1 files changed, 111 insertions, 24 deletions

diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 125c7dd55322..f1a45f5077fe 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -1416,12 +1416,13 @@ static void dissolve_free_huge_page(struct page *page)
 {
 	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);
+		list_del(&head->lru);
 		h->free_huge_pages--;
 		h->free_huge_pages_node[nid]--;
-		update_and_free_page(h, page);
+		update_and_free_page(h, head);
 	}
 	spin_unlock(&hugetlb_lock);
 }
@@ -1429,7 +1430,8 @@ static void dissolve_free_huge_page(struct page *page)
 /*
  * 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.
  */
 void dissolve_free_huge_pages(unsigned long start_pfn, unsigned long end_pfn)
 {
@@ -1438,7 +1440,6 @@ void dissolve_free_huge_pages(unsigned long start_pfn, unsigned long end_pfn)
 	if (!hugepages_supported())
 		return;
 
-	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));
 }
@@ -1722,23 +1723,32 @@ free:
 }
 
 /*
- * When releasing a hugetlb pool reservation, any surplus pages that were
- * allocated to satisfy the reservation must be explicitly freed if they were
- * never used.
- * Called with hugetlb_lock held.
+ * This routine has two main purposes:
+ * 1) Decrement the reservation count (resv_huge_pages) by the value passed
+ *    in unused_resv_pages.  This corresponds to the prior adjustments made
+ *    to the associated reservation map.
+ * 2) Free any unused surplus pages that may have been allocated to satisfy
+ *    the reservation.  As many as unused_resv_pages may be freed.
+ *
+ * Called with hugetlb_lock held.  However, the lock could be dropped (and
+ * reacquired) during calls to cond_resched_lock.  Whenever dropping the lock,
+ * we must make sure nobody else can claim pages we are in the process of
+ * freeing.  Do this by ensuring resv_huge_page always is greater than the
+ * number of huge pages we plan to free when dropping the lock.
  */
 static void return_unused_surplus_pages(struct hstate *h,
 					unsigned long unused_resv_pages)
 {
 	unsigned long nr_pages;
 
-	/* Uncommit the reservation */
-	h->resv_huge_pages -= unused_resv_pages;
-
 	/* Cannot return gigantic pages currently */
 	if (hstate_is_gigantic(h))
-		return;
+		goto out;
 
+	/*
+	 * Part (or even all) of the reservation could have been backed
+	 * by pre-allocated pages. Only free surplus pages.
+	 */
 	nr_pages = min(unused_resv_pages, h->surplus_huge_pages);
 
 	/*
@@ -1748,12 +1758,22 @@ static void return_unused_surplus_pages(struct hstate *h,
 	 * when the nodes with surplus pages have no free pages.
 	 * free_pool_huge_page() will balance the 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
+	 * we drop the lock, resv_huge_pages will still be sufficiently large
+	 * to cover subsequent pages we may free.
 	 */
 	while (nr_pages--) {
+		h->resv_huge_pages--;
+		unused_resv_pages--;
 		if (!free_pool_huge_page(h, &node_states[N_MEMORY], 1))
-			break;
+			goto out;
 		cond_resched_lock(&hugetlb_lock);
 	}
+
+out:
+	/* Fully uncommit the reservation */
+	h->resv_huge_pages -= unused_resv_pages;
 }
 
 
@@ -2018,6 +2038,7 @@ static void __init gather_bootmem_prealloc(void)
 		 */
 		if (hstate_is_gigantic(h))
 			adjust_managed_page_count(page, 1 << h->order);
+		cond_resched();
 	}
 }
 
@@ -3082,7 +3103,7 @@ static int is_hugetlb_entry_hwpoisoned(pte_t pte)
 int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src,
 			    struct vm_area_struct *vma)
 {
-	pte_t *src_pte, *dst_pte, entry;
+	pte_t *src_pte, *dst_pte, entry, dst_entry;
 	struct page *ptepage;
 	unsigned long addr;
 	int cow;
@@ -3110,15 +3131,30 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src,
 			break;
 		}
 
-		/* If the pagetables are shared don't copy or take references */
-		if (dst_pte == src_pte)
+		/*
+		 * If the pagetables are shared don't copy or take references.
+		 * dst_pte == src_pte is the common case of src/dest sharing.
+		 *
+		 * However, src could have 'unshared' and dst shares with
+		 * another vma.  If dst_pte !none, this implies sharing.
+		 * Check here before taking page table lock, and once again
+		 * after taking the lock below.
+		 */
+		dst_entry = huge_ptep_get(dst_pte);
+		if ((dst_pte == src_pte) || !huge_pte_none(dst_entry))
 			continue;
 
 		dst_ptl = huge_pte_lock(h, dst, dst_pte);
 		src_ptl = huge_pte_lockptr(h, src, src_pte);
 		spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING);
 		entry = huge_ptep_get(src_pte);
-		if (huge_pte_none(entry)) { /* skip none entry */
+		dst_entry = huge_ptep_get(dst_pte);
+		if (huge_pte_none(entry) || !huge_pte_none(dst_entry)) {
+			/*
+			 * Skip if src entry none.  Also, skip in the
+			 * unlikely case dst entry !none as this implies
+			 * sharing with another vma.
+			 */
 			;
 		} else if (unlikely(is_hugetlb_entry_migration(entry) ||
 				    is_hugetlb_entry_hwpoisoned(entry))) {
@@ -3516,6 +3552,12 @@ int huge_add_to_page_cache(struct page *page, struct address_space *mapping,
 		return err;
 	ClearPagePrivate(page);
 
+	/*
+	 * set page dirty so that it will not be removed from cache/file
+	 * by non-hugetlbfs specific code paths.
+	 */
+	set_page_dirty(page);
+
 	spin_lock(&inode->i_lock);
 	inode->i_blocks += blocks_per_huge_page(h);
 	spin_unlock(&inode->i_lock);
@@ -4011,6 +4053,14 @@ int hugetlb_reserve_pages(struct inode *inode,
 	struct resv_map *resv_map;
 	long gbl_reserve;
 
+	/* This should never happen */
+	if (from > to) {
+#ifdef CONFIG_DEBUG_VM
+		WARN(1, "%s called with a negative range\n", __func__);
+#endif
+		return -EINVAL;
+	}
+
 	/*
 	 * Only apply hugepage reservation if asked. At fault time, an
 	 * attempt will be made for VM_NORESERVE to allocate a page
@@ -4100,7 +4150,9 @@ int hugetlb_reserve_pages(struct inode *inode,
 	return 0;
 out_err:
 	if (!vma || vma->vm_flags & VM_MAYSHARE)
-		region_abort(resv_map, from, to);
+		/* Don't call region_abort if region_chg failed */
+		if (chg >= 0)
+			region_abort(resv_map, from, to);
 	if (vma && is_vma_resv_set(vma, HPAGE_RESV_OWNER))
 		kref_put(&resv_map->refs, resv_map_release);
 	return ret;
@@ -4174,13 +4226,41 @@ static bool vma_shareable(struct vm_area_struct *vma, unsigned long addr)
 	/*
 	 * check on proper vm_flags and page table alignment
 	 */
-	if (vma->vm_flags & VM_MAYSHARE &&
-	    vma->vm_start <= base && end <= vma->vm_end)
+	if (vma->vm_flags & VM_MAYSHARE && range_in_vma(vma, base, end))
 		return true;
 	return false;
 }
 
 /*
+ * Determine if start,end range within vma could be mapped by shared pmd.
+ * If yes, adjust start and end to cover range associated with possible
+ * shared pmd mappings.
+ */
+void adjust_range_if_pmd_sharing_possible(struct vm_area_struct *vma,
+				unsigned long *start, unsigned long *end)
+{
+	unsigned long check_addr = *start;
+
+	if (!(vma->vm_flags & VM_MAYSHARE))
+		return;
+
+	for (check_addr = *start; check_addr < *end; check_addr += PUD_SIZE) {
+		unsigned long a_start = check_addr & PUD_MASK;
+		unsigned long a_end = a_start + PUD_SIZE;
+
+		/*
+		 * If sharing is possible, adjust start/end if necessary.
+		 */
+		if (range_in_vma(vma, a_start, a_end)) {
+			if (a_start < *start)
+				*start = a_start;
+			if (a_end > *end)
+				*end = a_end;
+		}
+	}
+}
+
+/*
  * 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
@@ -4276,6 +4356,11 @@ int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep)
 {
 	return 0;
 }
+
+void adjust_range_if_pmd_sharing_possible(struct vm_area_struct *vma,
+				unsigned long *start, unsigned long *end)
+{
+}
 #define want_pmd_share()	(0)
 #endif /* CONFIG_ARCH_WANT_HUGE_PMD_SHARE */
 
@@ -4342,6 +4427,7 @@ follow_huge_pmd(struct mm_struct *mm, unsigned long address,
 {
 	struct page *page = NULL;
 	spinlock_t *ptl;
+	pte_t pte;
 retry:
 	ptl = pmd_lockptr(mm, pmd);
 	spin_lock(ptl);
@@ -4351,12 +4437,13 @@ retry:
 	 */
 	if (!pmd_huge(*pmd))
 		goto out;
-	if (pmd_present(*pmd)) {
+	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);
 	} else {
-		if (is_hugetlb_entry_migration(huge_ptep_get((pte_t *)pmd))) {
+		if (is_hugetlb_entry_migration(pte)) {
 			spin_unlock(ptl);
 			__migration_entry_wait(mm, (pte_t *)pmd, ptl);
 			goto retry;