Merge master.kernel.org:/pub/scm/linux/kernel/git/torvalds/linux-2.6 into for-linus

19 files changed, 154 insertions, 88 deletions

diff --git a/mm/bootmem.c b/mm/bootmem.c
index f6ff4337b424..2ccea700968f 100644
--- a/mm/bootmem.c
+++ b/mm/bootmem.c
@@ -125,6 +125,7 @@ static int __init reserve_bootmem_core(bootmem_data_t *bdata,
 	BUG_ON(!size);
 	BUG_ON(PFN_DOWN(addr) >= bdata->node_low_pfn);
 	BUG_ON(PFN_UP(addr + size) > bdata->node_low_pfn);
+	BUG_ON(addr < bdata->node_boot_start);
 
 	sidx = PFN_DOWN(addr - bdata->node_boot_start);
 	eidx = PFN_UP(addr + size - bdata->node_boot_start);
@@ -156,21 +157,31 @@ static void __init free_bootmem_core(bootmem_data_t *bdata, unsigned long addr,
 	unsigned long sidx, eidx;
 	unsigned long i;
 
+	BUG_ON(!size);
+
+	/* out range */
+	if (addr + size < bdata->node_boot_start ||
+		PFN_DOWN(addr) > bdata->node_low_pfn)
+		return;
 	/*
 	 * round down end of usable mem, partially free pages are
 	 * considered reserved.
 	 */
-	BUG_ON(!size);
-	BUG_ON(PFN_DOWN(addr + size) > bdata->node_low_pfn);
 
-	if (addr < bdata->last_success)
+	if (addr >= bdata->node_boot_start && addr < bdata->last_success)
 		bdata->last_success = addr;
 
 	/*
-	 * Round up the beginning of the address.
+	 * Round up to index to the range.
 	 */
-	sidx = PFN_UP(addr) - PFN_DOWN(bdata->node_boot_start);
+	if (PFN_UP(addr) > PFN_DOWN(bdata->node_boot_start))
+		sidx = PFN_UP(addr) - PFN_DOWN(bdata->node_boot_start);
+	else
+		sidx = 0;
+
 	eidx = PFN_DOWN(addr + size - bdata->node_boot_start);
+	if (eidx > bdata->node_low_pfn - PFN_DOWN(bdata->node_boot_start))
+		eidx = bdata->node_low_pfn - PFN_DOWN(bdata->node_boot_start);
 
 	for (i = sidx; i < eidx; i++) {
 		if (unlikely(!test_and_clear_bit(i, bdata->node_bootmem_map)))
@@ -421,7 +432,9 @@ int __init reserve_bootmem(unsigned long addr, unsigned long size,
 
 void __init free_bootmem(unsigned long addr, unsigned long size)
 {
-	free_bootmem_core(NODE_DATA(0)->bdata, addr, size);
+	bootmem_data_t *bdata;
+	list_for_each_entry(bdata, &bdata_list, list)
+		free_bootmem_core(bdata, addr, size);
 }
 
 unsigned long __init free_all_bootmem(void)
diff --git a/mm/filemap.c b/mm/filemap.c
index df343d1e6345..07e9d9258b48 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -343,7 +343,7 @@ int sync_page_range(struct inode *inode, struct address_space *mapping,
 EXPORT_SYMBOL(sync_page_range);
 
 /**
- * sync_page_range_nolock
+ * sync_page_range_nolock - write & wait on all pages in the passed range without locking
  * @inode:	target inode
  * @mapping:	target address_space
  * @pos:	beginning offset in pages to write
@@ -611,7 +611,10 @@ int __lock_page_killable(struct page *page)
 					sync_page_killable, TASK_KILLABLE);
 }
 
-/*
+/**
+ * __lock_page_nosync - get a lock on the page, without calling sync_page()
+ * @page: the page to lock
+ *
  * Variant of lock_page that does not require the caller to hold a reference
  * on the page's mapping.
  */
@@ -1538,9 +1541,20 @@ repeat:
 	return page;
 }
 
-/*
+/**
+ * read_cache_page_async - read into page cache, fill it if needed
+ * @mapping:	the page's address_space
+ * @index:	the page index
+ * @filler:	function to perform the read
+ * @data:	destination for read data
+ *
  * Same as read_cache_page, but don't wait for page to become unlocked
  * after submitting it to the filler.
+ *
+ * Read into the page cache. If a page already exists, and PageUptodate() is
+ * not set, try to fill the page but don't wait for it to become unlocked.
+ *
+ * If the page does not get brought uptodate, return -EIO.
  */
 struct page *read_cache_page_async(struct address_space *mapping,
 				pgoff_t index,
diff --git a/mm/fremap.c b/mm/fremap.c
index 69a37c2bdf81..07a9c82ce1a3 100644
--- a/mm/fremap.c
+++ b/mm/fremap.c
@@ -113,7 +113,7 @@ static int populate_range(struct mm_struct *mm, struct vm_area_struct *vma,
  * mmap()/mremap() it does not create any new vmas. The new mappings are
  * also safe across swapout.
  *
- * NOTE: the 'prot' parameter right now is ignored (but must be zero),
+ * NOTE: the @prot parameter right now is ignored (but must be zero),
  * and the vma's default protection is used. Arbitrary protections
  * might be implemented in the future.
  */
diff --git a/mm/highmem.c b/mm/highmem.c
index 35d47733cde4..7da4a7b6af11 100644
--- a/mm/highmem.c
+++ b/mm/highmem.c
@@ -104,8 +104,9 @@ static void flush_all_zero_pkmaps(void)
 	flush_tlb_kernel_range(PKMAP_ADDR(0), PKMAP_ADDR(LAST_PKMAP));
 }
 
-/* Flush all unused kmap mappings in order to remove stray
-   mappings. */
+/**
+ * kmap_flush_unused - flush all unused kmap mappings in order to remove stray mappings
+ */
 void kmap_flush_unused(void)
 {
 	spin_lock(&kmap_lock);
@@ -163,6 +164,14 @@ start:
 	return vaddr;
 }
 
+/**
+ * kmap_high - map a highmem page into memory
+ * @page: &struct page to map
+ *
+ * Returns the page's virtual memory address.
+ *
+ * We cannot call this from interrupts, as it may block.
+ */
 void *kmap_high(struct page *page)
 {
 	unsigned long vaddr;
@@ -170,8 +179,6 @@ void *kmap_high(struct page *page)
 	/*
 	 * For highmem pages, we can't trust "virtual" until
 	 * after we have the lock.
-	 *
-	 * We cannot call this from interrupts, as it may block
 	 */
 	spin_lock(&kmap_lock);
 	vaddr = (unsigned long)page_address(page);
@@ -185,6 +192,10 @@ void *kmap_high(struct page *page)
 
 EXPORT_SYMBOL(kmap_high);
 
+/**
+ * kunmap_high - map a highmem page into memory
+ * @page: &struct page to unmap
+ */
 void kunmap_high(struct page *page)
 {
 	unsigned long vaddr;
@@ -259,6 +270,12 @@ static struct page_address_slot *page_slot(struct page *page)
 	return &page_address_htable[hash_ptr(page, PA_HASH_ORDER)];
 }
 
+/**
+ * page_address - get the mapped virtual address of a page
+ * @page: &struct page to get the virtual address of
+ *
+ * Returns the page's virtual address.
+ */
 void *page_address(struct page *page)
 {
 	unsigned long flags;
@@ -288,6 +305,11 @@ done:
 
 EXPORT_SYMBOL(page_address);
 
+/**
+ * set_page_address - set a page's virtual address
+ * @page: &struct page to set
+ * @virtual: virtual address to use
+ */
 void set_page_address(struct page *page, void *virtual)
 {
 	unsigned long flags;
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 74c1b6b0b37b..51c9e2c01640 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -401,12 +401,20 @@ static void return_unused_surplus_pages(unsigned long unused_resv_pages)
 	struct page *page;
 	unsigned long nr_pages;
 
+	/*
+	 * We want to release as many surplus pages as possible, spread
+	 * evenly across all nodes. Iterate across all nodes until we
+	 * can no longer free unreserved surplus pages. This occurs when
+	 * the nodes with surplus pages have no free pages.
+	 */
+	unsigned long remaining_iterations = num_online_nodes();
+
 	/* Uncommit the reservation */
 	resv_huge_pages -= unused_resv_pages;
 
 	nr_pages = min(unused_resv_pages, surplus_huge_pages);
 
-	while (nr_pages) {
+	while (remaining_iterations-- && nr_pages) {
 		nid = next_node(nid, node_online_map);
 		if (nid == MAX_NUMNODES)
 			nid = first_node(node_online_map);
@@ -424,6 +432,7 @@ static void return_unused_surplus_pages(unsigned long unused_resv_pages)
 			surplus_huge_pages--;
 			surplus_huge_pages_node[nid]--;
 			nr_pages--;
+			remaining_iterations = num_online_nodes();
 		}
 	}
 }
@@ -671,9 +680,11 @@ int hugetlb_report_node_meminfo(int nid, char *buf)
 {
 	return sprintf(buf,
 		"Node %d HugePages_Total: %5u\n"
-		"Node %d HugePages_Free:  %5u\n",
+		"Node %d HugePages_Free:  %5u\n"
+		"Node %d HugePages_Surp:  %5u\n",
 		nid, nr_huge_pages_node[nid],
-		nid, free_huge_pages_node[nid]);
+		nid, free_huge_pages_node[nid],
+		nid, surplus_huge_pages_node[nid]);
 }
 
 /* Return the number pages of memory we physically have, in PAGE_SIZE units. */
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 8b9f6cae938e..9b648bd63451 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -1079,7 +1079,7 @@ static void mem_cgroup_move_task(struct cgroup_subsys *ss,
 	 * Only thread group leaders are allowed to migrate, the mm_struct is
 	 * in effect owned by the leader
 	 */
-	if (p->tgid != p->pid)
+	if (!thread_group_leader(p))
 		goto out;
 
 	css_get(&mem->css);
diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index 44b2da11bf43..f255eda693b0 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -37,6 +37,7 @@ static DEFINE_SPINLOCK(zone_scan_mutex);
  * badness - calculate a numeric value for how bad this task has been
  * @p: task struct of which task we should calculate
  * @uptime: current uptime in seconds
+ * @mem: target memory controller
  *
  * The formula used is relatively simple and documented inline in the
  * function. The main rationale is that we want to select a good task
@@ -264,6 +265,9 @@ static struct task_struct *select_bad_process(unsigned long *ppoints,
 }
 
 /**
+ * dump_tasks - dump current memory state of all system tasks
+ * @mem: target memory controller
+ *
  * Dumps the current memory state of all system tasks, excluding kernel threads.
  * State information includes task's pid, uid, tgid, vm size, rss, cpu, oom_adj
  * score, and name.
@@ -298,7 +302,7 @@ static void dump_tasks(const struct mem_cgroup *mem)
 	} while_each_thread(g, p);
 }
 
-/**
+/*
  * Send SIGKILL to the selected  process irrespective of  CAP_SYS_RAW_IO
  * flag though it's unlikely that  we select a process with CAP_SYS_RAW_IO
  * set.
@@ -504,6 +508,9 @@ void clear_zonelist_oom(struct zonelist *zonelist)
 
 /**
  * out_of_memory - kill the "best" process when we run out of memory
+ * @zonelist: zonelist pointer
+ * @gfp_mask: memory allocation flags
+ * @order: amount of memory being requested as a power of 2
  *
  * If we run out of memory, we have the choice between either
  * killing a random task (bad), letting the system crash (worse)
diff --git a/mm/pagewalk.c b/mm/pagewalk.c
index b4f27d22da91..1cf1417ef8b7 100644
--- a/mm/pagewalk.c
+++ b/mm/pagewalk.c
@@ -77,11 +77,11 @@ static int walk_pud_range(pgd_t *pgd, unsigned long addr, unsigned long end,
 
 /**
  * walk_page_range - walk a memory map's page tables with a callback
- * @mm - memory map to walk
- * @addr - starting address
- * @end - ending address
- * @walk - set of callbacks to invoke for each level of the tree
- * @private - private data passed to the callback function
+ * @mm: memory map to walk
+ * @addr: starting address
+ * @end: ending address
+ * @walk: set of callbacks to invoke for each level of the tree
+ * @private: private data passed to the callback function
  *
  * Recursively walk the page table for the memory area in a VMA,
  * calling supplied callbacks. Callbacks are called in-order (first
diff --git a/mm/readahead.c b/mm/readahead.c
index c9c50ca1ec38..8762e8988972 100644
--- a/mm/readahead.c
+++ b/mm/readahead.c
@@ -443,9 +443,10 @@ EXPORT_SYMBOL_GPL(page_cache_sync_readahead);
  *            pagecache pages
  *
  * page_cache_async_ondemand() should be called when a page is used which
- * has the PG_readahead flag: this is a marker to suggest that the application
+ * has the PG_readahead flag; this is a marker to suggest that the application
  * has used up enough of the readahead window that we should start pulling in
- * more pages. */
+ * more pages.
+ */
 void
 page_cache_async_readahead(struct address_space *mapping,
 			   struct file_ra_state *ra, struct file *filp,
diff --git a/mm/rmap.c b/mm/rmap.c
index 0c9a2df06c39..997f06907b6d 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -335,6 +335,7 @@ static int page_referenced_anon(struct page *page,
 /**
  * page_referenced_file - referenced check for object-based rmap
  * @page: the page we're checking references on.
+ * @mem_cont: target memory controller
  *
  * For an object-based mapped page, find all the places it is mapped and
  * check/clear the referenced flag.  This is done by following the page->mapping
@@ -402,6 +403,7 @@ static int page_referenced_file(struct page *page,
  * page_referenced - test if the page was referenced
  * @page: the page to test
  * @is_locked: caller holds lock on the page
+ * @mem_cont: target memory controller
  *
  * Quick test_and_clear_referenced for all mappings to a page,
  * returns the number of ptes which referenced the page.
@@ -506,7 +508,7 @@ int page_mkclean(struct page *page)
 EXPORT_SYMBOL_GPL(page_mkclean);
 
 /**
- * page_set_anon_rmap - setup new anonymous rmap
+ * __page_set_anon_rmap - setup new anonymous rmap
  * @page:	the page to add the mapping to
  * @vma:	the vm area in which the mapping is added
  * @address:	the user virtual address mapped
@@ -530,7 +532,7 @@ static void __page_set_anon_rmap(struct page *page,
 }
 
 /**
- * page_set_anon_rmap - sanity check anonymous rmap addition
+ * __page_check_anon_rmap - sanity check anonymous rmap addition
  * @page:	the page to add the mapping to
  * @vma:	the vm area in which the mapping is added
  * @address:	the user virtual address mapped
@@ -583,7 +585,7 @@ void page_add_anon_rmap(struct page *page,
 	}
 }
 
-/*
+/**
  * page_add_new_anon_rmap - add pte mapping to a new anonymous page
  * @page:	the page to add the mapping to
  * @vma:	the vm area in which the mapping is added
@@ -623,6 +625,8 @@ void page_add_file_rmap(struct page *page)
 /**
  * page_dup_rmap - duplicate pte mapping to a page
  * @page:	the page to add the mapping to
+ * @vma:	the vm area being duplicated
+ * @address:	the user virtual address mapped
  *
  * For copy_page_range only: minimal extract from page_add_file_rmap /
  * page_add_anon_rmap, avoiding unnecessary tests (already checked) so it's
@@ -642,6 +646,7 @@ void page_dup_rmap(struct page *page, struct vm_area_struct *vma, unsigned long
 /**
  * page_remove_rmap - take down pte mapping from a page
  * @page: page to remove mapping from
+ * @vma: the vm area in which the mapping is removed
  *
  * The caller needs to hold the pte lock.
  */
@@ -890,6 +895,7 @@ static int try_to_unmap_anon(struct page *page, int migration)
 /**
  * try_to_unmap_file - unmap file page using the object-based rmap method
  * @page: the page to unmap
+ * @migration: migration flag
  *
  * Find all the mappings of a page using the mapping pointer and the vma chains
  * contained in the address_space struct it points to.
@@ -986,6 +992,7 @@ out:
 /**
  * try_to_unmap - try to remove all page table mappings to a page
  * @page: the page to get unmapped
+ * @migration: migration flag
  *
  * Tries to remove all the page table entries which are mapping this
  * page, used in the pageout path.  Caller must hold the page lock.
diff --git a/mm/shmem.c b/mm/shmem.c
index 3372bc579e89..f514dd392cd9 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -244,9 +244,8 @@ static void shmem_free_inode(struct super_block *sb)
 	}
 }
 
-/*
+/**
  * shmem_recalc_inode - recalculate the size of an inode
- *
  * @inode: inode to recalc
  *
  * We have to calculate the free blocks since the mm can drop
@@ -270,9 +269,8 @@ static void shmem_recalc_inode(struct inode *inode)
 	}
 }
 
-/*
+/**
  * shmem_swp_entry - find the swap vector position in the info structure
- *
  * @info:  info structure for the inode
  * @index: index of the page to find
  * @page:  optional page to add to the structure. Has to be preset to
@@ -374,13 +372,13 @@ static void shmem_swp_set(struct shmem_inode_info *info, swp_entry_t *entry, uns
 	}
 }
 
-/*
+/**
  * shmem_swp_alloc - get the position of the swap entry for the page.
- *                   If it does not exist allocate the entry.
- *
  * @info:	info structure for the inode
  * @index:	index of the page to find
  * @sgp:	check and recheck i_size? skip allocation?
+ *
+ * If the entry does not exist, allocate it.
  */
 static swp_entry_t *shmem_swp_alloc(struct shmem_inode_info *info, unsigned long index, enum sgp_type sgp)
 {
@@ -440,9 +438,8 @@ static swp_entry_t *shmem_swp_alloc(struct shmem_inode_info *info, unsigned long
 	return entry;
 }
 
-/*
+/**
  * shmem_free_swp - free some swap entries in a directory
- *
  * @dir:        pointer to the directory
  * @edir:       pointer after last entry of the directory
  * @punch_lock: pointer to spinlock when needed for the holepunch case
@@ -2022,7 +2019,7 @@ static const struct inode_operations shmem_symlink_inode_operations = {
 };
 
 #ifdef CONFIG_TMPFS_POSIX_ACL
-/**
+/*
  * Superblocks without xattr inode operations will get security.* xattr
  * support from the VFS "for free". As soon as we have any other xattrs
  * like ACLs, we also need to implement the security.* handlers at
@@ -2561,12 +2558,11 @@ out4:
 }
 module_init(init_tmpfs)
 
-/*
+/**
  * shmem_file_setup - get an unlinked file living in tmpfs
- *
  * @name: name for dentry (to be seen in /proc/<pid>/maps
  * @size: size to be set for the file
- *
+ * @flags: vm_flags
  */
 struct file *shmem_file_setup(char *name, loff_t size, unsigned long flags)
 {
@@ -2621,9 +2617,8 @@ put_memory:
 	return ERR_PTR(error);
 }
 
-/*
+/**
  * shmem_zero_setup - setup a shared anonymous mapping
- *
  * @vma: the vma to be mmapped is prepared by do_mmap_pgoff
  */
 int shmem_zero_setup(struct vm_area_struct *vma)
diff --git a/mm/slab.c b/mm/slab.c
index e6c698f55674..04b308c3bc54 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -1481,7 +1481,7 @@ void __init kmem_cache_init(void)
 	list_add(&cache_cache.next, &cache_chain);
 	cache_cache.colour_off = cache_line_size();
 	cache_cache.array[smp_processor_id()] = &initarray_cache.cache;
-	cache_cache.nodelists[node] = &initkmem_list3[CACHE_CACHE];
+	cache_cache.nodelists[node] = &initkmem_list3[CACHE_CACHE + node];
 
 	/*
 	 * struct kmem_cache size depends on nr_node_ids, which
@@ -1602,7 +1602,7 @@ void __init kmem_cache_init(void)
 		int nid;
 
 		for_each_online_node(nid) {
-			init_list(&cache_cache, &initkmem_list3[CACHE_CACHE], nid);
+			init_list(&cache_cache, &initkmem_list3[CACHE_CACHE + nid], nid);
 
 			init_list(malloc_sizes[INDEX_AC].cs_cachep,
 				  &initkmem_list3[SIZE_AC + nid], nid);
@@ -3624,12 +3624,11 @@ void *kmem_cache_alloc(struct kmem_cache *cachep, gfp_t flags)
 EXPORT_SYMBOL(kmem_cache_alloc);
 
 /**
- * kmem_ptr_validate - check if an untrusted pointer might
- *	be a slab entry.
+ * kmem_ptr_validate - check if an untrusted pointer might be a slab entry.
  * @cachep: the cache we're checking against
  * @ptr: pointer to validate
  *
- * This verifies that the untrusted pointer looks sane:
+ * This verifies that the untrusted pointer looks sane;
  * it is _not_ a guarantee that the pointer is actually
  * part of the slab cache in question, but it at least
  * validates that the pointer can be dereferenced and
diff --git a/mm/slub.c b/mm/slub.c
index 96d63eb3ab17..84ed734b96b3 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -1470,6 +1470,9 @@ static void *__slab_alloc(struct kmem_cache *s,
 	void **object;
 	struct page *new;
 
+	/* We handle __GFP_ZERO in the caller */
+	gfpflags &= ~__GFP_ZERO;
+
 	if (!c->page)
 		goto new_slab;
 
@@ -1536,9 +1539,15 @@ new_slab:
 	 * That is only possible if certain conditions are met that are being
 	 * checked when a slab is created.
 	 */
-	if (!(gfpflags & __GFP_NORETRY) && (s->flags & __PAGE_ALLOC_FALLBACK))
-		return kmalloc_large(s->objsize, gfpflags);
-
+	if (!(gfpflags & __GFP_NORETRY) &&
+				(s->flags & __PAGE_ALLOC_FALLBACK)) {
+		if (gfpflags & __GFP_WAIT)
+			local_irq_enable();
+		object = kmalloc_large(s->objsize, gfpflags);
+		if (gfpflags & __GFP_WAIT)
+			local_irq_disable();
+		return object;
+	}
 	return NULL;
 debug:
 	if (!alloc_debug_processing(s, c->page, object, addr))
@@ -2679,6 +2688,7 @@ void kfree(const void *x)
 }
 EXPORT_SYMBOL(kfree);
 
+#if defined(SLUB_DEBUG) || defined(CONFIG_SLABINFO)
 static unsigned long count_partial(struct kmem_cache_node *n)
 {
 	unsigned long flags;
@@ -2691,6 +2701,7 @@ static unsigned long count_partial(struct kmem_cache_node *n)
 	spin_unlock_irqrestore(&n->list_lock, flags);
 	return x;
 }
+#endif
 
 /*
  * kmem_cache_shrink removes empty slabs from the partial lists and sorts
diff --git a/mm/sparse-vmemmap.c b/mm/sparse-vmemmap.c
index cd75b21dd4c3..99c4f36eb8a3 100644
--- a/mm/sparse-vmemmap.c
+++ b/mm/sparse-vmemmap.c
@@ -76,7 +76,7 @@ pte_t * __meminit vmemmap_pte_populate(pmd_t *pmd, unsigned long addr, int node)
 		pte_t entry;
 		void *p = vmemmap_alloc_block(PAGE_SIZE, node);
 		if (!p)
-			return 0;
+			return NULL;
 		entry = pfn_pte(__pa(p) >> PAGE_SHIFT, PAGE_KERNEL);
 		set_pte_at(&init_mm, addr, pte, entry);
 	}
@@ -89,7 +89,7 @@ pmd_t * __meminit vmemmap_pmd_populate(pud_t *pud, unsigned long addr, int node)
 	if (pmd_none(*pmd)) {
 		void *p = vmemmap_alloc_block(PAGE_SIZE, node);
 		if (!p)
-			return 0;
+			return NULL;
 		pmd_populate_kernel(&init_mm, pmd, p);
 	}
 	return pmd;
@@ -101,7 +101,7 @@ pud_t * __meminit vmemmap_pud_populate(pgd_t *pgd, unsigned long addr, int node)
 	if (pud_none(*pud)) {
 		void *p = vmemmap_alloc_block(PAGE_SIZE, node);
 		if (!p)
-			return 0;
+			return NULL;
 		pud_populate(&init_mm, pud, p);
 	}
 	return pud;
@@ -113,7 +113,7 @@ pgd_t * __meminit vmemmap_pgd_populate(unsigned long addr, int node)
 	if (pgd_none(*pgd)) {
 		void *p = vmemmap_alloc_block(PAGE_SIZE, node);
 		if (!p)
-			return 0;
+			return NULL;
 		pgd_populate(&init_mm, pgd, p);
 	}
 	return pgd;
diff --git a/mm/swap.c b/mm/swap.c
index d4ec59aa5c46..aa1139ccf3a7 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -78,12 +78,11 @@ void put_page(struct page *page)
 EXPORT_SYMBOL(put_page);
 
 /**
- * put_pages_list(): release a list of pages
+ * put_pages_list() - release a list of pages
+ * @pages: list of pages threaded on page->lru
  *
  * Release a list of pages which are strung together on page.lru.  Currently
  * used by read_cache_pages() and related error recovery code.
- *
- * @pages: list of pages threaded on page->lru
  */
 void put_pages_list(struct list_head *pages)
 {
diff --git a/mm/swap_state.c b/mm/swap_state.c
index ec42f01a8d02..50757ee3f9f3 100644
--- a/mm/swap_state.c
+++ b/mm/swap_state.c
@@ -115,6 +115,7 @@ void __delete_from_swap_cache(struct page *page)
 /**
  * add_to_swap - allocate swap space for a page
  * @page: page we want to move to swap
+ * @gfp_mask: memory allocation flags
  *
  * Allocate swap space for the page and add the page to the
  * swap cache.  Caller needs to hold the page lock. 
@@ -315,6 +316,7 @@ struct page *read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
 /**
  * swapin_readahead - swap in pages in hope we need them soon
  * @entry: swap entry of this memory
+ * @gfp_mask: memory allocation flags
  * @vma: user vma this address belongs to
  * @addr: target address for mempolicy
  *
diff --git a/mm/tiny-shmem.c b/mm/tiny-shmem.c
index 702083638c16..ae532f501943 100644
--- a/mm/tiny-shmem.c
+++ b/mm/tiny-shmem.c
@@ -39,12 +39,11 @@ static int __init init_tmpfs(void)
 }
 module_init(init_tmpfs)
 
-/*
+/**
  * shmem_file_setup - get an unlinked file living in tmpfs
- *
  * @name: name for dentry (to be seen in /proc/<pid>/maps
  * @size: size to be set for the file
- *
+ * @flags: vm_flags
  */
 struct file *shmem_file_setup(char *name, loff_t size, unsigned long flags)
 {
@@ -89,15 +88,16 @@ struct file *shmem_file_setup(char *name, loff_t size, unsigned long flags)
 
 close_file:
 	put_filp(file);
+	return ERR_PTR(error);
+
 put_dentry:
 	dput(dentry);
 put_memory:
 	return ERR_PTR(error);
 }
 
-/*
+/**
  * shmem_zero_setup - setup a shared anonymous mapping
- *
  * @vma: the vma to be mmapped is prepared by do_mmap_pgoff
  */
 int shmem_zero_setup(struct vm_area_struct *vma)
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index 950c0be9ca81..ecf91f8034bf 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -757,7 +757,8 @@ finished:
  *	@vma:		vma to cover (map full range of vma)
  *	@addr:		vmalloc memory
  *	@pgoff:		number of pages into addr before first page to map
- *	@returns:	0 for success, -Exxx on failure
+ *
+ *	Returns:	0 for success, -Exxx on failure
  *
  *	This function checks that addr is a valid vmalloc'ed area, and
  *	that it is big enough to cover the vma. Will return failure if
@@ -829,7 +830,8 @@ static int f(pte_t *pte, pgtable_t table, unsigned long addr, void *data)
 /**
  *	alloc_vm_area - allocate a range of kernel address space
  *	@size:		size of the area
- *	@returns:	NULL on failure, vm_struct on success
+ *
+ *	Returns:	NULL on failure, vm_struct on success
  *
  *	This function reserves a range of kernel address space, and
  *	allocates pagetables to map that range.  No actual mappings
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 45711585684e..4046434046e6 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -70,13 +70,6 @@ struct scan_control {
 
 	int order;
 
-	/*
-	 * Pages that have (or should have) IO pending.  If we run into
-	 * a lot of these, we're better off waiting a little for IO to
-	 * finish rather than scanning more pages in the VM.
-	 */
-	int nr_io_pages;
-
 	/* Which cgroup do we reclaim from */
 	struct mem_cgroup *mem_cgroup;
 
@@ -512,10 +505,8 @@ static unsigned long shrink_page_list(struct list_head *page_list,
 			 */
 			if (sync_writeback == PAGEOUT_IO_SYNC && may_enter_fs)
 				wait_on_page_writeback(page);
-			else {
-				sc->nr_io_pages++;
+			else
 				goto keep_locked;
-			}
 		}
 
 		referenced = page_referenced(page, 1, sc->mem_cgroup);
@@ -554,10 +545,8 @@ static unsigned long shrink_page_list(struct list_head *page_list,
 		if (PageDirty(page)) {
 			if (sc->order <= PAGE_ALLOC_COSTLY_ORDER && referenced)
 				goto keep_locked;
-			if (!may_enter_fs) {
-				sc->nr_io_pages++;
+			if (!may_enter_fs)
 				goto keep_locked;
-			}
 			if (!sc->may_writepage)
 				goto keep_locked;
 
@@ -568,10 +557,8 @@ static unsigned long shrink_page_list(struct list_head *page_list,
 			case PAGE_ACTIVATE:
 				goto activate_locked;
 			case PAGE_SUCCESS:
-				if (PageWriteback(page) || PageDirty(page)) {
-					sc->nr_io_pages++;
+				if (PageWriteback(page) || PageDirty(page))
 					goto keep;
-				}
 				/*
 				 * A synchronous write - probably a ramdisk.  Go
 				 * ahead and try to reclaim the page.
@@ -1344,7 +1331,6 @@ static unsigned long do_try_to_free_pages(struct zone **zones, gfp_t gfp_mask,
 
 	for (priority = DEF_PRIORITY; priority >= 0; priority--) {
 		sc->nr_scanned = 0;
-		sc->nr_io_pages = 0;
 		if (!priority)
 			disable_swap_token();
 		nr_reclaimed += shrink_zones(priority, zones, sc);
@@ -1379,8 +1365,7 @@ static unsigned long do_try_to_free_pages(struct zone **zones, gfp_t gfp_mask,
 		}
 
 		/* Take a nap, wait for some writeback to complete */
-		if (sc->nr_scanned && priority < DEF_PRIORITY - 2 &&
-				sc->nr_io_pages > sc->swap_cluster_max)
+		if (sc->nr_scanned && priority < DEF_PRIORITY - 2)
 			congestion_wait(WRITE, HZ/10);
 	}
 	/* top priority shrink_caches still had more to do? don't OOM, then */
@@ -1514,7 +1499,6 @@ loop_again:
 		if (!priority)
 			disable_swap_token();
 
-		sc.nr_io_pages = 0;
 		all_zones_ok = 1;
 
 		/*
@@ -1607,8 +1591,7 @@ loop_again:
 		 * OK, kswapd is getting into trouble.  Take a nap, then take
 		 * another pass across the zones.
 		 */
-		if (total_scanned && priority < DEF_PRIORITY - 2 &&
-					sc.nr_io_pages > sc.swap_cluster_max)
+		if (total_scanned && priority < DEF_PRIORITY - 2)
 			congestion_wait(WRITE, HZ/10);
 
 		/*