Merge ../linux-2.6

9 files changed, 255 insertions, 79 deletions

diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index a918f77f02f..1fe76d963ac 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -130,6 +130,7 @@ int online_pages(unsigned long pfn, unsigned long nr_pages)
 		onlined_pages++;
 	}
 	zone->present_pages += onlined_pages;
+	zone->zone_pgdat->node_present_pages += onlined_pages;
 
 	setup_per_zone_pages_min();
 
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 67af4cea1e2..954981b1430 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -197,7 +197,7 @@ static struct mempolicy *mpol_new(int mode, nodemask_t *nodes)
 	return policy;
 }
 
-static void gather_stats(struct page *, void *);
+static void gather_stats(struct page *, void *, int pte_dirty);
 static void migrate_page_add(struct page *page, struct list_head *pagelist,
 				unsigned long flags);
 
@@ -239,7 +239,7 @@ static int check_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
 			continue;
 
 		if (flags & MPOL_MF_STATS)
-			gather_stats(page, private);
+			gather_stats(page, private, pte_dirty(*pte));
 		else if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL))
 			migrate_page_add(page, private, flags);
 		else
@@ -954,7 +954,8 @@ asmlinkage long sys_migrate_pages(pid_t pid, unsigned long maxnode,
 		goto out;
 	}
 
-	err = do_migrate_pages(mm, &old, &new, MPOL_MF_MOVE);
+	err = do_migrate_pages(mm, &old, &new,
+		capable(CAP_SYS_ADMIN) ? MPOL_MF_MOVE_ALL : MPOL_MF_MOVE);
 out:
 	mmput(mm);
 	return err;
@@ -1752,66 +1753,145 @@ static inline int mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol)
 struct numa_maps {
 	unsigned long pages;
 	unsigned long anon;
-	unsigned long mapped;
+	unsigned long active;
+	unsigned long writeback;
 	unsigned long mapcount_max;
+	unsigned long dirty;
+	unsigned long swapcache;
 	unsigned long node[MAX_NUMNODES];
 };
 
-static void gather_stats(struct page *page, void *private)
+static void gather_stats(struct page *page, void *private, int pte_dirty)
 {
 	struct numa_maps *md = private;
 	int count = page_mapcount(page);
 
-	if (count)
-		md->mapped++;
+	md->pages++;
+	if (pte_dirty || PageDirty(page))
+		md->dirty++;
 
-	if (count > md->mapcount_max)
-		md->mapcount_max = count;
+	if (PageSwapCache(page))
+		md->swapcache++;
 
-	md->pages++;
+	if (PageActive(page))
+		md->active++;
+
+	if (PageWriteback(page))
+		md->writeback++;
 
 	if (PageAnon(page))
 		md->anon++;
 
+	if (count > md->mapcount_max)
+		md->mapcount_max = count;
+
 	md->node[page_to_nid(page)]++;
 	cond_resched();
 }
 
+#ifdef CONFIG_HUGETLB_PAGE
+static void check_huge_range(struct vm_area_struct *vma,
+		unsigned long start, unsigned long end,
+		struct numa_maps *md)
+{
+	unsigned long addr;
+	struct page *page;
+
+	for (addr = start; addr < end; addr += HPAGE_SIZE) {
+		pte_t *ptep = huge_pte_offset(vma->vm_mm, addr & HPAGE_MASK);
+		pte_t pte;
+
+		if (!ptep)
+			continue;
+
+		pte = *ptep;
+		if (pte_none(pte))
+			continue;
+
+		page = pte_page(pte);
+		if (!page)
+			continue;
+
+		gather_stats(page, md, pte_dirty(*ptep));
+	}
+}
+#else
+static inline void check_huge_range(struct vm_area_struct *vma,
+		unsigned long start, unsigned long end,
+		struct numa_maps *md)
+{
+}
+#endif
+
 int show_numa_map(struct seq_file *m, void *v)
 {
 	struct task_struct *task = m->private;
 	struct vm_area_struct *vma = v;
 	struct numa_maps *md;
+	struct file *file = vma->vm_file;
+	struct mm_struct *mm = vma->vm_mm;
 	int n;
 	char buffer[50];
 
-	if (!vma->vm_mm)
+	if (!mm)
 		return 0;
 
 	md = kzalloc(sizeof(struct numa_maps), GFP_KERNEL);
 	if (!md)
 		return 0;
 
-	check_pgd_range(vma, vma->vm_start, vma->vm_end,
-		    &node_online_map, MPOL_MF_STATS, md);
+	mpol_to_str(buffer, sizeof(buffer),
+			get_vma_policy(task, vma, vma->vm_start));
 
-	if (md->pages) {
-		mpol_to_str(buffer, sizeof(buffer),
-			    get_vma_policy(task, vma, vma->vm_start));
+	seq_printf(m, "%08lx %s", vma->vm_start, buffer);
 
-		seq_printf(m, "%08lx %s pages=%lu mapped=%lu maxref=%lu",
-			   vma->vm_start, buffer, md->pages,
-			   md->mapped, md->mapcount_max);
+	if (file) {
+		seq_printf(m, " file=");
+		seq_path(m, file->f_vfsmnt, file->f_dentry, "\n\t= ");
+	} else if (vma->vm_start <= mm->brk && vma->vm_end >= mm->start_brk) {
+		seq_printf(m, " heap");
+	} else if (vma->vm_start <= mm->start_stack &&
+			vma->vm_end >= mm->start_stack) {
+		seq_printf(m, " stack");
+	}
 
-		if (md->anon)
-			seq_printf(m," anon=%lu",md->anon);
+	if (is_vm_hugetlb_page(vma)) {
+		check_huge_range(vma, vma->vm_start, vma->vm_end, md);
+		seq_printf(m, " huge");
+	} else {
+		check_pgd_range(vma, vma->vm_start, vma->vm_end,
+				&node_online_map, MPOL_MF_STATS, md);
+	}
 
-		for_each_online_node(n)
-			if (md->node[n])
-				seq_printf(m, " N%d=%lu", n, md->node[n]);
+	if (!md->pages)
+		goto out;
 
-		seq_putc(m, '\n');
-	}
+	if (md->anon)
+		seq_printf(m," anon=%lu",md->anon);
+
+	if (md->dirty)
+		seq_printf(m," dirty=%lu",md->dirty);
+
+	if (md->pages != md->anon && md->pages != md->dirty)
+		seq_printf(m, " mapped=%lu", md->pages);
+
+	if (md->mapcount_max > 1)
+		seq_printf(m, " mapmax=%lu", md->mapcount_max);
+
+	if (md->swapcache)
+		seq_printf(m," swapcache=%lu", md->swapcache);
+
+	if (md->active < md->pages && !is_vm_hugetlb_page(vma))
+		seq_printf(m," active=%lu", md->active);
+
+	if (md->writeback)
+		seq_printf(m," writeback=%lu", md->writeback);
+
+	for_each_online_node(n)
+		if (md->node[n])
+			seq_printf(m, " N%d=%lu", n, md->node[n]);
+out:
+	seq_putc(m, '\n');
 	kfree(md);
 
 	if (m->count < m->size)
diff --git a/mm/nommu.c b/mm/nommu.c
index 99d21020ec9..4951f4786f2 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -53,7 +53,6 @@ DECLARE_RWSEM(nommu_vma_sem);
 struct vm_operations_struct generic_file_vm_ops = {
 };
 
-EXPORT_SYMBOL(vmalloc);
 EXPORT_SYMBOL(vfree);
 EXPORT_SYMBOL(vmalloc_to_page);
 EXPORT_SYMBOL(vmalloc_32);
@@ -205,6 +204,13 @@ void *vmalloc(unsigned long size)
 {
        return __vmalloc(size, GFP_KERNEL | __GFP_HIGHMEM, PAGE_KERNEL);
 }
+EXPORT_SYMBOL(vmalloc);
+
+void *vmalloc_node(unsigned long size, int node)
+{
+	return vmalloc(size);
+}
+EXPORT_SYMBOL(vmalloc_node);
 
 /*
  *	vmalloc_32  -  allocate virtually continguos memory (32bit addressable)
diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index 8123fad5a48..78747afad6b 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -302,7 +302,7 @@ void out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask, int order)
 {
 	struct mm_struct *mm = NULL;
 	task_t *p;
-	unsigned long points;
+	unsigned long points = 0;
 
 	if (printk_ratelimit()) {
 		printk("oom-killer: gfp_mask=0x%x, order=%d\n",
@@ -355,6 +355,7 @@ retry:
 	}
 
 out:
+	read_unlock(&tasklist_lock);
 	cpuset_unlock();
 	if (mm)
 		mmput(mm);
@@ -364,5 +365,5 @@ out:
 	 * retry to allocate memory unless "p" is current
 	 */
 	if (!test_thread_flag(TIF_MEMDIE))
-		schedule_timeout_interruptible(1);
+		schedule_timeout_uninterruptible(1);
 }
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 791690d7d3f..234bd4895d1 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -590,21 +590,20 @@ static int rmqueue_bulk(struct zone *zone, unsigned int order,
 }
 
 #ifdef CONFIG_NUMA
-/* Called from the slab reaper to drain remote pagesets */
-void drain_remote_pages(void)
+/*
+ * Called from the slab reaper to drain pagesets on a particular node that
+ * belong to the currently executing processor.
+ */
+void drain_node_pages(int nodeid)
 {
-	struct zone *zone;
-	int i;
+	int i, z;
 	unsigned long flags;
 
 	local_irq_save(flags);
-	for_each_zone(zone) {
+	for (z = 0; z < MAX_NR_ZONES; z++) {
+		struct zone *zone = NODE_DATA(nodeid)->node_zones + z;
 		struct per_cpu_pageset *pset;
 
-		/* Do not drain local pagesets */
-		if (zone->zone_pgdat->node_id == numa_node_id())
-			continue;
-
 		pset = zone_pcp(zone, smp_processor_id());
 		for (i = 0; i < ARRAY_SIZE(pset->pcp); i++) {
 			struct per_cpu_pages *pcp;
diff --git a/mm/rmap.c b/mm/rmap.c
index df2c41c2a9a..67f0e20b101 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -212,25 +212,33 @@ out:
  * through real pte's pointing to valid pages and then releasing
  * the page from the swap cache.
  *
- * Must hold page lock on page.
+ * Must hold page lock on page and mmap_sem of one vma that contains
+ * the page.
  */
 void remove_from_swap(struct page *page)
 {
 	struct anon_vma *anon_vma;
 	struct vm_area_struct *vma;
+	unsigned long mapping;
 
-	if (!PageAnon(page) || !PageSwapCache(page))
+	if (!PageSwapCache(page))
 		return;
 
-	anon_vma = page_lock_anon_vma(page);
-	if (!anon_vma)
+	mapping = (unsigned long)page->mapping;
+
+	if (!mapping || (mapping & PAGE_MAPPING_ANON) == 0)
 		return;
 
+	/*
+	 * We hold the mmap_sem lock. So no need to call page_lock_anon_vma.
+	 */
+	anon_vma = (struct anon_vma *) (mapping - PAGE_MAPPING_ANON);
+	spin_lock(&anon_vma->lock);
+
 	list_for_each_entry(vma, &anon_vma->head, anon_vma_node)
 		remove_vma_swap(vma, page);
 
 	spin_unlock(&anon_vma->lock);
-
 	delete_from_swap_cache(page);
 }
 EXPORT_SYMBOL(remove_from_swap);
@@ -529,9 +537,6 @@ void page_add_new_anon_rmap(struct page *page,
  */
 void page_add_file_rmap(struct page *page)
 {
-	BUG_ON(PageAnon(page));
-	BUG_ON(!pfn_valid(page_to_pfn(page)));
-
 	if (atomic_inc_and_test(&page->_mapcount))
 		__inc_page_state(nr_mapped);
 }
diff --git a/mm/slab.c b/mm/slab.c
index add05d808a4..d0bd7f07ab0 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -789,6 +789,47 @@ static void __slab_error(const char *function, struct kmem_cache *cachep, char *
 	dump_stack();
 }
 
+#ifdef CONFIG_NUMA
+/*
+ * Special reaping functions for NUMA systems called from cache_reap().
+ * These take care of doing round robin flushing of alien caches (containing
+ * objects freed on different nodes from which they were allocated) and the
+ * flushing of remote pcps by calling drain_node_pages.
+ */
+static DEFINE_PER_CPU(unsigned long, reap_node);
+
+static void init_reap_node(int cpu)
+{
+	int node;
+
+	node = next_node(cpu_to_node(cpu), node_online_map);
+	if (node == MAX_NUMNODES)
+		node = 0;
+
+	__get_cpu_var(reap_node) = node;
+}
+
+static void next_reap_node(void)
+{
+	int node = __get_cpu_var(reap_node);
+
+	/*
+	 * Also drain per cpu pages on remote zones
+	 */
+	if (node != numa_node_id())
+		drain_node_pages(node);
+
+	node = next_node(node, node_online_map);
+	if (unlikely(node >= MAX_NUMNODES))
+		node = first_node(node_online_map);
+	__get_cpu_var(reap_node) = node;
+}
+
+#else
+#define init_reap_node(cpu) do { } while (0)
+#define next_reap_node(void) do { } while (0)
+#endif
+
 /*
  * Initiate the reap timer running on the target CPU.  We run at around 1 to 2Hz
  * via the workqueue/eventd.
@@ -806,6 +847,7 @@ static void __devinit start_cpu_timer(int cpu)
 	 * at that time.
 	 */
 	if (keventd_up() && reap_work->func == NULL) {
+		init_reap_node(cpu);
 		INIT_WORK(reap_work, cache_reap, NULL);
 		schedule_delayed_work_on(cpu, reap_work, HZ + 3 * cpu);
 	}
@@ -884,6 +926,23 @@ static void __drain_alien_cache(struct kmem_cache *cachep,
 	}
 }
 
+/*
+ * Called from cache_reap() to regularly drain alien caches round robin.
+ */
+static void reap_alien(struct kmem_cache *cachep, struct kmem_list3 *l3)
+{
+	int node = __get_cpu_var(reap_node);
+
+	if (l3->alien) {
+		struct array_cache *ac = l3->alien[node];
+		if (ac && ac->avail) {
+			spin_lock_irq(&ac->lock);
+			__drain_alien_cache(cachep, ac, node);
+			spin_unlock_irq(&ac->lock);
+		}
+	}
+}
+
 static void drain_alien_cache(struct kmem_cache *cachep, struct array_cache **alien)
 {
 	int i = 0;
@@ -902,6 +961,7 @@ static void drain_alien_cache(struct kmem_cache *cachep, struct array_cache **al
 #else
 
 #define drain_alien_cache(cachep, alien) do { } while (0)
+#define reap_alien(cachep, l3) do { } while (0)
 
 static inline struct array_cache **alloc_alien_cache(int node, int limit)
 {
@@ -1124,6 +1184,7 @@ void __init kmem_cache_init(void)
 	struct cache_sizes *sizes;
 	struct cache_names *names;
 	int i;
+	int order;
 
 	for (i = 0; i < NUM_INIT_LISTS; i++) {
 		kmem_list3_init(&initkmem_list3[i]);
@@ -1167,11 +1228,15 @@ void __init kmem_cache_init(void)
 
 	cache_cache.buffer_size = ALIGN(cache_cache.buffer_size, cache_line_size());
 
-	cache_estimate(0, cache_cache.buffer_size, cache_line_size(), 0,
-		       &left_over, &cache_cache.num);
+	for (order = 0; order < MAX_ORDER; order++) {
+		cache_estimate(order, cache_cache.buffer_size,
+			cache_line_size(), 0, &left_over, &cache_cache.num);
+		if (cache_cache.num)
+			break;
+	}
 	if (!cache_cache.num)
 		BUG();
-
+	cache_cache.gfporder = order;
 	cache_cache.colour = left_over / cache_cache.colour_off;
 	cache_cache.slab_size = ALIGN(cache_cache.num * sizeof(kmem_bufctl_t) +
 				      sizeof(struct slab), cache_line_size());
@@ -1628,36 +1693,44 @@ static inline size_t calculate_slab_order(struct kmem_cache *cachep,
 			size_t size, size_t align, unsigned long flags)
 {
 	size_t left_over = 0;
+	int gfporder;
 
-	for (;; cachep->gfporder++) {
+	for (gfporder = 0 ; gfporder <= MAX_GFP_ORDER; gfporder++) {
 		unsigned int num;
 		size_t remainder;
 
-		if (cachep->gfporder > MAX_GFP_ORDER) {
-			cachep->num = 0;
-			break;
-		}
-
-		cache_estimate(cachep->gfporder, size, align, flags,
-			       &remainder, &num);
+		cache_estimate(gfporder, size, align, flags, &remainder, &num);
 		if (!num)
 			continue;
+
 		/* More than offslab_limit objects will cause problems */
-		if (flags & CFLGS_OFF_SLAB && cachep->num > offslab_limit)
+		if ((flags & CFLGS_OFF_SLAB) && num > offslab_limit)
 			break;
 
+		/* Found something acceptable - save it away */
 		cachep->num = num;
+		cachep->gfporder = gfporder;
 		left_over = remainder;
 
 		/*
+		 * A VFS-reclaimable slab tends to have most allocations
+		 * as GFP_NOFS and we really don't want to have to be allocating
+		 * higher-order pages when we are unable to shrink dcache.
+		 */
+		if (flags & SLAB_RECLAIM_ACCOUNT)
+			break;
+
+		/*
 		 * Large number of objects is good, but very large slabs are
 		 * currently bad for the gfp()s.
 		 */
-		if (cachep->gfporder >= slab_break_gfp_order)
+		if (gfporder >= slab_break_gfp_order)
 			break;
 
-		if ((left_over * 8) <= (PAGE_SIZE << cachep->gfporder))
-			/* Acceptable internal fragmentation */
+		/*
+		 * Acceptable internal fragmentation?
+		 */
+		if ((left_over * 8) <= (PAGE_SIZE << gfporder))
 			break;
 	}
 	return left_over;
@@ -1869,17 +1942,7 @@ kmem_cache_create (const char *name, size_t size, size_t align,
 
 	size = ALIGN(size, align);
 
-	if ((flags & SLAB_RECLAIM_ACCOUNT) && size <= PAGE_SIZE) {
-		/*
-		 * A VFS-reclaimable slab tends to have most allocations
-		 * as GFP_NOFS and we really don't want to have to be allocating
-		 * higher-order pages when we are unable to shrink dcache.
-		 */
-		cachep->gfporder = 0;
-		cache_estimate(cachep->gfporder, size, align, flags,
-			       &left_over, &cachep->num);
-	} else
-		left_over = calculate_slab_order(cachep, size, align, flags);
+	left_over = calculate_slab_order(cachep, size, align, flags);
 
 	if (!cachep->num) {
 		printk("kmem_cache_create: couldn't create cache %s.\n", name);
@@ -2554,7 +2617,7 @@ static void check_slabp(struct kmem_cache *cachep, struct slab *slabp)
 		       "slab: Internal list corruption detected in cache '%s'(%d), slabp %p(%d). Hexdump:\n",
 		       cachep->name, cachep->num, slabp, slabp->inuse);
 		for (i = 0;
-		     i < sizeof(slabp) + cachep->num * sizeof(kmem_bufctl_t);
+		     i < sizeof(*slabp) + cachep->num * sizeof(kmem_bufctl_t);
 		     i++) {
 			if ((i % 16) == 0)
 				printk("\n%03x:", i);
@@ -3494,8 +3557,7 @@ static void cache_reap(void *unused)
 		check_irq_on();
 
 		l3 = searchp->nodelists[numa_node_id()];
-		if (l3->alien)
-			drain_alien_cache(searchp, l3->alien);
+		reap_alien(searchp, l3);
 		spin_lock_irq(&l3->list_lock);
 
 		drain_array_locked(searchp, cpu_cache_get(searchp), 0,
@@ -3545,7 +3607,7 @@ static void cache_reap(void *unused)
 	}
 	check_irq_on();
 	mutex_unlock(&cache_chain_mutex);
-	drain_remote_pages();
+	next_reap_node();
 	/* Setup the next iteration */
 	schedule_delayed_work(&__get_cpu_var(reap_work), REAPTIMEOUT_CPUC);
 }
diff --git a/mm/swap.c b/mm/swap.c
index cce3dda59c5..e9ec06d845e 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -489,13 +489,34 @@ void percpu_counter_mod(struct percpu_counter *fbc, long amount)
 	if (count >= FBC_BATCH || count <= -FBC_BATCH) {
 		spin_lock(&fbc->lock);
 		fbc->count += count;
+		*pcount = 0;
 		spin_unlock(&fbc->lock);
-		count = 0;
+	} else {
+		*pcount = count;
 	}
-	*pcount = count;
 	put_cpu();
 }
 EXPORT_SYMBOL(percpu_counter_mod);
+
+/*
+ * Add up all the per-cpu counts, return the result.  This is a more accurate
+ * but much slower version of percpu_counter_read_positive()
+ */
+long percpu_counter_sum(struct percpu_counter *fbc)
+{
+	long ret;
+	int cpu;
+
+	spin_lock(&fbc->lock);
+	ret = fbc->count;
+	for_each_cpu(cpu) {
+		long *pcount = per_cpu_ptr(fbc->counters, cpu);
+		ret += *pcount;
+	}
+	spin_unlock(&fbc->lock);
+	return ret < 0 ? 0 : ret;
+}
+EXPORT_SYMBOL(percpu_counter_sum);
 #endif
 
 /*
diff --git a/mm/vmscan.c b/mm/vmscan.c
index b0af7593d01..7ccf763bb30 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1883,7 +1883,8 @@ int zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order)
 
 	if (!(gfp_mask & __GFP_WAIT) ||
 		zone->all_unreclaimable ||
-		atomic_read(&zone->reclaim_in_progress) > 0)
+		atomic_read(&zone->reclaim_in_progress) > 0 ||
+		(p->flags & PF_MEMALLOC))
 			return 0;
 
 	node_id = zone->zone_pgdat->node_id;