Merge branch 'akpm' (Andrew's patch-bomb)

Merge patches from Andrew Morton:
 "A few misc things and very nearly all of the MM tree.  A tremendous
  amount of stuff (again), including a significant rbtree library
  rework."

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (160 commits)
  sparc64: Support transparent huge pages.
  mm: thp: Use more portable PMD clearing sequenece in zap_huge_pmd().
  mm: Add and use update_mmu_cache_pmd() in transparent huge page code.
  sparc64: Document PGD and PMD layout.
  sparc64: Eliminate PTE table memory wastage.
  sparc64: Halve the size of PTE tables
  sparc64: Only support 4MB huge pages and 8KB base pages.
  memory-hotplug: suppress "Trying to free nonexistent resource <XXXXXXXXXXXXXXXX-YYYYYYYYYYYYYYYY>" warning
  mm: memcg: clean up mm_match_cgroup() signature
  mm: document PageHuge somewhat
  mm: use %pK for /proc/vmallocinfo
  mm, thp: fix mlock statistics
  mm, thp: fix mapped pages avoiding unevictable list on mlock
  memory-hotplug: update memory block's state and notify userspace
  memory-hotplug: preparation to notify memory block's state at memory hot remove
  mm: avoid section mismatch warning for memblock_type_name
  make GFP_NOTRACK definition unconditional
  cma: decrease cc.nr_migratepages after reclaiming pagelist
  CMA: migrate mlocked pages
  kpageflags: fix wrong KPF_THP on non-huge compound pages
  ...

1 files changed, 22 insertions, 12 deletions

diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index bc727122dd44..59a0059b39e2 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -30,7 +30,6 @@
 #include <linux/hugetlb.h>
 #include <linux/hugetlb_cgroup.h>
 #include <linux/node.h>
-#include <linux/hugetlb_cgroup.h>
 #include "internal.h"
 
 const unsigned long hugetlb_zero = 0, hugetlb_infinity = ~0UL;
@@ -637,6 +636,7 @@ static void free_huge_page(struct page *page)
 		h->surplus_huge_pages--;
 		h->surplus_huge_pages_node[nid]--;
 	} else {
+		arch_clear_hugepage_flags(page);
 		enqueue_huge_page(h, page);
 	}
 	spin_unlock(&hugetlb_lock);
@@ -671,6 +671,11 @@ static void prep_compound_gigantic_page(struct page *page, unsigned long order)
 	}
 }
 
+/*
+ * PageHuge() only returns true for hugetlbfs pages, but not for normal or
+ * transparent huge pages.  See the PageTransHuge() documentation for more
+ * details.
+ */
 int PageHuge(struct page *page)
 {
 	compound_page_dtor *dtor;
@@ -2355,13 +2360,15 @@ void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma,
 	struct page *page;
 	struct hstate *h = hstate_vma(vma);
 	unsigned long sz = huge_page_size(h);
+	const unsigned long mmun_start = start;	/* For mmu_notifiers */
+	const unsigned long mmun_end   = end;	/* For mmu_notifiers */
 
 	WARN_ON(!is_vm_hugetlb_page(vma));
 	BUG_ON(start & ~huge_page_mask(h));
 	BUG_ON(end & ~huge_page_mask(h));
 
 	tlb_start_vma(tlb, vma);
-	mmu_notifier_invalidate_range_start(mm, start, end);
+	mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end);
 again:
 	spin_lock(&mm->page_table_lock);
 	for (address = start; address < end; address += sz) {
@@ -2425,7 +2432,7 @@ again:
 		if (address < end && !ref_page)
 			goto again;
 	}
-	mmu_notifier_invalidate_range_end(mm, start, end);
+	mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end);
 	tlb_end_vma(tlb, vma);
 }
 
@@ -2473,7 +2480,6 @@ static int unmap_ref_private(struct mm_struct *mm, struct vm_area_struct *vma,
 	struct hstate *h = hstate_vma(vma);
 	struct vm_area_struct *iter_vma;
 	struct address_space *mapping;
-	struct prio_tree_iter iter;
 	pgoff_t pgoff;
 
 	/*
@@ -2481,7 +2487,8 @@ static int unmap_ref_private(struct mm_struct *mm, struct vm_area_struct *vma,
 	 * from page cache lookup which is in HPAGE_SIZE units.
 	 */
 	address = address & huge_page_mask(h);
-	pgoff = vma_hugecache_offset(h, vma, address);
+	pgoff = ((address - vma->vm_start) >> PAGE_SHIFT) +
+			vma->vm_pgoff;
 	mapping = vma->vm_file->f_dentry->d_inode->i_mapping;
 
 	/*
@@ -2490,7 +2497,7 @@ static int unmap_ref_private(struct mm_struct *mm, struct vm_area_struct *vma,
 	 * __unmap_hugepage_range() is called as the lock is already held
 	 */
 	mutex_lock(&mapping->i_mmap_mutex);
-	vma_prio_tree_foreach(iter_vma, &iter, &mapping->i_mmap, pgoff, pgoff) {
+	vma_interval_tree_foreach(iter_vma, &mapping->i_mmap, pgoff, pgoff) {
 		/* Do not unmap the current VMA */
 		if (iter_vma == vma)
 			continue;
@@ -2525,6 +2532,8 @@ static int hugetlb_cow(struct mm_struct *mm, struct vm_area_struct *vma,
 	struct page *old_page, *new_page;
 	int avoidcopy;
 	int outside_reserve = 0;
+	unsigned long mmun_start;	/* For mmu_notifiers */
+	unsigned long mmun_end;		/* For mmu_notifiers */
 
 	old_page = pte_page(pte);
 
@@ -2611,6 +2620,9 @@ retry_avoidcopy:
 			    pages_per_huge_page(h));
 	__SetPageUptodate(new_page);
 
+	mmun_start = address & huge_page_mask(h);
+	mmun_end = mmun_start + huge_page_size(h);
+	mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end);
 	/*
 	 * Retake the page_table_lock to check for racing updates
 	 * before the page tables are altered
@@ -2619,9 +2631,6 @@ retry_avoidcopy:
 	ptep = huge_pte_offset(mm, address & huge_page_mask(h));
 	if (likely(pte_same(huge_ptep_get(ptep), pte))) {
 		/* Break COW */
-		mmu_notifier_invalidate_range_start(mm,
-			address & huge_page_mask(h),
-			(address & huge_page_mask(h)) + huge_page_size(h));
 		huge_ptep_clear_flush(vma, address, ptep);
 		set_huge_pte_at(mm, address, ptep,
 				make_huge_pte(vma, new_page, 1));
@@ -2629,10 +2638,11 @@ retry_avoidcopy:
 		hugepage_add_new_anon_rmap(new_page, vma, address);
 		/* Make the old page be freed below */
 		new_page = old_page;
-		mmu_notifier_invalidate_range_end(mm,
-			address & huge_page_mask(h),
-			(address & huge_page_mask(h)) + huge_page_size(h));
 	}
+	spin_unlock(&mm->page_table_lock);
+	mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end);
+	/* Caller expects lock to be held */
+	spin_lock(&mm->page_table_lock);
 	page_cache_release(new_page);
 	page_cache_release(old_page);
 	return 0;