleak.h>
 #include <linux/range.h>
-#include <linux/memblock.h>
 #include <linux/bug.h>
 #include <linux/io.h>
-
-#include <asm/processor.h>
+#include <linux/bootmem.h>
 
 #include "internal.h"
 
@@ -712,7 +709,7 @@ void * __init ___alloc_bootmem_node_nopanic(pg_data_t *pgdat,
 	void *ptr;
 
 	if (WARN_ON_ONCE(slab_is_available()))
-		return kzalloc(size, GFP_NOWAIT);
+		return kzalloc_node(size, GFP_NOWAIT, pgdat->node_id);
 again:
 
 	/* do not panic in alloc_bootmem_bdata() */
@@ -738,9 +735,6 @@ again:
 void * __init __alloc_bootmem_node_nopanic(pg_data_t *pgdat, unsigned long size,
 				   unsigned long align, unsigned long goal)
 {
-	if (WARN_ON_ONCE(slab_is_available()))
-		return kzalloc_node(size, GFP_NOWAIT, pgdat->node_id);
-
 	return ___alloc_bootmem_node_nopanic(pgdat, size, align, goal, 0);
 }
 
@@ -812,10 +806,6 @@ void * __init __alloc_bootmem_node_high(pg_data_t *pgdat, unsigned long size,
 
 }
 
-#ifndef ARCH_LOW_ADDRESS_LIMIT
-#define ARCH_LOW_ADDRESS_LIMIT	0xffffffffUL
-#endif
-
 /**
  * __alloc_bootmem_low - allocate low boot memory
  * @size: size of the request in bytes
diff --git a/mm/compaction.c b/mm/compaction.c
index 9affb2908304..0409a4ad6ea1 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -997,8 +997,12 @@ isolate_migratepages_range(struct compact_control *cc, unsigned long start_pfn,
 #ifdef CONFIG_COMPACTION
 
 /* Returns true if the page is within a block suitable for migration to */
-static bool suitable_migration_target(struct page *page)
+static bool suitable_migration_target(struct compact_control *cc,
+							struct page *page)
 {
+	if (cc->ignore_block_suitable)
+		return true;
+
 	/* If the page is a large free page, then disallow migration */
 	if (PageBuddy(page)) {
 		/*
@@ -1083,7 +1087,7 @@ static void isolate_freepages(struct compact_control *cc)
 			continue;
 
 		/* Check the block is suitable for migration */
-		if (!suitable_migration_target(page))
+		if (!suitable_migration_target(cc, page))
 			continue;
 
 		/* If isolation recently failed, do not retry */
@@ -1316,7 +1320,7 @@ static enum compact_result __compact_finished(struct zone *zone, struct compact_
 		return COMPACT_CONTINUE;
 
 	/* Compaction run is not finished if the watermark is not met */
-	watermark = low_wmark_pages(zone);
+	watermark = zone->watermark[cc->alloc_flags & ALLOC_WMARK_MASK];
 
 	if (!zone_watermark_ok(zone, cc->order, watermark, cc->classzone_idx,
 							cc->alloc_flags))
@@ -1329,13 +1333,13 @@ static enum compact_result __compact_finished(struct zone *zone, struct compact_
 
 		/* Job done if page is free of the right migratetype */
 		if (!list_empty(&area->free_list[migratetype]))
-			return COMPACT_PARTIAL;
+			return COMPACT_SUCCESS;
 
 #ifdef CONFIG_CMA
 		/* MIGRATE_MOVABLE can fallback on MIGRATE_CMA */
 		if (migratetype == MIGRATE_MOVABLE &&
 			!list_empty(&area->free_list[MIGRATE_CMA]))
-			return COMPACT_PARTIAL;
+			return COMPACT_SUCCESS;
 #endif
 		/*
 		 * Job done if allocation would steal freepages from
@@ -1343,7 +1347,7 @@ static enum compact_result __compact_finished(struct zone *zone, struct compact_
 		 */
 		if (find_suitable_fallback(area, order, migratetype,
 						true, &can_steal) != -1)
-			return COMPACT_PARTIAL;
+			return COMPACT_SUCCESS;
 	}
 
 	return COMPACT_NO_SUITABLE_PAGE;
@@ -1367,7 +1371,7 @@ static enum compact_result compact_finished(struct zone *zone,
  * compaction_suitable: Is this suitable to run compaction on this zone now?
  * Returns
  *   COMPACT_SKIPPED  - If there are too few free pages for compaction
- *   COMPACT_PARTIAL  - If the allocation would succeed without compaction
+ *   COMPACT_SUCCESS  - If the allocation would succeed without compaction
  *   COMPACT_CONTINUE - If compaction should run now
  */
 static enum compact_result __compaction_suitable(struct zone *zone, int order,
@@ -1375,46 +1379,41 @@ static enum compact_result __compaction_suitable(struct zone *zone, int order,
 					int classzone_idx,
 					unsigned long wmark_target)
 {
-	int fragindex;
 	unsigned long watermark;
 
 	if (is_via_compact_memory(order))
 		return COMPACT_CONTINUE;
 
-	watermark = low_wmark_pages(zone);
+	watermark = zone->watermark[alloc_flags & ALLOC_WMARK_MASK];
 	/*
 	 * If watermarks for high-order allocation are already met, there
 	 * should be no need for compaction at all.
 	 */
 	if (zone_watermark_ok(zone, order, watermark, classzone_idx,
 								alloc_flags))
-		return COMPACT_PARTIAL;
+		return COMPACT_SUCCESS;
 
 	/*
-	 * Watermarks for order-0 must be met for compaction. Note the 2UL.
-	 * This is because during migration, copies of pages need to be
-	 * allocated and for a short time, the footprint is higher
+	 * Watermarks for order-0 must be met for compaction to be able to
+	 * isolate free pages for migration targets. This means that the
+	 * watermark and alloc_flags have to match, or be more pessimistic than
+	 * the check in __isolate_free_page(). We don't use the direct
+	 * compactor's alloc_flags, as they are not relevant for freepage
+	 * isolation. We however do use the direct compactor's classzone_idx to
+	 * skip over zones where lowmem reserves would prevent allocation even
+	 * if compaction succeeds.
+	 * For costly orders, we require low watermark instead of min for
+	 * compaction to proceed to increase its chances.
+	 * ALLOC_CMA is used, as pages in CMA pageblocks are considered
+	 * suitable migration targets
 	 */
-	watermark += (2UL << order);
+	watermark = (order > PAGE_ALLOC_COSTLY_ORDER) ?
+				low_wmark_pages(zone) : min_wmark_pages(zone);
+	watermark += compact_gap(order);
 	if (!__zone_watermark_ok(zone, 0, watermark, classzone_idx,
-				 alloc_flags, wmark_target))
+						ALLOC_CMA, wmark_target))
 		return COMPACT_SKIPPED;
 
-	/*
-	 * fragmentation index determines if allocation failures are due to
-	 * low memory or external fragmentation
-	 *
-	 * index of -1000 would imply allocations might succeed depending on
-	 * watermarks, but we already failed the high-order watermark check
-	 * index towards 0 implies failure is due to lack of memory
-	 * index towards 1000 implies failure is due to fragmentation
-	 *
-	 * Only compact if a failure would be due to fragmentation.
-	 */
-	fragindex = fragmentation_index(zone, order);
-	if (fragindex >= 0 && fragindex <= sysctl_extfrag_threshold)
-		return COMPACT_NOT_SUITABLE_ZONE;
-
 	return COMPACT_CONTINUE;
 }
 
@@ -1423,9 +1422,32 @@ enum compact_result compaction_suitable(struct zone *zone, int order,
 					int classzone_idx)
 {
 	enum compact_result ret;
+	int fragindex;
 
 	ret = __compaction_suitable(zone, order, alloc_flags, classzone_idx,
 				    zone_page_state(zone, NR_FREE_PAGES));
+	/*
+	 * fragmentation index determines if allocation failures are due to
+	 * low memory or external fragmentation
+	 *
+	 * index of -1000 would imply allocations might succeed depending on
+	 * watermarks, but we already failed the high-order watermark check
+	 * index towards 0 implies failure is due to lack of memory
+	 * index towards 1000 implies failure is due to fragmentation
+	 *
+	 * Only compact if a failure would be due to fragmentation. Also
+	 * ignore fragindex for non-costly orders where the alternative to
+	 * a successful reclaim/compaction is OOM. Fragindex and the
+	 * vm.extfrag_threshold sysctl is meant as a heuristic to prevent
+	 * excessive compaction for costly orders, but it should not be at the
+	 * expense of system stability.
+	 */
+	if (ret == COMPACT_CONTINUE && (order > PAGE_ALLOC_COSTLY_ORDER)) {
+		fragindex = fragmentation_index(zone, order);
+		if (fragindex >= 0 && fragindex <= sysctl_extfrag_threshold)
+			ret = COMPACT_NOT_SUITABLE_ZONE;
+	}
+
 	trace_mm_compaction_suitable(zone, order, ret);
 	if (ret == COMPACT_NOT_SUITABLE_ZONE)
 		ret = COMPACT_SKIPPED;
@@ -1458,8 +1480,7 @@ bool compaction_zonelist_suitable(struct alloc_context *ac, int order,
 		available += zone_page_state_snapshot(zone, NR_FREE_PAGES);
 		compact_result = __compaction_suitable(zone, order, alloc_flags,
 				ac_classzone_idx(ac), available);
-		if (compact_result != COMPACT_SKIPPED &&
-				compact_result != COMPACT_NOT_SUITABLE_ZONE)
+		if (compact_result != COMPACT_SKIPPED)
 			return true;
 	}
 
@@ -1477,7 +1498,7 @@ static enum compact_result compact_zone(struct zone *zone, struct compact_contro
 	ret = compaction_suitable(zone, cc->order, cc->alloc_flags,
 							cc->classzone_idx);
 	/* Compaction is likely to fail */
-	if (ret == COMPACT_PARTIAL || ret == COMPACT_SKIPPED)
+	if (ret == COMPACT_SUCCESS || ret == COMPACT_SKIPPED)
 		return ret;
 
 	/* huh, compaction_suitable is returning something unexpected */
@@ -1492,23 +1513,29 @@ static enum compact_result compact_zone(struct zone *zone, struct compact_contro
 
 	/*
 	 * Setup to move all movable pages to the end of the zone. Used cached
-	 * information on where the scanners should start but check that it
-	 * is initialised by ensuring the values are within zone boundaries.
+	 * information on where the scanners should start (unless we explicitly
+	 * want to compact the whole zone), but check that it is initialised
+	 * by ensuring the values are within zone boundaries.
 	 */
-	cc->migrate_pfn = zone->compact_cached_migrate_pfn[sync];
-	cc->free_pfn = zone->compact_cached_free_pfn;
-	if (cc->free_pfn < start_pfn || cc->free_pfn >= end_pfn) {
-		cc->free_pfn = pageblock_start_pfn(end_pfn - 1);
-		zone->compact_cached_free_pfn = cc->free_pfn;
-	}
-	if (cc->migrate_pfn < start_pfn || cc->migrate_pfn >= end_pfn) {
+	if (cc->whole_zone) {
 		cc->migrate_pfn = start_pfn;
-		zone->compact_cached_migrate_pfn[0] = cc->migrate_pfn;
-		zone->compact_cached_migrate_pfn[1] = cc->migrate_pfn;
-	}
+		cc->free_pfn = pageblock_start_pfn(end_pfn - 1);
+	} else {
+		cc->migrate_pfn = zone->compact_cached_migrate_pfn[sync];
+		cc->free_pfn = zone->compact_cached_free_pfn;
+		if (cc->free_pfn < start_pfn || cc->free_pfn >= end_pfn) {
+			cc->free_pfn = pageblock_start_pfn(end_pfn - 1);
+			zone->compact_cached_free_pfn = cc->free_pfn;
+		}
+		if (cc->migrate_pfn < start_pfn || cc->migrate_pfn >= end_pfn) {
+			cc->migrate_pfn = start_pfn;
+			zone->compact_cached_migrate_pfn[0] = cc->migrate_pfn;
+			zone->compact_cached_migrate_pfn[1] = cc->migrate_pfn;
+		}
 
-	if (cc->migrate_pfn == start_pfn)
-		cc->whole_zone = true;
+		if (cc->migrate_pfn == start_pfn)
+			cc->whole_zone = true;
+	}
 
 	cc->last_migrated_pfn = 0;
 
@@ -1638,6 +1665,9 @@ static enum compact_result compact_zone_order(struct zone *zone, int order,
 		.alloc_flags = alloc_flags,
 		.classzone_idx = classzone_idx,
 		.direct_compaction = true,
+		.whole_zone = (prio == MIN_COMPACT_PRIORITY),
+		.ignore_skip_hint = (prio == MIN_COMPACT_PRIORITY),
+		.ignore_block_suitable = (prio == MIN_COMPACT_PRIORITY)
 	};
 	INIT_LIST_HEAD(&cc.freepages);
 	INIT_LIST_HEAD(&cc.migratepages);
@@ -1683,7 +1713,8 @@ enum compact_result try_to_compact_pages(gfp_t gfp_mask, unsigned int order,
 								ac->nodemask) {
 		enum compact_result status;
 
-		if (compaction_deferred(zone, order)) {
+		if (prio > MIN_COMPACT_PRIORITY
+					&& compaction_deferred(zone, order)) {
 			rc = max_t(enum compact_result, COMPACT_DEFERRED, rc);
 			continue;
 		}
@@ -1692,9 +1723,8 @@ enum compact_result try_to_compact_pages(gfp_t gfp_mask, unsigned int order,
 					alloc_flags, ac_classzone_idx(ac));
 		rc = max(status, rc);
 
-		/* If a normal allocation would succeed, stop compacting */
-		if (zone_watermark_ok(zone, order, low_wmark_pages(zone),
-					ac_classzone_idx(ac), alloc_flags)) {
+		/* The allocation should succeed, stop compacting */
+		if (status == COMPACT_SUCCESS) {
 			/*
 			 * We think the allocation will succeed in this zone,
 			 * but it is not certain, hence the false. The caller
@@ -1730,10 +1760,18 @@ enum compact_result try_to_compact_pages(gfp_t gfp_mask, unsigned int order,
 
 
 /* Compact all zones within a node */
-static void __compact_pgdat(pg_data_t *pgdat, struct compact_control *cc)
+static void compact_node(int nid)
 {
+	pg_data_t *pgdat = NODE_DATA(nid);
 	int zoneid;
 	struct zone *zone;
+	struct compact_control cc = {
+		.order = -1,
+		.mode = MIGRATE_SYNC,
+		.ignore_skip_hint = true,
+		.whole_zone = true,
+	};
+
 
 	for (zoneid = 0; zoneid < MAX_NR_ZONES; zoneid++) {
 
@@ -1741,60 +1779,19 @@ static void __compact_pgdat(pg_data_t *pgdat, struct compact_control *cc)
 		if (!populated_zone(zone))
 			continue;
 
-		cc->nr_freepages = 0;
-		cc->nr_migratepages = 0;
-		cc->zone = zone;
-		INIT_LIST_HEAD(&cc->freepages);
-		INIT_LIST_HEAD(&cc->migratepages);
-
-		/*
-		 * When called via /proc/sys/vm/compact_memory
-		 * this makes sure we compact the whole zone regardless of
-		 * cached scanner positions.
-		 */
-		if (is_via_compact_memory(cc->order))
-			__reset_isolation_suitable(zone);
-
-		if (is_via_compact_memory(cc->order) ||
-				!compaction_deferred(zone, cc->order))
-			compact_zone(zone, cc);
-
-		VM_BUG_ON(!list_empty(&cc->freepages));
-		VM_BUG_ON(!list_empty(&cc->migratepages));
+		cc.nr_freepages = 0;
+		cc.nr_migratepages = 0;
+		cc.zone = zone;
+		INIT_LIST_HEAD(&cc.freepages);
+		INIT_LIST_HEAD(&cc.migratepages);
 
-		if (is_via_compact_memory(cc->order))
-			continue;
+		compact_zone(zone, &cc);
 
-		if (zone_watermark_ok(zone, cc->order,
-				low_wmark_pages(zone), 0, 0))
-			compaction_defer_reset(zone, cc->order, false);
+		VM_BUG_ON(!list_empty(&cc.freepages));
+		VM_BUG_ON(!list_empty(&cc.migratepages));
 	}
 }
 
-void compact_pgdat(pg_data_t *pgdat, int order)
-{
-	struct compact_control cc = {
-		.order = order,
-		.mode = MIGRATE_ASYNC,
-	};
-
-	if (!order)
-		return;
-
-	__compact_pgdat(pgdat, &cc);
-}
-
-static void compact_node(int nid)
-{
-	struct compact_control cc = {
-		.order = -1,
-		.mode = MIGRATE_SYNC,
-		.ignore_skip_hint = true,
-	};
-
-	__compact_pgdat(NODE_DATA(nid), &cc);
-}
-
 /* Compact all nodes in the system */
 static void compact_nodes(void)
 {
@@ -1900,8 +1897,6 @@ static void kcompactd_do_work(pg_data_t *pgdat)
 		.ignore_skip_hint = true,
 
 	};
-	bool success = false;
-
 	trace_mm_compaction_kcompactd_wake(pgdat->node_id, cc.order,
 							cc.classzone_idx);
 	count_vm_event(KCOMPACTD_WAKE);
@@ -1930,9 +1925,7 @@ static void kcompactd_do_work(pg_data_t *pgdat)
 			return;
 		status = compact_zone(zone, &cc);
 
-		if (zone_watermark_ok(zone, cc.order, low_wmark_pages(zone),
-						cc.classzone_idx, 0)) {
-			success = true;
+		if (status == COMPACT_SUCCESS) {
 			compaction_defer_reset(zone, cc.order, false);
 		} else if (status == COMPACT_PARTIAL_SKIPPED || status == COMPACT_COMPLETE) {
 			/*
diff --git a/mm/debug.c b/mm/debug.c
index 74c7cae4f683..9feb699c5d25 100644
--- a/mm/debug.c
+++ b/mm/debug.c
@@ -42,6 +42,11 @@ const struct trace_print_flags vmaflag_names[] = {
 
 void __dump_page(struct page *page, const char *reason)
 {
+	/*
+	 * Avoid VM_BUG_ON() in page_mapcount().
+	 * page->_mapcount space in struct page is used by sl[aou]b pages to
+	 * encode own info.
+	 */
 	int mapcount = PageSlab(page) ? 0 : page_mapcount(page);
 
 	pr_emerg("page:%p count:%d mapcount:%d mapping:%p index:%#lx",
diff --git a/mm/filemap.c b/mm/filemap.c
index 68f1813fbdc3..2f7b7783bd6b 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -1687,6 +1687,10 @@ static ssize_t do_generic_file_read(struct file *filp, loff_t *ppos,
 	unsigned int prev_offset;
 	int error = 0;
 
+	if (unlikely(*ppos >= inode->i_sb->s_maxbytes))
+		return -EINVAL;
+	iov_iter_truncate(iter, inode->i_sb->s_maxbytes);
+
 	index = *ppos >> PAGE_SHIFT;
 	prev_index = ra->prev_pos >> PAGE_SHIFT;
 	prev_offset = ra->prev_pos & (PAGE_SIZE-1);
@@ -1721,7 +1725,9 @@ find_page:
 			 * wait_on_page_locked is used to avoid unnecessarily
 			 * serialisations and why it's safe.
 			 */
-			wait_on_page_locked_killable(page);
+			error = wait_on_page_locked_killable(page);
+			if (unlikely(error))
+				goto readpage_error;
 			if (PageUptodate(page))
 				goto page_ok;
 
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 283583fcb1e7..cdcd25cb30fe 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -59,7 +59,7 @@ static struct shrinker deferred_split_shrinker;
 static atomic_t huge_zero_refcount;
 struct page *huge_zero_page __read_mostly;
 
-struct page *get_huge_zero_page(void)
+static struct page *get_huge_zero_page(void)
 {
 	struct page *zero_page;
 retry:
@@ -86,7 +86,7 @@ retry:
 	return READ_ONCE(huge_zero_page);
 }
 
-void put_huge_zero_page(void)
+static void put_huge_zero_page(void)
 {
 	/*
 	 * Counter should never go to zero here. Only shrinker can put
@@ -95,6 +95,26 @@ void put_huge_zero_page(void)
 	BUG_ON(atomic_dec_and_test(&huge_zero_refcount));
 }
 
+struct page *mm_get_huge_zero_page(struct mm_struct *mm)
+{
+	if (test_bit(MMF_HUGE_ZERO_PAGE, &mm->flags))
+		return READ_ONCE(huge_zero_page);
+
+	if (!get_huge_zero_page())
+		return NULL;
+
+	if (test_and_set_bit(MMF_HUGE_ZERO_PAGE, &mm->flags))
+		put_huge_zero_page();
+
+	return READ_ONCE(huge_zero_page);
+}
+
+void mm_put_huge_zero_page(struct mm_struct *mm)
+{
+	if (test_bit(MMF_HUGE_ZERO_PAGE, &mm->flags))
+		put_huge_zero_page();
+}
+
 static unsigned long shrink_huge_zero_page_count(struct shrinker *shrink,
 					struct shrink_control *sc)
 {
@@ -469,6 +489,49 @@ void prep_transhuge_page(struct page *page)
 	set_compound_page_dtor(page, TRANSHUGE_PAGE_DTOR);
 }
 
+unsigned long __thp_get_unmapped_area(struct file *filp, unsigned long len,
+		loff_t off, unsigned long flags, unsigned long size)
+{
+	unsigned long addr;
+	loff_t off_end = off + len;
+	loff_t off_align = round_up(off, size);
+	unsigned long len_pad;
+
+	if (off_end <= off_align || (off_end - off_align) < size)
+		return 0;
+
+	len_pad = len + size;
+	if (len_pad < len || (off + len_pad) < off)
+		return 0;
+
+	addr = current->mm->get_unmapped_area(filp, 0, len_pad,
+					      off >> PAGE_SHIFT, flags);
+	if (IS_ERR_VALUE(addr))
+		return 0;
+
+	addr += (off - addr) & (size - 1);
+	return addr;
+}
+
+unsigned long thp_get_unmapped_area(struct file *filp, unsigned long addr,
+		unsigned long len, unsigned long pgoff, unsigned long flags)
+{
+	loff_t off = (loff_t)pgoff << PAGE_SHIFT;
+
+	if (addr)
+		goto out;
+	if (!IS_DAX(filp->f_mapping->host) || !IS_ENABLED(CONFIG_FS_DAX_PMD))
+		goto out;
+
+	addr = __thp_get_unmapped_area(filp, len, off, flags, PMD_SIZE);
+	if (addr)
+		return addr;
+
+ out:
+	return current->mm->get_unmapped_area(filp, addr, len, pgoff, flags);
+}
+EXPORT_SYMBOL_GPL(thp_get_unmapped_area);
+
 static int __do_huge_pmd_anonymous_page(struct fault_env *fe, struct page *page,
 		gfp_t gfp)
 {
@@ -601,7 +664,7 @@ int do_huge_pmd_anonymous_page(struct fault_env *fe)
 		pgtable = pte_alloc_one(vma->vm_mm, haddr);
 		if (unlikely(!pgtable))
 			return VM_FAULT_OOM;
-		zero_page = get_huge_zero_page();
+		zero_page = mm_get_huge_zero_page(vma->vm_mm);
 		if (unlikely(!zero_page)) {
 			pte_free(vma->vm_mm, pgtable);
 			count_vm_event(THP_FAULT_FALLBACK);
@@ -623,10 +686,8 @@ int do_huge_pmd_anonymous_page(struct fault_env *fe)
 			}
 		} else
 			spin_unlock(fe->ptl);
-		if (!set) {
+		if (!set)
 			pte_free(vma->vm_mm, pgtable);
-			put_huge_zero_page();
-		}
 		return ret;
 	}
 	gfp = alloc_hugepage_direct_gfpmask(vma);
@@ -780,7 +841,7 @@ int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 		 * since we already have a zero page to copy. It just takes a
 		 * reference.
 		 */
-		zero_page = get_huge_zero_page();
+		zero_page = mm_get_huge_zero_page(dst_mm);
 		set_huge_zero_page(pgtable, dst_mm, vma, addr, dst_pmd,
 				zero_page);
 		ret = 0;
@@ -1038,7 +1099,6 @@ alloc:
 		update_mmu_cache_pmd(vma, fe->address, fe->pmd);
 		if (!page) {
 			add_mm_counter(vma->vm_mm, MM_ANONPAGES, HPAGE_PMD_NR);
-			put_huge_zero_page();
 		} else {
 			VM_BUG_ON_PAGE(!PageHead(page), page);
 			page_remove_rmap(page, true);
@@ -1499,7 +1559,6 @@ static void __split_huge_zero_page_pmd(struct vm_area_struct *vma,
 	}
 	smp_wmb(); /* make pte visible before pmd */
 	pmd_populate(mm, pmd, pgtable);
-	put_huge_zero_page();
 }
 
 static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd,
@@ -1522,8 +1581,6 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd,
 
 	if (!vma_is_anonymous(vma)) {
 		_pmd = pmdp_huge_clear_flush_notify(vma, haddr, pmd);
-		if (is_huge_zero_pmd(_pmd))
-			put_huge_zero_page();
 		if (vma_is_dax(vma))
 			return;
 		page = pmd_page(_pmd);
@@ -1563,7 +1620,7 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd,
 			if (soft_dirty)
 				entry = pte_swp_mksoft_dirty(entry);
 		} else {
-			entry = mk_pte(page + i, vma->vm_page_prot);
+			entry = mk_pte(page + i, READ_ONCE(vma->vm_page_prot));
 			entry = maybe_mkwrite(entry, vma);
 			if (!write)
 				entry = pte_wrprotect(entry);
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 87e11d8ad536..ec49d9ef1eef 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -567,13 +567,13 @@ retry:
  * appear as a "reserved" entry instead of simply dangling with incorrect
  * counts.
  */
-void hugetlb_fix_reserve_counts(struct inode *inode, bool restore_reserve)
+void hugetlb_fix_reserve_counts(struct inode *inode)
 {
 	struct hugepage_subpool *spool = subpool_inode(inode);
 	long rsv_adjust;
 
 	rsv_adjust = hugepage_subpool_get_pages(spool, 1);
-	if (restore_reserve && rsv_adjust) {
+	if (rsv_adjust) {
 		struct hstate *h = hstate_inode(inode);
 
 		hugetlb_acct_memory(h, 1);
@@ -1022,7 +1022,7 @@ static int hstate_next_node_to_free(struct hstate *h, nodemask_t *nodes_allowed)
 		((node = hstate_next_node_to_free(hs, mask)) || 1);	\
 		nr_nodes--)
 
-#if (defined(CONFIG_X86_64) || defined(CONFIG_S390)) && \
+#if defined(CONFIG_ARCH_HAS_GIGANTIC_PAGE) && \
 	((defined(CONFIG_MEMORY_ISOLATION) && defined(CONFIG_COMPACTION)) || \
 	defined(CONFIG_CMA))
 static void destroy_compound_gigantic_page(struct page *page,
@@ -1437,38 +1437,61 @@ static int free_pool_huge_page(struct hstate *h, nodemask_t *nodes_allowed,
 
 /*
  * Dissolve a given free hugepage into free buddy pages. This function does
- * nothing for in-use (including surplus) hugepages.
+ * nothing for in-use (including surplus) hugepages. Returns -EBUSY if the
+ * number of free hugepages would be reduced below the number of reserved
+ * hugepages.
  */
-static void dissolve_free_huge_page(struct page *page)
+static int dissolve_free_huge_page(struct page *page)
 {
+	int rc = 0;
+
 	spin_lock(&hugetlb_lock);
 	if (PageHuge(page) && !page_count(page)) {
-		struct hstate *h = page_hstate(page);
-		int nid = page_to_nid(page);
-		list_del(&page->lru);
+		struct page *head = compound_head(page);
+		struct hstate *h = page_hstate(head);
+		int nid = page_to_nid(head);
+		if (h->free_huge_pages - h->resv_huge_pages == 0) {
+			rc = -EBUSY;
+			goto out;
+		}
+		list_del(&head->lru);
 		h->free_huge_pages--;
 		h->free_huge_pages_node[nid]--;
 		h->max_huge_pages--;
-		update_and_free_page(h, page);
+		update_and_free_page(h, head);
 	}
+out:
 	spin_unlock(&hugetlb_lock);
+	return rc;
 }
 
 /*
  * Dissolve free hugepages in a given pfn range. Used by memory hotplug to
  * make specified memory blocks removable from the system.
- * Note that start_pfn should aligned with (minimum) hugepage size.
+ * Note that this will dissolve a free gigantic hugepage completely, if any
+ * part of it lies within the given range.
+ * Also note that if dissolve_free_huge_page() returns with an error, all
+ * free hugepages that were dissolved before that error are lost.
  */
-void dissolve_free_huge_pages(unsigned long start_pfn, unsigned long end_pfn)
+int dissolve_free_huge_pages(unsigned long start_pfn, unsigned long end_pfn)
 {
 	unsigned long pfn;
+	struct page *page;
+	int rc = 0;
 
 	if (!hugepages_supported())
-		return;
+		return rc;
+
+	for (pfn = start_pfn; pfn < end_pfn; pfn += 1 << minimum_order) {
+		page = pfn_to_page(pfn);
+		if (PageHuge(page) && !page_count(page)) {
+			rc = dissolve_free_huge_page(page);
+			if (rc)
+				break;
+		}
+	}
 
-	VM_BUG_ON(!IS_ALIGNED(start_pfn, 1 << minimum_order));
-	for (pfn = start_pfn; pfn < end_pfn; pfn += 1 << minimum_order)
-		dissolve_free_huge_page(pfn_to_page(pfn));
+	return rc;
 }
 
 /*
diff --git a/mm/internal.h b/mm/internal.h
index 1501304f87a4..537ac9951f5f 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -178,8 +178,9 @@ struct compact_control {
 	unsigned long last_migrated_pfn;/* Not yet flushed page being freed */
 	enum migrate_mode mode;		/* Async or sync migration mode */
 	bool ignore_skip_hint;		/* Scan blocks even if marked skip */
+	bool ignore_block_suitable;	/* Scan blocks considered unsuitable */
 	bool direct_compaction;		/* False from kcompactd or /proc/... */
-	bool whole_zone;		/* Whole zone has been scanned */
+	bool whole_zone;		/* Whole zone should/has been scanned */
 	int order;			/* order a direct compactor needs */
 	const gfp_t gfp_mask;		/* gfp mask of a direct compactor */
 	const unsigned int alloc_fla