Merge branch 'akpm' (Fixes from Andrew)

Merge misc fixes from Andrew Morton.

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (12 patches)
  revert "mm: fix-up zone present pages"
  tmpfs: change final i_blocks BUG to WARNING
  tmpfs: fix shmem_getpage_gfp() VM_BUG_ON
  mm: highmem: don't treat PKMAP_ADDR(LAST_PKMAP) as a highmem address
  mm: revert "mm: vmscan: scale number of pages reclaimed by reclaim/compaction based on failures"
  rapidio: fix kernel-doc warnings
  swapfile: fix name leak in swapoff
  memcg: fix hotplugged memory zone oops
  mips, arc: fix build failure
  memcg: oom: fix totalpages calculation for memory.swappiness==0
  mm: fix build warning for uninitialized value
  mm: add anon_vma_lock to validate_mm()

Documentation/cgroups/memory.txt

@@ -466,6 +466,10 @@ Note:
 5.3 swappiness
 
 Similar to /proc/sys/vm/swappiness, but affecting a hierarchy of groups only.
+Please note that unlike the global swappiness, memcg knob set to 0
+really prevents from any swapping even if there is a swap storage
+available. This might lead to memcg OOM killer if there are no file
+pages to reclaim.
 
 Following cgroups' swappiness can't be changed.
 - root cgroup (uses /proc/sys/vm/swappiness).

arch/ia64/mm/init.c

@@ -637,7 +637,6 @@ mem_init (void)
 
 	high_memory = __va(max_low_pfn * PAGE_SIZE);
 
-	reset_zone_present_pages();
 	for_each_online_pgdat(pgdat)
 		if (pgdat->bdata->node_bootmem_map)
 			totalram_pages += free_all_bootmem_node(pgdat);

arch/mips/fw/arc/misc.c

@@ -11,6 +11,7 @@
  */
 #include <linux/init.h>
 #include <linux/kernel.h>
+#include <linux/irqflags.h>
 
 #include <asm/bcache.h>
 

drivers/rapidio/rio.c

@@ -401,7 +401,7 @@ EXPORT_SYMBOL_GPL(rio_release_inb_pwrite);
 /**
  * rio_map_inb_region -- Map inbound memory region.
  * @mport: Master port.
- * @lstart: physical address of memory region to be mapped
+ * @local: physical address of memory region to be mapped
  * @rbase: RIO base address assigned to this window
  * @size: Size of the memory region
  * @rflags: Flags for mapping.

include/linux/mm.h

@@ -1684,9 +1684,5 @@ static inline unsigned int debug_guardpage_minorder(void) { return 0; }
 static inline bool page_is_guard(struct page *page) { return false; }
 #endif /* CONFIG_DEBUG_PAGEALLOC */
 
-extern void reset_zone_present_pages(void);
-extern void fixup_zone_present_pages(int nid, unsigned long start_pfn,
-				unsigned long end_pfn);
-
 #endif /* __KERNEL__ */
 #endif /* _LINUX_MM_H */

include/linux/mmzone.h

@@ -752,7 +752,7 @@ extern int init_currently_empty_zone(struct zone *zone, unsigned long start_pfn,
 				     unsigned long size,
 				     enum memmap_context context);
 
-extern void lruvec_init(struct lruvec *lruvec, struct zone *zone);
+extern void lruvec_init(struct lruvec *lruvec);
 
 static inline struct zone *lruvec_zone(struct lruvec *lruvec)
 {

include/linux/rio.h

@@ -275,9 +275,11 @@ struct rio_id_table {
  * struct rio_net - RIO network info
  * @node: Node in global list of RIO networks
  * @devices: List of devices in this network
+ * @switches: List of switches in this netowrk
  * @mports: List of master ports accessing this network
  * @hport: Default port for accessing this network
  * @id: RIO network ID
+ * @destid_table: destID allocation table
  */
 struct rio_net {
 	struct list_head node;	/* node in list of networks */

mm/bootmem.c

@@ -198,8 +198,6 @@ static unsigned long __init free_all_bootmem_core(bootmem_data_t *bdata)
 			int order = ilog2(BITS_PER_LONG);
 
 			__free_pages_bootmem(pfn_to_page(start), order);
-			fixup_zone_present_pages(page_to_nid(pfn_to_page(start)),
-					start, start + BITS_PER_LONG);
 			count += BITS_PER_LONG;
 			start += BITS_PER_LONG;
 		} else {
@@ -210,9 +208,6 @@ static unsigned long __init free_all_bootmem_core(bootmem_data_t *bdata)
 				if (vec & 1) {
 					page = pfn_to_page(start + off);
 					__free_pages_bootmem(page, 0);
-					fixup_zone_present_pages(
-						page_to_nid(page),
-						start + off, start + off + 1);
 					count++;
 				}
 				vec >>= 1;
@@ -226,11 +221,8 @@ static unsigned long __init free_all_bootmem_core(bootmem_data_t *bdata)
 	pages = bdata->node_low_pfn - bdata->node_min_pfn;
 	pages = bootmem_bootmap_pages(pages);
 	count += pages;
-	while (pages--) {
-		fixup_zone_present_pages(page_to_nid(page),
-				page_to_pfn(page), page_to_pfn(page) + 1);
+	while (pages--)
 		__free_pages_bootmem(page++, 0);
-	}
 
 	bdebug("nid=%td released=%lx\n", bdata - bootmem_node_data, count);
 

mm/highmem.c

@@ -98,7 +98,7 @@ struct page *kmap_to_page(void *vaddr)
 {
 	unsigned long addr = (unsigned long)vaddr;
 
-	if (addr >= PKMAP_ADDR(0) && addr <= PKMAP_ADDR(LAST_PKMAP)) {
+	if (addr >= PKMAP_ADDR(0) && addr < PKMAP_ADDR(LAST_PKMAP)) {
 		int i = (addr - PKMAP_ADDR(0)) >> PAGE_SHIFT;
 		return pte_page(pkmap_page_table[i]);
 	}

mm/memcontrol.c

@@ -1055,12 +1055,24 @@ struct lruvec *mem_cgroup_zone_lruvec(struct zone *zone,
 				      struct mem_cgroup *memcg)
 {
 	struct mem_cgroup_per_zone *mz;
+	struct lruvec *lruvec;
 
-	if (mem_cgroup_disabled())
-		return &zone->lruvec;
+	if (mem_cgroup_disabled()) {
+		lruvec = &zone->lruvec;
+		goto out;
+	}
 
 	mz = mem_cgroup_zoneinfo(memcg, zone_to_nid(zone), zone_idx(zone));
-	return &mz->lruvec;
+	lruvec = &mz->lruvec;
+out:
+	/*
+	 * Since a node can be onlined after the mem_cgroup was created,
+	 * we have to be prepared to initialize lruvec->zone here;
+	 * and if offlined then reonlined, we need to reinitialize it.
+	 */
+	if (unlikely(lruvec->zone != zone))
+		lruvec->zone = zone;
+	return lruvec;
 }
 
 /*
@@ -1087,9 +1099,12 @@ struct lruvec *mem_cgroup_page_lruvec(struct page *page, struct zone *zone)
 	struct mem_cgroup_per_zone *mz;
 	struct mem_cgroup *memcg;
 	struct page_cgroup *pc;
+	struct lruvec *lruvec;
 
-	if (mem_cgroup_disabled())
-		return &zone->lruvec;
+	if (mem_cgroup_disabled()) {
+		lruvec = &zone->lruvec;
+		goto out;
+	}
 
 	pc = lookup_page_cgroup(page);
 	memcg = pc->mem_cgroup;
@@ -1107,7 +1122,16 @@ struct lruvec *mem_cgroup_page_lruvec(struct page *page, struct zone *zone)
 		pc->mem_cgroup = memcg = root_mem_cgroup;
 
 	mz = page_cgroup_zoneinfo(memcg, page);
-	return &mz->lruvec;
+	lruvec = &mz->lruvec;
+out:
+	/*
+	 * Since a node can be onlined after the mem_cgroup was created,
+	 * we have to be prepared to initialize lruvec->zone here;
+	 * and if offlined then reonlined, we need to reinitialize it.
+	 */
+	if (unlikely(lruvec->zone != zone))
+		lruvec->zone = zone;
+	return lruvec;
 }
 
 /**
@@ -1452,17 +1476,26 @@ static int mem_cgroup_count_children(struct mem_cgroup *memcg)
 static u64 mem_cgroup_get_limit(struct mem_cgroup *memcg)
 {
 	u64 limit;
-	u64 memsw;
 
 	limit = res_counter_read_u64(&memcg->res, RES_LIMIT);
-	limit += total_swap_pages << PAGE_SHIFT;
 
-	memsw = res_counter_read_u64(&memcg->memsw, RES_LIMIT);
 	/*
-	 * If memsw is finite and limits the amount of swap space available
-	 * to this memcg, return that limit.
+	 * Do not consider swap space if we cannot swap due to swappiness
 	 */
-	return min(limit, memsw);
+	if (mem_cgroup_swappiness(memcg)) {
+		u64 memsw;
+
+		limit += total_swap_pages << PAGE_SHIFT;
+		memsw = res_counter_read_u64(&memcg->memsw, RES_LIMIT);
+
+		/*
+		 * If memsw is finite and limits the amount of swap space
+		 * available to this memcg, return that limit.
+		 */
+		limit = min(limit, memsw);
+	}
+
+	return limit;
 }
 
 void mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask,
@@ -3688,17 +3721,17 @@ unsigned long mem_cgroup_soft_limit_reclaim(struct zone *zone, int order,
 static bool mem_cgroup_force_empty_list(struct mem_cgroup *memcg,
 				int node, int zid, enum lru_list lru)
 {
-	struct mem_cgroup_per_zone *mz;
+	struct lruvec *lruvec;
 	unsigned long flags, loop;
 	struct list_head *list;
 	struct page *busy;
 	struct zone *zone;
 
 	zone = &NODE_DATA(node)->node_zones[zid];
-	mz = mem_cgroup_zoneinfo(memcg, node, zid);
-	list = &mz->lruvec.lists[lru];
+	lruvec = mem_cgroup_zone_lruvec(zone, memcg);
+	list = &lruvec->lists[lru];
 
-	loop = mz->lru_size[lru];
+	loop = mem_cgroup_get_lru_size(lruvec, lru);
 	/* give some margin against EBUSY etc...*/
 	loop += 256;
 	busy = NULL;
@@ -4736,7 +4769,7 @@ static int alloc_mem_cgroup_per_zone_info(struct mem_cgroup *memcg, int node)
 
 	for (zone = 0; zone < MAX_NR_ZONES; zone++) {
 		mz = &pn->zoneinfo[zone];
-		lruvec_init(&mz->lruvec, &NODE_DATA(node)->node_zones[zone]);
+		lruvec_init(&mz->lruvec);
 		mz->usage_in_excess = 0;
 		mz->on_tree = false;
 		mz->memcg = memcg;

mm/memory.c

@@ -2527,9 +2527,8 @@ static int do_wp_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	int ret = 0;
 	int page_mkwrite = 0;
 	struct page *dirty_page = NULL;
-	unsigned long mmun_start;	/* For mmu_notifiers */
-	unsigned long mmun_end;		/* For mmu_notifiers */
-	bool mmun_called = false;	/* For mmu_notifiers */
+	unsigned long mmun_start = 0;	/* For mmu_notifiers */
+	unsigned long mmun_end = 0;	/* For mmu_notifiers */
 
 	old_page = vm_normal_page(vma, address, orig_pte);
 	if (!old_page) {
@@ -2708,8 +2707,7 @@ static int do_wp_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		goto oom_free_new;
 
 	mmun_start  = address & PAGE_MASK;
-	mmun_end    = (address & PAGE_MASK) + PAGE_SIZE;
-	mmun_called = true;
+	mmun_end    = mmun_start + PAGE_SIZE;
 	mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end);
 
 	/*
@@ -2778,7 +2776,7 @@ static int do_wp_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		page_cache_release(new_page);
 unlock:
 	pte_unmap_unlock(page_table, ptl);
-	if (mmun_called)
+	if (mmun_end > mmun_start)
 		mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end);
 	if (old_page) {
 		/*

mm/memory_hotplug.c

@@ -106,7 +106,6 @@ static void get_page_bootmem(unsigned long info,  struct page *page,
 void __ref put_page_bootmem(struct page *page)
 {
 	unsigned long type;
-	struct zone *zone;
 
 	type = (unsigned long) page->lru.next;
 	BUG_ON(type < MEMORY_HOTPLUG_MIN_BOOTMEM_TYPE ||
@@ -117,12 +116,6 @@ void __ref put_page_bootmem(struct page *page)
 		set_page_private(page, 0);
 		INIT_LIST_HEAD(&page->lru);
 		__free_pages_bootmem(page, 0);
-
-		zone = page_zone(page);
-		zone_span_writelock(zone);
-		zone->present_pages++;
-		zone_span_writeunlock(zone);
-		totalram_pages++;
 	}
 
 }

mm/mmap.c

@@ -334,8 +334,10 @@ void validate_mm(struct mm_struct *mm)
 	struct vm_area_struct *vma = mm->mmap;
 	while (vma) {
 		struct anon_vma_chain *avc;
+		vma_lock_anon_vma(vma);
 		list_for_each_entry(avc, &vma->anon_vma_chain, same_vma)
 			anon_vma_interval_tree_verify(avc);
+		vma_unlock_anon_vma(vma);
 		vma = vma->vm_next;
 		i++;
 	}

mm/mmzone.c

@@ -87,7 +87,7 @@ int memmap_valid_within(unsigned long pfn,
 }
 #endif /* CONFIG_ARCH_HAS_HOLES_MEMORYMODEL */
 
-void lruvec_init(struct lruvec *lruvec, struct zone *zone)
+void lruvec_init(struct lruvec *lruvec)
 {
 	enum lru_list lru;
 
@@ -95,8 +95,4 @@ void lruvec_init(struct lruvec *lruvec, struct zone *zone)
 
 	for_each_lru(lru)
 		INIT_LIST_HEAD(&lruvec->lists[lru]);
-
-#ifdef CONFIG_MEMCG
-	lruvec->zone = zone;
-#endif
 }

mm/nobootmem.c

@@ -116,8 +116,6 @@ static unsigned long __init __free_memory_core(phys_addr_t start,
 		return 0;
 
 	__free_pages_memory(start_pfn, end_pfn);
-	fixup_zone_present_pages(pfn_to_nid(start >> PAGE_SHIFT),
-			start_pfn, end_pfn);
 
 	return end_pfn - start_pfn;
 }
@@ -128,7 +126,6 @@ unsigned long __init free_low_memory_core_early(int nodeid)
 	phys_addr_t start, end, size;
 	u64 i;
 
-	reset_zone_present_pages();
 	for_each_free_mem_range(i, MAX_NUMNODES, &start, &end, NULL)
 		count += __free_memory_core(start, end);
 

mm/page_alloc.c

@@ -4505,7 +4505,7 @@ static void __paginginit free_area_init_core(struct pglist_data *pgdat,
 		zone->zone_pgdat = pgdat;
 
 		zone_pcp_init(zone);
-		lruvec_init(&zone->lruvec, zone);
+		lruvec_init(&zone->lruvec);
 		if (!size)
 			continue;
 
@@ -6098,37 +6098,3 @@ void dump_page(struct page *page)
 	dump_page_flags(page->flags);
 	mem_cgroup_print_bad_page(page);
 }
-
-/* reset zone->present_pages */
-void reset_zone_present_pages(void)
-{
-	struct zone *z;
-	int i, nid;
-
-	for_each_node_state(nid, N_HIGH_MEMORY) {
-		for (i = 0; i < MAX_NR_ZONES; i++) {
-			z = NODE_DATA(nid)->node_zones + i;
-			z->present_pages = 0;
-		}
-	}
-}
-
-/* calculate zone's present pages in buddy system */
-void fixup_zone_present_pages(int nid, unsigned long start_pfn,
-				unsigned long end_pfn)
-{
-	struct zone *z;
-	unsigned long zone_start_pfn, zone_end_pfn;
-	int i;
-
-	for (i = 0; i < MAX_NR_ZONES; i++) {
-		z = NODE_DATA(nid)->node_zones + i;
-		zone_start_pfn = z->zone_start_pfn;
-		zone_end_pfn = zone_start_pfn + z->spanned_pages;
-
-		/* if the two regions intersect */
-		if (!(zone_start_pfn >= end_pfn	|| zone_end_pfn <= start_pfn))
-			z->present_pages += min(end_pfn, zone_end_pfn) -
-					    max(start_pfn, zone_start_pfn);
-	}
-}

mm/shmem.c

@@ -643,7 +643,7 @@ static void shmem_evict_inode(struct inode *inode)
 		kfree(info->symlink);
 
 	simple_xattrs_free(&info->xattrs);
-	BUG_ON(inode->i_blocks);
+	WARN_ON(inode->i_blocks);
 	shmem_free_inode(inode->i_sb);
 	clear_inode(inode);
 }
@@ -1145,8 +1145,20 @@ static int shmem_getpage_gfp(struct inode *inode, pgoff_t index,
 		if (!error) {
 			error = shmem_add_to_page_cache(page, mapping, index,
 						gfp, swp_to_radix_entry(swap));
-			/* We already confirmed swap, and make no allocation */
-			VM_BUG_ON(error);
+			/*
+			 * We already confirmed swap under page lock, and make
+			 * no memory allocation here, so usually no possibility
+			 * of error; but free_swap_and_cache() only trylocks a
+			 * page, so it is just possible that the entry has been
+			 * truncated or holepunched since swap was confirmed.
+			 * shmem_undo_range() will have done some of the
+			 * unaccounting, now delete_from_swap_cache() will do
+			 * the rest (including mem_cgroup_uncharge_swapcache).
+			 * Reset swap.val? No, leave it so "failed" goes back to
+			 * "repeat": reading a hole and writing should succeed.
+			 */
+			if (error)
+				delete_from_swap_cache(page);
 		}
 		if (error)
 			goto failed;

mm/swapfile.c

@@ -1494,9 +1494,8 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile)
 	BUG_ON(!current->mm);
 
 	pathname = getname(specialfile);
-	err = PTR_ERR(pathname);
 	if (IS_ERR(pathname))
-		goto out;
+		return PTR_ERR(pathname);
 
 	victim = file_open_name(pathname, O_RDWR|O_LARGEFILE, 0);
 	err = PTR_ERR(victim);
@@ -1608,6 +1607,7 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile)
 out_dput:
 	filp_close(victim, NULL);
 out:
+	putname(pathname);
 	return err;
 }
 

mm/vmscan.c

@@ -1760,28 +1760,6 @@ static bool in_reclaim_compaction(struct scan_control *sc)
 	return false;
 }
 
-#ifdef CONFIG_COMPACTION
-/*
- * If compaction is deferred for sc->order then scale the number of pages
- * reclaimed based on the number of consecutive allocation failures
- */
-static unsigned long scale_for_compaction(unsigned long pages_for_compaction,
-			struct lruvec *lruvec, struct scan_control *sc)
-{
-	struct zone *zone = lruvec_zone(lruvec);
-
-	if (zone->compact_order_failed <= sc->order)
-		pages_for_compaction <<= zone->compact_defer_shift;
-	return pages_for_compaction;
-}
-#else
-static unsigned long scale_for_compaction(unsigned long pages_for_compaction,
-			struct lruvec *lruvec, struct scan_control *sc)
-{
-	return pages_for_compaction;
-}
-#endif
-
 /*
  * Reclaim/compaction is used for high-order allocation requests. It reclaims
  * order-0 pages before compacting the zone. should_continue_reclaim() returns
@@ -1829,9 +1807,6 @@ static inline bool should_continue_reclaim(struct lruvec *lruvec,
 	 * inactive lists are large enough, continue reclaiming
 	 */
 	pages_for_compaction = (2UL << sc->order);
-
-	pages_for_compaction = scale_for_compaction(pages_for_compaction,
-						    lruvec, sc);
 	inactive_lru_pages = get_lru_size(lruvec, LRU_INACTIVE_FILE);
 	if (nr_swap_pages > 0)
 		inactive_lru_pages += get_lru_size(lruvec, LRU_INACTIVE_ANON);