1 files changed, 28 insertions, 72 deletions

diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 6001ee6347a9..e2f7f5aaaafb 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -20,6 +20,7 @@
 #include <linux/mman.h>
 #include <linux/pagemap.h>
 #include <linux/migrate.h>
+#include <linux/hashtable.h>
 
 #include <asm/tlb.h>
 #include <asm/pgalloc.h>
@@ -62,12 +63,11 @@ static DECLARE_WAIT_QUEUE_HEAD(khugepaged_wait);
 static unsigned int khugepaged_max_ptes_none __read_mostly = HPAGE_PMD_NR-1;
 
 static int khugepaged(void *none);
-static int mm_slots_hash_init(void);
 static int khugepaged_slab_init(void);
-static void khugepaged_slab_free(void);
 
-#define MM_SLOTS_HASH_HEADS 1024
-static struct hlist_head *mm_slots_hash __read_mostly;
+#define MM_SLOTS_HASH_BITS 10
+static __read_mostly DEFINE_HASHTABLE(mm_slots_hash, MM_SLOTS_HASH_BITS);
+
 static struct kmem_cache *mm_slot_cache __read_mostly;
 
 /**
@@ -105,7 +105,6 @@ static int set_recommended_min_free_kbytes(void)
 	struct zone *zone;
 	int nr_zones = 0;
 	unsigned long recommended_min;
-	extern int min_free_kbytes;
 
 	if (!khugepaged_enabled())
 		return 0;
@@ -634,12 +633,6 @@ static int __init hugepage_init(void)
 	if (err)
 		goto out;
 
-	err = mm_slots_hash_init();
-	if (err) {
-		khugepaged_slab_free();
-		goto out;
-	}
-
 	register_shrinker(&huge_zero_page_shrinker);
 
 	/*
@@ -1257,6 +1250,10 @@ struct page *follow_trans_huge_pmd(struct vm_area_struct *vma,
 	if (flags & FOLL_WRITE && !pmd_write(*pmd))
 		goto out;
 
+	/* Avoid dumping huge zero page */
+	if ((flags & FOLL_DUMP) && is_huge_zero_pmd(*pmd))
+		return ERR_PTR(-EFAULT);
+
 	page = pmd_page(*pmd);
 	VM_BUG_ON(!PageHead(page));
 	if (flags & FOLL_TOUCH) {
@@ -1298,7 +1295,6 @@ int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	int target_nid;
 	int current_nid = -1;
 	bool migrated;
-	bool page_locked = false;
 
 	spin_lock(&mm->page_table_lock);
 	if (unlikely(!pmd_same(pmd, *pmdp)))
@@ -1320,7 +1316,6 @@ int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	/* Acquire the page lock to serialise THP migrations */
 	spin_unlock(&mm->page_table_lock);
 	lock_page(page);
-	page_locked = true;
 
 	/* Confirm the PTE did not while locked */
 	spin_lock(&mm->page_table_lock);
@@ -1333,34 +1328,26 @@ int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 
 	/* Migrate the THP to the requested node */
 	migrated = migrate_misplaced_transhuge_page(mm, vma,
-				pmdp, pmd, addr,
-				page, target_nid);
-	if (migrated)
-		current_nid = target_nid;
-	else {
-		spin_lock(&mm->page_table_lock);
-		if (unlikely(!pmd_same(pmd, *pmdp))) {
-			unlock_page(page);
-			goto out_unlock;
-		}
-		goto clear_pmdnuma;
-	}
+				pmdp, pmd, addr, page, target_nid);
+	if (!migrated)
+		goto check_same;
 
-	task_numa_fault(current_nid, HPAGE_PMD_NR, migrated);
+	task_numa_fault(target_nid, HPAGE_PMD_NR, true);
 	return 0;
 
+check_same:
+	spin_lock(&mm->page_table_lock);
+	if (unlikely(!pmd_same(pmd, *pmdp)))
+		goto out_unlock;
 clear_pmdnuma:
 	pmd = pmd_mknonnuma(pmd);
 	set_pmd_at(mm, haddr, pmdp, pmd);
 	VM_BUG_ON(pmd_numa(*pmdp));
 	update_mmu_cache_pmd(vma, addr, pmdp);
-	if (page_locked)
-		unlock_page(page);
-
 out_unlock:
 	spin_unlock(&mm->page_table_lock);
 	if (current_nid != -1)
-		task_numa_fault(current_nid, HPAGE_PMD_NR, migrated);
+		task_numa_fault(current_nid, HPAGE_PMD_NR, false);
 	return 0;
 }
 
@@ -1652,7 +1639,7 @@ static void __split_huge_page_refcount(struct page *page)
 		page_tail->mapping = page->mapping;
 
 		page_tail->index = page->index + i;
-		page_xchg_last_nid(page_tail, page_last_nid(page));
+		page_nid_xchg_last(page_tail, page_nid_last(page));
 
 		BUG_ON(!PageAnon(page_tail));
 		BUG_ON(!PageUptodate(page_tail));
@@ -1842,7 +1829,7 @@ int split_huge_page(struct page *page)
 
 	BUG_ON(PageCompound(page));
 out_unlock:
-	anon_vma_unlock(anon_vma);
+	anon_vma_unlock_write(anon_vma);
 	put_anon_vma(anon_vma);
 out:
 	return ret;
@@ -1904,12 +1891,6 @@ static int __init khugepaged_slab_init(void)
 	return 0;
 }
 
-static void __init khugepaged_slab_free(void)
-{
-	kmem_cache_destroy(mm_slot_cache);
-	mm_slot_cache = NULL;
-}
-
 static inline struct mm_slot *alloc_mm_slot(void)
 {
 	if (!mm_slot_cache)	/* initialization failed */
@@ -1922,47 +1903,22 @@ static inline void free_mm_slot(struct mm_slot *mm_slot)
 	kmem_cache_free(mm_slot_cache, mm_slot);
 }
 
-static int __init mm_slots_hash_init(void)
-{
-	mm_slots_hash = kzalloc(MM_SLOTS_HASH_HEADS * sizeof(struct hlist_head),
-				GFP_KERNEL);
-	if (!mm_slots_hash)
-		return -ENOMEM;
-	return 0;
-}
-
-#if 0
-static void __init mm_slots_hash_free(void)
-{
-	kfree(mm_slots_hash);
-	mm_slots_hash = NULL;
-}
-#endif
-
 static struct mm_slot *get_mm_slot(struct mm_struct *mm)
 {
 	struct mm_slot *mm_slot;
-	struct hlist_head *bucket;
-	struct hlist_node *node;
 
-	bucket = &mm_slots_hash[((unsigned long)mm / sizeof(struct mm_struct))
-				% MM_SLOTS_HASH_HEADS];
-	hlist_for_each_entry(mm_slot, node, bucket, hash) {
+	hash_for_each_possible(mm_slots_hash, mm_slot, hash, (unsigned long)mm)
 		if (mm == mm_slot->mm)
 			return mm_slot;
-	}
+
 	return NULL;
 }
 
 static void insert_to_mm_slots_hash(struct mm_struct *mm,
 				    struct mm_slot *mm_slot)
 {
-	struct hlist_head *bucket;
-
-	bucket = &mm_slots_hash[((unsigned long)mm / sizeof(struct mm_struct))
-				% MM_SLOTS_HASH_HEADS];
 	mm_slot->mm = mm;
-	hlist_add_head(&mm_slot->hash, bucket);
+	hash_add(mm_slots_hash, &mm_slot->hash, (long)mm);
 }
 
 static inline int khugepaged_test_exit(struct mm_struct *mm)
@@ -2031,7 +1987,7 @@ void __khugepaged_exit(struct mm_struct *mm)
 	spin_lock(&khugepaged_mm_lock);
 	mm_slot = get_mm_slot(mm);
 	if (mm_slot && khugepaged_scan.mm_slot != mm_slot) {
-		hlist_del(&mm_slot->hash);
+		hash_del(&mm_slot->hash);
 		list_del(&mm_slot->mm_node);
 		free = 1;
 	}
@@ -2364,7 +2320,7 @@ static void collapse_huge_page(struct mm_struct *mm,
 		BUG_ON(!pmd_none(*pmd));
 		set_pmd_at(mm, address, pmd, _pmd);
 		spin_unlock(&mm->page_table_lock);
-		anon_vma_unlock(vma->anon_vma);
+		anon_vma_unlock_write(vma->anon_vma);
 		goto out;
 	}
 
@@ -2372,7 +2328,7 @@ static void collapse_huge_page(struct mm_struct *mm,
 	 * All pages are isolated and locked so anon_vma rmap
 	 * can't run anymore.
 	 */
-	anon_vma_unlock(vma->anon_vma);
+	anon_vma_unlock_write(vma->anon_vma);
 
 	__collapse_huge_page_copy(pte, new_page, vma, address, ptl);
 	pte_unmap(pte);
@@ -2419,7 +2375,7 @@ static int khugepaged_scan_pmd(struct mm_struct *mm,
 	struct page *page;
 	unsigned long _address;
 	spinlock_t *ptl;
-	int node = -1;
+	int node = NUMA_NO_NODE;
 
 	VM_BUG_ON(address & ~HPAGE_PMD_MASK);
 
@@ -2449,7 +2405,7 @@ static int khugepaged_scan_pmd(struct mm_struct *mm,
 		 * be more sophisticated and look at more pages,
 		 * but isn't for now.
 		 */
-		if (node == -1)
+		if (node == NUMA_NO_NODE)
 			node = page_to_nid(page);
 		VM_BUG_ON(PageCompound(page));
 		if (!PageLRU(page) || PageLocked(page) || !PageAnon(page))
@@ -2480,7 +2436,7 @@ static void collect_mm_slot(struct mm_slot *mm_slot)
 
 	if (khugepaged_test_exit(mm)) {
 		/* free mm_slot */
-		hlist_del(&mm_slot->hash);
+		hash_del(&mm_slot->hash);
 		list_del(&mm_slot->mm_node);
 
 		/*