Merge branch 'fixes' into pm-sleep

The 'fixes' branch contains material the next commit depends on.

9 files changed, 146 insertions, 195 deletions

diff --git a/mm/bootmem.c b/mm/bootmem.c
index ec4fcb7..7309663 100644
--- a/mm/bootmem.c
+++ b/mm/bootmem.c
@@ -698,7 +698,7 @@ void * __init __alloc_bootmem(unsigned long size, unsigned long align,
 	return ___alloc_bootmem(size, align, goal, limit);
 }
 
-static void * __init ___alloc_bootmem_node_nopanic(pg_data_t *pgdat,
+void * __init ___alloc_bootmem_node_nopanic(pg_data_t *pgdat,
 				unsigned long size, unsigned long align,
 				unsigned long goal, unsigned long limit)
 {
diff --git a/mm/compaction.c b/mm/compaction.c
index 7ea259d..2f42d95 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -701,8 +701,11 @@ static int compact_zone(struct zone *zone, struct compact_control *cc)
 		if (err) {
 			putback_lru_pages(&cc->migratepages);
 			cc->nr_migratepages = 0;
+			if (err == -ENOMEM) {
+				ret = COMPACT_PARTIAL;
+				goto out;
+			}
 		}
-
 	}
 
 out:
diff --git a/mm/madvise.c b/mm/madvise.c
index deff1b6..14d260f 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -15,6 +15,7 @@
 #include <linux/sched.h>
 #include <linux/ksm.h>
 #include <linux/fs.h>
+#include <linux/file.h>
 
 /*
  * Any behaviour which results in changes to the vma->vm_flags needs to
@@ -204,14 +205,16 @@ static long madvise_remove(struct vm_area_struct *vma,
 {
 	loff_t offset;
 	int error;
+	struct file *f;
 
 	*prev = NULL;	/* tell sys_madvise we drop mmap_sem */
 
 	if (vma->vm_flags & (VM_LOCKED|VM_NONLINEAR|VM_HUGETLB))
 		return -EINVAL;
 
-	if (!vma->vm_file || !vma->vm_file->f_mapping
-		|| !vma->vm_file->f_mapping->host) {
+	f = vma->vm_file;
+
+	if (!f || !f->f_mapping || !f->f_mapping->host) {
 			return -EINVAL;
 	}
 
@@ -221,11 +224,18 @@ static long madvise_remove(struct vm_area_struct *vma,
 	offset = (loff_t)(start - vma->vm_start)
 			+ ((loff_t)vma->vm_pgoff << PAGE_SHIFT);
 
-	/* filesystem's fallocate may need to take i_mutex */
+	/*
+	 * Filesystem's fallocate may need to take i_mutex.  We need to
+	 * explicitly grab a reference because the vma (and hence the
+	 * vma's reference to the file) can go away as soon as we drop
+	 * mmap_sem.
+	 */
+	get_file(f);
 	up_read(&current->mm->mmap_sem);
-	error = do_fallocate(vma->vm_file,
+	error = do_fallocate(f,
 				FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE,
 				offset, end - start);
+	fput(f);
 	down_read(&current->mm->mmap_sem);
 	return error;
 }
diff --git a/mm/memblock.c b/mm/memblock.c
index d438209..5cc6731 100644
--- a/mm/memblock.c
+++ b/mm/memblock.c
@@ -143,30 +143,6 @@ phys_addr_t __init_memblock memblock_find_in_range(phys_addr_t start,
 					   MAX_NUMNODES);
 }
 
-/*
- * Free memblock.reserved.regions
- */
-int __init_memblock memblock_free_reserved_regions(void)
-{
-	if (memblock.reserved.regions == memblock_reserved_init_regions)
-		return 0;
-
-	return memblock_free(__pa(memblock.reserved.regions),
-		 sizeof(struct memblock_region) * memblock.reserved.max);
-}
-
-/*
- * Reserve memblock.reserved.regions
- */
-int __init_memblock memblock_reserve_reserved_regions(void)
-{
-	if (memblock.reserved.regions == memblock_reserved_init_regions)
-		return 0;
-
-	return memblock_reserve(__pa(memblock.reserved.regions),
-		 sizeof(struct memblock_region) * memblock.reserved.max);
-}
-
 static void __init_memblock memblock_remove_region(struct memblock_type *type, unsigned long r)
 {
 	type->total_size -= type->regions[r].size;
@@ -184,6 +160,18 @@ static void __init_memblock memblock_remove_region(struct memblock_type *type, u
 	}
 }
 
+phys_addr_t __init_memblock get_allocated_memblock_reserved_regions_info(
+					phys_addr_t *addr)
+{
+	if (memblock.reserved.regions == memblock_reserved_init_regions)
+		return 0;
+
+	*addr = __pa(memblock.reserved.regions);
+
+	return PAGE_ALIGN(sizeof(struct memblock_region) *
+			  memblock.reserved.max);
+}
+
 /**
  * memblock_double_array - double the size of the memblock regions array
  * @type: memblock type of the regions array being doubled
@@ -204,6 +192,7 @@ static int __init_memblock memblock_double_array(struct memblock_type *type,
 						phys_addr_t new_area_size)
 {
 	struct memblock_region *new_array, *old_array;
+	phys_addr_t old_alloc_size, new_alloc_size;
 	phys_addr_t old_size, new_size, addr;
 	int use_slab = slab_is_available();
 	int *in_slab;
@@ -217,6 +206,12 @@ static int __init_memblock memblock_double_array(struct memblock_type *type,
 	/* Calculate new doubled size */
 	old_size = type->max * sizeof(struct memblock_region);
 	new_size = old_size << 1;
+	/*
+	 * We need to allocated new one align to PAGE_SIZE,
+	 *   so we can free them completely later.
+	 */
+	old_alloc_size = PAGE_ALIGN(old_size);
+	new_alloc_size = PAGE_ALIGN(new_size);
 
 	/* Retrieve the slab flag */
 	if (type == &memblock.memory)
@@ -245,11 +240,11 @@ static int __init_memblock memblock_double_array(struct memblock_type *type,
 
 		addr = memblock_find_in_range(new_area_start + new_area_size,
 						memblock.current_limit,
-						new_size, sizeof(phys_addr_t));
+						new_alloc_size, PAGE_SIZE);
 		if (!addr && new_area_size)
 			addr = memblock_find_in_range(0,
 					min(new_area_start, memblock.current_limit),
-					new_size, sizeof(phys_addr_t));
+					new_alloc_size, PAGE_SIZE);
 
 		new_array = addr ? __va(addr) : 0;
 	}
@@ -279,13 +274,13 @@ static int __init_memblock memblock_double_array(struct memblock_type *type,
 		kfree(old_array);
 	else if (old_array != memblock_memory_init_regions &&
 		 old_array != memblock_reserved_init_regions)
-		memblock_free(__pa(old_array), old_size);
+		memblock_free(__pa(old_array), old_alloc_size);
 
 	/* Reserve the new array if that comes from the memblock.
 	 * Otherwise, we needn't do it
 	 */
 	if (!use_slab)
-		BUG_ON(memblock_reserve(addr, new_size));
+		BUG_ON(memblock_reserve(addr, new_alloc_size));
 
 	/* Update slab flag */
 	*in_slab = use_slab;
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 0d7e3ec..427bb29 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -618,7 +618,7 @@ int __ref add_memory(int nid, u64 start, u64 size)
 		pgdat = hotadd_new_pgdat(nid, start);
 		ret = -ENOMEM;
 		if (!pgdat)
-			goto out;
+			goto error;
 		new_pgdat = 1;
 	}
 
diff --git a/mm/nobootmem.c b/mm/nobootmem.c
index d23415c..4055730 100644
--- a/mm/nobootmem.c
+++ b/mm/nobootmem.c
@@ -105,27 +105,35 @@ static void __init __free_pages_memory(unsigned long start, unsigned long end)
 		__free_pages_bootmem(pfn_to_page(i), 0);
 }
 
+static unsigned long __init __free_memory_core(phys_addr_t start,
+				 phys_addr_t end)
+{
+	unsigned long start_pfn = PFN_UP(start);
+	unsigned long end_pfn = min_t(unsigned long,
+				      PFN_DOWN(end), max_low_pfn);
+
+	if (start_pfn > end_pfn)
+		return 0;
+
+	__free_pages_memory(start_pfn, end_pfn);
+
+	return end_pfn - start_pfn;
+}
+
 unsigned long __init free_low_memory_core_early(int nodeid)
 {
 	unsigned long count = 0;
-	phys_addr_t start, end;
+	phys_addr_t start, end, size;
 	u64 i;
 
-	/* free reserved array temporarily so that it's treated as free area */
-	memblock_free_reserved_regions();
-
-	for_each_free_mem_range(i, MAX_NUMNODES, &start, &end, NULL) {
-		unsigned long start_pfn = PFN_UP(start);
-		unsigned long end_pfn = min_t(unsigned long,
-					      PFN_DOWN(end), max_low_pfn);
-		if (start_pfn < end_pfn) {
-			__free_pages_memory(start_pfn, end_pfn);
-			count += end_pfn - start_pfn;
-		}
-	}
+	for_each_free_mem_range(i, MAX_NUMNODES, &start, &end, NULL)
+		count += __free_memory_core(start, end);
+
+	/* free range that is used for reserved array if we allocate it */
+	size = get_allocated_memblock_reserved_regions_info(&start);
+	if (size)
+		count += __free_memory_core(start, start + size);
 
-	/* put region array back? */
-	memblock_reserve_reserved_regions();
 	return count;
 }
 
@@ -274,7 +282,7 @@ void * __init __alloc_bootmem(unsigned long size, unsigned long align,
 	return ___alloc_bootmem(size, align, goal, limit);
 }
 
-static void * __init ___alloc_bootmem_node_nopanic(pg_data_t *pgdat,
+void * __init ___alloc_bootmem_node_nopanic(pg_data_t *pgdat,
 						   unsigned long size,
 						   unsigned long align,
 						   unsigned long goal,
diff --git a/mm/shmem.c b/mm/shmem.c
index a15a466..bd10636 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -264,46 +264,55 @@ static int shmem_radix_tree_replace(struct address_space *mapping,
 }
 
 /*
+ * Sometimes, before we decide whether to proceed or to fail, we must check
+ * that an entry was not already brought back from swap by a racing thread.
+ *
+ * Checking page is not enough: by the time a SwapCache page is locked, it
+ * might be reused, and again be SwapCache, using the same swap as before.
+ */
+static bool shmem_confirm_swap(struct address_space *mapping,
+			       pgoff_t index, swp_entry_t swap)
+{
+	void *item;
+
+	rcu_read_lock();
+	item = radix_tree_lookup(&mapping->page_tree, index);
+	rcu_read_unlock();
+	return item == swp_to_radix_entry(swap);
+}
+
+/*
  * Like add_to_page_cache_locked, but error if expected item has gone.
  */
 static int shmem_add_to_page_cache(struct page *page,
 				   struct address_space *mapping,
 				   pgoff_t index, gfp_t gfp, void *expected)
 {
-	int error = 0;
+	int error;
 
 	VM_BUG_ON(!PageLocked(page));
 	VM_BUG_ON(!PageSwapBacked(page));
 
+	page_cache_get(page);
+	page->mapping = mapping;
+	page->index = index;
+
+	spin_lock_irq(&mapping->tree_lock);
 	if (!expected)
-		error = radix_tree_preload(gfp & GFP_RECLAIM_MASK);
+		error = radix_tree_insert(&mapping->page_tree, index, page);
+	else
+		error = shmem_radix_tree_replace(mapping, index, expected,
+								 page);
 	if (!error) {
-		page_cache_get(page);
-		page->mapping = mapping;
-		page->index = index;
-
-		spin_lock_irq(&mapping->tree_lock);
-		if (!expected)
-			error = radix_tree_insert(&mapping->page_tree,
-							index, page);
-		else
-			error = shmem_radix_tree_replace(mapping, index,
-							expected, page);
-		if (!error) {
-			mapping->nrpages++;
-			__inc_zone_page_state(page, NR_FILE_PAGES);
-			__inc_zone_page_state(page, NR_SHMEM);
-			spin_unlock_irq(&mapping->tree_lock);
-		} else {
-			page->mapping = NULL;
-			spin_unlock_irq(&mapping->tree_lock);
-			page_cache_release(page);
-		}
-		if (!expected)
-			radix_tree_preload_end();
+		mapping->nrpages++;
+		__inc_zone_page_state(page, NR_FILE_PAGES);
+		__inc_zone_page_state(page, NR_SHMEM);
+		spin_unlock_irq(&mapping->tree_lock);
+	} else {
+		page->mapping = NULL;
+		spin_unlock_irq(&mapping->tree_lock);
+		page_cache_release(page);
 	}
-	if (error)
-		mem_cgroup_uncharge_cache_page(page);
 	return error;
 }
 
@@ -1124,9 +1133,9 @@ repeat:
 		/* We have to do this with page locked to prevent races */
 		lock_page(page);
 		if (!PageSwapCache(page) || page_private(page) != swap.val ||
-		    page->mapping) {
+		    !shmem_confirm_swap(mapping, index, swap)) {
 			error = -EEXIST;	/* try again */
-			goto failed;
+			goto unlock;
 		}
 		if (!PageUptodate(page)) {
 			error = -EIO;
@@ -1142,9 +1151,12 @@ repeat:
 
 		error = mem_cgroup_cache_charge(page, current->mm,
 						gfp & GFP_RECLAIM_MASK);
-		if (!error)
+		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);
+		}
 		if (error)
 			goto failed;
 
@@ -1181,11 +1193,18 @@ repeat:
 		__set_page_locked(page);
 		error = mem_cgroup_cache_charge(page, current->mm,
 						gfp & GFP_RECLAIM_MASK);
-		if (!error)
-			error = shmem_add_to_page_cache(page, mapping, index,
-						gfp, NULL);
 		if (error)
 			goto decused;
+		error = radix_tree_preload(gfp & GFP_RECLAIM_MASK);
+		if (!error) {
+			error = shmem_add_to_page_cache(page, mapping, index,
+							gfp, NULL);
+			radix_tree_preload_end();
+		}
+		if (error) {
+			mem_cgroup_uncharge_cache_page(page);
+			goto decused;
+		}
 		lru_cache_add_anon(page);
 
 		spin_lock(&info->lock);
@@ -1245,14 +1264,10 @@ decused:
 unacct:
 	shmem_unacct_blocks(info->flags, 1);
 failed:
-	if (swap.val && error != -EINVAL) {
-		struct page *test = find_get_page(mapping, index);
-		if (test && !radix_tree_exceptional_entry(test))
-			page_cache_release(test);
-		/* Have another try if the entry has changed */
-		if (test != swp_to_radix_entry(swap))
-			error = -EEXIST;
-	}
+	if (swap.val && error != -EINVAL &&
+	    !shmem_confirm_swap(mapping, index, swap))
+		error = -EEXIST;
+unlock:
 	if (page) {
 		unlock_page(page);
 		page_cache_release(page);
@@ -1264,7 +1279,7 @@ failed:
 		spin_unlock(&info->lock);
 		goto repeat;
 	}
-	if (error == -EEXIST)
+	if (error == -EEXIST)	/* from above or from radix_tree_insert */
 		goto repeat;
 	return error;
 }
@@ -1594,6 +1609,7 @@ static ssize_t shmem_file_splice_read(struct file *in, loff_t *ppos,
 	struct splice_pipe_desc spd = {
 		.pages = pages,
 		.partial = partial,
+		.nr_pages_max = PIPE_DEF_BUFFERS,
 		.flags = flags,
 		.ops = &page_cache_pipe_buf_ops,
 		.spd_release = spd_release_page,
@@ -1682,7 +1698,7 @@ static ssize_t shmem_file_splice_read(struct file *in, loff_t *ppos,
 	if (spd.nr_pages)
 		error = splice_to_pipe(pipe, &spd);
 
-	splice_shrink_spd(pipe, &spd);
+	splice_shrink_spd(&spd);
 
 	if (error > 0) {
 		*ppos += error;
@@ -1691,98 +1707,6 @@ static ssize_t shmem_file_splice_read(struct file *in, loff_t *ppos,
 	return error;
 }
 
-/*
- * llseek SEEK_DATA or SEEK_HOLE through the radix_tree.
- */
-static pgoff_t shmem_seek_hole_data(struct address_space *mapping,
-				    pgoff_t index, pgoff_t end, int origin)
-{
-	struct page *page;
-	struct pagevec pvec;
-	pgoff_t indices[PAGEVEC_SIZE];
-	bool done = false;
-	int i;
-
-	pagevec_init(&pvec, 0);
-	pvec.nr = 1;		/* start small: we may be there already */
-	while (!done) {
-		pvec.nr = shmem_find_get_pages_and_swap(mapping, index,
-					pvec.nr, pvec.pages, indices);
-		if (!pvec.nr) {
-			if (origin == SEEK_DATA)
-				index = end;
-			break;
-		}
-		for (i = 0; i < pvec.nr; i++, index++) {
-			if (index < indices[i]) {
-				if (origin == SEEK_HOLE) {
-					done = true;
-					break;
-				}
-				index = indices[i];
-			}
-			page = pvec.pages[i];
-			if (page && !radix_tree_exceptional_entry(page)) {
-				if (!PageUptodate(page))
-					page = NULL;
-			}
-			if (index >= end ||
-			    (page && origin == SEEK_DATA) ||
-			    (!page && origin == SEEK_HOLE)) {
-				done = true;
-				break;
-			}
-		}
-		shmem_deswap_pagevec(&pvec);
-		pagevec_release(&pvec);
-		pvec.nr = PAGEVEC_SIZE;
-		cond_resched();
-	}
-	return index;
-}
-
-static loff_t shmem_file_llseek(struct file *file, loff_t offset, int origin)
-{
-	struct address_space *mapping;
-	struct inode *inode;
-	pgoff_t start, end;
-	loff_t new_offset;
-
-	if (origin != SEEK_DATA && origin != SEEK_HOLE)
-		return generic_file_llseek_size(file, offset, origin,
-							MAX_LFS_FILESIZE);
-	mapping = file->f_mapping;
-	inode = mapping->host;
-	mutex_lock(&inode->i_mutex);
-	/* We're holding i_mutex so we can access i_size directly */
-
-	if (offset < 0)
-		offset = -EINVAL;
-	else if (offset >= inode->i_size)
-		offset = -ENXIO;
-	else {
-		start = offset >> PAGE_CACHE_SHIFT;
-		end = (inode->i_size + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
-		new_offset = shmem_seek_hole_data(mapping, start, end, origin);
-		new_offset <<= PAGE_CACHE_SHIFT;
-		if (new_offset > offset) {
-			if (new_offset < inode->i_size)
-				offset = new_offset;
-			else if (origin == SEEK_DATA)
-				offset = -ENXIO;
-			else
-				offset = inode->i_size;
-		}
-	}
-
-	if (offset >= 0 && offset != file->f_pos) {
-		file->f_pos = offset;
-		file->f_version = 0;
-	}
-	mutex_unlock(&inode->i_mutex);
-	return offset;
-}
-
 static long shmem_fallocate(struct file *file, int mode, loff_t offset,
 							 loff_t len)
 {
@@ -2786,7 +2710,7 @@ static const struct address_space_operations shmem_aops = {
 static const struct file_operations shmem_file_operations = {
 	.mmap		= shmem_mmap,
 #ifdef CONFIG_TMPFS
-	.llseek		= shmem_file_llseek,
+	.llseek		= generic_file_llseek,
 	.read		= do_sync_read,
 	.write		= do_sync_write,
 	.aio_read	= shmem_file_aio_read,
diff --git a/mm/sparse.c b/mm/sparse.c
index 6a4bf91..c7bb952 100644
--- a/mm/sparse.c
+++ b/mm/sparse.c
@@ -275,8 +275,9 @@ static unsigned long * __init
 sparse_early_usemaps_alloc_pgdat_section(struct pglist_data *pgdat,
 					 unsigned long size)
 {
-	pg_data_t *host_pgdat;
-	unsigned long goal;
+	unsigned long goal, limit;
+	unsigned long *p;
+	int nid;
 	/*
 	 * A page may contain usemaps for other sections preventing the
 	 * page being freed and making a section unremovable while
@@ -287,10 +288,17 @@ sparse_early_usemaps_alloc_pgdat_section(struct pglist_data *pgdat,
 	 * from the same section as the pgdat where possible to avoid
 	 * this problem.
 	 */
-	goal = __pa(pgdat) & PAGE_SECTION_MASK;
-	host_pgdat = NODE_DATA(early_pfn_to_nid(goal >> PAGE_SHIFT));
-	return __alloc_bootmem_node_nopanic(host_pgdat, size,
-					    SMP_CACHE_BYTES, goal);
+	goal = __pa(pgdat) & (PAGE_SECTION_MASK << PAGE_SHIFT);
+	limit = goal + (1UL << PA_SECTION_SHIFT);
+	nid = early_pfn_to_nid(goal >> PAGE_SHIFT);
+again:
+	p = ___alloc_bootmem_node_nopanic(NODE_DATA(nid), size,
+					  SMP_CACHE_BYTES, goal, limit);
+	if (!p && limit) {
+		limit = 0;
+		goto again;
+	}
+	return p;
 }
 
 static void __init check_usemap_section_nr(int nid, unsigned long *usemap)
diff --git a/mm/vmscan.c b/mm/vmscan.c
index eeb3bc9..6615763 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2955,14 +2955,17 @@ int kswapd_run(int nid)
 }
 
 /*
- * Called by memory hotplug when all memory in a node is offlined.
+ * Called by memory hotplug when all memory in a node is offlined.  Caller must
+ * hold lock_memory_hotplug().
  */
 void kswapd_stop(int nid)
 {
 	struct task_struct *kswapd = NODE_DATA(nid)->kswapd;
 
-	if (kswapd)
+	if (kswapd) {
 		kthread_stop(kswapd);
+		NODE_DATA(nid)->kswapd = NULL;
+	}
 }
 
 static int __init kswapd_init(void)