Merge branch 'linus' into sched/core

Merge reason: update from -rc5 to -almost-final

Signed-off-by: Ingo Molnar <mingo@elte.hu>

12 files changed, 118 insertions, 65 deletions

diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index c2bf86f..65d4204 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -30,6 +30,7 @@ EXPORT_SYMBOL_GPL(default_backing_dev_info);
 
 struct backing_dev_info noop_backing_dev_info = {
 	.name		= "noop",
+	.capabilities	= BDI_CAP_NO_ACCT_AND_WRITEBACK,
 };
 EXPORT_SYMBOL_GPL(noop_backing_dev_info);
 
@@ -243,6 +244,7 @@ static int __init default_bdi_init(void)
 	err = bdi_init(&default_backing_dev_info);
 	if (!err)
 		bdi_register(&default_backing_dev_info, NULL, "default");
+	err = bdi_init(&noop_backing_dev_info);
 
 	return err;
 }
diff --git a/mm/fremap.c b/mm/fremap.c
index 46f5dac..ec520c7 100644
--- a/mm/fremap.c
+++ b/mm/fremap.c
@@ -125,7 +125,6 @@ SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size,
 {
 	struct mm_struct *mm = current->mm;
 	struct address_space *mapping;
-	unsigned long end = start + size;
 	struct vm_area_struct *vma;
 	int err = -EINVAL;
 	int has_write_lock = 0;
@@ -142,6 +141,10 @@ SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size,
 	if (start + size <= start)
 		return err;
 
+	/* Does pgoff wrap? */
+	if (pgoff + (size >> PAGE_SHIFT) < pgoff)
+		return err;
+
 	/* Can we represent this offset inside this architecture's pte's? */
 #if PTE_FILE_MAX_BITS < BITS_PER_LONG
 	if (pgoff + (size >> PAGE_SHIFT) >= (1UL << PTE_FILE_MAX_BITS))
@@ -168,7 +171,7 @@ SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size,
 	if (!(vma->vm_flags & VM_CAN_NONLINEAR))
 		goto out;
 
-	if (end <= start || start < vma->vm_start || end > vma->vm_end)
+	if (start < vma->vm_start || start + size > vma->vm_end)
 		goto out;
 
 	/* Must set VM_NONLINEAR before any pages are populated. */
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index cc5be78..c032738 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -2324,11 +2324,8 @@ retry_avoidcopy:
 	 * and just make the page writable */
 	avoidcopy = (page_mapcount(old_page) == 1);
 	if (avoidcopy) {
-		if (!trylock_page(old_page)) {
-			if (PageAnon(old_page))
-				page_move_anon_rmap(old_page, vma, address);
-		} else
-			unlock_page(old_page);
+		if (PageAnon(old_page))
+			page_move_anon_rmap(old_page, vma, address);
 		set_huge_ptep_writable(vma, address, ptep);
 		return 0;
 	}
@@ -2404,7 +2401,7 @@ retry_avoidcopy:
 		set_huge_pte_at(mm, address, ptep,
 				make_huge_pte(vma, new_page, 1));
 		page_remove_rmap(old_page);
-		hugepage_add_anon_rmap(new_page, vma, address);
+		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,
@@ -2631,10 +2628,16 @@ int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 								vma, address);
 	}
 
-	if (!pagecache_page) {
-		page = pte_page(entry);
+	/*
+	 * hugetlb_cow() requires page locks of pte_page(entry) and
+	 * pagecache_page, so here we need take the former one
+	 * when page != pagecache_page or !pagecache_page.
+	 * Note that locking order is always pagecache_page -> page,
+	 * so no worry about deadlock.
+	 */
+	page = pte_page(entry);
+	if (page != pagecache_page)
 		lock_page(page);
-	}
 
 	spin_lock(&mm->page_table_lock);
 	/* Check for a racing update before calling hugetlb_cow */
@@ -2661,9 +2664,8 @@ out_page_table_lock:
 	if (pagecache_page) {
 		unlock_page(pagecache_page);
 		put_page(pagecache_page);
-	} else {
-		unlock_page(page);
 	}
+	unlock_page(page);
 
 out_mutex:
 	mutex_unlock(&hugetlb_instantiation_mutex);
diff --git a/mm/ksm.c b/mm/ksm.c
index b1873cf..65ab5c7 100644
--- a/mm/ksm.c
+++ b/mm/ksm.c
@@ -712,7 +712,7 @@ static int write_protect_page(struct vm_area_struct *vma, struct page *page,
 	if (!ptep)
 		goto out;
 
-	if (pte_write(*ptep)) {
+	if (pte_write(*ptep) || pte_dirty(*ptep)) {
 		pte_t entry;
 
 		swapped = PageSwapCache(page);
@@ -735,7 +735,9 @@ static int write_protect_page(struct vm_area_struct *vma, struct page *page,
 			set_pte_at(mm, addr, ptep, entry);
 			goto out_unlock;
 		}
-		entry = pte_wrprotect(entry);
+		if (pte_dirty(entry))
+			set_page_dirty(page);
+		entry = pte_mkclean(pte_wrprotect(entry));
 		set_pte_at_notify(mm, addr, ptep, entry);
 	}
 	*orig_pte = *ptep;
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 3eed583..9be3cf8 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -3587,9 +3587,13 @@ unlock:
 
 static void mem_cgroup_threshold(struct mem_cgroup *memcg)
 {
-	__mem_cgroup_threshold(memcg, false);
-	if (do_swap_account)
-		__mem_cgroup_threshold(memcg, true);
+	while (memcg) {
+		__mem_cgroup_threshold(memcg, false);
+		if (do_swap_account)
+			__mem_cgroup_threshold(memcg, true);
+
+		memcg = parent_mem_cgroup(memcg);
+	}
 }
 
 static int compare_thresholds(const void *a, const void *b)
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 9c26eec..757f6b0 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -183,7 +183,7 @@ EXPORT_SYMBOL_GPL(hwpoison_filter);
  * signal.
  */
 static int kill_proc_ao(struct task_struct *t, unsigned long addr, int trapno,
-			unsigned long pfn)
+			unsigned long pfn, struct page *page)
 {
 	struct siginfo si;
 	int ret;
@@ -198,7 +198,7 @@ static int kill_proc_ao(struct task_struct *t, unsigned long addr, int trapno,
 #ifdef __ARCH_SI_TRAPNO
 	si.si_trapno = trapno;
 #endif
-	si.si_addr_lsb = PAGE_SHIFT;
+	si.si_addr_lsb = compound_order(compound_head(page)) + PAGE_SHIFT;
 	/*
 	 * Don't use force here, it's convenient if the signal
 	 * can be temporarily blocked.
@@ -235,7 +235,7 @@ void shake_page(struct page *p, int access)
 		int nr;
 		do {
 			nr = shrink_slab(1000, GFP_KERNEL, 1000);
-			if (page_count(p) == 0)
+			if (page_count(p) == 1)
 				break;
 		} while (nr > 10);
 	}
@@ -327,7 +327,7 @@ static void add_to_kill(struct task_struct *tsk, struct page *p,
  * wrong earlier.
  */
 static void kill_procs_ao(struct list_head *to_kill, int doit, int trapno,
-			  int fail, unsigned long pfn)
+			  int fail, struct page *page, unsigned long pfn)
 {
 	struct to_kill *tk, *next;
 
@@ -352,7 +352,7 @@ static void kill_procs_ao(struct list_head *to_kill, int doit, int trapno,
 			 * process anyways.
 			 */
 			else if (kill_proc_ao(tk->tsk, tk->addr, trapno,
-					      pfn) < 0)
+					      pfn, page) < 0)
 				printk(KERN_ERR
 		"MCE %#lx: Cannot send advisory machine check signal to %s:%d\n",
 					pfn, tk->tsk->comm, tk->tsk->pid);
@@ -928,7 +928,7 @@ static int hwpoison_user_mappings(struct page *p, unsigned long pfn,
 	 * any accesses to the poisoned memory.
 	 */
 	kill_procs_ao(&tokill, !!PageDirty(hpage), trapno,
-		      ret != SWAP_SUCCESS, pfn);
+		      ret != SWAP_SUCCESS, p, pfn);
 
 	return ret;
 }
diff --git a/mm/mmap.c b/mm/mmap.c
index 6128dc8..00161a4 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -2009,6 +2009,7 @@ static int __split_vma(struct mm_struct * mm, struct vm_area_struct * vma,
 			removed_exe_file_vma(mm);
 		fput(new->vm_file);
 	}
+	unlink_anon_vmas(new);
  out_free_mpol:
 	mpol_put(pol);
  out_free_vma:
diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index fc81cb2..4029583 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -121,8 +121,8 @@ struct task_struct *find_lock_task_mm(struct task_struct *p)
 }
 
 /* return true if the task is not adequate as candidate victim task. */
-static bool oom_unkillable_task(struct task_struct *p, struct mem_cgroup *mem,
-			   const nodemask_t *nodemask)
+static bool oom_unkillable_task(struct task_struct *p,
+		const struct mem_cgroup *mem, const nodemask_t *nodemask)
 {
 	if (is_global_init(p))
 		return true;
@@ -208,8 +208,13 @@ unsigned int oom_badness(struct task_struct *p, struct mem_cgroup *mem,
 	 */
 	points += p->signal->oom_score_adj;
 
-	if (points < 0)
-		return 0;
+	/*
+	 * Never return 0 for an eligible task that may be killed since it's
+	 * possible that no single user task uses more than 0.1% of memory and
+	 * no single admin tasks uses more than 3.0%.
+	 */
+	if (points <= 0)
+		return 1;
 	return (points < 1000) ? points : 1000;
 }
 
@@ -339,26 +344,24 @@ static struct task_struct *select_bad_process(unsigned int *ppoints,
 /**
  * dump_tasks - dump current memory state of all system tasks
  * @mem: current's memory controller, if constrained
+ * @nodemask: nodemask passed to page allocator for mempolicy ooms
  *
- * Dumps the current memory state of all system tasks, excluding kernel threads.
+ * Dumps the current memory state of all eligible tasks.  Tasks not in the same
+ * memcg, not in the same cpuset, or bound to a disjoint set of mempolicy nodes
+ * are not shown.
  * State information includes task's pid, uid, tgid, vm size, rss, cpu, oom_adj
  * value, oom_score_adj value, and name.
  *
- * If the actual is non-NULL, only tasks that are a member of the mem_cgroup are
- * shown.
- *
  * Call with tasklist_lock read-locked.
  */
-static void dump_tasks(const struct mem_cgroup *mem)
+static void dump_tasks(const struct mem_cgroup *mem, const nodemask_t *nodemask)
 {
 	struct task_struct *p;
 	struct task_struct *task;
 
 	pr_info("[ pid ]   uid  tgid total_vm      rss cpu oom_adj oom_score_adj name\n");
 	for_each_process(p) {
-		if (p->flags & PF_KTHREAD)
-			continue;
-		if (mem && !task_in_mem_cgroup(p, mem))
+		if (oom_unkillable_task(p, mem, nodemask))
 			continue;
 
 		task = find_lock_task_mm(p);
@@ -381,7 +384,7 @@ static void dump_tasks(const struct mem_cgroup *mem)
 }
 
 static void dump_header(struct task_struct *p, gfp_t gfp_mask, int order,
-							struct mem_cgroup *mem)
+			struct mem_cgroup *mem, const nodemask_t *nodemask)
 {
 	task_lock(current);
 	pr_warning("%s invoked oom-killer: gfp_mask=0x%x, order=%d, "
@@ -394,7 +397,7 @@ static void dump_header(struct task_struct *p, gfp_t gfp_mask, int order,
 	mem_cgroup_print_oom_info(mem, p);
 	show_mem();
 	if (sysctl_oom_dump_tasks)
-		dump_tasks(mem);
+		dump_tasks(mem, nodemask);
 }
 
 #define K(x) ((x) << (PAGE_SHIFT-10))
@@ -436,7 +439,7 @@ static int oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order,
 	unsigned int victim_points = 0;
 
 	if (printk_ratelimit())
-		dump_header(p, gfp_mask, order, mem);
+		dump_header(p, gfp_mask, order, mem, nodemask);
 
 	/*
 	 * If the task is already exiting, don't alarm the sysadmin or kill
@@ -482,7 +485,7 @@ static int oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order,
  * Determines whether the kernel must panic because of the panic_on_oom sysctl.
  */
 static void check_panic_on_oom(enum oom_constraint constraint, gfp_t gfp_mask,
-				int order)
+				int order, const nodemask_t *nodemask)
 {
 	if (likely(!sysctl_panic_on_oom))
 		return;
@@ -496,7 +499,7 @@ static void check_panic_on_oom(enum oom_constraint constraint, gfp_t gfp_mask,
 			return;
 	}
 	read_lock(&tasklist_lock);
-	dump_header(NULL, gfp_mask, order, NULL);
+	dump_header(NULL, gfp_mask, order, NULL, nodemask);
 	read_unlock(&tasklist_lock);
 	panic("Out of memory: %s panic_on_oom is enabled\n",
 		sysctl_panic_on_oom == 2 ? "compulsory" : "system-wide");
@@ -509,7 +512,7 @@ void mem_cgroup_out_of_memory(struct mem_cgroup *mem, gfp_t gfp_mask)
 	unsigned int points = 0;
 	struct task_struct *p;
 
-	check_panic_on_oom(CONSTRAINT_MEMCG, gfp_mask, 0);
+	check_panic_on_oom(CONSTRAINT_MEMCG, gfp_mask, 0, NULL);
 	limit = mem_cgroup_get_limit(mem) >> PAGE_SHIFT;
 	read_lock(&tasklist_lock);
 retry:
@@ -641,6 +644,7 @@ static void clear_system_oom(void)
 void out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask,
 		int order, nodemask_t *nodemask)
 {
+	const nodemask_t *mpol_mask;
 	struct task_struct *p;
 	unsigned long totalpages;
 	unsigned long freed = 0;
@@ -670,7 +674,8 @@ void out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask,
 	 */
 	constraint = constrained_alloc(zonelist, gfp_mask, nodemask,
 						&totalpages);
-	check_panic_on_oom(constraint, gfp_mask, order);
+	mpol_mask = (constraint == CONSTRAINT_MEMORY_POLICY) ? nodemask : NULL;
+	check_panic_on_oom(constraint, gfp_mask, order, mpol_mask);
 
 	read_lock(&tasklist_lock);
 	if (sysctl_oom_kill_allocating_task &&
@@ -688,15 +693,13 @@ void out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask,
 	}
 
 retry:
-	p = select_bad_process(&points, totalpages, NULL,
-			constraint == CONSTRAINT_MEMORY_POLICY ? nodemask :
-								 NULL);
+	p = select_bad_process(&points, totalpages, NULL, mpol_mask);
 	if (PTR_ERR(p) == -1UL)
 		goto out;
 
 	/* Found nothing?!?! Either we hang forever, or we panic. */
 	if (!p) {
-		dump_header(NULL, gfp_mask, order, NULL);
+		dump_header(NULL, gfp_mask, order, NULL, mpol_mask);
 		read_unlock(&tasklist_lock);
 		panic("Out of memory and no killable processes...\n");
 	}
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index a8cfa9c..f12ad18 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -5182,9 +5182,9 @@ void *__init alloc_large_system_hash(const char *tablename,
 	if (!table)
 		panic("Failed to allocate %s hash table\n", tablename);
 
-	printk(KERN_INFO "%s hash table entries: %d (order: %d, %lu bytes)\n",
+	printk(KERN_INFO "%s hash table entries: %ld (order: %d, %lu bytes)\n",
 	       tablename,
-	       (1U << log2qty),
+	       (1UL << log2qty),
 	       ilog2(size) - PAGE_SHIFT,
 	       size);
 
diff --git a/mm/percpu.c b/mm/percpu.c
index 58c572b..c76ef38 100644
--- a/mm/percpu.c
+++ b/mm/percpu.c
@@ -1401,9 +1401,9 @@ int __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai,
 
 			if (pcpu_first_unit_cpu == NR_CPUS)
 				pcpu_first_unit_cpu = cpu;
+			pcpu_last_unit_cpu = cpu;
 		}
 	}
-	pcpu_last_unit_cpu = cpu;
 	pcpu_nr_units = unit;
 
 	for_each_possible_cpu(cpu)
diff --git a/mm/rmap.c b/mm/rmap.c
index f6f0d2d..92e6757 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -381,7 +381,13 @@ vma_address(struct page *page, struct vm_area_struct *vma)
 unsigned long page_address_in_vma(struct page *page, struct vm_area_struct *vma)
 {
 	if (PageAnon(page)) {
-		if (vma->anon_vma->root != page_anon_vma(page)->root)
+		struct anon_vma *page__anon_vma = page_anon_vma(page);
+		/*
+		 * Note: swapoff's unuse_vma() is more efficient with this
+		 * check, and needs it to match anon_vma when KSM is active.
+		 */
+		if (!vma->anon_vma || !page__anon_vma ||
+		    vma->anon_vma->root != page__anon_vma->root)
 			return -EFAULT;
 	} else if (page->mapping && !(vma->vm_flags & VM_NONLINEAR)) {
 		if (!vma->vm_file ||
@@ -1564,13 +1570,14 @@ static void __hugepage_set_anon_rmap(struct page *page,
 	struct vm_area_struct *vma, unsigned long address, int exclusive)
 {
 	struct anon_vma *anon_vma = vma->anon_vma;
+
 	BUG_ON(!anon_vma);
-	if (!exclusive) {
-		struct anon_vma_chain *avc;
-		avc = list_entry(vma->anon_vma_chain.prev,
-				 struct anon_vma_chain, same_vma);
-		anon_vma = avc->anon_vma;
-	}
+
+	if (PageAnon(page))
+		return;
+	if (!exclusive)
+		anon_vma = anon_vma->root;
+
 	anon_vma = (void *) anon_vma + PAGE_MAPPING_ANON;
 	page->mapping = (struct address_space *) anon_vma;
 	page->index = linear_page_index(vma, address);
@@ -1581,6 +1588,8 @@ void hugepage_add_anon_rmap(struct page *page,
 {
 	struct anon_vma *anon_vma = vma->anon_vma;
 	int first;
+
+	BUG_ON(!PageLocked(page));
 	BUG_ON(!anon_vma);
 	BUG_ON(address < vma->vm_start || address >= vma->vm_end);
 	first = atomic_inc_and_test(&page->_mapcount);
diff --git a/mm/vmscan.c b/mm/vmscan.c
index c391c32..c5dfabf 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1804,12 +1804,11 @@ static void shrink_zone(int priority, struct zone *zone,
  * If a zone is deemed to be full of pinned pages then just give it a light
  * scan then give up on it.
  */
-static bool shrink_zones(int priority, struct zonelist *zonelist,
+static void shrink_zones(int priority, struct zonelist *zonelist,
 					struct scan_control *sc)
 {
 	struct zoneref *z;
 	struct zone *zone;
-	bool all_unreclaimable = true;
 
 	for_each_zone_zonelist_nodemask(zone, z, zonelist,
 					gfp_zone(sc->gfp_mask), sc->nodemask) {
@@ -1827,8 +1826,38 @@ static bool shrink_zones(int priority, struct zonelist *zonelist,
 		}
 
 		shrink_zone(priority, zone, sc);
-		all_unreclaimable = false;
 	}
+}
+
+static bool zone_reclaimable(struct zone *zone)
+{
+	return zone->pages_scanned < zone_reclaimable_pages(zone) * 6;
+}
+
+/*
+ * As hibernation is going on, kswapd is freezed so that it can't mark
+ * the zone into all_unreclaimable. It can't handle OOM during hibernation.
+ * So let's check zone's unreclaimable in direct reclaim as well as kswapd.
+ */
+static bool all_unreclaimable(struct zonelist *zonelist,
+		struct scan_control *sc)
+{
+	struct zoneref *z;
+	struct zone *zone;
+	bool all_unreclaimable = true;
+
+	for_each_zone_zonelist_nodemask(zone, z, zonelist,
+			gfp_zone(sc->gfp_mask), sc->nodemask) {
+		if (!populated_zone(zone))
+			continue;
+		if (!cpuset_zone_allowed_hardwall(zone, GFP_KERNEL))
+			continue;
+		if (zone_reclaimable(zone)) {
+			all_unreclaimable = false;
+			break;
+		}
+	}
+
 	return all_unreclaimable;
 }
 
@@ -1852,7 +1881,6 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist,
 					struct scan_control *sc)
 {
 	int priority;
-	bool all_unreclaimable;
 	unsigned long total_scanned = 0;
 	struct reclaim_state *reclaim_state = current->reclaim_state;
 	struct zoneref *z;
@@ -1869,7 +1897,7 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist,
 		sc->nr_scanned = 0;
 		if (!priority)
 			disable_swap_token();
-		all_unreclaimable = shrink_zones(priority, zonelist, sc);
+		shrink_zones(priority, zonelist, sc);
 		/*
 		 * Don't shrink slabs when reclaiming memory from
 		 * over limit cgroups
@@ -1931,7 +1959,7 @@ out:
 		return sc->nr_reclaimed;
 
 	/* top priority shrink_zones still had more to do? don't OOM, then */
-	if (scanning_global_lru(sc) && !all_unreclaimable)
+	if (scanning_global_lru(sc) && !all_unreclaimable(zonelist, sc))
 		return 1;
 
 	return 0;
@@ -2197,8 +2225,7 @@ loop_again:
 			total_scanned += sc.nr_scanned;
 			if (zone->all_unreclaimable)
 				continue;
-			if (nr_slab == 0 &&
-			    zone->pages_scanned >= (zone_reclaimable_pages(zone) * 6))
+			if (nr_slab == 0 && !zone_reclaimable(zone))
 				zone->all_unreclaimable = 1;
 			/*
 			 * If we've done a decent amount of scanning and