Merge branch 'akpm'

* akpm: (182 commits)
  fbdev: bf54x-lq043fb: use kzalloc over kmalloc/memset
  fbdev: *bfin*: fix __dev{init,exit} markings
  fbdev: *bfin*: drop unnecessary calls to memset
  fbdev: bfin-t350mcqb-fb: drop unused local variables
  fbdev: blackfin has __raw I/O accessors, so use them in fb.h
  fbdev: s1d13xxxfb: add accelerated bitblt functions
  tcx: use standard fields for framebuffer physical address and length
  fbdev: add support for handoff from firmware to hw framebuffers
  intelfb: fix a bug when changing video timing
  fbdev: use framebuffer_release() for freeing fb_info structures
  radeon: P2G2CLK_ALWAYS_ONb tested twice, should 2nd be P2G2CLK_DAC_ALWAYS_ONb?
  s3c-fb: CPUFREQ frequency scaling support
  s3c-fb: fix resource releasing on error during probing
  carminefb: fix possible access beyond end of carmine_modedb[]
  acornfb: remove fb_mmap function
  mb862xxfb: use CONFIG_OF instead of CONFIG_PPC_OF
  mb862xxfb: restrict compliation of platform driver to PPC
  Samsung SoC Framebuffer driver: add Alpha Channel support
  atmel-lcdc: fix pixclock upper bound detection
  offb: use framebuffer_alloc() to allocate fb_info struct
  ...

Manually fix up conflicts due to kmemcheck in mm/slab.c

mm/Kconfig

@@ -203,25 +203,13 @@ config VIRT_TO_BUS
 	def_bool y
 	depends on !ARCH_NO_VIRT_TO_BUS
 
-config UNEVICTABLE_LRU
-	bool "Add LRU list to track non-evictable pages"
-	default y
-	help
-	  Keeps unevictable pages off of the active and inactive pageout
-	  lists, so kswapd will not waste CPU time or have its balancing
-	  algorithms thrown off by scanning these pages.  Selecting this
-	  will use one page flag and increase the code size a little,
-	  say Y unless you know what you are doing.
-
-	  See Documentation/vm/unevictable-lru.txt for more information.
-
 config HAVE_MLOCK
 	bool
 	default y if MMU=y
 
 config HAVE_MLOCKED_PAGE_BIT
 	bool
-	default y if HAVE_MLOCK=y && UNEVICTABLE_LRU=y
+	default y if HAVE_MLOCK=y
 
 config MMU_NOTIFIER
 	bool

mm/Makefile

@@ -12,6 +12,7 @@ obj-y			:= bootmem.o filemap.o mempool.o oom_kill.o fadvise.o \
 			   readahead.o swap.o truncate.o vmscan.o shmem.o \
 			   prio_tree.o util.o mmzone.o vmstat.o backing-dev.o \
 			   page_isolation.o mm_init.o $(mmu-y)
+obj-y += init-mm.o
 
 obj-$(CONFIG_PROC_PAGE_MONITOR) += pagewalk.o
 obj-$(CONFIG_BOUNCE)	+= bounce.o

mm/fadvise.c

@@ -101,7 +101,7 @@ SYSCALL_DEFINE(fadvise64_64)(int fd, loff_t offset, loff_t len, int advice)
 		
 		ret = force_page_cache_readahead(mapping, file,
 				start_index,
-				max_sane_readahead(nrpages));
+				nrpages);
 		if (ret > 0)
 			ret = 0;
 		break;

mm/filemap.c

@@ -521,7 +521,7 @@ struct page *__page_cache_alloc(gfp_t gfp)
 {
 	if (cpuset_do_page_mem_spread()) {
 		int n = cpuset_mem_spread_node();
-		return alloc_pages_node(n, gfp, 0);
+		return alloc_pages_exact_node(n, gfp, 0);
 	}
 	return alloc_pages(gfp, 0);
 }
@@ -1004,9 +1004,6 @@ EXPORT_SYMBOL(grab_cache_page_nowait);
 static void shrink_readahead_size_eio(struct file *filp,
 					struct file_ra_state *ra)
 {
-	if (!ra->ra_pages)
-		return;
-
 	ra->ra_pages /= 4;
 }
 
@@ -1390,8 +1387,7 @@ do_readahead(struct address_space *mapping, struct file *filp,
 	if (!mapping || !mapping->a_ops || !mapping->a_ops->readpage)
 		return -EINVAL;
 
-	force_page_cache_readahead(mapping, filp, index,
-					max_sane_readahead(nr));
+	force_page_cache_readahead(mapping, filp, index, nr);
 	return 0;
 }
 
@@ -1457,6 +1453,73 @@ static int page_cache_read(struct file *file, pgoff_t offset)
 
 #define MMAP_LOTSAMISS  (100)
 
+/*
+ * Synchronous readahead happens when we don't even find
+ * a page in the page cache at all.
+ */
+static void do_sync_mmap_readahead(struct vm_area_struct *vma,
+				   struct file_ra_state *ra,
+				   struct file *file,
+				   pgoff_t offset)
+{
+	unsigned long ra_pages;
+	struct address_space *mapping = file->f_mapping;
+
+	/* If we don't want any read-ahead, don't bother */
+	if (VM_RandomReadHint(vma))
+		return;
+
+	if (VM_SequentialReadHint(vma) ||
+			offset - 1 == (ra->prev_pos >> PAGE_CACHE_SHIFT)) {
+		page_cache_sync_readahead(mapping, ra, file, offset,
+					  ra->ra_pages);
+		return;
+	}
+
+	if (ra->mmap_miss < INT_MAX)
+		ra->mmap_miss++;
+
+	/*
+	 * Do we miss much more than hit in this file? If so,
+	 * stop bothering with read-ahead. It will only hurt.
+	 */
+	if (ra->mmap_miss > MMAP_LOTSAMISS)
+		return;
+
+	/*
+	 * mmap read-around
+	 */
+	ra_pages = max_sane_readahead(ra->ra_pages);
+	if (ra_pages) {
+		ra->start = max_t(long, 0, offset - ra_pages/2);
+		ra->size = ra_pages;
+		ra->async_size = 0;
+		ra_submit(ra, mapping, file);
+	}
+}
+
+/*
+ * Asynchronous readahead happens when we find the page and PG_readahead,
+ * so we want to possibly extend the readahead further..
+ */
+static void do_async_mmap_readahead(struct vm_area_struct *vma,
+				    struct file_ra_state *ra,
+				    struct file *file,
+				    struct page *page,
+				    pgoff_t offset)
+{
+	struct address_space *mapping = file->f_mapping;
+
+	/* If we don't want any read-ahead, don't bother */
+	if (VM_RandomReadHint(vma))
+		return;
+	if (ra->mmap_miss > 0)
+		ra->mmap_miss--;
+	if (PageReadahead(page))
+		page_cache_async_readahead(mapping, ra, file,
+					   page, offset, ra->ra_pages);
+}
+
 /**
  * filemap_fault - read in file data for page fault handling
  * @vma:	vma in which the fault was taken
@@ -1476,78 +1539,44 @@ int filemap_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 	struct address_space *mapping = file->f_mapping;
 	struct file_ra_state *ra = &file->f_ra;
 	struct inode *inode = mapping->host;
+	pgoff_t offset = vmf->pgoff;
 	struct page *page;
 	pgoff_t size;
-	int did_readaround = 0;
 	int ret = 0;
 
 	size = (i_size_read(inode) + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
-	if (vmf->pgoff >= size)
+	if (offset >= size)
 		return VM_FAULT_SIGBUS;
 
-	/* If we don't want any read-ahead, don't bother */
-	if (VM_RandomReadHint(vma))
-		goto no_cached_page;
-
 	/*
 	 * Do we have something in the page cache already?
 	 */
-retry_find:
-	page = find_lock_page(mapping, vmf->pgoff);
-	/*
-	 * For sequential accesses, we use the generic readahead logic.
-	 */
-	if (VM_SequentialReadHint(vma)) {
-		if (!page) {
-			page_cache_sync_readahead(mapping, ra, file,
-							   vmf->pgoff, 1);
-			page = find_lock_page(mapping, vmf->pgoff);
-			if (!page)
-				goto no_cached_page;
-		}
-		if (PageReadahead(page)) {
-			page_cache_async_readahead(mapping, ra, file, page,
-							   vmf->pgoff, 1);
-		}
-	}
-
-	if (!page) {
-		unsigned long ra_pages;
-
-		ra->mmap_miss++;
-
+	page = find_get_page(mapping, offset);
+	if (likely(page)) {
 		/*
-		 * Do we miss much more than hit in this file? If so,
-		 * stop bothering with read-ahead. It will only hurt.
+		 * We found the page, so try async readahead before
+		 * waiting for the lock.
 		 */
-		if (ra->mmap_miss > MMAP_LOTSAMISS)
+		do_async_mmap_readahead(vma, ra, file, page, offset);
+		lock_page(page);
+
+		/* Did it get truncated? */
+		if (unlikely(page->mapping != mapping)) {
+			unlock_page(page);
+			put_page(page);
 			goto no_cached_page;
-
-		/*
-		 * To keep the pgmajfault counter straight, we need to
-		 * check did_readaround, as this is an inner loop.
-		 */
-		if (!did_readaround) {
-			ret = VM_FAULT_MAJOR;
-			count_vm_event(PGMAJFAULT);
 		}
-		did_readaround = 1;
-		ra_pages = max_sane_readahead(file->f_ra.ra_pages);
-		if (ra_pages) {
-			pgoff_t start = 0;
-
-			if (vmf->pgoff > ra_pages / 2)
-				start = vmf->pgoff - ra_pages / 2;
-			do_page_cache_readahead(mapping, file, start, ra_pages);
-		}
-		page = find_lock_page(mapping, vmf->pgoff);
+	} else {
+		/* No page in the page cache at all */
+		do_sync_mmap_readahead(vma, ra, file, offset);
+		count_vm_event(PGMAJFAULT);
+		ret = VM_FAULT_MAJOR;
+retry_find:
+		page = find_lock_page(mapping, offset);
 		if (!page)
 			goto no_cached_page;
 	}
 
-	if (!did_readaround)
-		ra->mmap_miss--;
-
 	/*
 	 * We have a locked page in the page cache, now we need to check
 	 * that it's up-to-date. If not, it is going to be due to an error.
@@ -1555,18 +1584,18 @@ retry_find:
 	if (unlikely(!PageUptodate(page)))
 		goto page_not_uptodate;
 
-	/* Must recheck i_size under page lock */
+	/*
+	 * Found the page and have a reference on it.
+	 * We must recheck i_size under page lock.
+	 */
 	size = (i_size_read(inode) + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
-	if (unlikely(vmf->pgoff >= size)) {
+	if (unlikely(offset >= size)) {
 		unlock_page(page);
 		page_cache_release(page);
 		return VM_FAULT_SIGBUS;
 	}
 
-	/*
-	 * Found the page and have a reference on it.
-	 */
-	ra->prev_pos = (loff_t)page->index << PAGE_CACHE_SHIFT;
+	ra->prev_pos = (loff_t)offset << PAGE_CACHE_SHIFT;
 	vmf->page = page;
 	return ret | VM_FAULT_LOCKED;
 
@@ -1575,7 +1604,7 @@ no_cached_page:
 	 * We're only likely to ever get here if MADV_RANDOM is in
 	 * effect.
 	 */
-	error = page_cache_read(file, vmf->pgoff);
+	error = page_cache_read(file, offset);
 
 	/*
 	 * The page we want has now been added to the page cache.
@@ -1595,12 +1624,6 @@ no_cached_page:
 	return VM_FAULT_SIGBUS;
 
 page_not_uptodate:
-	/* IO error path */
-	if (!did_readaround) {
-		ret = VM_FAULT_MAJOR;
-		count_vm_event(PGMAJFAULT);
-	}
-
 	/*
 	 * Umm, take care of errors if the page isn't up-to-date.
 	 * Try to re-read it _once_. We do this synchronously,

mm/hugetlb.c

@@ -578,41 +578,6 @@ static void free_huge_page(struct page *page)
 		hugetlb_put_quota(mapping, 1);
 }
 
-/*
- * Increment or decrement surplus_huge_pages.  Keep node-specific counters
- * balanced by operating on them in a round-robin fashion.
- * Returns 1 if an adjustment was made.
- */
-static int adjust_pool_surplus(struct hstate *h, int delta)
-{
-	static int prev_nid;
-	int nid = prev_nid;
-	int ret = 0;
-
-	VM_BUG_ON(delta != -1 && delta != 1);
-	do {
-		nid = next_node(nid, node_online_map);
-		if (nid == MAX_NUMNODES)
-			nid = first_node(node_online_map);
-
-		/* To shrink on this node, there must be a surplus page */
-		if (delta < 0 && !h->surplus_huge_pages_node[nid])
-			continue;
-		/* Surplus cannot exceed the total number of pages */
-		if (delta > 0 && h->surplus_huge_pages_node[nid] >=
-						h->nr_huge_pages_node[nid])
-			continue;
-
-		h->surplus_huge_pages += delta;
-		h->surplus_huge_pages_node[nid] += delta;
-		ret = 1;
-		break;
-	} while (nid != prev_nid);
-
-	prev_nid = nid;
-	return ret;
-}
-
 static void prep_new_huge_page(struct hstate *h, struct page *page, int nid)
 {
 	set_compound_page_dtor(page, free_huge_page);
@@ -623,6 +588,34 @@ static void prep_new_huge_page(struct hstate *h, struct page *page, int nid)
 	put_page(page); /* free it into the hugepage allocator */
 }
 
+static void prep_compound_gigantic_page(struct page *page, unsigned long order)
+{
+	int i;
+	int nr_pages = 1 << order;
+	struct page *p = page + 1;
+
+	/* we rely on prep_new_huge_page to set the destructor */
+	set_compound_order(page, order);
+	__SetPageHead(page);
+	for (i = 1; i < nr_pages; i++, p = mem_map_next(p, page, i)) {
+		__SetPageTail(p);
+		p->first_page = page;
+	}
+}
+
+int PageHuge(struct page *page)
+{
+	compound_page_dtor *dtor;
+
+	if (!PageCompound(page))
+		return 0;
+
+	page = compound_head(page);
+	dtor = get_compound_page_dtor(page);
+
+	return dtor == free_huge_page;
+}
+
 static struct page *alloc_fresh_huge_page_node(struct hstate *h, int nid)
 {
 	struct page *page;
@@ -630,7 +623,7 @@ static struct page *alloc_fresh_huge_page_node(struct hstate *h, int nid)
 	if (h->order >= MAX_ORDER)
 		return NULL;
 
-	page = alloc_pages_node(nid,
+	page = alloc_pages_exact_node(nid,
 		htlb_alloc_mask|__GFP_COMP|__GFP_THISNODE|
 						__GFP_REPEAT|__GFP_NOWARN,
 		huge_page_order(h));
@@ -649,7 +642,7 @@ static struct page *alloc_fresh_huge_page_node(struct hstate *h, int nid)
  * Use a helper variable to find the next node and then
  * copy it back to hugetlb_next_nid afterwards:
  * otherwise there's a window in which a racer might
- * pass invalid nid MAX_NUMNODES to alloc_pages_node.
+ * pass invalid nid MAX_NUMNODES to alloc_pages_exact_node.
  * But we don't need to use a spin_lock here: it really
  * doesn't matter if occasionally a racer chooses the
  * same nid as we do.  Move nid forward in the mask even
@@ -875,7 +868,7 @@ static void return_unused_surplus_pages(struct hstate *h,
 	 * 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();
+	unsigned long remaining_iterations = nr_online_nodes;
 
 	/* Uncommit the reservation */
 	h->resv_huge_pages -= unused_resv_pages;
@@ -904,7 +897,7 @@ static void return_unused_surplus_pages(struct hstate *h,
 			h->surplus_huge_pages--;
 			h->surplus_huge_pages_node[nid]--;
 			nr_pages--;
-			remaining_iterations = num_online_nodes();
+			remaining_iterations = nr_online_nodes;
 		}
 	}
 }
@@ -1140,6 +1133,41 @@ static inline void try_to_free_low(struct hstate *h, unsigned long count)
 }
 #endif
 
+/*
+ * Increment or decrement surplus_huge_pages.  Keep node-specific counters
+ * balanced by operating on them in a round-robin fashion.
+ * Returns 1 if an adjustment was made.
+ */
+static int adjust_pool_surplus(struct hstate *h, int delta)
+{
+	static int prev_nid;
+	int nid = prev_nid;
+	int ret = 0;
+
+	VM_BUG_ON(delta != -1 && delta != 1);
+	do {
+		nid = next_node(nid, node_online_map);
+		if (nid == MAX_NUMNODES)
+			nid = first_node(node_online_map);
+
+		/* To shrink on this node, there must be a surplus page */
+		if (delta < 0 && !h->surplus_huge_pages_node[nid])
+			continue;
+		/* Surplus cannot exceed the total number of pages */
+		if (delta > 0 && h->surplus_huge_pages_node[nid] >=
+						h->nr_huge_pages_node[nid])
+			continue;
+
+		h->surplus_huge_pages += delta;
+		h->surplus_huge_pages_node[nid] += delta;
+		ret = 1;
+		break;
+	} while (nid != prev_nid);
+
+	prev_nid = nid;
+	return ret;
+}
+
 #define persistent_huge_pages(h) (h->nr_huge_pages - h->surplus_huge_pages)
 static unsigned long set_max_huge_pages(struct hstate *h, unsigned long count)
 {

mm/init-mm.c

@@ -0,0 +1,20 @@
+#include <linux/mm_types.h>
+#include <linux/rbtree.h>
+#include <linux/rwsem.h>
+#include <linux/spinlock.h>
+#include <linux/list.h>
+#include <linux/cpumask.h>
+
+#include <asm/atomic.h>
+#include <asm/pgtable.h>
+
+struct mm_struct init_mm = {
+	.mm_rb		= RB_ROOT,
+	.pgd		= swapper_pg_dir,
+	.mm_users	= ATOMIC_INIT(2),
+	.mm_count	= ATOMIC_INIT(1),
+	.mmap_sem	= __RWSEM_INITIALIZER(init_mm.mmap_sem),
+	.page_table_lock =  __SPIN_LOCK_UNLOCKED(init_mm.page_table_lock),
+	.mmlist		= LIST_HEAD_INIT(init_mm.mmlist),
+	.cpu_vm_mask	= CPU_MASK_ALL,
+};

mm/internal.h

@@ -16,9 +16,6 @@
 void free_pgtables(struct mmu_gather *tlb, struct vm_area_struct *start_vma,
 		unsigned long floor, unsigned long ceiling);
 
-extern void prep_compound_page(struct page *page, unsigned long order);
-extern void prep_compound_gigantic_page(struct page *page, unsigned long order);
-
 static inline void set_page_count(struct page *page, int v)
 {
 	atomic_set(&page->_count, v);
@@ -51,6 +48,8 @@ extern void putback_lru_page(struct page *page);
  */
 extern unsigned long highest_memmap_pfn;
 extern void __free_pages_bootmem(struct page *page, unsigned int order);
+extern void prep_compound_page(struct page *page, unsigned long order);
+
 
 /*
  * function for dealing with page's order in buddy system.
@@ -74,7 +73,6 @@ static inline void munlock_vma_pages_all(struct vm_area_struct *vma)
 }
 #endif
 
-#ifdef CONFIG_UNEVICTABLE_LRU
 /*
  * unevictable_migrate_page() called only from migrate_page_copy() to
  * migrate unevictable flag to new page.
@@ -86,11 +84,6 @@ static inline void unevictable_migrate_page(struct page *new, struct page *old)
 	if (TestClearPageUnevictable(old))
 		SetPageUnevictable(new);
 }
-#else
-static inline void unevictable_migrate_page(struct page *new, struct page *old)
-{
-}
-#endif
 
 #ifdef CONFIG_HAVE_MLOCKED_PAGE_BIT
 /*
@@ -150,23 +143,6 @@ static inline void mlock_migrate_page(struct page *newpage, struct page *page)
 	}
 }
 
-/*
- * free_page_mlock() -- clean up attempts to free and mlocked() page.
- * Page should not be on lru, so no need to fix that up.
- * free_pages_check() will verify...
- */
-static inline void free_page_mlock(struct page *page)
-{
-	if (unlikely(TestClearPageMlocked(page))) {
-		unsigned long flags;
-
-		local_irq_save(flags);
-		__dec_zone_page_state(page, NR_MLOCK);
-		__count_vm_event(UNEVICTABLE_MLOCKFREED);
-		local_irq_restore(flags);
-	}
-}
-
 #else /* CONFIG_HAVE_MLOCKED_PAGE_BIT */
 static inline int is_mlocked_vma(struct vm_area_struct *v, struct page *p)
 {
@@ -175,7 +151,6 @@ static inline int is_mlocked_vma(struct vm_area_struct *v, struct page *p)
 static inline void clear_page_mlock(struct page *page) { }
 static inline void mlock_vma_page(struct page *page) { }
 static inline void mlock_migrate_page(struct page *new, struct page *old) { }
-static inline void free_page_mlock(struct page *page) { }
 
 #endif /* CONFIG_HAVE_MLOCKED_PAGE_BIT */
 
@@ -284,4 +259,8 @@ int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
 		     unsigned long start, int len, int flags,
 		     struct page **pages, struct vm_area_struct **vmas);
 
+#define ZONE_RECLAIM_NOSCAN	-2
+#define ZONE_RECLAIM_FULL	-1
+#define ZONE_RECLAIM_SOME	0
+#define ZONE_RECLAIM_SUCCESS	1
 #endif

mm/madvise.c

@@ -123,8 +123,7 @@ static long madvise_willneed(struct vm_area_struct * vma,
 		end = vma->vm_end;
 	end = ((end - vma->vm_start) >> PAGE_SHIFT) + vma->vm_pgoff;
 
-	force_page_cache_readahead(file->f_mapping,
-			file, start, max_sane_readahead(end - start));
+	force_page_cache_readahead(file->f_mapping, file, start, end - start);
 	return 0;
 }
 
@@ -239,12 +238,30 @@ madvise_vma(struct vm_area_struct *vma, struct vm_area_struct **prev,
 		break;
 
 	default:
-		error = -EINVAL;
+		BUG();
 		break;
 	}
 	return error;
 }
 
+static int
+madvise_behavior_valid(int behavior)
+{
+	switch (behavior) {
+	case MADV_DOFORK:
+	case MADV_DONTFORK:
+	case MADV_NORMAL:
+	case MADV_SEQUENTIAL:
+	case MADV_RANDOM:
+	case MADV_REMOVE:
+	case MADV_WILLNEED:
+	case MADV_DONTNEED:
+		return 1;
+
+	default:
+		return 0;
+	}
+}
 /*
  * The madvise(2) system call.
  *
@@ -290,6 +307,9 @@ SYSCALL_DEFINE3(madvise, unsigned long, start, size_t, len_in, int, behavior)
 	int write;
 	size_t len;
 
+	if (!madvise_behavior_valid(behavior))
+		return error;
+
 	write = madvise_need_mmap_write(behavior);
 	if (write)
 		down_write(&current->mm->mmap_sem);

mm/memcontrol.c

@@ -570,6 +570,17 @@ int mem_cgroup_inactive_anon_is_low(struct mem_cgroup *memcg)
 	return 0;
 }
 
+int mem_cgroup_inactive_file_is_low(struct mem_cgroup *memcg)
+{
+	unsigned long active;
+	unsigned long inactive;
+
+	inactive = mem_cgroup_get_local_zonestat(memcg, LRU_INACTIVE_FILE);
+	active = mem_cgroup_get_local_zonestat(memcg, LRU_ACTIVE_FILE);
+
+	return (active > inactive);
+}
+
 unsigned long mem_cgroup_zone_nr_pages(struct mem_cgroup *memcg,
 				       struct zone *zone,
 				       enum lru_list lru)

mm/memory.c

@@ -1360,6 +1360,56 @@ int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
 	return i;
 }
 
+/**
+ * get_user_pages() - pin user pages in memory
+ * @tsk:	task_struct of target task
+ * @mm:		mm_struct of target mm
+ * @start:	starting user address
+ * @len:	number of pages from start to pin
+ * @write:	whether pages will be written to by the caller
+ * @force:	whether to force write access even if user mapping is
+ *		readonly. This will result in the page being COWed even
+ *		in MAP_SHARED mappings. You do not want this.
+ * @pages:	array that receives pointers to the pages pinned.
+ *		Should be at least nr_pages long. Or NULL, if caller
+ *		only intends to ensure the pages are faulted in.
+ * @vmas:	array of pointers to vmas corresponding to each page.
+ *		Or NULL if the caller does not require them.
+ *
+ * Returns number of pages pinned. This may be fewer than the number
+ * requested. If len is 0 or negative, returns 0. If no pages
+ * were pinned, returns -errno. Each page returned must be released
+ * with a put_page() call when it is finished with. vmas will only
+ * remain valid while mmap_sem is held.
+ *
+ * Must be called with mmap_sem held for read or write.
+ *
+ * get_user_pages walks a process's page tables and takes a reference to
+ * each struct page that each user address corresponds to at a given
+ * instant. That is, it takes the page that would be accessed if a user
+ * thread accesses the given user virtual address at that instant.
+ *
+ * This does not guarantee that the page exists in the user mappings when
+ * get_user_pages returns, and there may even be a completely different
+ * page there in some cases (eg. if mmapped pagecache has been invalidated
+ * and subsequently re faulted). However it does guarantee that the page
+ * won't be freed completely. And mostly callers simply care that the page
+ * contains data that was valid *at some point in time*. Typically, an IO
+ * or similar operation cannot guarantee anything stronger anyway because
+ * locks can't be held over the syscall boundary.
+ *
+ * If write=0, the page must not be written to. If the page is written to,
+ * set_page_dirty (or set_page_dirty_lock, as appropriate) must be called
+ * after the page is finished with, and before put_page is called.
+ *
+ * get_user_pages is typically used for fewer-copy IO operations, to get a
+ * handle on the memory by some means other than accesses via the user virtual
+ * addresses. The pages may be submitted for DMA to devices or accessed via
+ * their kernel linear mapping (via the kmap APIs). Care should be taken to
+ * use the correct cache flushing APIs.
+ *
+ * See also get_user_pages_fast, for performance critical applications.
+ */
 int get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
 		unsigned long start, int len, int write, int force,
 		struct page **pages, struct vm_area_struct **vmas)
@@ -3053,22 +3103,13 @@ int in_gate_area_no_task(unsigned long addr)
 
 #endif	/* __HAVE_ARCH_GATE_AREA */
 
-#ifdef CONFIG_HAVE_IOREMAP_PROT
-int follow_phys(struct vm_area_struct *vma,
-		unsigned long address, unsigned int flags,
-		unsigned long *prot, resource_size_t *phys)
+static int follow_pte(struct mm_struct *mm, unsigned long address,
+		pte_t **ptepp, spinlock_t **ptlp)
 {
 	pgd_t *pgd;
 	pud_t *pud;
 	pmd_t *pmd;
-	pte_t *ptep, pte;
-	spinlock_t *ptl;
-	resource_size_t phys_addr = 0;
-	struct mm_struct *mm = vma->vm_mm;
-	int ret = -EINVAL;
-
-	if (!(vma->vm_flags & (VM_IO | VM_PFNMAP)))
-		goto out;
+	pte_t *ptep;
 
 	pgd = pgd_offset(mm, address);
 	if (pgd_none(*pgd) || unlikely(pgd_bad(*pgd)))
@@ -3086,22 +3127,71 @@ int follow_phys(struct vm_area_struct *vma,
 	if (pmd_huge(*pmd))
 		goto out;
 
-	ptep = pte_offset_map_lock(mm, pmd, address, &ptl);
+	ptep = pte_offset_map_lock(mm, pmd, address, ptlp);
 	if (!ptep)
 		goto out;
-
-	pte = *ptep;
-	if (!pte_present(pte))
+	if (!pte_present(*ptep))
 		goto unlock;
+	*ptepp = ptep;
+	return 0;
+unlock:
+	pte_unmap_unlock(ptep, *ptlp);
+out:
+	return -EINVAL;
+}
+
+/**
+ * follow_pfn - look up PFN at a user virtual address
+ * @vma: memory mapping
+ * @address: user virtual address
+ * @pfn: location to store found PFN
+ *
+ * Only IO mappings and raw PFN mappings are allowed.
+ *
+ * Returns zero and the pfn at @pfn on success, -ve otherwise.
+ */
+int follow_pfn(struct vm_area_struct *vma, unsigned long address,
+	unsigned long *pfn)
+{
+	int ret = -EINVAL;
+	spinlock_t *ptl;
+	pte_t *ptep;
+
+	if (!(vma->vm_flags & (VM_IO | VM_PFNMAP)))
+		return ret;
+
+	ret = follow_pte(vma->vm_mm, address, &ptep, &ptl);
+	if (ret)
+		return ret;
+	*pfn = pte_pfn(*ptep);
+	pte_unmap_unlock(ptep, ptl);
+	return 0;
+}
+EXPORT_SYMBOL(follow_pfn);
+
+#ifdef CONFIG_HAVE_IOREMAP_PROT
+int follow_phys(struct vm_area_struct *vma,
+		unsigned long address, unsigned int flags,
+		unsigned long *prot, resource_size_t *phys)
+{
+	int ret = -EINVAL;
+	pte_t *ptep, pte;
+	spinlock_t *ptl;
+
+	if (!(vma->vm_flags & (VM_IO | VM_PFNMAP)))
+		goto out;
+
+	if (follow_pte(vma->vm_mm, address, &ptep, &ptl))
+		goto out;
+	pte = *ptep;
+
 	if ((flags & FOLL_WRITE) && !pte_write(pte))
 		goto unlock;
-	phys_addr = pte_pfn(pte);
-	phys_addr <<= PAGE_SHIFT; /* Shift here to avoid overflow on PAE */
 
 	*prot = pgprot_val(pte_pgprot(pte));
-	*phys = phys_addr;
-	ret = 0;
+	*phys = (resource_size_t)pte_pfn(pte) << PAGE_SHIFT;
 
+	ret = 0;
 unlock:
 	pte_unmap_unlock(ptep, ptl);
 out:

mm/memory_hotplug.c

@@ -422,7 +422,8 @@ int online_pages(unsigned long pfn, unsigned long nr_pages)
 	zone->present_pages += onlined_pages;
 	zone->zone_pgdat->node_present_pages += onlined_pages;
 
-	setup_per_zone_pages_min();
+	setup_per_zone_wmarks();
+	calculate_zone_inactive_ratio(zone);
 	if (onlined_pages) {
 		kswapd_run(zone_to_nid(zone));
 		node_set_state(zone_to_nid(zone), N_HIGH_MEMORY);
@@ -832,6 +833,9 @@ repeat:
 	totalram_pages -= offlined_pages;
 	num_physpages -= offlined_pages;
 
+	setup_per_zone_wmarks();
+	calculate_zone_inactive_ratio(zone);
+
 	vm_total_pages = nr_free_pagecache_pages();
 	writeback_set_ratelimit();
 

mm/mempolicy.c

@@ -182,13 +182,54 @@ static int mpol_new_bind(struct mempolicy *pol, const nodemask_t *nodes)
 	return 0;
 }
 
-/* Create a new policy */
+/*
+ * mpol_set_nodemask is called after mpol_new() to set up the nodemask, if
+ * any, for the new policy.  mpol_new() has already validated the nodes
+ * parameter with respect to the policy mode and flags.  But, we need to
+ * handle an empty nodemask with MPOL_PREFERRED here.
+ *
+ * Must be called holding task's alloc_lock to protect task's mems_allowed
+ * and mempolicy.  May also be called holding the mmap_semaphore for write.
+ */
+static int mpol_set_nodemask(struct mempolicy *pol, const nodemask_t *nodes)
+{
+	nodemask_t cpuset_context_nmask;
+	int ret;
+
+	/* if mode is MPOL_DEFAULT, pol is NULL. This is right. */
+	if (pol == NULL)
+		return 0;
+
+	VM_BUG_ON(!nodes);
+	if (pol->mode == MPOL_PREFERRED && nodes_empty(*nodes))
+		nodes = NULL;	/* explicit local allocation */
+	else {
+		if (pol->flags & MPOL_F_RELATIVE_NODES)
+			mpol_relative_nodemask(&cpuset_context_nmask, nodes,
+					       &cpuset_current_mems_allowed);
+		else
+			nodes_and(cpuset_context_nmask, *nodes,
+				  cpuset_current_mems_allowed);
+		if (mpol_store_user_nodemask(pol))
+			pol->w.user_nodemask = *nodes;
+		else
+			pol->w.cpuset_mems_allowed =
+						cpuset_current_mems_allowed;
+	}
+
+	ret = mpol_ops[pol->mode].create(pol,
+				nodes ? &cpuset_context_nmask : NULL);
+	return ret;
+}
+
+/*
+ * This function just creates a new policy, does some check and simple
+ * initialization. You must invoke mpol_set_nodemask() to set nodes.
+ */
 static struct mempolicy *mpol_new(unsigned short mode, unsigned short flags,
 				  nodemask_t *nodes)
 {
 	struct mempolicy *policy;
-	nodemask_t cpuset_context_nmask;
-	int ret;
 
 	pr_debug("setting mode %d flags %d nodes[0] %lx\n",
 		 mode, flags, nodes ? nodes_addr(*nodes)[0] : -1);
@@ -210,7 +251,6 @@ static struct mempolicy *mpol_new(unsigned short mode, unsigned short flags,
 			if (((flags & MPOL_F_STATIC_NODES) ||
 			     (flags & MPOL_F_RELATIVE_NODES)))
 				return ERR_PTR(-EINVAL);
-			nodes = NULL;	/* flag local alloc */
 		}
 	} else if (nodes_empty(*nodes))
 		return ERR_PTR(-EINVAL);
@@ -221,30 +261,6 @@ static struct mempolicy *mpol_new(unsigned short mode, unsigned short flags,
 	policy->mode = mode;
 	policy->flags = flags;
 
-	if (nodes) {
-		/*
-		 * cpuset related setup doesn't apply to local allocation
-		 */
-		cpuset_update_task_memory_state();
-		if (flags & MPOL_F_RELATIVE_NODES)
-			mpol_relative_nodemask(&cpuset_context_nmask, nodes,
-					       &cpuset_current_mems_allowed);
-		else
-			nodes_and(cpuset_context_nmask, *nodes,
-				  cpuset_current_mems_allowed);
-		if (mpol_store_user_nodemask(policy))
-			policy->w.user_nodemask = *nodes;
-		else
-			policy->w.cpuset_mems_allowed =
-						cpuset_mems_allowed(current);
-	}
-
-	ret = mpol_ops[mode].create(policy,
-				nodes ? &cpuset_context_nmask : NULL);
-	if (ret < 0) {
-		kmem_cache_free(policy_cache, policy);
-		return ERR_PTR(ret);
-	}
 	return policy;
 }
 
@@ -324,6 +340,8 @@ static void mpol_rebind_policy(struct mempolicy *pol,
 /*
  * Wrapper for mpol_rebind_policy() that just requires task
  * pointer, and updates task mempolicy.
+ *
+ * Called with task's alloc_lock held.
  */
 
 void mpol_rebind_task(struct task_struct *tsk, const nodemask_t *new)
@@ -600,8 +618,9 @@ static void mpol_set_task_struct_flag(void)
 static long do_set_mempolicy(unsigned short mode, unsigned short flags,
 			     nodemask_t *nodes)
 {
-	struct mempolicy *new;
+	struct mempolicy *new, *old;
 	struct mm_struct *mm = current->mm;
+	int ret;
 
 	new = mpol_new(mode, flags, nodes);
 	if (IS_ERR(new))
@@ -615,20 +634,33 @@ static long do_set_mempolicy(unsigned short mode, unsigned short flags,
 	 */
 	if (mm)
 		down_write(&mm->mmap_sem);
-	mpol_put(current->mempolicy);
+	task_lock(current);
+	ret = mpol_set_nodemask(new, nodes);
+	if (ret) {
+		task_unlock(current);
+		if (mm)
+			up_write(&mm->mmap_sem);
+		mpol_put(new);
+		return ret;
+	}
+	old = current->mempolicy;
 	current->mempolicy = new;
 	mpol_set_task_struct_flag();
 	if (new && new->mode == MPOL_INTERLEAVE &&
 	    nodes_weight(new->v.nodes))
 		current->il_next = first_node(new->v.nodes);
+	task_unlock(current);
 	if (mm)
 		up_write(&mm->mmap_sem);
 
+	mpol_put(old);
 	return 0;
 }
 
 /*
  * Return nodemask for policy for get_mempolicy() query
+ *
+ * Called with task's alloc_lock held
  */
 static void get_policy_nodemask(struct mempolicy *p, nodemask_t *nodes)
 {
@@ -674,7 +706,6 @@ static long do_get_mempolicy(int *policy, nodemask_t *nmask,
 	struct vm_area_struct *vma = NULL;
 	struct mempolicy *pol = current->mempolicy;
 
-	cpuset_update_task_memory_state();
 	if (flags &
 		~(unsigned long)(MPOL_F_NODE|MPOL_F_ADDR|MPOL_F_MEMS_ALLOWED))
 		return -EINVAL;
@@ -683,7 +714,9 @@ static long do_get_mempolicy(int *policy, nodemask_t *nmask,
 		if (flags & (MPOL_F_NODE|MPOL_F_ADDR))
 			return -EINVAL;
 		*policy = 0;	/* just so it's initialized */
+		task_lock(current);
 		*nmask  = cpuset_current_mems_allowed;
+		task_unlock(current);
 		return 0;
 	}
 
@@ -738,8 +771,11 @@ static long do_get_mempolicy(int *policy, nodemask_t *nmask,
 	}
 
 	err = 0;
-	if (nmask)
+	if (nmask) {
+		task_lock(current);
 		get_policy_nodemask(pol, nmask);
+		task_unlock(current);
+	}
 
  out:
 	mpol_cond_put(pol);
@@ -767,7 +803,7 @@ static void migrate_page_add(struct page *page, struct list_head *pagelist,
 
 static struct page *new_node_page(struct page *page, unsigned long node, int **x)
 {
-	return alloc_pages_node(node, GFP_HIGHUSER_MOVABLE, 0);
+	return alloc_pages_exact_node(node, GFP_HIGHUSER_MOVABLE, 0);
 }
 
 /*
@@ -979,6 +1015,14 @@ static long do_mbind(unsigned long start, unsigned long len,
 			return err;
 	}
 	down_write(&mm->mmap_sem);
+	task_lock(current);
+	err = mpol_set_nodemask(new, nmask);
+	task_unlock(current);
+	if (err) {
+		up_write(&mm->mmap_sem);
+		mpol_put(new);
+		return err;
+	}
 	vma = check_range(mm, start, end, nmask,
 			  flags | MPOL_MF_INVERT, &pagelist);
 
@@ -1545,8 +1589,6 @@ alloc_page_vma(gfp_t gfp, struct vm_area_struct *vma, unsigned long addr)
 	struct mempolicy *pol = get_vma_policy(current, vma, addr);
 	struct zonelist *zl;
 
-	cpuset_update_task_memory_state();
-
 	if (unlikely(pol->mode == MPOL_INTERLEAVE)) {
 		unsigned nid;
 
@@ -1593,8 +1635,6 @@ struct page *alloc_pages_current(gfp_t gfp, unsigned order)
 {
 	struct mempolicy *pol = current->mempolicy;
 
-	if ((gfp & __GFP_WAIT) && !in_interrupt())
-		cpuset_update_task_memory_state();
 	if (!pol || in_interrupt() || (gfp & __GFP_THISNODE))
 		pol = &default_policy;
 
@@ -1854,6 +1894,8 @@ restart:
  */
 void mpol_shared_policy_init(struct shared_policy *sp, struct mempolicy *mpol)
 {
+	int ret;
+
 	sp->root = RB_ROOT;		/* empty tree == default mempolicy */
 	spin_lock_init(&sp->lock);
 
@@ -1863,9 +1905,19 @@ void mpol_shared_policy_init(struct shared_policy *sp, struct mempolicy *mpol)
 
 		/* contextualize the tmpfs mount point mempolicy */
 		new = mpol_new(mpol->mode, mpol->flags, &mpol->w.user_nodemask);
-		mpol_put(mpol);	/* drop our ref on sb mpol */
-		if (IS_ERR(new))
+		if (IS_ERR(new)) {
+			mpol_put(mpol);	/* drop our ref on sb mpol */
 			return;		/* no valid nodemask intersection */
+		}
+
+		task_lock(current);
+		ret = mpol_set_nodemask(new, &mpol->w.user_nodemask);
+		task_unlock(current);
+		mpol_put(mpol);	/* drop our ref on sb mpol */
+		if (ret) {
+			mpol_put(new);
+			return;
+		}
 
 		/* Create pseudo-vma that contains just the policy */
 		memset(&pvma, 0, sizeof(struct vm_area_struct));
@@ -2086,8 +2138,19 @@ int mpol_parse_str(char *str, struct mempolicy **mpol, int no_context)
 	new = mpol_new(mode, mode_flags, &nodes);
 	if (IS_ERR(new))
 		err = 1;
-	else if (no_context)
-		new->w.user_nodemask = nodes;	/* save for contextualization */
+	else {
+		int ret;
+
+		task_lock(current);
+		ret = mpol_set_nodemask(new, &nodes);
+		task_unlock(current);
+		if (ret)
+			err = 1;
+		else if (no_context) {
+			/* save for contextualization */
+			new->w.user_nodemask = nodes;
+		}
+	}
 
 out:
 	/* Restore string for error message */

mm/migrate.c

@@ -802,7 +802,7 @@ static struct page *new_page_node(struct page *p, unsigned long private,
 
 	*result = &pm->status;
 
-	return alloc_pages_node(pm->node,
+	return alloc_pages_exact_node(pm->node,
 				GFP_HIGHUSER_MOVABLE | GFP_THISNODE, 0);
 }
 
@@ -820,7 +820,6 @@ static int do_move_page_to_node_array(struct mm_struct *mm,
 	struct page_to_node *pp;
 	LIST_HEAD(pagelist);
 
-	migrate_prep();
 	down_read(&mm->mmap_sem);
 
 	/*
@@ -907,6 +906,9 @@ static int do_pages_move(struct mm_struct *mm, struct task_struct *task,
 	pm = (struct page_to_node *)__get_free_page(GFP_KERNEL);
 	if (!pm)
 		goto out;
+
+	migrate_prep();
+
 	/*
 	 * Store a chunk of page_to_node array in a page,
 	 * but keep the last one as a marker

mm/mlock.c

@@ -31,7 +31,6 @@ int can_do_mlock(void)
 }
 EXPORT_SYMBOL(can_do_mlock);
 
-#ifdef CONFIG_UNEVICTABLE_LRU
 /*
  * Mlocked pages are marked with PageMlocked() flag for efficient testing
  * in vmscan and, possibly, the fault path; and to support semi-accurate
@@ -261,27 +260,6 @@ static int __mlock_posix_error_return(long retval)
 	return retval;
 }
 
-#else /* CONFIG_UNEVICTABLE_LRU */
-
-/*
- * Just make pages present if VM_LOCKED.  No-op if unlocking.
- */
-static long __mlock_vma_pages_range(struct vm_area_struct *vma,
-				   unsigned long start, unsigned long end,
-				   int mlock)
-{
-	if (mlock && (vma->vm_flags & VM_LOCKED))
-		return make_pages_present(start, end);
-	return 0;
-}
-
-static inline int __mlock_posix_error_return(long retval)
-{
-	return 0;
-}
-
-#endif /* CONFIG_UNEVICTABLE_LRU */
-
 /**
  * mlock_vma_pages_range() - mlock pages in specified vma range.
  * @vma - the vma containing the specfied address range

mm/oom_kill.c

@@ -58,6 +58,7 @@ unsigned long badness(struct task_struct *p, unsigned long uptime)
 	unsigned long points, cpu_time, run_time;
 	struct mm_struct *mm;
 	struct task_struct *child;
+	int oom_adj;
 
 	task_lock(p);
 	mm = p->mm;
@@ -65,6 +66,11 @@ unsigned long badness(struct task_struct *p, unsigned long uptime)
 		task_unlock(p);
 		return 0;
 	}
+	oom_adj = mm->oom_adj;
+	if (oom_adj == OOM_DISABLE) {
+		task_unlock(p);
+		return 0;
+	}
 
 	/*
 	 * The memory size of the process is the basis for the badness.
@@ -148,15 +154,15 @@ unsigned long badness(struct task_struct *p, unsigned long uptime)
 		points /= 8;
 
 	/*
-	 * Adjust the score by oomkilladj.
+	 * Adjust the score by oom_adj.
 	 */
-	if (p->oomkilladj) {
-		if (p->oomkilladj > 0) {
+	if (oom_adj) {
+		if (oom_adj > 0) {
 			if (!points)
 				points = 1;
-			points <<= p->oomkilladj;
+			points <<= oom_adj;
 		} else
-			points >>= -(p->oomkilladj);
+			points >>= -(oom_adj);
 	}
 
 #ifdef DEBUG
@@ -251,11 +257,8 @@ static struct task_struct *select_bad_process(unsigned long *ppoints,
 			*ppoints = ULONG_MAX;
 		}
 
-		if (p->oomkilladj == OOM_DISABLE)
-			continue;
-
 		points = badness(p, uptime.tv_sec);
-		if (points > *ppoints || !chosen) {
+		if (points > *ppoints) {
 			chosen = p;
 			*ppoints = points;
 		}
@@ -304,8 +307,7 @@ static void dump_tasks(const struct mem_cgroup *mem)
 		}
 		printk(KERN_INFO "[%5d] %5d %5d %8lu %8lu %3d     %3d %s\n",
 		       p->pid, __task_cred(p)->uid, p->tgid, mm->total_vm,
-		       get_mm_rss(mm), (int)task_cpu(p), p->oomkilladj,
-		       p->comm);
+		       get_mm_rss(mm), (int)task_cpu(p), mm->oom_adj, p->comm);
 		task_unlock(p);
 	} while_each_thread(g, p);
 }
@@ -323,11 +325,8 @@ static void __oom_kill_task(struct task_struct *p, int verbose)
 		return;
 	}
 
-	if (!p->mm) {
-		WARN_ON(1);
-		printk(KERN_WARNING "tried to kill an mm-less task!\n");
+	if (!p->mm)
 		return;
-	}
 
 	if (verbose)
 		printk(KERN_ERR "Killed process %d (%s)\n",
@@ -349,28 +348,13 @@ static int oom_kill_task(struct task_struct *p)
 	struct mm_struct *mm;
 	struct task_struct *g, *q;
 
+	task_lock(p);
 	mm = p->mm;
-
-	/* WARNING: mm may not be dereferenced since we did not obtain its
-	 * value from get_task_mm(p).  This is OK since all we need to do is
-	 * compare mm to q->mm below.
-	 *
-	 * Furthermore, even if mm contains a non-NULL value, p->mm may
-	 * change to NULL at any time since we do not hold task_lock(p).
-	 * However, this is of no concern to us.
-	 */
-
-	if (mm == NULL)
+	if (!mm || mm->oom_adj == OOM_DISABLE) {
+		task_unlock(p);
 		return 1;
-
-	/*
-	 * Don't kill the process if any threads are set to OOM_DISABLE
-	 */
-	do_each_thread(g, q) {
-		if (q->mm == mm && q->oomkilladj == OOM_DISABLE)
-			return 1;
-	} while_each_thread(g, q);
-
+	}
+	task_unlock(p);
 	__oom_kill_task(p, 1);
 
 	/*
@@ -393,10 +377,11 @@ static int oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order,
 	struct task_struct *c;
 
 	if (printk_ratelimit()) {
-		printk(KERN_WARNING "%s invoked oom-killer: "
-			"gfp_mask=0x%x, order=%d, oomkilladj=%d\n",
-			current->comm, gfp_mask, order, current->oomkilladj);
 		task_lock(current);
+		printk(KERN_WARNING "%s invoked oom-killer: "
+			"gfp_mask=0x%x, order=%d, oom_adj=%d\n",
+			current->comm, gfp_mask, order,
+			current->mm ? current->mm->oom_adj : OOM_DISABLE);
 		cpuset_print_task_mems_allowed(current);
 		task_unlock(current);
 		dump_stack();
@@ -409,8 +394,9 @@ static int oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order,
 	/*
 	 * If the task is already exiting, don't alarm the sysadmin or kill
 	 * its children or threads, just set TIF_MEMDIE so it can die quickly
+	 * if its mm is still attached.
 	 */
-	if (p->flags & PF_EXITING) {
+	if (p->mm && (p->flags & PF_EXITING)) {
 		__oom_kill_task(p, 0);
 		return 0;
 	}

mm/page-writeback.c

@@ -265,18 +265,19 @@ static void bdi_writeout_fraction(struct backing_dev_info *bdi,
  * This avoids exceeding the total dirty_limit when the floating averages
  * fluctuate too quickly.
  */
-static void
-clip_bdi_dirty_limit(struct backing_dev_info *bdi, long dirty, long *pbdi_dirty)
+static void clip_bdi_dirty_limit(struct backing_dev_info *bdi,
+		unsigned long dirty, unsigned long *pbdi_dirty)
 {
-	long avail_dirty;
+	unsigned long avail_dirty;
 
-	avail_dirty = dirty -
-		(global_page_state(NR_FILE_DIRTY) +
+	avail_dirty = global_page_state(NR_FILE_DIRTY) +
 		 global_page_state(NR_WRITEBACK) +
 		 global_page_state(NR_UNSTABLE_NFS) +
-		 global_page_state(NR_WRITEBACK_TEMP));
+		 global_page_state(NR_WRITEBACK_TEMP);
 
-	if (avail_dirty < 0)
+	if (avail_dirty < dirty)
+		avail_dirty = dirty - avail_dirty;
+	else
 		avail_dirty = 0;
 
 	avail_dirty += bdi_stat(bdi, BDI_RECLAIMABLE) +
@@ -299,10 +300,10 @@ static inline void task_dirties_fraction(struct task_struct *tsk,
  *
  *   dirty -= (dirty/8) * p_{t}
  */
-static void task_dirty_limit(struct task_struct *tsk, long *pdirty)
+static void task_dirty_limit(struct task_struct *tsk, unsigned long *pdirty)
 {
 	long numerator, denominator;
-	long dirty = *pdirty;
+	unsigned long dirty = *pdirty;
 	u64 inv = dirty >> 3;
 
 	task_dirties_fraction(tsk, &numerator, &denominator);

mm/page_io.c

@@ -120,7 +120,7 @@ out:
 	return ret;
 }
 
-int swap_readpage(struct file *file, struct page *page)
+int swap_readpage(struct page *page)
 {
 	struct bio *bio;
 	int ret = 0;

mm/readahead.c

@@ -133,15 +133,12 @@ out:
 }
 
 /*
- * do_page_cache_readahead actually reads a chunk of disk.  It allocates all
+ * __do_page_cache_readahead() actually reads a chunk of disk.  It allocates all
  * the pages first, then submits them all for I/O. This avoids the very bad
  * behaviour which would occur if page allocations are causing VM writeback.
  * We really don't want to intermingle reads and writes like that.
  *
  * Returns the number of pages requested, or the maximum amount of I/O allowed.
- *
- * do_page_cache_readahead() returns -1 if it encountered request queue
- * congestion.
  */
 static int
 __do_page_cache_readahead(struct address_space *mapping, struct file *filp,
@@ -210,6 +207,7 @@ int force_page_cache_readahead(struct address_space *mapping, struct file *filp,
 	if (unlikely(!mapping->a_ops->readpage && !mapping->a_ops->readpages))
 		return -EINVAL;
 
+	nr_to_read = max_sane_readahead(nr_to_read);
 	while (nr_to_read) {
 		int err;
 
@@ -230,22 +228,6 @@ int force_page_cache_readahead(struct address_space *mapping, struct file *filp,
 	return ret;
 }
 
-/*
- * This version skips the IO if the queue is read-congested, and will tell the
- * block layer to abandon the readahead if request allocation would block.
- *
- * force_page_cache_readahead() will ignore queue congestion and will block on
- * request queues.
- */
-int do_page_cache_readahead(struct address_space *mapping, struct file *filp,
-			pgoff_t offset, unsigned long nr_to_read)
-{
-	if (bdi_read_congested(mapping->backing_dev_info))
-		return -1;
-
-	return __do_page_cache_readahead(mapping, filp, offset, nr_to_read, 0);
-}
-
 /*
  * Given a desired number of PAGE_CACHE_SIZE readahead pages, return a
  * sensible upper limit.
@@ -259,7 +241,7 @@ unsigned long max_sane_readahead(unsigned long nr)
 /*
  * Submit IO for the read-ahead request in file_ra_state.
  */
-static unsigned long ra_submit(struct file_ra_state *ra,
+unsigned long ra_submit(struct file_ra_state *ra,
 		       struct address_space *mapping, struct file *filp)
 {
 	int actual;
@@ -347,6 +329,59 @@ static unsigned long get_next_ra_size(struct file_ra_state *ra,
  * it approaches max_readhead.
  */
 
+/*
+ * Count contiguously cached pages from @offset-1 to @offset-@max,
+ * this count is a conservative estimation of
+ * 	- length of the sequential read sequence, or
+ * 	- thrashing threshold in memory tight systems
+ */
+static pgoff_t count_history_pages(struct address_space *mapping,
+				   struct file_ra_state *ra,
+				   pgoff_t offset, unsigned long max)
+{
+	pgoff_t head;
+
+	rcu_read_lock();
+	head = radix_tree_prev_hole(&mapping->page_tree, offset - 1, max);
+	rcu_read_unlock();
+
+	return offset - 1 - head;
+}
+
+/*
+ * page cache context based read-ahead
+ */
+static int try_context_readahead(struct address_space *mapping,
+				 struct file_ra_state *ra,
+				 pgoff_t offset,
+				 unsigned long req_size,
+				 unsigned long max)
+{
+	pgoff_t size;
+
+	size = count_history_pages(mapping, ra, offset, max);
+
+	/*
+	 * no history pages:
+	 * it could be a random read
+	 */
+	if (!size)
+		return 0;
+
+	/*
+	 * starts from beginning of file:
+	 * it is a strong indication of long-run stream (or whole-file-read)
+	 */
+	if (size >= offset)
+		size *= 2;
+
+	ra->start = offset;
+	ra->size = get_init_ra_size(size + req_size, max);
+	ra->async_size = ra->size;
+
+	return 1;
+}
+
 /*
  * A minimal readahead algorithm for trivial sequential/random reads.
  */
@@ -356,34 +391,26 @@ ondemand_readahead(struct address_space *mapping,
 		   bool hit_readahead_marker, pgoff_t offset,
 		   unsigned long req_size)
 {
-	int	max = ra->ra_pages;	/* max readahead pages */
-	pgoff_t prev_offset;
-	int	sequential;
+	unsigned long max = max_sane_readahead(ra->ra_pages);
+
+	/*
+	 * start of file
+	 */
+	if (!offset)
+		goto initial_readahead;
 
 	/*
 	 * It's the expected callback offset, assume sequential access.
 	 * Ramp up sizes, and push forward the readahead window.
 	 */
-	if (offset && (offset == (ra->start + ra->size - ra->async_size) ||
-			offset == (ra->start + ra->size))) {
+	if ((offset == (ra->start + ra->size - ra->async_size) ||
+	     offset == (ra->start + ra->size))) {
 		ra->start += ra->size;
 		ra->size = get_next_ra_size(ra, max);
 		ra->async_size = ra->size;
 		goto readit;
 	}
 
-	prev_offset = ra->prev_pos >> PAGE_CACHE_SHIFT;
-	sequential = offset - prev_offset <= 1UL || req_size > max;
-
-	/*
-	 * Standalone, small read.
-	 * Read as is, and do not pollute the readahead state.
-	 */
-	if (!hit_readahead_marker && !sequential) {
-		return __do_page_cache_readahead(mapping, filp,
-						offset, req_size, 0);
-	}
-
 	/*
 	 * Hit a marked page without valid readahead state.
 	 * E.g. interleaved reads.
@@ -394,7 +421,7 @@ ondemand_readahead(struct address_space *mapping,
 		pgoff_t start;
 
 		rcu_read_lock();
-		start = radix_tree_next_hole(&mapping->page_tree, offset,max+1);
+		start = radix_tree_next_hole(&mapping->page_tree, offset+1,max);
 		rcu_read_unlock();
 
 		if (!start || start - offset > max)
@@ -402,23 +429,53 @@ ondemand_readahead(struct address_space *mapping,
 
 		ra->start = start;
 		ra->size = start - offset;	/* old async_size */
+		ra->size += req_size;
 		ra->size = get_next_ra_size(ra, max);
 		ra->async_size = ra->size;
 		goto readit;
 	}
 
 	/*
-	 * It may be one of
-	 * 	- first read on start of file
-	 * 	- sequential cache miss
-	 * 	- oversize random read
-	 * Start readahead for it.
+	 * oversize read
 	 */
+	if (req_size > max)
+		goto initial_readahead;
+
+	/*
+	 * sequential cache miss
+	 */
+	if (offset - (ra->prev_pos >> PAGE_CACHE_SHIFT) <= 1UL)
+		goto initial_readahead;
+
+	/*
+	 * Query the page cache and look for the traces(cached history pages)
+	 * that a sequential stream would leave behind.
+	 */
+	if (try_context_readahead(mapping, ra, offset, req_size, max))
+		goto readit;
+
+	/*
+	 * standalone, small random read
+	 * Read as is, and do not pollute the readahead state.
+	 */
+	return __do_page_cache_readahead(mapping, filp, offset, req_size, 0);
+
+initial_readahead:
 	ra->start = offset;
 	ra->size = get_init_ra_size(req_size, max);
 	ra->async_size = ra->size > req_size ? ra->size - req_size : ra->size;
 
 readit:
+	/*
+	 * Will this read hit the readahead marker made by itself?
+	 * If so, trigger the readahead marker hit now, and merge
+	 * the resulted next readahead window into the current one.
+	 */
+	if (offset == ra->start && ra->size == ra->async_size) {
+		ra->async_size = get_next_ra_size(ra, max);
+		ra->size += ra->async_size;
+	}
+
 	return ra_submit(ra, mapping, filp);
 }
 

mm/rmap.c

@@ -333,7 +333,9 @@ static int page_mapped_in_vma(struct page *page, struct vm_area_struct *vma)
  * repeatedly from either page_referenced_anon or page_referenced_file.
  */
 static int page_referenced_one(struct page *page,
-	struct vm_area_struct *vma, unsigned int *mapcount)
+			       struct vm_area_struct *vma,
+			       unsigned int *mapcount,
+			       unsigned long *vm_flags)
 {
 	struct mm_struct *mm = vma->vm_mm;
 	unsigned long address;
@@ -381,11 +383,14 @@ out_unmap:
 	(*mapcount)--;
 	pte_unmap_unlock(pte, ptl);
 out:
+	if (referenced)
+		*vm_flags |= vma->vm_flags;
 	return referenced;
 }
 
 static int page_referenced_anon(struct page *page,
-				struct mem_cgroup *mem_cont)
+				struct mem_cgroup *mem_cont,
+				unsigned long *vm_flags)
 {
 	unsigned int mapcount;
 	struct anon_vma *anon_vma;
@@ -405,7 +410,8 @@ static int page_referenced_anon(struct page *page,
 		 */
 		if (mem_cont && !mm_match_cgroup(vma->vm_mm, mem_cont))
 			continue;
-		referenced += page_referenced_one(page, vma, &mapcount);
+		referenced += page_referenced_one(page, vma,
+						  &mapcount, vm_flags);
 		if (!mapcount)
 			break;
 	}
@@ -418,6 +424,7 @@ 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
+ * @vm_flags: collect encountered vma->vm_flags who actually referenced the page
  *
  * 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
@@ -427,7 +434,8 @@ static int page_referenced_anon(struct page *page,
  * This function is only called from page_referenced for object-based pages.
  */
 static int page_referenced_file(struct page *page,
-				struct mem_cgroup *mem_cont)
+				struct mem_cgroup *mem_cont,
+				unsigned long *vm_flags)
 {
 	unsigned int mapcount;
 	struct address_space *mapping = page->mapping;
@@ -467,7 +475,8 @@ static int page_referenced_file(struct page *page,
 		 */
 		if (mem_cont && !mm_match_cgroup(vma->vm_mm, mem_cont))
 			continue;
-		referenced += page_referenced_one(page, vma, &mapcount);
+		referenced += page_referenced_one(page, vma,
+						  &mapcount, vm_flags);
 		if (!mapcount)
 			break;
 	}
@@ -481,29 +490,35 @@ static int page_referenced_file(struct page *page,
  * @page: the page to test
  * @is_locked: caller holds lock on the page
  * @mem_cont: target memory controller
+ * @vm_flags: collect encountered vma->vm_flags who actually referenced the page
  *
  * Quick test_and_clear_referenced for all mappings to a page,
  * returns the number of ptes which referenced the page.
  */
-int page_referenced(struct page *page, int is_locked,
-			struct mem_cgroup *mem_cont)
+int page_referenced(struct page *page,
+		    int is_locked,
+		    struct mem_cgroup *mem_cont,
+		    unsigned long *vm_flags)
 {
 	int referenced = 0;
 
 	if (TestClearPageReferenced(page))
 		referenced++;
 
+	*vm_flags = 0;
 	if (page_mapped(page) && page->mapping) {
 		if (PageAnon(page))
-			referenced += page_referenced_anon(page, mem_cont);
+			referenced += page_referenced_anon(page, mem_cont,
+								vm_flags);
 		else if (is_locked)
-			referenced += page_referenced_file(page, mem_cont);
+			referenced += page_referenced_file(page, mem_cont,
+								vm_flags);
 		else if (!trylock_page(page))
 			referenced++;
 		else {
 			if (page->mapping)
-				referenced +=
-					page_referenced_file(page, mem_cont);
+				referenced += page_referenced_file(page,
+							mem_cont, vm_flags);
 			unlock_page(page);
 		}
 	}
@@ -1202,7 +1217,6 @@ int try_to_unmap(struct page *page, int migration)
 	return ret;
 }
 
-#ifdef CONFIG_UNEVICTABLE_LRU
 /**
  * try_to_munlock - try to munlock a page
  * @page: the page to be munlocked
@@ -1226,4 +1240,4 @@ int try_to_munlock(struct page *page)
 	else
 		return try_to_unmap_file(page, 1, 0);
 }
-#endif
+