Merge branch 'akpm' (final batch from Andrew)

Merge third patch-bumb from Andrew Morton:
 "This wraps me up for -rc1.
   - Lots of misc stuff and things which were deferred/missed from
     patchbombings 1 & 2.
   - ocfs2 things
   - lib/scatterlist
   - hfsplus
   - fatfs
   - documentation
   - signals
   - procfs
   - lockdep
   - coredump
   - seqfile core
   - kexec
   - Tejun's large IDR tree reworkings
   - ipmi
   - partitions
   - nbd
   - random() things
   - kfifo
   - tools/testing/selftests updates
   - Sasha's large and pointless hlist cleanup"

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (163 commits)
  hlist: drop the node parameter from iterators
  kcmp: make it depend on CHECKPOINT_RESTORE
  selftests: add a simple doc
  tools/testing/selftests/Makefile: rearrange targets
  selftests/efivarfs: add create-read test
  selftests/efivarfs: add empty file creation test
  selftests: add tests for efivarfs
  kfifo: fix kfifo_alloc() and kfifo_init()
  kfifo: move kfifo.c from kernel/ to lib/
  arch Kconfig: centralise CONFIG_ARCH_NO_VIRT_TO_BUS
  w1: add support for DS2413 Dual Channel Addressable Switch
  memstick: move the dereference below the NULL test
  drivers/pps/clients/pps-gpio.c: use devm_kzalloc
  Documentation/DMA-API-HOWTO.txt: fix typo
  include/linux/eventfd.h: fix incorrect filename is a comment
  mtd: mtd_stresstest: use prandom_bytes()
  mtd: mtd_subpagetest: convert to use prandom library
  mtd: mtd_speedtest: use prandom_bytes
  mtd: mtd_pagetest: convert to use prandom library
  mtd: mtd_oobtest: convert to use prandom library
  ...

7 files changed, 41 insertions, 42 deletions

diff --git a/mm/Kconfig b/mm/Kconfig
index 2c7aea7106f9..ae55c1e04d10 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -287,7 +287,7 @@ config NR_QUICK
 
 config VIRT_TO_BUS
 	def_bool y
-	depends on !ARCH_NO_VIRT_TO_BUS
+	depends on HAVE_VIRT_TO_BUS
 
 config MMU_NOTIFIER
 	bool
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index bfa142e67b1c..e2f7f5aaaafb 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1906,9 +1906,8 @@ static inline void free_mm_slot(struct mm_slot *mm_slot)
 static struct mm_slot *get_mm_slot(struct mm_struct *mm)
 {
 	struct mm_slot *mm_slot;
-	struct hlist_node *node;
 
-	hash_for_each_possible(mm_slots_hash, mm_slot, node, hash, (unsigned long)mm)
+	hash_for_each_possible(mm_slots_hash, mm_slot, hash, (unsigned long)mm)
 		if (mm == mm_slot->mm)
 			return mm_slot;
 
diff --git a/mm/internal.h b/mm/internal.h
index 1c0c4cc0fcf7..8562de0a5197 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -195,7 +195,7 @@ static inline int mlocked_vma_newpage(struct vm_area_struct *vma,
  * must be called with vma's mmap_sem held for read or write, and page locked.
  */
 extern void mlock_vma_page(struct page *page);
-extern void munlock_vma_page(struct page *page);
+extern unsigned int munlock_vma_page(struct page *page);
 
 /*
  * Clear the page's PageMlocked().  This can be useful in a situation where
diff --git a/mm/kmemleak.c b/mm/kmemleak.c
index 83dd5fbf5e60..c8d7f3110fd0 100644
--- a/mm/kmemleak.c
+++ b/mm/kmemleak.c
@@ -436,7 +436,7 @@ static int get_object(struct kmemleak_object *object)
  */
 static void free_object_rcu(struct rcu_head *rcu)
 {
-	struct hlist_node *elem, *tmp;
+	struct hlist_node *tmp;
 	struct kmemleak_scan_area *area;
 	struct kmemleak_object *object =
 		container_of(rcu, struct kmemleak_object, rcu);
@@ -445,8 +445,8 @@ static void free_object_rcu(struct rcu_head *rcu)
 	 * Once use_count is 0 (guaranteed by put_object), there is no other
 	 * code accessing this object, hence no need for locking.
 	 */
-	hlist_for_each_entry_safe(area, elem, tmp, &object->area_list, node) {
-		hlist_del(elem);
+	hlist_for_each_entry_safe(area, tmp, &object->area_list, node) {
+		hlist_del(&area->node);
 		kmem_cache_free(scan_area_cache, area);
 	}
 	kmem_cache_free(object_cache, object);
@@ -1177,7 +1177,6 @@ static void scan_block(void *_start, void *_end,
 static void scan_object(struct kmemleak_object *object)
 {
 	struct kmemleak_scan_area *area;
-	struct hlist_node *elem;
 	unsigned long flags;
 
 	/*
@@ -1205,7 +1204,7 @@ static void scan_object(struct kmemleak_object *object)
 			spin_lock_irqsave(&object->lock, flags);
 		}
 	} else
-		hlist_for_each_entry(area, elem, &object->area_list, node)
+		hlist_for_each_entry(area, &object->area_list, node)
 			scan_block((void *)area->start,
 				   (void *)(area->start + area->size),
 				   object, 0);
diff --git a/mm/ksm.c b/mm/ksm.c
index ab2ba9ad3c59..85bfd4c16346 100644
--- a/mm/ksm.c
+++ b/mm/ksm.c
@@ -320,10 +320,9 @@ static inline void free_mm_slot(struct mm_slot *mm_slot)
 
 static struct mm_slot *get_mm_slot(struct mm_struct *mm)
 {
-	struct hlist_node *node;
 	struct mm_slot *slot;
 
-	hash_for_each_possible(mm_slots_hash, slot, node, link, (unsigned long)mm)
+	hash_for_each_possible(mm_slots_hash, slot, link, (unsigned long)mm)
 		if (slot->mm == mm)
 			return slot;
 
@@ -496,9 +495,8 @@ static inline int get_kpfn_nid(unsigned long kpfn)
 static void remove_node_from_stable_tree(struct stable_node *stable_node)
 {
 	struct rmap_item *rmap_item;
-	struct hlist_node *hlist;
 
-	hlist_for_each_entry(rmap_item, hlist, &stable_node->hlist, hlist) {
+	hlist_for_each_entry(rmap_item, &stable_node->hlist, hlist) {
 		if (rmap_item->hlist.next)
 			ksm_pages_sharing--;
 		else
@@ -1898,7 +1896,6 @@ int page_referenced_ksm(struct page *page, struct mem_cgroup *memcg,
 {
 	struct stable_node *stable_node;
 	struct rmap_item *rmap_item;
-	struct hlist_node *hlist;
 	unsigned int mapcount = page_mapcount(page);
 	int referenced = 0;
 	int search_new_forks = 0;
@@ -1910,7 +1907,7 @@ int page_referenced_ksm(struct page *page, struct mem_cgroup *memcg,
 	if (!stable_node)
 		return 0;
 again:
-	hlist_for_each_entry(rmap_item, hlist, &stable_node->hlist, hlist) {
+	hlist_for_each_entry(rmap_item, &stable_node->hlist, hlist) {
 		struct anon_vma *anon_vma = rmap_item->anon_vma;
 		struct anon_vma_chain *vmac;
 		struct vm_area_struct *vma;
@@ -1952,7 +1949,6 @@ out:
 int try_to_unmap_ksm(struct page *page, enum ttu_flags flags)
 {
 	struct stable_node *stable_node;
-	struct hlist_node *hlist;
 	struct rmap_item *rmap_item;
 	int ret = SWAP_AGAIN;
 	int search_new_forks = 0;
@@ -1964,7 +1960,7 @@ int try_to_unmap_ksm(struct page *page, enum ttu_flags flags)
 	if (!stable_node)
 		return SWAP_FAIL;
 again:
-	hlist_for_each_entry(rmap_item, hlist, &stable_node->hlist, hlist) {
+	hlist_for_each_entry(rmap_item, &stable_node->hlist, hlist) {
 		struct anon_vma *anon_vma = rmap_item->anon_vma;
 		struct anon_vma_chain *vmac;
 		struct vm_area_struct *vma;
@@ -2005,7 +2001,6 @@ int rmap_walk_ksm(struct page *page, int (*rmap_one)(struct page *,
 		  struct vm_area_struct *, unsigned long, void *), void *arg)
 {
 	struct stable_node *stable_node;
-	struct hlist_node *hlist;
 	struct rmap_item *rmap_item;
 	int ret = SWAP_AGAIN;
 	int search_new_forks = 0;
@@ -2017,7 +2012,7 @@ int rmap_walk_ksm(struct page *page, int (*rmap_one)(struct page *,
 	if (!stable_node)
 		return ret;
 again:
-	hlist_for_each_entry(rmap_item, hlist, &stable_node->hlist, hlist) {
+	hlist_for_each_entry(rmap_item, &stable_node->hlist, hlist) {
 		struct anon_vma *anon_vma = rmap_item->anon_vma;
 		struct anon_vma_chain *vmac;
 		struct vm_area_struct *vma;
diff --git a/mm/mlock.c b/mm/mlock.c
index e6638f565d42..1c5e33fce639 100644
--- a/mm/mlock.c
+++ b/mm/mlock.c
@@ -102,13 +102,16 @@ void mlock_vma_page(struct page *page)
  * can't isolate the page, we leave it for putback_lru_page() and vmscan
  * [page_referenced()/try_to_unmap()] to deal with.
  */
-void munlock_vma_page(struct page *page)
+unsigned int munlock_vma_page(struct page *page)
 {
+	unsigned int page_mask = 0;
+
 	BUG_ON(!PageLocked(page));
 
 	if (TestClearPageMlocked(page)) {
-		mod_zone_page_state(page_zone(page), NR_MLOCK,
-				    -hpage_nr_pages(page));
+		unsigned int nr_pages = hpage_nr_pages(page);
+		mod_zone_page_state(page_zone(page), NR_MLOCK, -nr_pages);
+		page_mask = nr_pages - 1;
 		if (!isolate_lru_page(page)) {
 			int ret = SWAP_AGAIN;
 
@@ -141,6 +144,8 @@ void munlock_vma_page(struct page *page)
 				count_vm_event(UNEVICTABLE_PGMUNLOCKED);
 		}
 	}
+
+	return page_mask;
 }
 
 /**
@@ -159,7 +164,6 @@ long __mlock_vma_pages_range(struct vm_area_struct *vma,
 		unsigned long start, unsigned long end, int *nonblocking)
 {
 	struct mm_struct *mm = vma->vm_mm;
-	unsigned long addr = start;
 	unsigned long nr_pages = (end - start) / PAGE_SIZE;
 	int gup_flags;
 
@@ -189,7 +193,7 @@ long __mlock_vma_pages_range(struct vm_area_struct *vma,
 	 * We made sure addr is within a VMA, so the following will
 	 * not result in a stack expansion that recurses back here.
 	 */
-	return __get_user_pages(current, mm, addr, nr_pages, gup_flags,
+	return __get_user_pages(current, mm, start, nr_pages, gup_flags,
 				NULL, NULL, nonblocking);
 }
 
@@ -226,13 +230,12 @@ static int __mlock_posix_error_return(long retval)
 void munlock_vma_pages_range(struct vm_area_struct *vma,
 			     unsigned long start, unsigned long end)
 {
-	unsigned long addr;
-
-	lru_add_drain();
 	vma->vm_flags &= ~VM_LOCKED;
 
-	for (addr = start; addr < end; addr += PAGE_SIZE) {
+	while (start < end) {
 		struct page *page;
+		unsigned int page_mask, page_increm;
+
 		/*
 		 * Although FOLL_DUMP is intended for get_dump_page(),
 		 * it just so happens that its special treatment of the
@@ -240,13 +243,22 @@ void munlock_vma_pages_range(struct vm_area_struct *vma,
 		 * suits munlock very well (and if somehow an abnormal page
 		 * has sneaked into the range, we won't oops here: great).
 		 */
-		page = follow_page(vma, addr, FOLL_GET | FOLL_DUMP);
+		page = follow_page_mask(vma, start, FOLL_GET | FOLL_DUMP,
+					&page_mask);
 		if (page && !IS_ERR(page)) {
 			lock_page(page);
-			munlock_vma_page(page);
+			lru_add_drain();
+			/*
+			 * Any THP page found by follow_page_mask() may have
+			 * gotten split before reaching munlock_vma_page(),
+			 * so we need to recompute the page_mask here.
+			 */
+			page_mask = munlock_vma_page(page);
 			unlock_page(page);
 			put_page(page);
 		}
+		page_increm = 1 + (~(start >> PAGE_SHIFT) & page_mask);
+		start += page_increm * PAGE_SIZE;
 		cond_resched();
 	}
 }
diff --git a/mm/mmu_notifier.c b/mm/mmu_notifier.c
index 2175fb0d501c..be04122fb277 100644
--- a/mm/mmu_notifier.c
+++ b/mm/mmu_notifier.c
@@ -95,11 +95,10 @@ int __mmu_notifier_clear_flush_young(struct mm_struct *mm,
 					unsigned long address)
 {
 	struct mmu_notifier *mn;
-	struct hlist_node *n;
 	int young = 0, id;
 
 	id = srcu_read_lock(&srcu);
-	hlist_for_each_entry_rcu(mn, n, &mm->mmu_notifier_mm->list, hlist) {
+	hlist_for_each_entry_rcu(mn, &mm->mmu_notifier_mm->list, hlist) {
 		if (mn->ops->clear_flush_young)
 			young |= mn->ops->clear_flush_young(mn, mm, address);
 	}
@@ -112,11 +111,10 @@ int __mmu_notifier_test_young(struct mm_struct *mm,
 			      unsigned long address)
 {
 	struct mmu_notifier *mn;
-	struct hlist_node *n;
 	int young = 0, id;
 
 	id = srcu_read_lock(&srcu);
-	hlist_for_each_entry_rcu(mn, n, &mm->mmu_notifier_mm->list, hlist) {
+	hlist_for_each_entry_rcu(mn, &mm->mmu_notifier_mm->list, hlist) {
 		if (mn->ops->test_young) {
 			young = mn->ops->test_young(mn, mm, address);
 			if (young)
@@ -132,11 +130,10 @@ void __mmu_notifier_change_pte(struct mm_struct *mm, unsigned long address,
 			       pte_t pte)
 {
 	struct mmu_notifier *mn;
-	struct hlist_node *n;
 	int id;
 
 	id = srcu_read_lock(&srcu);
-	hlist_for_each_entry_rcu(mn, n, &mm->mmu_notifier_mm->list, hlist) {
+	hlist_for_each_entry_rcu(mn, &mm->mmu_notifier_mm->list, hlist) {
 		if (mn->ops->change_pte)
 			mn->ops->change_pte(mn, mm, address, pte);
 	}
@@ -147,11 +144,10 @@ void __mmu_notifier_invalidate_page(struct mm_struct *mm,
 					  unsigned long address)
 {
 	struct mmu_notifier *mn;
-	struct hlist_node *n;
 	int id;
 
 	id = srcu_read_lock(&srcu);
-	hlist_for_each_entry_rcu(mn, n, &mm->mmu_notifier_mm->list, hlist) {
+	hlist_for_each_entry_rcu(mn, &mm->mmu_notifier_mm->list, hlist) {
 		if (mn->ops->invalidate_page)
 			mn->ops->invalidate_page(mn, mm, address);
 	}
@@ -162,11 +158,10 @@ void __mmu_notifier_invalidate_range_start(struct mm_struct *mm,
 				  unsigned long start, unsigned long end)
 {
 	struct mmu_notifier *mn;
-	struct hlist_node *n;
 	int id;
 
 	id = srcu_read_lock(&srcu);
-	hlist_for_each_entry_rcu(mn, n, &mm->mmu_notifier_mm->list, hlist) {
+	hlist_for_each_entry_rcu(mn, &mm->mmu_notifier_mm->list, hlist) {
 		if (mn->ops->invalidate_range_start)
 			mn->ops->invalidate_range_start(mn, mm, start, end);
 	}
@@ -178,11 +173,10 @@ void __mmu_notifier_invalidate_range_end(struct mm_struct *mm,
 				  unsigned long start, unsigned long end)
 {
 	struct mmu_notifier *mn;
-	struct hlist_node *n;
 	int id;
 
 	id = srcu_read_lock(&srcu);
-	hlist_for_each_entry_rcu(mn, n, &mm->mmu_notifier_mm->list, hlist) {
+	hlist_for_each_entry_rcu(mn, &mm->mmu_notifier_mm->list, hlist) {
 		if (mn->ops->invalidate_range_end)
 			mn->ops->invalidate_range_end(mn, mm, start, end);
 	}