Update Linux to v5.10.109

Sourced from [1]

[1] https://cdn.kernel.org/pub/linux/kernel/v5.x/linux-5.10.109.tar.xz

Change-Id: I19bca9fc6762d4e63bcf3e4cba88bbe560d9c76c
Signed-off-by: Olivier Deprez <olivier.deprez@arm.com>
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 95a3274..fce705f 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -19,6 +19,7 @@
 #include <linux/memblock.h>
 #include <linux/sysfs.h>
 #include <linux/slab.h>
+#include <linux/sched/mm.h>
 #include <linux/mmdebug.h>
 #include <linux/sched/signal.h>
 #include <linux/rmap.h>
@@ -28,9 +29,10 @@
 #include <linux/jhash.h>
 #include <linux/numa.h>
 #include <linux/llist.h>
+#include <linux/cma.h>
 
 #include <asm/page.h>
-#include <asm/pgtable.h>
+#include <asm/pgalloc.h>
 #include <asm/tlb.h>
 
 #include <linux/io.h>
@@ -44,6 +46,12 @@
 int hugetlb_max_hstate __read_mostly;
 unsigned int default_hstate_idx;
 struct hstate hstates[HUGE_MAX_HSTATE];
+
+#ifdef CONFIG_CMA
+static struct cma *hugetlb_cma[MAX_NUMNODES];
+#endif
+static unsigned long hugetlb_cma_size __initdata;
+
 /*
  * Minimum page order among possible hugepage sizes, set to a proper value
  * at boot time.
@@ -55,8 +63,8 @@
 /* for command line parsing */
 static struct hstate * __initdata parsed_hstate;
 static unsigned long __initdata default_hstate_max_huge_pages;
-static unsigned long __initdata default_hstate_size;
 static bool __initdata parsed_valid_hugepagesz = true;
+static bool __initdata parsed_default_hugepagesz;
 
 /*
  * Protects updates to hugepage_freelists, hugepage_activelist, nr_huge_pages,
@@ -96,7 +104,7 @@
 	spin_unlock(&spool->lock);
 
 	/* If no pages are used, and no other handles to the subpool
-	 * remain, give up any reservations mased on minimum size and
+	 * remain, give up any reservations based on minimum size and
 	 * free the subpool */
 	if (free) {
 		if (spool->min_hpages != -1)
@@ -141,10 +149,10 @@
 /*
  * Subpool accounting for allocating and reserving pages.
  * Return -ENOMEM if there are not enough resources to satisfy the
- * the request.  Otherwise, return the number of pages by which the
+ * request.  Otherwise, return the number of pages by which the
  * global pools must be adjusted (upward).  The returned value may
  * only be different than the passed value (delta) in the case where
- * a subpool minimum size must be manitained.
+ * a subpool minimum size must be maintained.
  */
 static long hugepage_subpool_get_pages(struct hugepage_subpool *spool,
 				      long delta)
@@ -235,114 +243,317 @@
 	return subpool_inode(file_inode(vma->vm_file));
 }
 
-/*
- * Region tracking -- allows tracking of reservations and instantiated pages
- *                    across the pages in a mapping.
- *
- * The region data structures are embedded into a resv_map and protected
- * by a resv_map's lock.  The set of regions within the resv_map represent
- * reservations for huge pages, or huge pages that have already been
- * instantiated within the map.  The from and to elements are huge page
- * indicies into the associated mapping.  from indicates the starting index
- * of the region.  to represents the first index past the end of  the region.
- *
- * For example, a file region structure with from == 0 and to == 4 represents
- * four huge pages in a mapping.  It is important to note that the to element
- * represents the first element past the end of the region. This is used in
- * arithmetic as 4(to) - 0(from) = 4 huge pages in the region.
- *
- * Interval notation of the form [from, to) will be used to indicate that
- * the endpoint from is inclusive and to is exclusive.
+/* Helper that removes a struct file_region from the resv_map cache and returns
+ * it for use.
  */
-struct file_region {
-	struct list_head link;
-	long from;
-	long to;
-};
-
-/*
- * Add the huge page range represented by [f, t) to the reserve
- * map.  In the normal case, existing regions will be expanded
- * to accommodate the specified range.  Sufficient regions should
- * exist for expansion due to the previous call to region_chg
- * with the same range.  However, it is possible that region_del
- * could have been called after region_chg and modifed the map
- * in such a way that no region exists to be expanded.  In this
- * case, pull a region descriptor from the cache associated with
- * the map and use that for the new range.
- *
- * Return the number of new huge pages added to the map.  This
- * number is greater than or equal to zero.
- */
-static long region_add(struct resv_map *resv, long f, long t)
+static struct file_region *
+get_file_region_entry_from_cache(struct resv_map *resv, long from, long to)
 {
-	struct list_head *head = &resv->regions;
-	struct file_region *rg, *nrg, *trg;
-	long add = 0;
+	struct file_region *nrg = NULL;
 
-	spin_lock(&resv->lock);
-	/* Locate the region we are either in or before. */
-	list_for_each_entry(rg, head, link)
-		if (f <= rg->to)
-			break;
+	VM_BUG_ON(resv->region_cache_count <= 0);
 
-	/*
-	 * If no region exists which can be expanded to include the
-	 * specified range, the list must have been modified by an
-	 * interleving call to region_del().  Pull a region descriptor
-	 * from the cache and use it for this range.
-	 */
-	if (&rg->link == head || t < rg->from) {
-		VM_BUG_ON(resv->region_cache_count <= 0);
+	resv->region_cache_count--;
+	nrg = list_first_entry(&resv->region_cache, struct file_region, link);
+	list_del(&nrg->link);
 
-		resv->region_cache_count--;
-		nrg = list_first_entry(&resv->region_cache, struct file_region,
-					link);
-		list_del(&nrg->link);
+	nrg->from = from;
+	nrg->to = to;
 
-		nrg->from = f;
-		nrg->to = t;
-		list_add(&nrg->link, rg->link.prev);
+	return nrg;
+}
 
-		add += t - f;
-		goto out_locked;
+static void copy_hugetlb_cgroup_uncharge_info(struct file_region *nrg,
+					      struct file_region *rg)
+{
+#ifdef CONFIG_CGROUP_HUGETLB
+	nrg->reservation_counter = rg->reservation_counter;
+	nrg->css = rg->css;
+	if (rg->css)
+		css_get(rg->css);
+#endif
+}
+
+/* Helper that records hugetlb_cgroup uncharge info. */
+static void record_hugetlb_cgroup_uncharge_info(struct hugetlb_cgroup *h_cg,
+						struct hstate *h,
+						struct resv_map *resv,
+						struct file_region *nrg)
+{
+#ifdef CONFIG_CGROUP_HUGETLB
+	if (h_cg) {
+		nrg->reservation_counter =
+			&h_cg->rsvd_hugepage[hstate_index(h)];
+		nrg->css = &h_cg->css;
+		/*
+		 * The caller will hold exactly one h_cg->css reference for the
+		 * whole contiguous reservation region. But this area might be
+		 * scattered when there are already some file_regions reside in
+		 * it. As a result, many file_regions may share only one css
+		 * reference. In order to ensure that one file_region must hold
+		 * exactly one h_cg->css reference, we should do css_get for
+		 * each file_region and leave the reference held by caller
+		 * untouched.
+		 */
+		css_get(&h_cg->css);
+		if (!resv->pages_per_hpage)
+			resv->pages_per_hpage = pages_per_huge_page(h);
+		/* pages_per_hpage should be the same for all entries in
+		 * a resv_map.
+		 */
+		VM_BUG_ON(resv->pages_per_hpage != pages_per_huge_page(h));
+	} else {
+		nrg->reservation_counter = NULL;
+		nrg->css = NULL;
+	}
+#endif
+}
+
+static void put_uncharge_info(struct file_region *rg)
+{
+#ifdef CONFIG_CGROUP_HUGETLB
+	if (rg->css)
+		css_put(rg->css);
+#endif
+}
+
+static bool has_same_uncharge_info(struct file_region *rg,
+				   struct file_region *org)
+{
+#ifdef CONFIG_CGROUP_HUGETLB
+	return rg && org &&
+	       rg->reservation_counter == org->reservation_counter &&
+	       rg->css == org->css;
+
+#else
+	return true;
+#endif
+}
+
+static void coalesce_file_region(struct resv_map *resv, struct file_region *rg)
+{
+	struct file_region *nrg = NULL, *prg = NULL;
+
+	prg = list_prev_entry(rg, link);
+	if (&prg->link != &resv->regions && prg->to == rg->from &&
+	    has_same_uncharge_info(prg, rg)) {
+		prg->to = rg->to;
+
+		list_del(&rg->link);
+		put_uncharge_info(rg);
+		kfree(rg);
+
+		rg = prg;
 	}
 
-	/* Round our left edge to the current segment if it encloses us. */
-	if (f > rg->from)
-		f = rg->from;
+	nrg = list_next_entry(rg, link);
+	if (&nrg->link != &resv->regions && nrg->from == rg->to &&
+	    has_same_uncharge_info(nrg, rg)) {
+		nrg->from = rg->from;
 
-	/* Check for and consume any regions we now overlap with. */
-	nrg = rg;
-	list_for_each_entry_safe(rg, trg, rg->link.prev, link) {
-		if (&rg->link == head)
-			break;
+		list_del(&rg->link);
+		put_uncharge_info(rg);
+		kfree(rg);
+	}
+}
+
+/*
+ * Must be called with resv->lock held.
+ *
+ * Calling this with regions_needed != NULL will count the number of pages
+ * to be added but will not modify the linked list. And regions_needed will
+ * indicate the number of file_regions needed in the cache to carry out to add
+ * the regions for this range.
+ */
+static long add_reservation_in_range(struct resv_map *resv, long f, long t,
+				     struct hugetlb_cgroup *h_cg,
+				     struct hstate *h, long *regions_needed)
+{
+	long add = 0;
+	struct list_head *head = &resv->regions;
+	long last_accounted_offset = f;
+	struct file_region *rg = NULL, *trg = NULL, *nrg = NULL;
+
+	if (regions_needed)
+		*regions_needed = 0;
+
+	/* In this loop, we essentially handle an entry for the range
+	 * [last_accounted_offset, rg->from), at every iteration, with some
+	 * bounds checking.
+	 */
+	list_for_each_entry_safe(rg, trg, head, link) {
+		/* Skip irrelevant regions that start before our range. */
+		if (rg->from < f) {
+			/* If this region ends after the last accounted offset,
+			 * then we need to update last_accounted_offset.
+			 */
+			if (rg->to > last_accounted_offset)
+				last_accounted_offset = rg->to;
+			continue;
+		}
+
+		/* When we find a region that starts beyond our range, we've
+		 * finished.
+		 */
 		if (rg->from > t)
 			break;
 
-		/* If this area reaches higher then extend our area to
-		 * include it completely.  If this is not the first area
-		 * which we intend to reuse, free it. */
-		if (rg->to > t)
-			t = rg->to;
-		if (rg != nrg) {
-			/* Decrement return value by the deleted range.
-			 * Another range will span this area so that by
-			 * end of routine add will be >= zero
-			 */
-			add -= (rg->to - rg->from);
-			list_del(&rg->link);
-			kfree(rg);
+		/* Add an entry for last_accounted_offset -> rg->from, and
+		 * update last_accounted_offset.
+		 */
+		if (rg->from > last_accounted_offset) {
+			add += rg->from - last_accounted_offset;
+			if (!regions_needed) {
+				nrg = get_file_region_entry_from_cache(
+					resv, last_accounted_offset, rg->from);
+				record_hugetlb_cgroup_uncharge_info(h_cg, h,
+								    resv, nrg);
+				list_add(&nrg->link, rg->link.prev);
+				coalesce_file_region(resv, nrg);
+			} else
+				*regions_needed += 1;
 		}
+
+		last_accounted_offset = rg->to;
 	}
 
-	add += (nrg->from - f);		/* Added to beginning of region */
-	nrg->from = f;
-	add += t - nrg->to;		/* Added to end of region */
-	nrg->to = t;
+	/* Handle the case where our range extends beyond
+	 * last_accounted_offset.
+	 */
+	if (last_accounted_offset < t) {
+		add += t - last_accounted_offset;
+		if (!regions_needed) {
+			nrg = get_file_region_entry_from_cache(
+				resv, last_accounted_offset, t);
+			record_hugetlb_cgroup_uncharge_info(h_cg, h, resv, nrg);
+			list_add(&nrg->link, rg->link.prev);
+			coalesce_file_region(resv, nrg);
+		} else
+			*regions_needed += 1;
+	}
 
-out_locked:
-	resv->adds_in_progress--;
+	VM_BUG_ON(add < 0);
+	return add;
+}
+
+/* Must be called with resv->lock acquired. Will drop lock to allocate entries.
+ */
+static int allocate_file_region_entries(struct resv_map *resv,
+					int regions_needed)
+	__must_hold(&resv->lock)
+{
+	struct list_head allocated_regions;
+	int to_allocate = 0, i = 0;
+	struct file_region *trg = NULL, *rg = NULL;
+
+	VM_BUG_ON(regions_needed < 0);
+
+	INIT_LIST_HEAD(&allocated_regions);
+
+	/*
+	 * Check for sufficient descriptors in the cache to accommodate
+	 * the number of in progress add operations plus regions_needed.
+	 *
+	 * This is a while loop because when we drop the lock, some other call
+	 * to region_add or region_del may have consumed some region_entries,
+	 * so we keep looping here until we finally have enough entries for
+	 * (adds_in_progress + regions_needed).
+	 */
+	while (resv->region_cache_count <
+	       (resv->adds_in_progress + regions_needed)) {
+		to_allocate = resv->adds_in_progress + regions_needed -
+			      resv->region_cache_count;
+
+		/* At this point, we should have enough entries in the cache
+		 * for all the existings adds_in_progress. We should only be
+		 * needing to allocate for regions_needed.
+		 */
+		VM_BUG_ON(resv->region_cache_count < resv->adds_in_progress);
+
+		spin_unlock(&resv->lock);
+		for (i = 0; i < to_allocate; i++) {
+			trg = kmalloc(sizeof(*trg), GFP_KERNEL);
+			if (!trg)
+				goto out_of_memory;
+			list_add(&trg->link, &allocated_regions);
+		}
+
+		spin_lock(&resv->lock);
+
+		list_splice(&allocated_regions, &resv->region_cache);
+		resv->region_cache_count += to_allocate;
+	}
+
+	return 0;
+
+out_of_memory:
+	list_for_each_entry_safe(rg, trg, &allocated_regions, link) {
+		list_del(&rg->link);
+		kfree(rg);
+	}
+	return -ENOMEM;
+}
+
+/*
+ * Add the huge page range represented by [f, t) to the reserve
+ * map.  Regions will be taken from the cache to fill in this range.
+ * Sufficient regions should exist in the cache due to the previous
+ * call to region_chg with the same range, but in some cases the cache will not
+ * have sufficient entries due to races with other code doing region_add or
+ * region_del.  The extra needed entries will be allocated.
+ *
+ * regions_needed is the out value provided by a previous call to region_chg.
+ *
+ * Return the number of new huge pages added to the map.  This number is greater
+ * than or equal to zero.  If file_region entries needed to be allocated for
+ * this operation and we were not able to allocate, it returns -ENOMEM.
+ * region_add of regions of length 1 never allocate file_regions and cannot
+ * fail; region_chg will always allocate at least 1 entry and a region_add for
+ * 1 page will only require at most 1 entry.
+ */
+static long region_add(struct resv_map *resv, long f, long t,
+		       long in_regions_needed, struct hstate *h,
+		       struct hugetlb_cgroup *h_cg)
+{
+	long add = 0, actual_regions_needed = 0;
+
+	spin_lock(&resv->lock);
+retry:
+
+	/* Count how many regions are actually needed to execute this add. */
+	add_reservation_in_range(resv, f, t, NULL, NULL,
+				 &actual_regions_needed);
+
+	/*
+	 * Check for sufficient descriptors in the cache to accommodate
+	 * this add operation. Note that actual_regions_needed may be greater
+	 * than in_regions_needed, as the resv_map may have been modified since
+	 * the region_chg call. In this case, we need to make sure that we
+	 * allocate extra entries, such that we have enough for all the
+	 * existing adds_in_progress, plus the excess needed for this
+	 * operation.
+	 */
+	if (actual_regions_needed > in_regions_needed &&
+	    resv->region_cache_count <
+		    resv->adds_in_progress +
+			    (actual_regions_needed - in_regions_needed)) {
+		/* region_add operation of range 1 should never need to
+		 * allocate file_region entries.
+		 */
+		VM_BUG_ON(t - f <= 1);
+
+		if (allocate_file_region_entries(
+			    resv, actual_regions_needed - in_regions_needed)) {
+			return -ENOMEM;
+		}
+
+		goto retry;
+	}
+
+	add = add_reservation_in_range(resv, f, t, h_cg, h, NULL);
+
+	resv->adds_in_progress -= in_regions_needed;
+
 	spin_unlock(&resv->lock);
 	VM_BUG_ON(add < 0);
 	return add;
@@ -355,111 +566,38 @@
  * call to region_add that will actually modify the reserve
  * map to add the specified range [f, t).  region_chg does
  * not change the number of huge pages represented by the
- * map.  However, if the existing regions in the map can not
- * be expanded to represent the new range, a new file_region
- * structure is added to the map as a placeholder.  This is
- * so that the subsequent region_add call will have all the
- * regions it needs and will not fail.
+ * map.  A number of new file_region structures is added to the cache as a
+ * placeholder, for the subsequent region_add call to use. At least 1
+ * file_region structure is added.
  *
- * Upon entry, region_chg will also examine the cache of region descriptors
- * associated with the map.  If there are not enough descriptors cached, one
- * will be allocated for the in progress add operation.
+ * out_regions_needed is the number of regions added to the
+ * resv->adds_in_progress.  This value needs to be provided to a follow up call
+ * to region_add or region_abort for proper accounting.
  *
  * Returns the number of huge pages that need to be added to the existing
  * reservation map for the range [f, t).  This number is greater or equal to
  * zero.  -ENOMEM is returned if a new file_region structure or cache entry
  * is needed and can not be allocated.
  */
-static long region_chg(struct resv_map *resv, long f, long t)
+static long region_chg(struct resv_map *resv, long f, long t,
+		       long *out_regions_needed)
 {
-	struct list_head *head = &resv->regions;
-	struct file_region *rg, *nrg = NULL;
 	long chg = 0;
 
-retry:
 	spin_lock(&resv->lock);
-retry_locked:
-	resv->adds_in_progress++;
 
-	/*
-	 * Check for sufficient descriptors in the cache to accommodate
-	 * the number of in progress add operations.
-	 */
-	if (resv->adds_in_progress > resv->region_cache_count) {
-		struct file_region *trg;
+	/* Count how many hugepages in this range are NOT represented. */
+	chg = add_reservation_in_range(resv, f, t, NULL, NULL,
+				       out_regions_needed);
 
-		VM_BUG_ON(resv->adds_in_progress - resv->region_cache_count > 1);
-		/* Must drop lock to allocate a new descriptor. */
-		resv->adds_in_progress--;
-		spin_unlock(&resv->lock);
+	if (*out_regions_needed == 0)
+		*out_regions_needed = 1;
 
-		trg = kmalloc(sizeof(*trg), GFP_KERNEL);
-		if (!trg) {
-			kfree(nrg);
-			return -ENOMEM;
-		}
+	if (allocate_file_region_entries(resv, *out_regions_needed))
+		return -ENOMEM;
 
-		spin_lock(&resv->lock);
-		list_add(&trg->link, &resv->region_cache);
-		resv->region_cache_count++;
-		goto retry_locked;
-	}
+	resv->adds_in_progress += *out_regions_needed;
 
-	/* Locate the region we are before or in. */
-	list_for_each_entry(rg, head, link)
-		if (f <= rg->to)
-			break;
-
-	/* If we are below the current region then a new region is required.
-	 * Subtle, allocate a new region at the position but make it zero
-	 * size such that we can guarantee to record the reservation. */
-	if (&rg->link == head || t < rg->from) {
-		if (!nrg) {
-			resv->adds_in_progress--;
-			spin_unlock(&resv->lock);
-			nrg = kmalloc(sizeof(*nrg), GFP_KERNEL);
-			if (!nrg)
-				return -ENOMEM;
-
-			nrg->from = f;
-			nrg->to   = f;
-			INIT_LIST_HEAD(&nrg->link);
-			goto retry;
-		}
-
-		list_add(&nrg->link, rg->link.prev);
-		chg = t - f;
-		goto out_nrg;
-	}
-
-	/* Round our left edge to the current segment if it encloses us. */
-	if (f > rg->from)
-		f = rg->from;
-	chg = t - f;
-
-	/* Check for and consume any regions we now overlap with. */
-	list_for_each_entry(rg, rg->link.prev, link) {
-		if (&rg->link == head)
-			break;
-		if (rg->from > t)
-			goto out;
-
-		/* We overlap with this area, if it extends further than
-		 * us then we must extend ourselves.  Account for its
-		 * existing reservation. */
-		if (rg->to > t) {
-			chg += rg->to - t;
-			t = rg->to;
-		}
-		chg -= rg->to - rg->from;
-	}
-
-out:
-	spin_unlock(&resv->lock);
-	/*  We already know we raced and no longer need the new region */
-	kfree(nrg);
-	return chg;
-out_nrg:
 	spin_unlock(&resv->lock);
 	return chg;
 }
@@ -469,17 +607,20 @@
  * of the resv_map keeps track of the operations in progress between
  * calls to region_chg and region_add.  Operations are sometimes
  * aborted after the call to region_chg.  In such cases, region_abort
- * is called to decrement the adds_in_progress counter.
+ * is called to decrement the adds_in_progress counter. regions_needed
+ * is the value returned by the region_chg call, it is used to decrement
+ * the adds_in_progress counter.
  *
  * NOTE: The range arguments [f, t) are not needed or used in this
  * routine.  They are kept to make reading the calling code easier as
  * arguments will match the associated region_chg call.
  */
-static void region_abort(struct resv_map *resv, long f, long t)
+static void region_abort(struct resv_map *resv, long f, long t,
+			 long regions_needed)
 {
 	spin_lock(&resv->lock);
 	VM_BUG_ON(!resv->region_cache_count);
-	resv->adds_in_progress--;
+	resv->adds_in_progress -= regions_needed;
 	spin_unlock(&resv->lock);
 }
 
@@ -543,10 +684,15 @@
 			}
 
 			del += t - f;
+			hugetlb_cgroup_uncharge_file_region(
+				resv, rg, t - f, false);
 
 			/* New entry for end of split region */
 			nrg->from = t;
 			nrg->to = rg->to;
+
+			copy_hugetlb_cgroup_uncharge_info(nrg, rg);
+
 			INIT_LIST_HEAD(&nrg->link);
 
 			/* Original entry is trimmed */
@@ -559,15 +705,23 @@
 
 		if (f <= rg->from && t >= rg->to) { /* Remove entire region */
 			del += rg->to - rg->from;
+			hugetlb_cgroup_uncharge_file_region(resv, rg,
+							    rg->to - rg->from, true);
 			list_del(&rg->link);
 			kfree(rg);
 			continue;
 		}
 
 		if (f <= rg->from) {	/* Trim beginning of region */
+			hugetlb_cgroup_uncharge_file_region(resv, rg,
+							    t - rg->from, false);
+
 			del += t - rg->from;
 			rg->from = t;
 		} else {		/* Trim end of region */
+			hugetlb_cgroup_uncharge_file_region(resv, rg,
+							    rg->to - f, false);
+
 			del += rg->to - f;
 			rg->to = f;
 		}
@@ -718,6 +872,25 @@
 	vma->vm_private_data = (void *)value;
 }
 
+static void
+resv_map_set_hugetlb_cgroup_uncharge_info(struct resv_map *resv_map,
+					  struct hugetlb_cgroup *h_cg,
+					  struct hstate *h)
+{
+#ifdef CONFIG_CGROUP_HUGETLB
+	if (!h_cg || !h) {
+		resv_map->reservation_counter = NULL;
+		resv_map->pages_per_hpage = 0;
+		resv_map->css = NULL;
+	} else {
+		resv_map->reservation_counter =
+			&h_cg->rsvd_hugepage[hstate_index(h)];
+		resv_map->pages_per_hpage = pages_per_huge_page(h);
+		resv_map->css = &h_cg->css;
+	}
+#endif
+}
+
 struct resv_map *resv_map_alloc(void)
 {
 	struct resv_map *resv_map = kmalloc(sizeof(*resv_map), GFP_KERNEL);
@@ -734,6 +907,13 @@
 	INIT_LIST_HEAD(&resv_map->regions);
 
 	resv_map->adds_in_progress = 0;
+	/*
+	 * Initialize these to 0. On shared mappings, 0's here indicate these
+	 * fields don't do cgroup accounting. On private mappings, these will be
+	 * re-initialized to the proper values, to indicate that hugetlb cgroup
+	 * reservations are to be un-charged from here.
+	 */
+	resv_map_set_hugetlb_cgroup_uncharge_info(resv_map, NULL, NULL);
 
 	INIT_LIST_HEAD(&resv_map->region_cache);
 	list_add(&rg->link, &resv_map->region_cache);
@@ -847,7 +1027,7 @@
 		 * We know VM_NORESERVE is not set.  Therefore, there SHOULD
 		 * be a region map for all pages.  The only situation where
 		 * there is no region map is if a hole was punched via
-		 * fallocate.  In this case, there really are no reverves to
+		 * fallocate.  In this case, there really are no reserves to
 		 * use.  This situation is indicated if chg != 0.
 		 */
 		if (chg)
@@ -897,22 +1077,24 @@
 static struct page *dequeue_huge_page_node_exact(struct hstate *h, int nid)
 {
 	struct page *page;
+	bool nocma = !!(current->flags & PF_MEMALLOC_NOCMA);
 
-	list_for_each_entry(page, &h->hugepage_freelists[nid], lru)
-		if (!PageHWPoison(page))
-			break;
-	/*
-	 * if 'non-isolated free hugepage' not found on the list,
-	 * the allocation fails.
-	 */
-	if (&h->hugepage_freelists[nid] == &page->lru)
-		return NULL;
-	list_move(&page->lru, &h->hugepage_activelist);
-	set_page_refcounted(page);
-	ClearPageHugeFreed(page);
-	h->free_huge_pages--;
-	h->free_huge_pages_node[nid]--;
-	return page;
+	list_for_each_entry(page, &h->hugepage_freelists[nid], lru) {
+		if (nocma && is_migrate_cma_page(page))
+			continue;
+
+		if (PageHWPoison(page))
+			continue;
+
+		list_move(&page->lru, &h->hugepage_activelist);
+		set_page_refcounted(page);
+		ClearPageHugeFreed(page);
+		h->free_huge_pages--;
+		h->free_huge_pages_node[nid]--;
+		return page;
+	}
+
+	return NULL;
 }
 
 static struct page *dequeue_huge_page_nodemask(struct hstate *h, gfp_t gfp_mask, int nid,
@@ -951,15 +1133,6 @@
 	return NULL;
 }
 
-/* Movability of hugepages depends on migration support. */
-static inline gfp_t htlb_alloc_mask(struct hstate *h)
-{
-	if (hugepage_movable_supported(h))
-		return GFP_HIGHUSER_MOVABLE;
-	else
-		return GFP_HIGHUSER;
-}
-
 static struct page *dequeue_huge_page_vma(struct hstate *h,
 				struct vm_area_struct *vma,
 				unsigned long address, int avoid_reserve,
@@ -1079,104 +1252,69 @@
 	struct page *p = page + 1;
 
 	atomic_set(compound_mapcount_ptr(page), 0);
+	atomic_set(compound_pincount_ptr(page), 0);
+
 	for (i = 1; i < nr_pages; i++, p = mem_map_next(p, page, i)) {
 		clear_compound_head(p);
 		set_page_refcounted(p);
 	}
 
 	set_compound_order(page, 0);
+	page[1].compound_nr = 0;
 	__ClearPageHead(page);
 }
 
 static void free_gigantic_page(struct page *page, unsigned int order)
 {
+	/*
+	 * If the page isn't allocated using the cma allocator,
+	 * cma_release() returns false.
+	 */
+#ifdef CONFIG_CMA
+	if (cma_release(hugetlb_cma[page_to_nid(page)], page, 1 << order))
+		return;
+#endif
+
 	free_contig_range(page_to_pfn(page), 1 << order);
 }
 
 #ifdef CONFIG_CONTIG_ALLOC
-static int __alloc_gigantic_page(unsigned long start_pfn,
-				unsigned long nr_pages, gfp_t gfp_mask)
-{
-	unsigned long end_pfn = start_pfn + nr_pages;
-	return alloc_contig_range(start_pfn, end_pfn, MIGRATE_MOVABLE,
-				  gfp_mask);
-}
-
-static bool pfn_range_valid_gigantic(struct zone *z,
-			unsigned long start_pfn, unsigned long nr_pages)
-{
-	unsigned long i, end_pfn = start_pfn + nr_pages;
-	struct page *page;
-
-	for (i = start_pfn; i < end_pfn; i++) {
-		page = pfn_to_online_page(i);
-		if (!page)
-			return false;
-
-		if (page_zone(page) != z)
-			return false;
-
-		if (PageReserved(page))
-			return false;
-
-		if (page_count(page) > 0)
-			return false;
-
-		if (PageHuge(page))
-			return false;
-	}
-
-	return true;
-}
-
-static bool zone_spans_last_pfn(const struct zone *zone,
-			unsigned long start_pfn, unsigned long nr_pages)
-{
-	unsigned long last_pfn = start_pfn + nr_pages - 1;
-	return zone_spans_pfn(zone, last_pfn);
-}
-
 static struct page *alloc_gigantic_page(struct hstate *h, gfp_t gfp_mask,
 		int nid, nodemask_t *nodemask)
 {
-	unsigned int order = huge_page_order(h);
-	unsigned long nr_pages = 1 << order;
-	unsigned long ret, pfn, flags;
-	struct zonelist *zonelist;
-	struct zone *zone;
-	struct zoneref *z;
+	unsigned long nr_pages = 1UL << huge_page_order(h);
+	if (nid == NUMA_NO_NODE)
+		nid = numa_mem_id();
 
-	zonelist = node_zonelist(nid, gfp_mask);
-	for_each_zone_zonelist_nodemask(zone, z, zonelist, gfp_zone(gfp_mask), nodemask) {
-		spin_lock_irqsave(&zone->lock, flags);
+#ifdef CONFIG_CMA
+	{
+		struct page *page;
+		int node;
 
-		pfn = ALIGN(zone->zone_start_pfn, nr_pages);
-		while (zone_spans_last_pfn(zone, pfn, nr_pages)) {
-			if (pfn_range_valid_gigantic(zone, pfn, nr_pages)) {
-				/*
-				 * We release the zone lock here because
-				 * alloc_contig_range() will also lock the zone
-				 * at some point. If there's an allocation
-				 * spinning on this lock, it may win the race
-				 * and cause alloc_contig_range() to fail...
-				 */
-				spin_unlock_irqrestore(&zone->lock, flags);
-				ret = __alloc_gigantic_page(pfn, nr_pages, gfp_mask);
-				if (!ret)
-					return pfn_to_page(pfn);
-				spin_lock_irqsave(&zone->lock, flags);
-			}
-			pfn += nr_pages;
+		if (hugetlb_cma[nid]) {
+			page = cma_alloc(hugetlb_cma[nid], nr_pages,
+					huge_page_order(h), true);
+			if (page)
+				return page;
 		}
 
-		spin_unlock_irqrestore(&zone->lock, flags);
-	}
+		if (!(gfp_mask & __GFP_THISNODE)) {
+			for_each_node_mask(node, *nodemask) {
+				if (node == nid || !hugetlb_cma[node])
+					continue;
 
-	return NULL;
+				page = cma_alloc(hugetlb_cma[node], nr_pages,
+						huge_page_order(h), true);
+				if (page)
+					return page;
+			}
+		}
+	}
+#endif
+
+	return alloc_contig_pages(nr_pages, gfp_mask, nid, nodemask);
 }
 
-static void prep_new_huge_page(struct hstate *h, struct page *page, int nid);
-static void prep_compound_gigantic_page(struct page *page, unsigned int order);
 #else /* !CONFIG_CONTIG_ALLOC */
 static struct page *alloc_gigantic_page(struct hstate *h, gfp_t gfp_mask,
 					int nid, nodemask_t *nodemask)
@@ -1214,11 +1352,18 @@
 				1 << PG_writeback);
 	}
 	VM_BUG_ON_PAGE(hugetlb_cgroup_from_page(page), page);
+	VM_BUG_ON_PAGE(hugetlb_cgroup_from_page_rsvd(page), page);
 	set_compound_page_dtor(page, NULL_COMPOUND_DTOR);
 	set_page_refcounted(page);
 	if (hstate_is_gigantic(h)) {
+		/*
+		 * Temporarily drop the hugetlb_lock, because
+		 * we might block in free_gigantic_page().
+		 */
+		spin_unlock(&hugetlb_lock);
 		destroy_compound_gigantic_page(page, huge_page_order(h));
 		free_gigantic_page(page, huge_page_order(h));
+		spin_lock(&hugetlb_lock);
 	} else {
 		__free_pages(page, huge_page_order(h));
 	}
@@ -1324,6 +1469,8 @@
 	clear_page_huge_active(page);
 	hugetlb_cgroup_uncharge_page(hstate_index(h),
 				     pages_per_huge_page(h), page);
+	hugetlb_cgroup_uncharge_page_rsvd(hstate_index(h),
+					  pages_per_huge_page(h), page);
 	if (restore_reserve)
 		h->resv_huge_pages++;
 
@@ -1396,8 +1543,9 @@
 {
 	INIT_LIST_HEAD(&page->lru);
 	set_compound_page_dtor(page, HUGETLB_PAGE_DTOR);
-	spin_lock(&hugetlb_lock);
 	set_hugetlb_cgroup(page, NULL);
+	set_hugetlb_cgroup_rsvd(page, NULL);
+	spin_lock(&hugetlb_lock);
 	h->nr_huge_pages++;
 	h->nr_huge_pages_node[nid]++;
 	ClearPageHugeFreed(page);
@@ -1419,7 +1567,7 @@
 		 * For gigantic hugepages allocated through bootmem at
 		 * boot, it's safer to be consistent with the not-gigantic
 		 * hugepages and clear the PG_reserved bit from all tail pages
-		 * too.  Otherwse drivers using get_user_pages() to access tail
+		 * too.  Otherwise drivers using get_user_pages() to access tail
 		 * pages may get the reference counting wrong if they see
 		 * PG_reserved set on a tail page (despite the head page not
 		 * having PG_reserved set).  Enforcing this consistency between
@@ -1432,6 +1580,7 @@
 		set_compound_head(p, page);
 	}
 	atomic_set(compound_mapcount_ptr(page), -1);
+	atomic_set(compound_pincount_ptr(page), 0);
 }
 
 /*
@@ -1458,7 +1607,27 @@
 	if (!PageHead(page_head))
 		return 0;
 
-	return get_compound_page_dtor(page_head) == free_huge_page;
+	return page_head[1].compound_dtor == HUGETLB_PAGE_DTOR;
+}
+
+/*
+ * Find and lock address space (mapping) in write mode.
+ *
+ * Upon entry, the page is locked which means that page_mapping() is
+ * stable.  Due to locking order, we can only trylock_write.  If we can
+ * not get the lock, simply return NULL to caller.
+ */
+struct address_space *hugetlb_page_mapping_lock_write(struct page *hpage)
+{
+	struct address_space *mapping = page_mapping(hpage);
+
+	if (!mapping)
+		return mapping;
+
+	if (i_mmap_trylock_write(mapping))
+		return mapping;
+
+	return NULL;
 }
 
 pgoff_t hugetlb_basepage_index(struct page *page)
@@ -1753,7 +1922,7 @@
 	return page;
 }
 
-struct page *alloc_migrate_huge_page(struct hstate *h, gfp_t gfp_mask,
+static struct page *alloc_migrate_huge_page(struct hstate *h, gfp_t gfp_mask,
 				     int nid, nodemask_t *nmask)
 {
 	struct page *page;
@@ -1795,31 +1964,9 @@
 }
 
 /* page migration callback function */
-struct page *alloc_huge_page_node(struct hstate *h, int nid)
-{
-	gfp_t gfp_mask = htlb_alloc_mask(h);
-	struct page *page = NULL;
-
-	if (nid != NUMA_NO_NODE)
-		gfp_mask |= __GFP_THISNODE;
-
-	spin_lock(&hugetlb_lock);
-	if (h->free_huge_pages - h->resv_huge_pages > 0)
-		page = dequeue_huge_page_nodemask(h, gfp_mask, nid, NULL);
-	spin_unlock(&hugetlb_lock);
-
-	if (!page)
-		page = alloc_migrate_huge_page(h, gfp_mask, nid, NULL);
-
-	return page;
-}
-
-/* page migration callback function */
 struct page *alloc_huge_page_nodemask(struct hstate *h, int preferred_nid,
-		nodemask_t *nmask)
+		nodemask_t *nmask, gfp_t gfp_mask)
 {
-	gfp_t gfp_mask = htlb_alloc_mask(h);
-
 	spin_lock(&hugetlb_lock);
 	if (h->free_huge_pages - h->resv_huge_pages > 0) {
 		struct page *page;
@@ -1847,7 +1994,7 @@
 
 	gfp_mask = htlb_alloc_mask(h);
 	node = huge_node(vma, address, gfp_mask, &mpol, &nodemask);
-	page = alloc_huge_page_nodemask(h, node, nodemask);
+	page = alloc_huge_page_nodemask(h, node, nodemask, gfp_mask);
 	mpol_cond_put(mpol);
 
 	return page;
@@ -1858,6 +2005,7 @@
  * of size 'delta'.
  */
 static int gather_surplus_pages(struct hstate *h, int delta)
+	__must_hold(&hugetlb_lock)
 {
 	struct list_head surplus_list;
 	struct page *page, *tmp;
@@ -1975,7 +2123,7 @@
 	 * evenly across all nodes with memory. Iterate across these nodes
 	 * until we can no longer free unreserved surplus pages. This occurs
 	 * when the nodes with surplus pages have no free pages.
-	 * free_pool_huge_page() will balance the the freed pages across the
+	 * free_pool_huge_page() will balance the freed pages across the
 	 * on-line nodes with memory and will handle the hstate accounting.
 	 *
 	 * Note that we decrement resv_huge_pages as we free the pages.  If
@@ -2033,6 +2181,7 @@
 	struct resv_map *resv;
 	pgoff_t idx;
 	long ret;
+	long dummy_out_regions_needed;
 
 	resv = vma_resv_map(vma);
 	if (!resv)
@@ -2041,20 +2190,29 @@
 	idx = vma_hugecache_offset(h, vma, addr);
 	switch (mode) {
 	case VMA_NEEDS_RESV:
-		ret = region_chg(resv, idx, idx + 1);
+		ret = region_chg(resv, idx, idx + 1, &dummy_out_regions_needed);
+		/* We assume that vma_reservation_* routines always operate on
+		 * 1 page, and that adding to resv map a 1 page entry can only
+		 * ever require 1 region.
+		 */
+		VM_BUG_ON(dummy_out_regions_needed != 1);
 		break;
 	case VMA_COMMIT_RESV:
-		ret = region_add(resv, idx, idx + 1);
+		ret = region_add(resv, idx, idx + 1, 1, NULL, NULL);
+		/* region_add calls of range 1 should never fail. */
+		VM_BUG_ON(ret < 0);
 		break;
 	case VMA_END_RESV:
-		region_abort(resv, idx, idx + 1);
+		region_abort(resv, idx, idx + 1, 1);
 		ret = 0;
 		break;
 	case VMA_ADD_RESV:
-		if (vma->vm_flags & VM_MAYSHARE)
-			ret = region_add(resv, idx, idx + 1);
-		else {
-			region_abort(resv, idx, idx + 1);
+		if (vma->vm_flags & VM_MAYSHARE) {
+			ret = region_add(resv, idx, idx + 1, 1, NULL, NULL);
+			/* region_add calls of range 1 should never fail. */
+			VM_BUG_ON(ret < 0);
+		} else {
+			region_abort(resv, idx, idx + 1, 1);
 			ret = region_del(resv, idx, idx + 1);
 		}
 		break;
@@ -2165,6 +2323,7 @@
 	long gbl_chg;
 	int ret, idx;
 	struct hugetlb_cgroup *h_cg;
+	bool deferred_reserve;
 
 	idx = hstate_index(h);
 	/*
@@ -2202,9 +2361,19 @@
 			gbl_chg = 1;
 	}
 
+	/* If this allocation is not consuming a reservation, charge it now.
+	 */
+	deferred_reserve = map_chg || avoid_reserve || !vma_resv_map(vma);
+	if (deferred_reserve) {
+		ret = hugetlb_cgroup_charge_cgroup_rsvd(
+			idx, pages_per_huge_page(h), &h_cg);
+		if (ret)
+			goto out_subpool_put;
+	}
+
 	ret = hugetlb_cgroup_charge_cgroup(idx, pages_per_huge_page(h), &h_cg);
 	if (ret)
-		goto out_subpool_put;
+		goto out_uncharge_cgroup_reservation;
 
 	spin_lock(&hugetlb_lock);
 	/*
@@ -2223,10 +2392,18 @@
 			h->resv_huge_pages--;
 		}
 		spin_lock(&hugetlb_lock);
-		list_move(&page->lru, &h->hugepage_activelist);
+		list_add(&page->lru, &h->hugepage_activelist);
 		/* Fall through */
 	}
 	hugetlb_cgroup_commit_charge(idx, pages_per_huge_page(h), h_cg, page);
+	/* If allocation is not consuming a reservation, also store the
+	 * hugetlb_cgroup pointer on the page.
+	 */
+	if (deferred_reserve) {
+		hugetlb_cgroup_commit_charge_rsvd(idx, pages_per_huge_page(h),
+						  h_cg, page);
+	}
+
 	spin_unlock(&hugetlb_lock);
 
 	set_page_private(page, (unsigned long)spool);
@@ -2246,11 +2423,18 @@
 
 		rsv_adjust = hugepage_subpool_put_pages(spool, 1);
 		hugetlb_acct_memory(h, -rsv_adjust);
+		if (deferred_reserve)
+			hugetlb_cgroup_uncharge_page_rsvd(hstate_index(h),
+					pages_per_huge_page(h), page);
 	}
 	return page;
 
 out_uncharge_cgroup:
 	hugetlb_cgroup_uncharge_cgroup(idx, pages_per_huge_page(h), h_cg);
+out_uncharge_cgroup_reservation:
+	if (deferred_reserve)
+		hugetlb_cgroup_uncharge_cgroup_rsvd(idx, pages_per_huge_page(h),
+						    h_cg);
 out_subpool_put:
 	if (map_chg || avoid_reserve)
 		hugepage_subpool_put_pages(spool, 1);
@@ -2292,16 +2476,10 @@
 	return 1;
 }
 
-static void __init prep_compound_huge_page(struct page *page,
-		unsigned int order)
-{
-	if (unlikely(order > (MAX_ORDER - 1)))
-		prep_compound_gigantic_page(page, order);
-	else
-		prep_compound_page(page, order);
-}
-
-/* Put bootmem huge pages into the standard lists after mem_map is up */
+/*
+ * Put bootmem huge pages into the standard lists after mem_map is up.
+ * Note: This only applies to gigantic (order > MAX_ORDER) pages.
+ */
 static void __init gather_bootmem_prealloc(void)
 {
 	struct huge_bootmem_page *m;
@@ -2310,20 +2488,19 @@
 		struct page *page = virt_to_page(m);
 		struct hstate *h = m->hstate;
 
+		VM_BUG_ON(!hstate_is_gigantic(h));
 		WARN_ON(page_count(page) != 1);
-		prep_compound_huge_page(page, h->order);
+		prep_compound_gigantic_page(page, huge_page_order(h));
 		WARN_ON(PageReserved(page));
 		prep_new_huge_page(h, page, page_to_nid(page));
 		put_page(page); /* free it into the hugepage allocator */
 
 		/*
-		 * If we had gigantic hugepages allocated at boot time, we need
-		 * to restore the 'stolen' pages to totalram_pages in order to
-		 * fix confusing memory reports from free(1) and another
-		 * side-effects, like CommitLimit going negative.
+		 * We need to restore the 'stolen' pages to totalram_pages
+		 * in order to fix confusing memory reports from free(1) and
+		 * other side-effects, like CommitLimit going negative.
 		 */
-		if (hstate_is_gigantic(h))
-			adjust_managed_page_count(page, 1 << h->order);
+		adjust_managed_page_count(page, pages_per_huge_page(h));
 		cond_resched();
 	}
 }
@@ -2353,6 +2530,10 @@
 
 	for (i = 0; i < h->max_huge_pages; ++i) {
 		if (hstate_is_gigantic(h)) {
+			if (hugetlb_cma_size) {
+				pr_warn_once("HugeTLB: hugetlb_cma is enabled, skip boot time allocation\n");
+				goto free;
+			}
 			if (!alloc_bootmem_huge_page(h))
 				break;
 		} else if (!alloc_pool_huge_page(h,
@@ -2369,7 +2550,7 @@
 			h->max_huge_pages, buf, i);
 		h->max_huge_pages = i;
 	}
-
+free:
 	kfree(node_alloc_noretry);
 }
 
@@ -2839,7 +3020,7 @@
 		err = hugetlb_sysfs_add_hstate(h, hugepages_kobj,
 					 hstate_kobjs, &hstate_attr_group);
 		if (err)
-			pr_err("Hugetlb: Unable to add hstate %s", h->name);
+			pr_err("HugeTLB: Unable to add hstate %s", h->name);
 	}
 }
 
@@ -2943,7 +3124,7 @@
 						nhs->hstate_kobjs,
 						&per_node_hstate_attr_group);
 		if (err) {
-			pr_err("Hugetlb: Unable to add hstate %s for node %d\n",
+			pr_err("HugeTLB: Unable to add hstate %s for node %d\n",
 				h->name, node->dev.id);
 			hugetlb_unregister_node(node);
 			break;
@@ -2991,25 +3172,44 @@
 {
 	int i;
 
-	if (!hugepages_supported())
+	if (!hugepages_supported()) {
+		if (hugetlb_max_hstate || default_hstate_max_huge_pages)
+			pr_warn("HugeTLB: huge pages not supported, ignoring associated command-line parameters\n");
 		return 0;
+	}
 
-	if (!size_to_hstate(default_hstate_size)) {
-		if (default_hstate_size != 0) {
-			pr_err("HugeTLB: unsupported default_hugepagesz %lu. Reverting to %lu\n",
-			       default_hstate_size, HPAGE_SIZE);
+	/*
+	 * Make sure HPAGE_SIZE (HUGETLB_PAGE_ORDER) hstate exists.  Some
+	 * architectures depend on setup being done here.
+	 */
+	hugetlb_add_hstate(HUGETLB_PAGE_ORDER);
+	if (!parsed_default_hugepagesz) {
+		/*
+		 * If we did not parse a default huge page size, set
+		 * default_hstate_idx to HPAGE_SIZE hstate. And, if the
+		 * number of huge pages for this default size was implicitly
+		 * specified, set that here as well.
+		 * Note that the implicit setting will overwrite an explicit
+		 * setting.  A warning will be printed in this case.
+		 */
+		default_hstate_idx = hstate_index(size_to_hstate(HPAGE_SIZE));
+		if (default_hstate_max_huge_pages) {
+			if (default_hstate.max_huge_pages) {
+				char buf[32];
+
+				string_get_size(huge_page_size(&default_hstate),
+					1, STRING_UNITS_2, buf, 32);
+				pr_warn("HugeTLB: Ignoring hugepages=%lu associated with %s page size\n",
+					default_hstate.max_huge_pages, buf);
+				pr_warn("HugeTLB: Using hugepages=%lu for number of default huge pages\n",
+					default_hstate_max_huge_pages);
+			}
+			default_hstate.max_huge_pages =
+				default_hstate_max_huge_pages;
 		}
-
-		default_hstate_size = HPAGE_SIZE;
-		if (!size_to_hstate(default_hstate_size))
-			hugetlb_add_hstate(HUGETLB_PAGE_ORDER);
-	}
-	default_hstate_idx = hstate_index(size_to_hstate(default_hstate_size));
-	if (default_hstate_max_huge_pages) {
-		if (!default_hstate.max_huge_pages)
-			default_hstate.max_huge_pages = default_hstate_max_huge_pages;
 	}
 
+	hugetlb_cma_check();
 	hugetlb_init_hstates();
 	gather_bootmem_prealloc();
 	report_hugepages();
@@ -3034,10 +3234,10 @@
 }
 subsys_initcall(hugetlb_init);
 
-/* Should be called on processing a hugepagesz=... option */
-void __init hugetlb_bad_size(void)
+/* Overwritten by architectures with more huge page sizes */
+bool __init __attribute((weak)) arch_hugetlb_valid_size(unsigned long size)
 {
-	parsed_valid_hugepagesz = false;
+	return size == HPAGE_SIZE;
 }
 
 void __init hugetlb_add_hstate(unsigned int order)
@@ -3046,7 +3246,6 @@
 	unsigned long i;
 
 	if (size_to_hstate(PAGE_SIZE << order)) {
-		pr_warn("hugepagesz= specified twice, ignoring\n");
 		return;
 	}
 	BUG_ON(hugetlb_max_hstate >= HUGE_MAX_HSTATE);
@@ -3067,20 +3266,29 @@
 	parsed_hstate = h;
 }
 
-static int __init hugetlb_nrpages_setup(char *s)
+/*
+ * hugepages command line processing
+ * hugepages normally follows a valid hugepagsz or default_hugepagsz
+ * specification.  If not, ignore the hugepages value.  hugepages can also
+ * be the first huge page command line  option in which case it implicitly
+ * specifies the number of huge pages for the default size.
+ */
+static int __init hugepages_setup(char *s)
 {
 	unsigned long *mhp;
 	static unsigned long *last_mhp;
 
 	if (!parsed_valid_hugepagesz) {
-		pr_warn("hugepages = %s preceded by "
-			"an unsupported hugepagesz, ignoring\n", s);
+		pr_warn("HugeTLB: hugepages=%s does not follow a valid hugepagesz, ignoring\n", s);
 		parsed_valid_hugepagesz = true;
-		return 1;
+		return 0;
 	}
+
 	/*
-	 * !hugetlb_max_hstate means we haven't parsed a hugepagesz= parameter yet,
-	 * so this hugepages= parameter goes to the "default hstate".
+	 * !hugetlb_max_hstate means we haven't parsed a hugepagesz= parameter
+	 * yet, so this hugepages= parameter goes to the "default hstate".
+	 * Otherwise, it goes with the previously parsed hugepagesz or
+	 * default_hugepagesz.
 	 */
 	else if (!hugetlb_max_hstate)
 		mhp = &default_hstate_max_huge_pages;
@@ -3088,8 +3296,8 @@
 		mhp = &parsed_hstate->max_huge_pages;
 
 	if (mhp == last_mhp) {
-		pr_warn("hugepages= specified twice without interleaving hugepagesz=, ignoring\n");
-		return 1;
+		pr_warn("HugeTLB: hugepages= specified twice without interleaving hugepagesz=, ignoring hugepages=%s\n", s);
+		return 0;
 	}
 
 	if (sscanf(s, "%lu", mhp) <= 0)
@@ -3107,22 +3315,118 @@
 
 	return 1;
 }
-__setup("hugepages=", hugetlb_nrpages_setup);
+__setup("hugepages=", hugepages_setup);
 
-static int __init hugetlb_default_setup(char *s)
+/*
+ * hugepagesz command line processing
+ * A specific huge page size can only be specified once with hugepagesz.
+ * hugepagesz is followed by hugepages on the command line.  The global
+ * variable 'parsed_valid_hugepagesz' is used to determine if prior
+ * hugepagesz argument was valid.
+ */
+static int __init hugepagesz_setup(char *s)
 {
-	default_hstate_size = memparse(s, &s);
+	unsigned long size;
+	struct hstate *h;
+
+	parsed_valid_hugepagesz = false;
+	size = (unsigned long)memparse(s, NULL);
+
+	if (!arch_hugetlb_valid_size(size)) {
+		pr_err("HugeTLB: unsupported hugepagesz=%s\n", s);
+		return 0;
+	}
+
+	h = size_to_hstate(size);
+	if (h) {
+		/*
+		 * hstate for this size already exists.  This is normally
+		 * an error, but is allowed if the existing hstate is the
+		 * default hstate.  More specifically, it is only allowed if
+		 * the number of huge pages for the default hstate was not
+		 * previously specified.
+		 */
+		if (!parsed_default_hugepagesz ||  h != &default_hstate ||
+		    default_hstate.max_huge_pages) {
+			pr_warn("HugeTLB: hugepagesz=%s specified twice, ignoring\n", s);
+			return 0;
+		}
+
+		/*
+		 * No need to call hugetlb_add_hstate() as hstate already
+		 * exists.  But, do set parsed_hstate so that a following
+		 * hugepages= parameter will be applied to this hstate.
+		 */
+		parsed_hstate = h;
+		parsed_valid_hugepagesz = true;
+		return 1;
+	}
+
+	hugetlb_add_hstate(ilog2(size) - PAGE_SHIFT);
+	parsed_valid_hugepagesz = true;
 	return 1;
 }
-__setup("default_hugepagesz=", hugetlb_default_setup);
+__setup("hugepagesz=", hugepagesz_setup);
 
-static unsigned int cpuset_mems_nr(unsigned int *array)
+/*
+ * default_hugepagesz command line input
+ * Only one instance of default_hugepagesz allowed on command line.
+ */
+static int __init default_hugepagesz_setup(char *s)
+{
+	unsigned long size;
+
+	parsed_valid_hugepagesz = false;
+	if (parsed_default_hugepagesz) {
+		pr_err("HugeTLB: default_hugepagesz previously specified, ignoring %s\n", s);
+		return 0;
+	}
+
+	size = (unsigned long)memparse(s, NULL);
+
+	if (!arch_hugetlb_valid_size(size)) {
+		pr_err("HugeTLB: unsupported default_hugepagesz=%s\n", s);
+		return 0;
+	}
+
+	hugetlb_add_hstate(ilog2(size) - PAGE_SHIFT);
+	parsed_valid_hugepagesz = true;
+	parsed_default_hugepagesz = true;
+	default_hstate_idx = hstate_index(size_to_hstate(size));
+
+	/*
+	 * The number of default huge pages (for this size) could have been
+	 * specified as the first hugetlb parameter: hugepages=X.  If so,
+	 * then default_hstate_max_huge_pages is set.  If the default huge
+	 * page size is gigantic (>= MAX_ORDER), then the pages must be
+	 * allocated here from bootmem allocator.
+	 */
+	if (default_hstate_max_huge_pages) {
+		default_hstate.max_huge_pages = default_hstate_max_huge_pages;
+		if (hstate_is_gigantic(&default_hstate))
+			hugetlb_hstate_alloc_pages(&default_hstate);
+		default_hstate_max_huge_pages = 0;
+	}
+
+	return 1;
+}
+__setup("default_hugepagesz=", default_hugepagesz_setup);
+
+static unsigned int allowed_mems_nr(struct hstate *h)
 {
 	int node;
 	unsigned int nr = 0;
+	nodemask_t *mpol_allowed;
+	unsigned int *array = h->free_huge_pages_node;
+	gfp_t gfp_mask = htlb_alloc_mask(h);
 
-	for_each_node_mask(node, cpuset_current_mems_allowed)
-		nr += array[node];
+	mpol_allowed = policy_nodemask_current(gfp_mask);
+
+	for_each_node_mask(node, cpuset_current_mems_allowed) {
+		if (!mpol_allowed ||
+		    (mpol_allowed && node_isset(node, *mpol_allowed)))
+			nr += array[node];
+	}
 
 	return nr;
 }
@@ -3146,7 +3450,7 @@
 
 static int hugetlb_sysctl_handler_common(bool obey_mempolicy,
 			 struct ctl_table *table, int write,
-			 void __user *buffer, size_t *length, loff_t *ppos)
+			 void *buffer, size_t *length, loff_t *ppos)
 {
 	struct hstate *h = &default_hstate;
 	unsigned long tmp = h->max_huge_pages;
@@ -3168,7 +3472,7 @@
 }
 
 int hugetlb_sysctl_handler(struct ctl_table *table, int write,
-			  void __user *buffer, size_t *length, loff_t *ppos)
+			  void *buffer, size_t *length, loff_t *ppos)
 {
 
 	return hugetlb_sysctl_handler_common(false, table, write,
@@ -3177,7 +3481,7 @@
 
 #ifdef CONFIG_NUMA
 int hugetlb_mempolicy_sysctl_handler(struct ctl_table *table, int write,
-			  void __user *buffer, size_t *length, loff_t *ppos)
+			  void *buffer, size_t *length, loff_t *ppos)
 {
 	return hugetlb_sysctl_handler_common(true, table, write,
 							buffer, length, ppos);
@@ -3185,8 +3489,7 @@
 #endif /* CONFIG_NUMA */
 
 int hugetlb_overcommit_handler(struct ctl_table *table, int write,
-			void __user *buffer,
-			size_t *length, loff_t *ppos)
+		void *buffer, size_t *length, loff_t *ppos)
 {
 	struct hstate *h = &default_hstate;
 	unsigned long tmp;
@@ -3246,18 +3549,20 @@
 	seq_printf(m, "Hugetlb:        %8lu kB\n", total / 1024);
 }
 
-int hugetlb_report_node_meminfo(int nid, char *buf)
+int hugetlb_report_node_meminfo(char *buf, int len, int nid)
 {
 	struct hstate *h = &default_hstate;
+
 	if (!hugepages_supported())
 		return 0;
-	return sprintf(buf,
-		"Node %d HugePages_Total: %5u\n"
-		"Node %d HugePages_Free:  %5u\n"
-		"Node %d HugePages_Surp:  %5u\n",
-		nid, h->nr_huge_pages_node[nid],
-		nid, h->free_huge_pages_node[nid],
-		nid, h->surplus_huge_pages_node[nid]);
+
+	return sysfs_emit_at(buf, len,
+			     "Node %d HugePages_Total: %5u\n"
+			     "Node %d HugePages_Free:  %5u\n"
+			     "Node %d HugePages_Surp:  %5u\n",
+			     nid, h->nr_huge_pages_node[nid],
+			     nid, h->free_huge_pages_node[nid],
+			     nid, h->surplus_huge_pages_node[nid]);
 }
 
 void hugetlb_show_meminfo(void)
@@ -3316,12 +3621,18 @@
 	 * we fall back to check against current free page availability as
 	 * a best attempt and hopefully to minimize the impact of changing
 	 * semantics that cpuset has.
+	 *
+	 * Apart from cpuset, we also have memory policy mechanism that
+	 * also determines from which node the kernel will allocate memory
+	 * in a NUMA system. So similar to cpuset, we also should consider
+	 * the memory policy of the current task. Similar to the description
+	 * above.
 	 */
 	if (delta > 0) {
 		if (gather_surplus_pages(h, delta) < 0)
 			goto out;
 
-		if (delta > cpuset_mems_nr(h->free_huge_pages_node)) {
+		if (delta > allowed_mems_nr(h)) {
 			return_unused_surplus_pages(h, delta);
 			goto out;
 		}
@@ -3348,8 +3659,10 @@
 	 * after this open call completes.  It is therefore safe to take a
 	 * new reference here without additional locking.
 	 */
-	if (resv && is_vma_resv_set(vma, HPAGE_RESV_OWNER))
+	if (resv && is_vma_resv_set(vma, HPAGE_RESV_OWNER)) {
+		resv_map_dup_hugetlb_cgroup_uncharge_info(resv);
 		kref_get(&resv->refs);
+	}
 }
 
 static void hugetlb_vm_op_close(struct vm_area_struct *vma)
@@ -3367,9 +3680,7 @@
 	end = vma_hugecache_offset(h, vma, vma->vm_end);
 
 	reserve = (end - start) - region_count(resv, start, end);
-
-	kref_put(&resv->refs, resv_map_release);
-
+	hugetlb_cgroup_uncharge_counter(resv, start, end);
 	if (reserve) {
 		/*
 		 * Decrement reserve counts.  The global reserve count may be
@@ -3378,6 +3689,8 @@
 		gbl_reserve = hugepage_subpool_put_pages(spool, reserve);
 		hugetlb_acct_memory(h, -gbl_reserve);
 	}
+
+	kref_put(&resv->refs, resv_map_release);
 }
 
 static int hugetlb_vm_op_split(struct vm_area_struct *vma, unsigned long addr)
@@ -3457,23 +3770,23 @@
 	if (huge_pte_none(pte) || pte_present(pte))
 		return false;
 	swp = pte_to_swp_entry(pte);
-	if (non_swap_entry(swp) && is_migration_entry(swp))
+	if (is_migration_entry(swp))
 		return true;
 	else
 		return false;
 }
 
-static int is_hugetlb_entry_hwpoisoned(pte_t pte)
+static bool is_hugetlb_entry_hwpoisoned(pte_t pte)
 {
 	swp_entry_t swp;
 
 	if (huge_pte_none(pte) || pte_present(pte))
-		return 0;
+		return false;
 	swp = pte_to_swp_entry(pte);
-	if (non_swap_entry(swp) && is_hwpoison_entry(swp))
-		return 1;
+	if (is_hwpoison_entry(swp))
+		return true;
 	else
-		return 0;
+		return false;
 }
 
 int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src,
@@ -3485,6 +3798,7 @@
 	int cow;
 	struct hstate *h = hstate_vma(vma);
 	unsigned long sz = huge_page_size(h);
+	struct address_space *mapping = vma->vm_file->f_mapping;
 	struct mmu_notifier_range range;
 	int ret = 0;
 
@@ -3495,6 +3809,14 @@
 					vma->vm_start,
 					vma->vm_end);
 		mmu_notifier_invalidate_range_start(&range);
+	} else {
+		/*
+		 * For shared mappings i_mmap_rwsem must be held to call
+		 * huge_pte_alloc, otherwise the returned ptep could go
+		 * away if part of a shared pmd and another thread calls
+		 * huge_pmd_unshare.
+		 */
+		i_mmap_lock_read(mapping);
 	}
 
 	for (addr = vma->vm_start; addr < vma->vm_end; addr += sz) {
@@ -3572,6 +3894,8 @@
 
 	if (cow)
 		mmu_notifier_invalidate_range_end(&range);
+	else
+		i_mmap_unlock_read(mapping);
 
 	return ret;
 }
@@ -3589,6 +3913,7 @@
 	struct hstate *h = hstate_vma(vma);
 	unsigned long sz = huge_page_size(h);
 	struct mmu_notifier_range range;
+	bool force_flush = false;
 
 	WARN_ON(!is_vm_hugetlb_page(vma));
 	BUG_ON(start & ~huge_page_mask(h));
@@ -3615,12 +3940,10 @@
 			continue;
 
 		ptl = huge_pte_lock(h, mm, ptep);
-		if (huge_pmd_unshare(mm, &address, ptep)) {
+		if (huge_pmd_unshare(mm, vma, &address, ptep)) {
 			spin_unlock(ptl);
-			/*
-			 * We just unmapped a page of PMDs by clearing a PUD.
-			 * The caller's TLB flush range should cover this area.
-			 */
+			tlb_flush_pmd_range(tlb, address & PUD_MASK, PUD_SIZE);
+			force_flush = true;
 			continue;
 		}
 
@@ -3677,6 +4000,22 @@
 	}
 	mmu_notifier_invalidate_range_end(&range);
 	tlb_end_vma(tlb, vma);
+
+	/*
+	 * If we unshared PMDs, the TLB flush was not recorded in mmu_gather. We
+	 * could defer the flush until now, since by holding i_mmap_rwsem we
+	 * guaranteed that the last refernece would not be dropped. But we must
+	 * do the flushing before we return, as otherwise i_mmap_rwsem will be
+	 * dropped and the last reference to the shared PMDs page might be
+	 * dropped as well.
+	 *
+	 * In theory we could defer the freeing of the PMD pages as well, but
+	 * huge_pmd_unshare() relies on the exact page_count for the PMD page to
+	 * detect sharing, so we cannot defer the release of the page either.
+	 * Instead, do flush now.
+	 */
+	if (force_flush)
+		tlb_flush_mmu_tlbonly(tlb);
 }
 
 void __unmap_hugepage_range_final(struct mmu_gather *tlb,
@@ -3839,10 +4178,30 @@
 		 * may get SIGKILLed if it later faults.
 		 */
 		if (outside_reserve) {
+			struct address_space *mapping = vma->vm_file->f_mapping;
+			pgoff_t idx;
+			u32 hash;
+
 			put_page(old_page);
 			BUG_ON(huge_pte_none(pte));
+			/*
+			 * Drop hugetlb_fault_mutex and i_mmap_rwsem before
+			 * unmapping.  unmapping needs to hold i_mmap_rwsem
+			 * in write mode.  Dropping i_mmap_rwsem in read mode
+			 * here is OK as COW mappings do not interact with
+			 * PMD sharing.
+			 *
+			 * Reacquire both after unmap operation.
+			 */
+			idx = vma_hugecache_offset(h, vma, haddr);
+			hash = hugetlb_fault_mutex_hash(mapping, idx);
+			mutex_unlock(&hugetlb_fault_mutex_table[hash]);
+			i_mmap_unlock_read(mapping);
+
 			unmap_ref_private(mm, vma, old_page, haddr);
-			BUG_ON(huge_pte_none(pte));
+
+			i_mmap_lock_read(mapping);
+			mutex_lock(&hugetlb_fault_mutex_table[hash]);
 			spin_lock(ptl);
 			ptep = huge_pte_offset(mm, haddr, huge_page_size(h));
 			if (likely(ptep &&
@@ -3991,16 +4350,17 @@
 	}
 
 	/*
-	 * Use page lock to guard against racing truncation
-	 * before we get page_table_lock.
+	 * We can not race with truncation due to holding i_mmap_rwsem.
+	 * i_size is modified when holding i_mmap_rwsem, so check here
+	 * once for faults beyond end of file.
 	 */
+	size = i_size_read(mapping->host) >> huge_page_shift(h);
+	if (idx >= size)
+		goto out;
+
 retry:
 	page = find_lock_page(mapping, idx);
 	if (!page) {
-		size = i_size_read(mapping->host) >> huge_page_shift(h);
-		if (idx >= size)
-			goto out;
-
 		/*
 		 * Check for page in userfault range
 		 */
@@ -4020,13 +4380,15 @@
 			};
 
 			/*
-			 * hugetlb_fault_mutex must be dropped before
-			 * handling userfault.  Reacquire after handling
-			 * fault to make calling code simpler.
+			 * hugetlb_fault_mutex and i_mmap_rwsem must be
+			 * dropped before handling userfault.  Reacquire
+			 * after handling fault to make calling code simpler.
 			 */
-			hash = hugetlb_fault_mutex_hash(h, mapping, idx);
+			hash = hugetlb_fault_mutex_hash(mapping, idx);
 			mutex_unlock(&hugetlb_fault_mutex_table[hash]);
+			i_mmap_unlock_read(mapping);
 			ret = handle_userfault(&vmf, VM_UFFD_MISSING);
+			i_mmap_lock_read(mapping);
 			mutex_lock(&hugetlb_fault_mutex_table[hash]);
 			goto out;
 		}
@@ -4104,10 +4466,6 @@
 	}
 
 	ptl = huge_pte_lock(h, mm, ptep);
-	size = i_size_read(mapping->host) >> huge_page_shift(h);
-	if (idx >= size)
-		goto backout;
-
 	ret = 0;
 	if (!huge_pte_none(huge_ptep_get(ptep)))
 		goto backout;
@@ -4151,8 +4509,7 @@
 }
 
 #ifdef CONFIG_SMP
-u32 hugetlb_fault_mutex_hash(struct hstate *h, struct address_space *mapping,
-			    pgoff_t idx)
+u32 hugetlb_fault_mutex_hash(struct address_space *mapping, pgoff_t idx)
 {
 	unsigned long key[2];
 	u32 hash;
@@ -4169,8 +4526,7 @@
  * For uniprocesor systems we always use a single mutex, so just
  * return 0 and avoid the hashing overhead.
  */
-u32 hugetlb_fault_mutex_hash(struct hstate *h, struct address_space *mapping,
-			    pgoff_t idx)
+u32 hugetlb_fault_mutex_hash(struct address_space *mapping, pgoff_t idx)
 {
 	return 0;
 }
@@ -4193,6 +4549,11 @@
 
 	ptep = huge_pte_offset(mm, haddr, huge_page_size(h));
 	if (ptep) {
+		/*
+		 * Since we hold no locks, ptep could be stale.  That is
+		 * OK as we are only making decisions based on content and
+		 * not actually modifying content here.
+		 */
 		entry = huge_ptep_get(ptep);
 		if (unlikely(is_hugetlb_entry_migration(entry))) {
 			migration_entry_wait_huge(vma, mm, ptep);
@@ -4200,21 +4561,34 @@
 		} else if (unlikely(is_hugetlb_entry_hwpoisoned(entry)))
 			return VM_FAULT_HWPOISON_LARGE |
 				VM_FAULT_SET_HINDEX(hstate_index(h));
-	} else {
-		ptep = huge_pte_alloc(mm, haddr, huge_page_size(h));
-		if (!ptep)
-			return VM_FAULT_OOM;
 	}
 
+	/*
+	 * Acquire i_mmap_rwsem before calling huge_pte_alloc and hold
+	 * until finished with ptep.  This serves two purposes:
+	 * 1) It prevents huge_pmd_unshare from being called elsewhere
+	 *    and making the ptep no longer valid.
+	 * 2) It synchronizes us with i_size modifications during truncation.
+	 *
+	 * ptep could have already be assigned via huge_pte_offset.  That
+	 * is OK, as huge_pte_alloc will return the same value unless
+	 * something has changed.
+	 */
 	mapping = vma->vm_file->f_mapping;
-	idx = vma_hugecache_offset(h, vma, haddr);
+	i_mmap_lock_read(mapping);
+	ptep = huge_pte_alloc(mm, haddr, huge_page_size(h));
+	if (!ptep) {
+		i_mmap_unlock_read(mapping);
+		return VM_FAULT_OOM;
+	}
 
 	/*
 	 * Serialize hugepage allocation and instantiation, so that we don't
 	 * get spurious allocation failures if two CPUs race to instantiate
 	 * the same page in the page cache.
 	 */
-	hash = hugetlb_fault_mutex_hash(h, mapping, idx);
+	idx = vma_hugecache_offset(h, vma, haddr);
+	hash = hugetlb_fault_mutex_hash(mapping, idx);
 	mutex_lock(&hugetlb_fault_mutex_table[hash]);
 
 	entry = huge_ptep_get(ptep);
@@ -4228,9 +4602,9 @@
 	/*
 	 * entry could be a migration/hwpoison entry at this point, so this
 	 * check prevents the kernel from going below assuming that we have
-	 * a active hugepage in pagecache. This goto expects the 2nd page fault,
-	 * and is_hugetlb_entry_(migration|hwpoisoned) check will properly
-	 * handle it.
+	 * an active hugepage in pagecache. This goto expects the 2nd page
+	 * fault, and is_hugetlb_entry_(migration|hwpoisoned) check will
+	 * properly handle it.
 	 */
 	if (!pte_present(entry))
 		goto out_mutex;
@@ -4301,6 +4675,7 @@
 	}
 out_mutex:
 	mutex_unlock(&hugetlb_fault_mutex_table[hash]);
+	i_mmap_unlock_read(mapping);
 	/*
 	 * Generally it's safe to hold refcount during waiting page lock. But
 	 * here we just wait to defer the next page fault to avoid busy loop and
@@ -4354,7 +4729,7 @@
 						(const void __user *) src_addr,
 						pages_per_huge_page(h), false);
 
-		/* fallback to copy_from_user outside mmap_sem */
+		/* fallback to copy_from_user outside mmap_lock */
 		if (unlikely(ret)) {
 			ret = -ENOENT;
 			*pagep = page;
@@ -4457,7 +4832,7 @@
 long follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma,
 			 struct page **pages, struct vm_area_struct **vmas,
 			 unsigned long *position, unsigned long *nr_pages,
-			 long i, unsigned int flags, int *nonblocking)
+			 long i, unsigned int flags, int *locked)
 {
 	unsigned long pfn_offset;
 	unsigned long vaddr = *position;
@@ -4528,14 +4903,17 @@
 				spin_unlock(ptl);
 			if (flags & FOLL_WRITE)
 				fault_flags |= FAULT_FLAG_WRITE;
-			if (nonblocking)
-				fault_flags |= FAULT_FLAG_ALLOW_RETRY;
+			if (locked)
+				fault_flags |= FAULT_FLAG_ALLOW_RETRY |
+					FAULT_FLAG_KILLABLE;
 			if (flags & FOLL_NOWAIT)
 				fault_flags |= FAULT_FLAG_ALLOW_RETRY |
 					FAULT_FLAG_RETRY_NOWAIT;
 			if (flags & FOLL_TRIED) {
-				VM_WARN_ON_ONCE(fault_flags &
-						FAULT_FLAG_ALLOW_RETRY);
+				/*
+				 * Note: FAULT_FLAG_ALLOW_RETRY and
+				 * FAULT_FLAG_TRIED can co-exist
+				 */
 				fault_flags |= FAULT_FLAG_TRIED;
 			}
 			ret = hugetlb_fault(mm, vma, vaddr, fault_flags);
@@ -4545,9 +4923,9 @@
 				break;
 			}
 			if (ret & VM_FAULT_RETRY) {
-				if (nonblocking &&
+				if (locked &&
 				    !(fault_flags & FAULT_FLAG_RETRY_NOWAIT))
-					*nonblocking = 0;
+					*locked = 0;
 				*nr_pages = 0;
 				/*
 				 * VM_FAULT_RETRY must not return an
@@ -4567,22 +4945,39 @@
 		page = pte_page(huge_ptep_get(pte));
 
 		/*
-		 * Instead of doing 'try_get_page()' below in the same_page
-		 * loop, just check the count once here.
+		 * If subpage information not requested, update counters
+		 * and skip the same_page loop below.
 		 */
-		if (unlikely(page_count(page) <= 0)) {
-			if (pages) {
+		if (!pages && !vmas && !pfn_offset &&
+		    (vaddr + huge_page_size(h) < vma->vm_end) &&
+		    (remainder >= pages_per_huge_page(h))) {
+			vaddr += huge_page_size(h);
+			remainder -= pages_per_huge_page(h);
+			i += pages_per_huge_page(h);
+			spin_unlock(ptl);
+			continue;
+		}
+
+same_page:
+		if (pages) {
+			pages[i] = mem_map_offset(page, pfn_offset);
+			/*
+			 * try_grab_page() should always succeed here, because:
+			 * a) we hold the ptl lock, and b) we've just checked
+			 * that the huge page is present in the page tables. If
+			 * the huge page is present, then the tail pages must
+			 * also be present. The ptl prevents the head page and
+			 * tail pages from being rearranged in any way. So this
+			 * page must be available at this point, unless the page
+			 * refcount overflowed:
+			 */
+			if (WARN_ON_ONCE(!try_grab_page(pages[i], flags))) {
 				spin_unlock(ptl);
 				remainder = 0;
 				err = -ENOMEM;
 				break;
 			}
 		}
-same_page:
-		if (pages) {
-			pages[i] = mem_map_offset(page, pfn_offset);
-			get_page(pages[i]);
-		}
 
 		if (vmas)
 			vmas[i] = vma;
@@ -4652,7 +5047,7 @@
 		if (!ptep)
 			continue;
 		ptl = huge_pte_lock(h, mm, ptep);
-		if (huge_pmd_unshare(mm, &address, ptep)) {
+		if (huge_pmd_unshare(mm, vma, &address, ptep)) {
 			pages++;
 			spin_unlock(ptl);
 			shared_pmd = true;
@@ -4717,11 +5112,12 @@
 					struct vm_area_struct *vma,
 					vm_flags_t vm_flags)
 {
-	long ret, chg;
+	long ret, chg, add = -1;
 	struct hstate *h = hstate_inode(inode);
 	struct hugepage_subpool *spool = subpool_inode(inode);
 	struct resv_map *resv_map;
-	long gbl_reserve;
+	struct hugetlb_cgroup *h_cg = NULL;
+	long gbl_reserve, regions_needed = 0;
 
 	/* This should never happen */
 	if (from > to) {
@@ -4751,9 +5147,10 @@
 		 */
 		resv_map = inode_resv_map(inode);
 
-		chg = region_chg(resv_map, from, to);
+		chg = region_chg(resv_map, from, to, &regions_needed);
 
 	} else {
+		/* Private mapping. */
 		resv_map = resv_map_alloc();
 		if (!resv_map)
 			return -ENOMEM;
@@ -4769,6 +5166,21 @@
 		goto out_err;
 	}
 
+	ret = hugetlb_cgroup_charge_cgroup_rsvd(
+		hstate_index(h), chg * pages_per_huge_page(h), &h_cg);
+
+	if (ret < 0) {
+		ret = -ENOMEM;
+		goto out_err;
+	}
+
+	if (vma && !(vma->vm_flags & VM_MAYSHARE) && h_cg) {
+		/* For private mappings, the hugetlb_cgroup uncharge info hangs
+		 * of the resv_map.
+		 */
+		resv_map_set_hugetlb_cgroup_uncharge_info(resv_map, h_cg, h);
+	}
+
 	/*
 	 * There must be enough pages in the subpool for the mapping. If
 	 * the subpool has a minimum size, there may be some global
@@ -4777,7 +5189,7 @@
 	gbl_reserve = hugepage_subpool_get_pages(spool, chg);
 	if (gbl_reserve < 0) {
 		ret = -ENOSPC;
-		goto out_err;
+		goto out_uncharge_cgroup;
 	}
 
 	/*
@@ -4786,9 +5198,7 @@
 	 */
 	ret = hugetlb_acct_memory(h, gbl_reserve);
 	if (ret < 0) {
-		/* put back original number of pages, chg */
-		(void)hugepage_subpool_put_pages(spool, chg);
-		goto out_err;
+		goto out_put_pages;
 	}
 
 	/*
@@ -4803,9 +5213,13 @@
 	 * else has to be done for private mappings here
 	 */
 	if (!vma || vma->vm_flags & VM_MAYSHARE) {
-		long add = region_add(resv_map, from, to);
+		add = region_add(resv_map, from, to, regions_needed, h, h_cg);
 
-		if (unlikely(chg > add)) {
+		if (unlikely(add < 0)) {
+			hugetlb_acct_memory(h, -gbl_reserve);
+			ret = add;
+			goto out_put_pages;
+		} else if (unlikely(chg > add)) {
 			/*
 			 * pages in this range were added to the reserve
 			 * map between region_chg and region_add.  This
@@ -4815,17 +5229,41 @@
 			 */
 			long rsv_adjust;
 
+			/*
+			 * hugetlb_cgroup_uncharge_cgroup_rsvd() will put the
+			 * reference to h_cg->css. See comment below for detail.
+			 */
+			hugetlb_cgroup_uncharge_cgroup_rsvd(
+				hstate_index(h),
+				(chg - add) * pages_per_huge_page(h), h_cg);
+
 			rsv_adjust = hugepage_subpool_put_pages(spool,
 								chg - add);
 			hugetlb_acct_memory(h, -rsv_adjust);
+		} else if (h_cg) {
+			/*
+			 * The file_regions will hold their own reference to
+			 * h_cg->css. So we should release the reference held
+			 * via hugetlb_cgroup_charge_cgroup_rsvd() when we are
+			 * done.
+			 */
+			hugetlb_cgroup_put_rsvd_cgroup(h_cg);
 		}
 	}
 	return 0;
+out_put_pages:
+	/* put back original number of pages, chg */
+	(void)hugepage_subpool_put_pages(spool, chg);
+out_uncharge_cgroup:
+	hugetlb_cgroup_uncharge_cgroup_rsvd(hstate_index(h),
+					    chg * pages_per_huge_page(h), h_cg);
 out_err:
 	if (!vma || vma->vm_flags & VM_MAYSHARE)
-		/* Don't call region_abort if region_chg failed */
-		if (chg >= 0)
-			region_abort(resv_map, from, to);
+		/* Only call region_abort if the region_chg succeeded but the
+		 * region_add failed or didn't run.
+		 */
+		if (chg >= 0 && add < 0)
+			region_abort(resv_map, from, to, regions_needed);
 	if (vma && is_vma_resv_set(vma, HPAGE_RESV_OWNER))
 		kref_put(&resv_map->refs, resv_map_release);
 	return ret;
@@ -4939,10 +5377,18 @@
  * Search for a shareable pmd page for hugetlb. In any case calls pmd_alloc()
  * and returns the corresponding pte. While this is not necessary for the
  * !shared pmd case because we can allocate the pmd later as well, it makes the
- * code much cleaner. pmd allocation is essential for the shared case because
- * pud has to be populated inside the same i_mmap_rwsem section - otherwise
- * racing tasks could either miss the sharing (see huge_pte_offset) or select a
- * bad pmd for sharing.
+ * code much cleaner.
+ *
+ * This routine must be called with i_mmap_rwsem held in at least read mode if
+ * sharing is possible.  For hugetlbfs, this prevents removal of any page
+ * table entries associated with the address space.  This is important as we
+ * are setting up sharing based on existing page table entries (mappings).
+ *
+ * NOTE: This routine is only called from huge_pte_alloc.  Some callers of
+ * huge_pte_alloc know that sharing is not possible and do not take
+ * i_mmap_rwsem as a performance optimization.  This is handled by the
+ * if !vma_shareable check at the beginning of the routine. i_mmap_rwsem is
+ * only required for subsequent processing.
  */
 pte_t *huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud)
 {
@@ -4959,7 +5405,7 @@
 	if (!vma_shareable(vma, addr))
 		return (pte_t *)pmd_alloc(mm, pud, addr);
 
-	i_mmap_lock_write(mapping);
+	i_mmap_assert_locked(mapping);
 	vma_interval_tree_foreach(svma, &mapping->i_mmap, idx, idx) {
 		if (svma == vma)
 			continue;
@@ -4989,7 +5435,6 @@
 	spin_unlock(ptl);
 out:
 	pte = (pte_t *)pmd_alloc(mm, pud, addr);
-	i_mmap_unlock_write(mapping);
 	return pte;
 }
 
@@ -5000,17 +5445,19 @@
  * indicated by page_count > 1, unmap is achieved by clearing pud and
  * decrementing the ref count. If count == 1, the pte page is not shared.
  *
- * called with page table lock held.
+ * Called with page table lock held and i_mmap_rwsem held in write mode.
  *
  * returns: 1 successfully unmapped a shared pte page
  *	    0 the underlying pte page is not shared, or it is the last user
  */
-int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep)
+int huge_pmd_unshare(struct mm_struct *mm, struct vm_area_struct *vma,
+					unsigned long *addr, pte_t *ptep)
 {
 	pgd_t *pgd = pgd_offset(mm, *addr);
 	p4d_t *p4d = p4d_offset(pgd, *addr);
 	pud_t *pud = pud_offset(p4d, *addr);
 
+	i_mmap_assert_write_locked(vma->vm_file->f_mapping);
 	BUG_ON(page_count(virt_to_page(ptep)) == 0);
 	if (page_count(virt_to_page(ptep)) == 1)
 		return 0;
@@ -5028,7 +5475,8 @@
 	return NULL;
 }
 
-int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep)
+int huge_pmd_unshare(struct mm_struct *mm, struct vm_area_struct *vma,
+				unsigned long *addr, pte_t *ptep)
 {
 	return 0;
 }
@@ -5074,8 +5522,8 @@
  * huge_pte_offset() - Walk the page table to resolve the hugepage
  * entry at address @addr
  *
- * Return: Pointer to page table or swap entry (PUD or PMD) for
- * address @addr, or NULL if a p*d_none() entry is encountered and the
+ * Return: Pointer to page table entry (PUD or PMD) for
+ * address @addr, or NULL if a !p*d_present() entry is encountered and the
  * size @sz doesn't match the hugepage size at this level of the page
  * table.
  */
@@ -5084,8 +5532,8 @@
 {
 	pgd_t *pgd;
 	p4d_t *p4d;
-	pud_t *pud, pud_entry;
-	pmd_t *pmd, pmd_entry;
+	pud_t *pud;
+	pmd_t *pmd;
 
 	pgd = pgd_offset(mm, addr);
 	if (!pgd_present(*pgd))
@@ -5095,22 +5543,16 @@
 		return NULL;
 
 	pud = pud_offset(p4d, addr);
-	pud_entry = READ_ONCE(*pud);
-	if (sz != PUD_SIZE && pud_none(pud_entry))
-		return NULL;
-	/* hugepage or swap? */
-	if (pud_huge(pud_entry) || !pud_present(pud_entry))
+	if (sz == PUD_SIZE)
+		/* must be pud huge, non-present or none */
 		return (pte_t *)pud;
+	if (!pud_present(*pud))
+		return NULL;
+	/* must have a valid entry and size to go further */
 
 	pmd = pmd_offset(pud, addr);
-	pmd_entry = READ_ONCE(*pmd);
-	if (sz != PMD_SIZE && pmd_none(pmd_entry))
-		return NULL;
-	/* hugepage or swap? */
-	if (pmd_huge(pmd_entry) || !pmd_present(pmd_entry))
-		return (pte_t *)pmd;
-
-	return NULL;
+	/* must be pmd huge, non-present or none */
+	return (pte_t *)pmd;
 }
 
 #endif /* CONFIG_ARCH_WANT_GENERAL_HUGETLB */
@@ -5141,6 +5583,12 @@
 	struct page *page = NULL;
 	spinlock_t *ptl;
 	pte_t pte;
+
+	/* FOLL_GET and FOLL_PIN are mutually exclusive. */
+	if (WARN_ON_ONCE((flags & (FOLL_PIN | FOLL_GET)) ==
+			 (FOLL_PIN | FOLL_GET)))
+		return NULL;
+
 retry:
 	ptl = pmd_lockptr(mm, pmd);
 	spin_lock(ptl);
@@ -5153,8 +5601,18 @@
 	pte = huge_ptep_get((pte_t *)pmd);
 	if (pte_present(pte)) {
 		page = pmd_page(*pmd) + ((address & ~PMD_MASK) >> PAGE_SHIFT);
-		if (flags & FOLL_GET)
-			get_page(page);
+		/*
+		 * try_grab_page() should always succeed here, because: a) we
+		 * hold the pmd (ptl) lock, and b) we've just checked that the
+		 * huge pmd (head) page is present in the page tables. The ptl
+		 * prevents the head page and tail pages from being rearranged
+		 * in any way. So this page must be available at this point,
+		 * unless the page refcount overflowed:
+		 */
+		if (WARN_ON_ONCE(!try_grab_page(page, flags))) {
+			page = NULL;
+			goto out;
+		}
 	} else {
 		if (is_hugetlb_entry_migration(pte)) {
 			spin_unlock(ptl);
@@ -5175,7 +5633,7 @@
 follow_huge_pud(struct mm_struct *mm, unsigned long address,
 		pud_t *pud, int flags)
 {
-	if (flags & FOLL_GET)
+	if (flags & (FOLL_GET | FOLL_PIN))
 		return NULL;
 
 	return pte_page(*(pte_t *)pud) + ((address & ~PUD_MASK) >> PAGE_SHIFT);
@@ -5184,7 +5642,7 @@
 struct page * __weak
 follow_huge_pgd(struct mm_struct *mm, unsigned long address, pgd_t *pgd, int flags)
 {
-	if (flags & FOLL_GET)
+	if (flags & (FOLL_GET | FOLL_PIN))
 		return NULL;
 
 	return pte_page(*(pte_t *)pgd) + ((address & ~PGDIR_MASK) >> PAGE_SHIFT);
@@ -5249,3 +5707,75 @@
 		spin_unlock(&hugetlb_lock);
 	}
 }
+
+#ifdef CONFIG_CMA
+static bool cma_reserve_called __initdata;
+
+static int __init cmdline_parse_hugetlb_cma(char *p)
+{
+	hugetlb_cma_size = memparse(p, &p);
+	return 0;
+}
+
+early_param("hugetlb_cma", cmdline_parse_hugetlb_cma);
+
+void __init hugetlb_cma_reserve(int order)
+{
+	unsigned long size, reserved, per_node;
+	int nid;
+
+	cma_reserve_called = true;
+
+	if (!hugetlb_cma_size)
+		return;
+
+	if (hugetlb_cma_size < (PAGE_SIZE << order)) {
+		pr_warn("hugetlb_cma: cma area should be at least %lu MiB\n",
+			(PAGE_SIZE << order) / SZ_1M);
+		return;
+	}
+
+	/*
+	 * If 3 GB area is requested on a machine with 4 numa nodes,
+	 * let's allocate 1 GB on first three nodes and ignore the last one.
+	 */
+	per_node = DIV_ROUND_UP(hugetlb_cma_size, nr_online_nodes);
+	pr_info("hugetlb_cma: reserve %lu MiB, up to %lu MiB per node\n",
+		hugetlb_cma_size / SZ_1M, per_node / SZ_1M);
+
+	reserved = 0;
+	for_each_node_state(nid, N_ONLINE) {
+		int res;
+		char name[CMA_MAX_NAME];
+
+		size = min(per_node, hugetlb_cma_size - reserved);
+		size = round_up(size, PAGE_SIZE << order);
+
+		snprintf(name, sizeof(name), "hugetlb%d", nid);
+		res = cma_declare_contiguous_nid(0, size, 0, PAGE_SIZE << order,
+						 0, false, name,
+						 &hugetlb_cma[nid], nid);
+		if (res) {
+			pr_warn("hugetlb_cma: reservation failed: err %d, node %d",
+				res, nid);
+			continue;
+		}
+
+		reserved += size;
+		pr_info("hugetlb_cma: reserved %lu MiB on node %d\n",
+			size / SZ_1M, nid);
+
+		if (reserved >= hugetlb_cma_size)
+			break;
+	}
+}
+
+void __init hugetlb_cma_check(void)
+{
+	if (!hugetlb_cma_size || cma_reserve_called)
+		return;
+
+	pr_warn("hugetlb_cma: the option isn't supported by current arch\n");
+}
+
+#endif /* CONFIG_CMA */