Merge branch 'linus' into sched/clock

18 files changed, 103 insertions, 66 deletions

diff --git a/mm/filemap.c b/mm/filemap.c
index 42bbc6909ba..54e96865085 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -558,14 +558,14 @@ EXPORT_SYMBOL(wait_on_page_bit);
  * But that's OK - sleepers in wait_on_page_writeback() just go back to sleep.
  *
  * The first mb is necessary to safely close the critical section opened by the
- * TestSetPageLocked(), the second mb is necessary to enforce ordering between
- * the clear_bit and the read of the waitqueue (to avoid SMP races with a
- * parallel wait_on_page_locked()).
+ * test_and_set_bit() to lock the page; the second mb is necessary to enforce
+ * ordering between the clear_bit and the read of the waitqueue (to avoid SMP
+ * races with a parallel wait_on_page_locked()).
  */
 void unlock_page(struct page *page)
 {
 	smp_mb__before_clear_bit();
-	if (!TestClearPageLocked(page))
+	if (!test_and_clear_bit(PG_locked, &page->flags))
 		BUG();
 	smp_mb__after_clear_bit(); 
 	wake_up_page(page, PG_locked);
@@ -931,7 +931,7 @@ grab_cache_page_nowait(struct address_space *mapping, pgoff_t index)
 	struct page *page = find_get_page(mapping, index);
 
 	if (page) {
-		if (!TestSetPageLocked(page))
+		if (trylock_page(page))
 			return page;
 		page_cache_release(page);
 		return NULL;
@@ -1027,7 +1027,7 @@ find_page:
 			if (inode->i_blkbits == PAGE_CACHE_SHIFT ||
 					!mapping->a_ops->is_partially_uptodate)
 				goto page_not_up_to_date;
-			if (TestSetPageLocked(page))
+			if (!trylock_page(page))
 				goto page_not_up_to_date;
 			if (!mapping->a_ops->is_partially_uptodate(page,
 								desc, offset))
@@ -1879,7 +1879,7 @@ void iov_iter_advance(struct iov_iter *i, size_t bytes)
 		 * The !iov->iov_len check ensures we skip over unlikely
 		 * zero-length segments (without overruning the iovec).
 		 */
-		while (bytes || unlikely(!iov->iov_len && i->count)) {
+		while (bytes || unlikely(i->count && !iov->iov_len)) {
 			int copy;
 
 			copy = min(bytes, iov->iov_len - base);
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 254ce2b9015..757ca983fd9 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -1283,7 +1283,12 @@ module_exit(hugetlb_exit);
 
 static int __init hugetlb_init(void)
 {
-	BUILD_BUG_ON(HPAGE_SHIFT == 0);
+	/* Some platform decide whether they support huge pages at boot
+	 * time. On these, such as powerpc, HPAGE_SHIFT is set to 0 when
+	 * there is no such support
+	 */
+	if (HPAGE_SHIFT == 0)
+		return 0;
 
 	if (!size_to_hstate(default_hstate_size)) {
 		default_hstate_size = HPAGE_SIZE;
diff --git a/mm/madvise.c b/mm/madvise.c
index 23a0ec3e0ea..f9349c18a1b 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -132,10 +132,10 @@ static long madvise_willneed(struct vm_area_struct * vma,
  * Application no longer needs these pages.  If the pages are dirty,
  * it's OK to just throw them away.  The app will be more careful about
  * data it wants to keep.  Be sure to free swap resources too.  The
- * zap_page_range call sets things up for refill_inactive to actually free
+ * zap_page_range call sets things up for shrink_active_list to actually free
  * these pages later if no one else has touched them in the meantime,
  * although we could add these pages to a global reuse list for
- * refill_inactive to pick up before reclaiming other pages.
+ * shrink_active_list to pick up before reclaiming other pages.
  *
  * NB: This interface discards data rather than pushes it out to swap,
  * as some implementations do.  This has performance implications for
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index fba566c5132..7056c3bdb47 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -1168,9 +1168,6 @@ static void mem_cgroup_move_task(struct cgroup_subsys *ss,
 	mem = mem_cgroup_from_cont(cont);
 	old_mem = mem_cgroup_from_cont(old_cont);
 
-	if (mem == old_mem)
-		goto out;
-
 	/*
 	 * Only thread group leaders are allowed to migrate, the mm_struct is
 	 * in effect owned by the leader
diff --git a/mm/memory.c b/mm/memory.c
index 67f0ab9077d..1002f473f49 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -994,6 +994,29 @@ unsigned long zap_page_range(struct vm_area_struct *vma, unsigned long address,
 	return end;
 }
 
+/**
+ * zap_vma_ptes - remove ptes mapping the vma
+ * @vma: vm_area_struct holding ptes to be zapped
+ * @address: starting address of pages to zap
+ * @size: number of bytes to zap
+ *
+ * This function only unmaps ptes assigned to VM_PFNMAP vmas.
+ *
+ * The entire address range must be fully contained within the vma.
+ *
+ * Returns 0 if successful.
+ */
+int zap_vma_ptes(struct vm_area_struct *vma, unsigned long address,
+		unsigned long size)
+{
+	if (address < vma->vm_start || address + size > vma->vm_end ||
+	    		!(vma->vm_flags & VM_PFNMAP))
+		return -1;
+	zap_page_range(vma, address, size, NULL);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(zap_vma_ptes);
+
 /*
  * Do a quick page-table lookup for a single page.
  */
@@ -1766,7 +1789,7 @@ static int do_wp_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	 * not dirty accountable.
 	 */
 	if (PageAnon(old_page)) {
-		if (!TestSetPageLocked(old_page)) {
+		if (trylock_page(old_page)) {
 			reuse = can_share_swap_page(old_page);
 			unlock_page(old_page);
 		}
@@ -2742,16 +2765,26 @@ int make_pages_present(unsigned long addr, unsigned long end)
 
 	vma = find_vma(current->mm, addr);
 	if (!vma)
-		return -1;
+		return -ENOMEM;
 	write = (vma->vm_flags & VM_WRITE) != 0;
 	BUG_ON(addr >= end);
 	BUG_ON(end > vma->vm_end);
 	len = DIV_ROUND_UP(end, PAGE_SIZE) - addr/PAGE_SIZE;
 	ret = get_user_pages(current, current->mm, addr,
 			len, write, 0, NULL, NULL);
-	if (ret < 0)
+	if (ret < 0) {
+		/*
+		   SUS require strange return value to mlock
+		    - invalid addr generate to ENOMEM.
+		    - out of memory should generate EAGAIN.
+		*/
+		if (ret == -EFAULT)
+			ret = -ENOMEM;
+		else if (ret == -ENOMEM)
+			ret = -EAGAIN;
 		return ret;
-	return ret == len ? 0 : -1;
+	}
+	return ret == len ? 0 : -ENOMEM;
 }
 
 #if !defined(__HAVE_ARCH_GATE_AREA)
diff --git a/mm/migrate.c b/mm/migrate.c
index 153572fb60b..2a80136b23b 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -605,7 +605,7 @@ static int move_to_new_page(struct page *newpage, struct page *page)
 	 * establishing additional references. We are the only one
 	 * holding a reference to the new page at this point.
 	 */
-	if (TestSetPageLocked(newpage))
+	if (!trylock_page(newpage))
 		BUG();
 
 	/* Prepare mapping for the new page.*/
@@ -667,7 +667,7 @@ static int unmap_and_move(new_page_t get_new_page, unsigned long private,
 	BUG_ON(charge);
 
 	rc = -EAGAIN;
-	if (TestSetPageLocked(page)) {
+	if (!trylock_page(page)) {
 		if (!force)
 			goto move_newpage;
 		lock_page(page);
diff --git a/mm/mlock.c b/mm/mlock.c
index 7b2656055d6..01fbe93eff5 100644
--- a/mm/mlock.c
+++ b/mm/mlock.c
@@ -78,8 +78,6 @@ success:
 
 	mm->locked_vm -= pages;
 out:
-	if (ret == -ENOMEM)
-		ret = -EAGAIN;
 	return ret;
 }
 
diff --git a/mm/mm_init.c b/mm/mm_init.c
index c6af41ea999..936ef2efd89 100644
--- a/mm/mm_init.c
+++ b/mm/mm_init.c
@@ -14,6 +14,10 @@
 #ifdef CONFIG_DEBUG_MEMORY_INIT
 int __meminitdata mminit_loglevel;
 
+#ifndef SECTIONS_SHIFT
+#define SECTIONS_SHIFT	0
+#endif
+
 /* The zonelists are simply reported, validation is manual. */
 void mminit_verify_zonelist(void)
 {
@@ -74,11 +78,7 @@ void __init mminit_verify_pageflags_layout(void)
 		NR_PAGEFLAGS);
 	mminit_dprintk(MMINIT_TRACE, "pageflags_layout_shifts",
 		"Section %d Node %d Zone %d\n",
-#ifdef SECTIONS_SHIFT
 		SECTIONS_SHIFT,
-#else
-		0,
-#endif
 		NODES_SHIFT,
 		ZONES_SHIFT);
 	mminit_dprintk(MMINIT_TRACE, "pageflags_layout_offsets",
diff --git a/mm/mmap.c b/mm/mmap.c
index 245c3d69067..971d0eda754 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -370,7 +370,7 @@ find_vma_prepare(struct mm_struct *mm, unsigned long addr,
 		if (vma_tmp->vm_end > addr) {
 			vma = vma_tmp;
 			if (vma_tmp->vm_start <= addr)
-				return vma;
+				break;
 			__rb_link = &__rb_parent->rb_left;
 		} else {
 			rb_prev = __rb_parent;
diff --git a/mm/nommu.c b/mm/nommu.c
index 5edccd9c921..ed75bc962fb 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -266,6 +266,27 @@ void *vmalloc_node(unsigned long size, int node)
 }
 EXPORT_SYMBOL(vmalloc_node);
 
+#ifndef PAGE_KERNEL_EXEC
+# define PAGE_KERNEL_EXEC PAGE_KERNEL
+#endif
+
+/**
+ *	vmalloc_exec  -  allocate virtually contiguous, executable memory
+ *	@size:		allocation size
+ *
+ *	Kernel-internal function to allocate enough pages to cover @size
+ *	the page level allocator and map them into contiguous and
+ *	executable kernel virtual space.
+ *
+ *	For tight control over page level allocator and protection flags
+ *	use __vmalloc() instead.
+ */
+
+void *vmalloc_exec(unsigned long size)
+{
+	return __vmalloc(size, GFP_KERNEL | __GFP_HIGHMEM, PAGE_KERNEL_EXEC);
+}
+
 /**
  * vmalloc_32  -  allocate virtually contiguous memory (32bit addressable)
  *	@size:		allocation size
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 3cf3d05b6bd..401d104d2bb 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -3753,23 +3753,6 @@ unsigned long __init find_min_pfn_with_active_regions(void)
 	return find_min_pfn_for_node(MAX_NUMNODES);
 }
 
-/**
- * find_max_pfn_with_active_regions - Find the maximum PFN registered
- *
- * It returns the maximum PFN based on information provided via
- * add_active_range().
- */
-unsigned long __init find_max_pfn_with_active_regions(void)
-{
-	int i;
-	unsigned long max_pfn = 0;
-
-	for (i = 0; i < nr_nodemap_entries; i++)
-		max_pfn = max(max_pfn, early_node_map[i].end_pfn);
-
-	return max_pfn;
-}
-
 /*
  * early_calculate_totalpages()
  * Sum pages in active regions for movable zone.
diff --git a/mm/rmap.c b/mm/rmap.c
index 99bc3f9cd79..1ea4e6fcee7 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -422,7 +422,7 @@ int page_referenced(struct page *page, int is_locked,
 			referenced += page_referenced_anon(page, mem_cont);
 		else if (is_locked)
 			referenced += page_referenced_file(page, mem_cont);
-		else if (TestSetPageLocked(page))
+		else if (!trylock_page(page))
 			referenced++;
 		else {
 			if (page->mapping)
@@ -667,7 +667,8 @@ void page_remove_rmap(struct page *page, struct vm_area_struct *vma)
 		 * Leaving it set also helps swapoff to reinstate ptes
 		 * faster for those pages still in swapcache.
 		 */
-		if (page_test_dirty(page)) {
+		if ((!PageAnon(page) || PageSwapCache(page)) &&
+		    page_test_dirty(page)) {
 			page_clear_dirty(page);
 			set_page_dirty(page);
 		}
diff --git a/mm/shmem.c b/mm/shmem.c
index c1e5a3b4f75..04fb4f1ab88 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -1265,7 +1265,7 @@ repeat:
 		}
 
 		/* We have to do this with page locked to prevent races */
-		if (TestSetPageLocked(swappage)) {
+		if (!trylock_page(swappage)) {
 			shmem_swp_unmap(entry);
 			spin_unlock(&info->lock);
 			wait_on_page_locked(swappage);
@@ -1329,7 +1329,7 @@ repeat:
 		shmem_swp_unmap(entry);
 		filepage = find_get_page(mapping, idx);
 		if (filepage &&
-		    (!PageUptodate(filepage) || TestSetPageLocked(filepage))) {
+		    (!PageUptodate(filepage) || !trylock_page(filepage))) {
 			spin_unlock(&info->lock);
 			wait_on_page_locked(filepage);
 			page_cache_release(filepage);
diff --git a/mm/swap.c b/mm/swap.c
index dd89234ee51..9e0cb311807 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -278,9 +278,10 @@ int lru_add_drain_all(void)
  * Avoid taking zone->lru_lock if possible, but if it is taken, retain it
  * for the remainder of the operation.
  *
- * The locking in this function is against shrink_cache(): we recheck the
- * page count inside the lock to see whether shrink_cache grabbed the page
- * via the LRU.  If it did, give up: shrink_cache will free it.
+ * The locking in this function is against shrink_inactive_list(): we recheck
+ * the page count inside the lock to see whether shrink_inactive_list()
+ * grabbed the page via the LRU.  If it did, give up: shrink_inactive_list()
+ * will free it.
  */
 void release_pages(struct page **pages, int nr, int cold)
 {
@@ -443,7 +444,7 @@ void pagevec_strip(struct pagevec *pvec)
 	for (i = 0; i < pagevec_count(pvec); i++) {
 		struct page *page = pvec->pages[i];
 
-		if (PagePrivate(page) && !TestSetPageLocked(page)) {
+		if (PagePrivate(page) && trylock_page(page)) {
 			if (PagePrivate(page))
 				try_to_release_page(page, 0);
 			unlock_page(page);
diff --git a/mm/swap_state.c b/mm/swap_state.c
index b8035b05512..167cf2dc8a0 100644
--- a/mm/swap_state.c
+++ b/mm/swap_state.c
@@ -201,7 +201,7 @@ void delete_from_swap_cache(struct page *page)
  */
 static inline void free_swap_cache(struct page *page)
 {
-	if (PageSwapCache(page) && !TestSetPageLocked(page)) {
+	if (PageSwapCache(page) && trylock_page(page)) {
 		remove_exclusive_swap_page(page);
 		unlock_page(page);
 	}
@@ -302,9 +302,9 @@ struct page *read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
 		 * re-using the just freed swap entry for an existing page.
 		 * May fail (-ENOMEM) if radix-tree node allocation failed.
 		 */
-		SetPageLocked(new_page);
+		set_page_locked(new_page);
 		err = add_to_swap_cache(new_page, entry, gfp_mask & GFP_KERNEL);
-		if (!err) {
+		if (likely(!err)) {
 			/*
 			 * Initiate read into locked page and return.
 			 */
@@ -312,7 +312,7 @@ struct page *read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
 			swap_readpage(NULL, new_page);
 			return new_page;
 		}
-		ClearPageLocked(new_page);
+		clear_page_locked(new_page);
 		swap_free(entry);
 	} while (err != -ENOMEM);
 
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 6beb6251e99..1e330f2998f 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -403,7 +403,7 @@ void free_swap_and_cache(swp_entry_t entry)
 	if (p) {
 		if (swap_entry_free(p, swp_offset(entry)) == 1) {
 			page = find_get_page(&swapper_space, entry.val);
-			if (page && unlikely(TestSetPageLocked(page))) {
+			if (page && unlikely(!trylock_page(page))) {
 				page_cache_release(page);
 				page = NULL;
 			}
@@ -656,8 +656,8 @@ static int unuse_mm(struct mm_struct *mm,
 
 	if (!down_read_trylock(&mm->mmap_sem)) {
 		/*
-		 * Activate page so shrink_cache is unlikely to unmap its
-		 * ptes while lock is dropped, so swapoff can make progress.
+		 * Activate page so shrink_inactive_list is unlikely to unmap
+		 * its ptes while lock is dropped, so swapoff can make progress.
 		 */
 		activate_page(page);
 		unlock_page(page);
diff --git a/mm/truncate.c b/mm/truncate.c
index e68443d7456..250505091d3 100644
--- a/mm/truncate.c
+++ b/mm/truncate.c
@@ -104,7 +104,6 @@ truncate_complete_page(struct address_space *mapping, struct page *page)
 	cancel_dirty_page(page, PAGE_CACHE_SIZE);
 
 	remove_from_page_cache(page);
-	ClearPageUptodate(page);
 	ClearPageMappedToDisk(page);
 	page_cache_release(page);	/* pagecache ref */
 }
@@ -188,7 +187,7 @@ void truncate_inode_pages_range(struct address_space *mapping,
 			if (page_index > next)
 				next = page_index;
 			next++;
-			if (TestSetPageLocked(page))
+			if (!trylock_page(page))
 				continue;
 			if (PageWriteback(page)) {
 				unlock_page(page);
@@ -281,7 +280,7 @@ unsigned long __invalidate_mapping_pages(struct address_space *mapping,
 			pgoff_t index;
 			int lock_failed;
 
-			lock_failed = TestSetPageLocked(page);
+			lock_failed = !trylock_page(page);
 
 			/*
 			 * We really shouldn't be looking at the ->index of an
@@ -356,7 +355,6 @@ invalidate_complete_page2(struct address_space *mapping, struct page *page)
 	BUG_ON(PagePrivate(page));
 	__remove_from_page_cache(page);
 	spin_unlock_irq(&mapping->tree_lock);
-	ClearPageUptodate(page);
 	page_cache_release(page);	/* pagecache ref */
 	return 1;
 failed:
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 8f71761bc4b..1ff1a58e7c1 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -496,7 +496,7 @@ static unsigned long shrink_page_list(struct list_head *page_list,
 		page = lru_to_page(page_list);
 		list_del(&page->lru);
 
-		if (TestSetPageLocked(page))
+		if (!trylock_page(page))
 			goto keep;
 
 		VM_BUG_ON(PageActive(page));
@@ -582,7 +582,7 @@ static unsigned long shrink_page_list(struct list_head *page_list,
 				 * A synchronous write - probably a ramdisk.  Go
 				 * ahead and try to reclaim the page.
 				 */
-				if (TestSetPageLocked(page))
+				if (!trylock_page(page))
 					goto keep;
 				if (PageDirty(page) || PageWriteback(page))
 					goto keep_locked;
@@ -1408,7 +1408,7 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist,
 		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 */
+	/* top priority shrink_zones still had more to do? don't OOM, then */
 	if (!sc->all_unreclaimable && scan_global_lru(sc))
 		ret = nr_reclaimed;
 out:
@@ -1979,7 +1979,7 @@ module_init(kswapd_init)
 int zone_reclaim_mode __read_mostly;
 
 #define RECLAIM_OFF 0
-#define RECLAIM_ZONE (1<<0)	/* Run shrink_cache on the zone */
+#define RECLAIM_ZONE (1<<0)	/* Run shrink_inactive_list on the zone */
 #define RECLAIM_WRITE (1<<1)	/* Writeout pages during reclaim */
 #define RECLAIM_SWAP (1<<2)	/* Swap pages out during reclaim */