Merge ../linux-2.6

12 files changed, 170 insertions, 86 deletions

diff --git a/mm/filemap.c b/mm/filemap.c
index 3ef20739e725..fd57442186cb 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -697,6 +697,38 @@ unsigned find_get_pages(struct address_space *mapping, pgoff_t start,
         return ret;
 }
 
+/**
+ * find_get_pages_contig - gang contiguous pagecache lookup
+ * @mapping:    The address_space to search
+ * @index:      The starting page index
+ * @nr_pages:   The maximum number of pages
+ * @pages:      Where the resulting pages are placed
+ *
+ * find_get_pages_contig() works exactly like find_get_pages(), except
+ * that the returned number of pages are guaranteed to be contiguous.
+ *
+ * find_get_pages_contig() returns the number of pages which were found.
+ */
+unsigned find_get_pages_contig(struct address_space *mapping, pgoff_t index,
+                               unsigned int nr_pages, struct page **pages)
+{
+        unsigned int i;
+        unsigned int ret;
+
+        read_lock_irq(&mapping->tree_lock);
+        ret = radix_tree_gang_lookup(&mapping->page_tree,
+                                (void **)pages, index, nr_pages);
+        for (i = 0; i < ret; i++) {
+                if (pages[i]->mapping == NULL || pages[i]->index != index)
+                        break;
+
+                page_cache_get(pages[i]);
+                index++;
+        }
+        read_unlock_irq(&mapping->tree_lock);
+        return i;
+}
+
 /*
  * Like find_get_pages, except we only return pages which are tagged with
  * `tag'.   We update *index to index the next page for the traversal.
diff --git a/mm/madvise.c b/mm/madvise.c
index af3d573b0141..4e196155a0c3 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -168,6 +168,9 @@ static long madvise_remove(struct vm_area_struct *vma,
                         return -EINVAL;
         }
 
+        if ((vma->vm_flags & (VM_SHARED|VM_WRITE)) != (VM_SHARED|VM_WRITE))
+                return -EACCES;
+
         mapping = vma->vm_file->f_mapping;
 
         offset = (loff_t)(start - vma->vm_start)
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 1fe76d963ac2..70df5c0d957e 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -69,12 +69,16 @@ int __add_pages(struct zone *zone, unsigned long phys_start_pfn,
         for (i = 0; i < nr_pages; i += PAGES_PER_SECTION) {
                 err = __add_section(zone, phys_start_pfn + i);
 
-                if (err)
+                /* We want to keep adding the rest of the
+                 * sections if the first ones already exist
+                 */
+                if (err && (err != -EEXIST))
                         break;
         }
 
         return err;
 }
+EXPORT_SYMBOL_GPL(__add_pages);
 
 static void grow_zone_span(struct zone *zone,
                 unsigned long start_pfn, unsigned long end_pfn)
@@ -87,8 +91,8 @@ static void grow_zone_span(struct zone *zone,
         if (start_pfn < zone->zone_start_pfn)
                 zone->zone_start_pfn = start_pfn;
 
-        if (end_pfn > old_zone_end_pfn)
-                zone->spanned_pages = end_pfn - zone->zone_start_pfn;
+        zone->spanned_pages = max(old_zone_end_pfn, end_pfn) -
+                                zone->zone_start_pfn;
 
         zone_span_writeunlock(zone);
 }
@@ -102,8 +106,8 @@ static void grow_pgdat_span(struct pglist_data *pgdat,
         if (start_pfn < pgdat->node_start_pfn)
                 pgdat->node_start_pfn = start_pfn;
 
-        if (end_pfn > old_pgdat_end_pfn)
-                pgdat->node_spanned_pages = end_pfn - pgdat->node_start_pfn;
+        pgdat->node_spanned_pages = max(old_pgdat_end_pfn, end_pfn) -
+                                        pgdat->node_start_pfn;
 }
 
 int online_pages(unsigned long pfn, unsigned long nr_pages)
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index dec8249e972d..8778f58880c4 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -1761,7 +1761,6 @@ static void gather_stats(struct page *page, void *private, int pte_dirty)
                 md->mapcount_max = count;
 
         md->node[page_to_nid(page)]++;
-        cond_resched();
 }
 
 #ifdef CONFIG_HUGETLB_PAGE
diff --git a/mm/migrate.c b/mm/migrate.c
index d444229f2599..1c25040693d2 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -439,6 +439,17 @@ redo:
                         goto unlock_both;
                 }
 
+                /* Make sure the dirty bit is up to date */
+                if (try_to_unmap(page, 1) == SWAP_FAIL) {
+                        rc = -EPERM;
+                        goto unlock_both;
+                }
+
+                if (page_mapcount(page)) {
+                        rc = -EAGAIN;
+                        goto unlock_both;
+                }
+
                 /*
                  * Default handling if a filesystem does not provide
                  * a migration function. We can only migrate clean
diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index 78747afad6b0..042e6436c3ee 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -46,15 +46,25 @@
 unsigned long badness(struct task_struct *p, unsigned long uptime)
 {
         unsigned long points, cpu_time, run_time, s;
-        struct list_head *tsk;
+        struct mm_struct *mm;
+        struct task_struct *child;
 
-        if (!p->mm)
+        task_lock(p);
+        mm = p->mm;
+        if (!mm) {
+                task_unlock(p);
                 return 0;
+        }
 
         /*
          * The memory size of the process is the basis for the badness.
          */
-        points = p->mm->total_vm;
+        points = mm->total_vm;
+
+        /*
+         * After this unlock we can no longer dereference local variable `mm'
+         */
+        task_unlock(p);
 
         /*
          * Processes which fork a lot of child processes are likely
@@ -64,11 +74,11 @@ unsigned long badness(struct task_struct *p, unsigned long uptime)
          * child is eating the vast majority of memory, adding only half
          * to the parents will make the child our kill candidate of choice.
          */
-        list_for_each(tsk, &p->children) {
-                struct task_struct *chld;
-                chld = list_entry(tsk, struct task_struct, sibling);
-                if (chld->mm != p->mm && chld->mm)
-                        points += chld->mm->total_vm/2 + 1;
+        list_for_each_entry(child, &p->children, sibling) {
+                task_lock(child);
+                if (child->mm != mm && child->mm)
+                        points += child->mm->total_vm/2 + 1;
+                task_unlock(child);
         }
 
         /*
@@ -244,17 +254,24 @@ static void __oom_kill_task(task_t *p, const char *message)
         force_sig(SIGKILL, p);
 }
 
-static struct mm_struct *oom_kill_task(task_t *p, const char *message)
+static int oom_kill_task(task_t *p, const char *message)
 {
-        struct mm_struct *mm = get_task_mm(p);
+        struct mm_struct *mm;
         task_t * g, * q;
 
-        if (!mm)
-                return NULL;
-        if (mm == &init_mm) {
-                mmput(mm);
-                return NULL;
-        }
+        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 || mm == &init_mm)
+                return 1;
 
         __oom_kill_task(p, message);
         /*
@@ -266,13 +283,12 @@ static struct mm_struct *oom_kill_task(task_t *p, const char *message)
                         __oom_kill_task(q, message);
         while_each_thread(g, q);
 
-        return mm;
+        return 0;
 }
 
-static struct mm_struct *oom_kill_process(struct task_struct *p,
-                                unsigned long points, const char *message)
+static int oom_kill_process(struct task_struct *p, unsigned long points,
+                const char *message)
 {
-        struct mm_struct *mm;
         struct task_struct *c;
         struct list_head *tsk;
 
@@ -283,9 +299,8 @@ static struct mm_struct *oom_kill_process(struct task_struct *p,
                 c = list_entry(tsk, struct task_struct, sibling);
                 if (c->mm == p->mm)
                         continue;
-                mm = oom_kill_task(c, message);
-                if (mm)
-                        return mm;
+                if (!oom_kill_task(c, message))
+                        return 0;
         }
         return oom_kill_task(p, message);
 }
@@ -300,7 +315,6 @@ static struct mm_struct *oom_kill_process(struct task_struct *p,
  */
 void out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask, int order)
 {
-        struct mm_struct *mm = NULL;
         task_t *p;
         unsigned long points = 0;
 
@@ -320,12 +334,12 @@ void out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask, int order)
          */
         switch (constrained_alloc(zonelist, gfp_mask)) {
         case CONSTRAINT_MEMORY_POLICY:
-                mm = oom_kill_process(current, points,
+                oom_kill_process(current, points,
                                 "No available memory (MPOL_BIND)");
                 break;
 
         case CONSTRAINT_CPUSET:
-                mm = oom_kill_process(current, points,
+                oom_kill_process(current, points,
                                 "No available memory in cpuset");
                 break;
 
@@ -347,8 +361,7 @@ retry:
                         panic("Out of memory and no killable processes...\n");
                 }
 
-                mm = oom_kill_process(p, points, "Out of memory");
-                if (!mm)
+                if (oom_kill_process(p, points, "Out of memory"))
                         goto retry;
 
                 break;
@@ -357,8 +370,6 @@ retry:
 out:
         read_unlock(&tasklist_lock);
         cpuset_unlock();
-        if (mm)
-                mmput(mm);
 
         /*
          * Give "p" a good chance of killing itself before we
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 97d6827c7d66..253a450c400d 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -39,6 +39,7 @@
 #include <linux/mempolicy.h>
 
 #include <asm/tlbflush.h>
+#include <asm/div64.h>
 #include "internal.h"
 
 /*
@@ -232,11 +233,13 @@ static inline void prep_zero_page(struct page *page, int order, gfp_t gfp_flags)
  * zone->lock is already acquired when we use these.
  * So, we don't need atomic page->flags operations here.
  */
-static inline unsigned long page_order(struct page *page) {
+static inline unsigned long page_order(struct page *page)
+{
         return page_private(page);
 }
 
-static inline void set_page_order(struct page *page, int order) {
+static inline void set_page_order(struct page *page, int order)
+{
         set_page_private(page, order);
         __SetPageBuddy(page);
 }
@@ -299,9 +302,9 @@ static inline int page_is_buddy(struct page *page, int order)
 
         if (PageBuddy(page) && page_order(page) == order) {
                 BUG_ON(page_count(page) != 0);
-               return 1;
+                return 1;
         }
-       return 0;
+        return 0;
 }
 
 /*
@@ -948,7 +951,7 @@ restart:
                 goto got_pg;
 
         do {
-                if (cpuset_zone_allowed(*z, gfp_mask))
+                if (cpuset_zone_allowed(*z, gfp_mask|__GFP_HARDWALL))
                         wakeup_kswapd(*z, order);
         } while (*(++z));
 
@@ -967,7 +970,8 @@ restart:
                 alloc_flags |= ALLOC_HARDER;
         if (gfp_mask & __GFP_HIGH)
                 alloc_flags |= ALLOC_HIGH;
-        alloc_flags |= ALLOC_CPUSET;
+        if (wait)
+                alloc_flags |= ALLOC_CPUSET;
 
         /*
          * Go through the zonelist again. Let __GFP_HIGH and allocations
@@ -1960,7 +1964,7 @@ static inline void free_zone_pagesets(int cpu)
         }
 }
 
-static int __cpuinit pageset_cpuup_callback(struct notifier_block *nfb,
+static int pageset_cpuup_callback(struct notifier_block *nfb,
                 unsigned long action,
                 void *hcpu)
 {
@@ -2121,14 +2125,22 @@ static void __init alloc_node_mem_map(struct pglist_data *pgdat)
 #ifdef CONFIG_FLAT_NODE_MEM_MAP
         /* ia64 gets its own node_mem_map, before this, without bootmem */
         if (!pgdat->node_mem_map) {
-                unsigned long size;
+                unsigned long size, start, end;
                 struct page *map;
 
-                size = (pgdat->node_spanned_pages + 1) * sizeof(struct page);
+                /*
+                 * The zone's endpoints aren't required to be MAX_ORDER
+                 * aligned but the node_mem_map endpoints must be in order
+                 * for the buddy allocator to function correctly.
+                 */
+                start = pgdat->node_start_pfn & ~(MAX_ORDER_NR_PAGES - 1);
+                end = pgdat->node_start_pfn + pgdat->node_spanned_pages;
+                end = ALIGN(end, MAX_ORDER_NR_PAGES);
+                size =  (end - start) * sizeof(struct page);
                 map = alloc_remap(pgdat->node_id, size);
                 if (!map)
                         map = alloc_bootmem_node(pgdat, size);
-                pgdat->node_mem_map = map;
+                pgdat->node_mem_map = map + (pgdat->node_start_pfn - start);
         }
 #ifdef CONFIG_FLATMEM
         /*
@@ -2564,9 +2576,11 @@ void setup_per_zone_pages_min(void)
         }
 
         for_each_zone(zone) {
-                unsigned long tmp;
+                u64 tmp;
+
                 spin_lock_irqsave(&zone->lru_lock, flags);
-                tmp = (pages_min * zone->present_pages) / lowmem_pages;
+                tmp = (u64)pages_min * zone->present_pages;
+                do_div(tmp, lowmem_pages);
                 if (is_highmem(zone)) {
                         /*
                          * __GFP_HIGH and PF_MEMALLOC allocations usually don't
@@ -2593,8 +2607,8 @@ void setup_per_zone_pages_min(void)
                         zone->pages_min = tmp;
                 }
 
-                zone->pages_low   = zone->pages_min + tmp / 4;
-                zone->pages_high  = zone->pages_min + tmp / 2;
+                zone->pages_low   = zone->pages_min + (tmp >> 2);
+                zone->pages_high  = zone->pages_min + (tmp >> 1);
                 spin_unlock_irqrestore(&zone->lru_lock, flags);
         }
 
diff --git a/mm/shmem.c b/mm/shmem.c
index 37eaf42ed2c6..4c5e68e4e9ae 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -46,6 +46,8 @@
 #include <linux/mempolicy.h>
 #include <linux/namei.h>
 #include <linux/ctype.h>
+#include <linux/migrate.h>
+
 #include <asm/uaccess.h>
 #include <asm/div64.h>
 #include <asm/pgtable.h>
@@ -2173,6 +2175,7 @@ static struct address_space_operations shmem_aops = {
         .prepare_write  = shmem_prepare_write,
         .commit_write   = simple_commit_write,
 #endif
+        .migratepage    = migrate_page,
 };
 
 static struct file_operations shmem_file_operations = {
diff --git a/mm/slab.c b/mm/slab.c
index e6ef9bd52335..f1b644eb39d8 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -207,11 +207,6 @@ typedef unsigned int kmem_bufctl_t;
 #define BUFCTL_ACTIVE   (((kmem_bufctl_t)(~0U))-2)
 #define SLAB_LIMIT      (((kmem_bufctl_t)(~0U))-3)
 
-/* Max number of objs-per-slab for caches which use off-slab slabs.
- * Needed to avoid a possible looping condition in cache_grow().
- */
-static unsigned long offslab_limit;
-
 /*
  * struct slab
  *
@@ -700,6 +695,14 @@ static enum {
         FULL
 } g_cpucache_up;
 
+/*
+ * used by boot code to determine if it can use slab based allocator
+ */
+int slab_is_available(void)
+{
+        return g_cpucache_up == FULL;
+}
+
 static DEFINE_PER_CPU(struct work_struct, reap_work);
 
 static void free_block(struct kmem_cache *cachep, void **objpp, int len,
@@ -979,7 +982,8 @@ static void __drain_alien_cache(struct kmem_cache *cachep,
                  * That way we could avoid the overhead of putting the objects
                  * into the free lists and getting them back later.
                  */
-                transfer_objects(rl3->shared, ac, ac->limit);
+                if (rl3->shared)
+                        transfer_objects(rl3->shared, ac, ac->limit);
 
                 free_block(cachep, ac->entry, ac->avail, node);
                 ac->avail = 0;
@@ -1036,7 +1040,7 @@ static inline void free_alien_cache(struct array_cache **ac_ptr)
 
 #endif
 
-static int __devinit cpuup_callback(struct notifier_block *nfb,
+static int cpuup_callback(struct notifier_block *nfb,
                                     unsigned long action, void *hcpu)
 {
         long cpu = (long)hcpu;
@@ -1347,12 +1351,6 @@ void __init kmem_cache_init(void)
                                         NULL, NULL);
                 }
 
-                /* Inc off-slab bufctl limit until the ceiling is hit. */
-                if (!(OFF_SLAB(sizes->cs_cachep))) {
-                        offslab_limit = sizes->cs_size - sizeof(struct slab);
-                        offslab_limit /= sizeof(kmem_bufctl_t);
-                }
-
                 sizes->cs_dmacachep = kmem_cache_create(names->name_dma,
                                         sizes->cs_size,
                                         ARCH_KMALLOC_MINALIGN,
@@ -1771,6 +1769,7 @@ static void set_up_list3s(struct kmem_cache *cachep, int index)
 static size_t calculate_slab_order(struct kmem_cache *cachep,
                         size_t size, size_t align, unsigned long flags)
 {
+        unsigned long offslab_limit;
         size_t left_over = 0;
         int gfporder;
 
@@ -1782,9 +1781,18 @@ static size_t calculate_slab_order(struct kmem_cache *cachep,
                 if (!num)
                         continue;
 
-                /* More than offslab_limit objects will cause problems */
-                if ((flags & CFLGS_OFF_SLAB) && num > offslab_limit)
-                        break;
+                if (flags & CFLGS_OFF_SLAB) {
+                        /*
+                         * Max number of objs-per-slab for caches which
+                         * use off-slab slabs. Needed to avoid a possible
+                         * looping condition in cache_grow().
+                         */
+                        offslab_limit = size - sizeof(struct slab);
+                        offslab_limit /= sizeof(kmem_bufctl_t);
+
+                        if (num > offslab_limit)
+                                break;
+                }
 
                 /* Found something acceptable - save it away */
                 cachep->num = num;
@@ -2191,11 +2199,14 @@ static void drain_cpu_caches(struct kmem_cache *cachep)
         check_irq_on();
         for_each_online_node(node) {
                 l3 = cachep->nodelists[node];
-                if (l3) {
+                if (l3 && l3->alien)
+                        drain_alien_cache(cachep, l3->alien);
+        }
+
+        for_each_online_node(node) {
+                l3 = cachep->nodelists[node];
+                if (l3)
                         drain_array(cachep, l3, l3->shared, 1, node);
-                        if (l3->alien)
-                                drain_alien_cache(cachep, l3->alien);
-                }
         }
 }
 
diff --git a/mm/slob.c b/mm/slob.c
index 9bcc7e2cabfd..a68255ba4553 100644
--- a/mm/slob.c
+++ b/mm/slob.c
@@ -354,9 +354,7 @@ void *__alloc_percpu(size_t size)
         if (!pdata)
                 return NULL;
 
-        for (i = 0; i < NR_CPUS; i++) {
-                if (!cpu_possible(i))
-                        continue;
+        for_each_possible_cpu(i) {
                 pdata->ptrs[i] = kmalloc(size, GFP_KERNEL);
                 if (!pdata->ptrs[i])
                         goto unwind_oom;
@@ -383,11 +381,9 @@ free_percpu(const void *objp)
         int i;
         struct percpu_data *p = (struct percpu_data *) (~(unsigned long) objp);
 
-        for (i = 0; i < NR_CPUS; i++) {
-                if (!cpu_possible(i))
-                        continue;
+        for_each_possible_cpu(i)
                 kfree(p->ptrs[i]);
-        }
+
         kfree(p);
 }
 EXPORT_SYMBOL(free_percpu);
diff --git a/mm/sparse.c b/mm/sparse.c
index 0a51f36ba3a1..100040c0dfb6 100644
--- a/mm/sparse.c
+++ b/mm/sparse.c
@@ -32,7 +32,10 @@ static struct mem_section *sparse_index_alloc(int nid)
         unsigned long array_size = SECTIONS_PER_ROOT *
                                    sizeof(struct mem_section);
 
-        section = alloc_bootmem_node(NODE_DATA(nid), array_size);
+        if (slab_is_available())
+                section = kmalloc_node(array_size, GFP_KERNEL, nid);
+        else
+                section = alloc_bootmem_node(NODE_DATA(nid), array_size);
 
         if (section)
                 memset(section, 0, array_size);
@@ -84,11 +87,8 @@ int __section_nr(struct mem_section* ms)
         unsigned long root_nr;
         struct mem_section* root;
 
-        for (root_nr = 0;
-             root_nr < NR_MEM_SECTIONS;
-             root_nr += SECTIONS_PER_ROOT) {
-                root = __nr_to_section(root_nr);
-
+        for (root_nr = 0; root_nr < NR_SECTION_ROOTS; root_nr++) {
+                root = __nr_to_section(root_nr * SECTIONS_PER_ROOT);
                 if (!root)
                         continue;
 
@@ -281,9 +281,9 @@ int sparse_add_one_section(struct zone *zone, unsigned long start_pfn,
 
         ret = sparse_init_one_section(ms, section_nr, memmap);
 
-        if (ret <= 0)
-                __kfree_section_memmap(memmap, nr_pages);
 out:
         pgdat_resize_unlock(pgdat, &flags);
+        if (ret <= 0)
+                __kfree_section_memmap(memmap, nr_pages);
         return ret;
 }
diff --git a/mm/vmscan.c b/mm/vmscan.c
index acdf001d6941..4649a63a8cb6 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1328,7 +1328,7 @@ repeat:
    not required for correctness.  So if the last cpu in a node goes
    away, we get changed to run anywhere: as the first one comes back,
    restore their cpu bindings. */
-static int __devinit cpu_callback(struct notifier_block *nfb,
+static int cpu_callback(struct notifier_block *nfb,
                                   unsigned long action, void *hcpu)
 {
         pg_data_t *pgdat;