Merge branch 'master'

10 files changed, 67 insertions, 52 deletions

diff --git a/mm/Kconfig b/mm/Kconfig
index 4e9937ac3529..391ffc54d136 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -29,7 +29,7 @@ config FLATMEM_MANUAL
           If unsure, choose this option (Flat Memory) over any other.
 
 config DISCONTIGMEM_MANUAL
-        bool "Discontigious Memory"
+        bool "Discontiguous Memory"
         depends on ARCH_DISCONTIGMEM_ENABLE
         help
           This option provides enhanced support for discontiguous
@@ -52,7 +52,7 @@ config SPARSEMEM_MANUAL
           memory hotplug systems.  This is normal.
 
           For many other systems, this will be an alternative to
-          "Discontigious Memory".  This option provides some potential
+          "Discontiguous Memory".  This option provides some potential
           performance benefits, along with decreased code complexity,
           but it is newer, and more experimental.
 
diff --git a/mm/bootmem.c b/mm/bootmem.c
index 8ec4e4c2a179..c1330cc19783 100644
--- a/mm/bootmem.c
+++ b/mm/bootmem.c
@@ -61,17 +61,9 @@ static unsigned long __init init_bootmem_core (pg_data_t *pgdat,
 {
         bootmem_data_t *bdata = pgdat->bdata;
         unsigned long mapsize = ((end - start)+7)/8;
-        static struct pglist_data *pgdat_last;
-
-        pgdat->pgdat_next = NULL;
-        /* Add new nodes last so that bootmem always starts
-           searching in the first nodes, not the last ones */
-        if (pgdat_last)
-                pgdat_last->pgdat_next = pgdat;
-        else {
-                pgdat_list = pgdat;     
-                pgdat_last = pgdat;
-        }
+
+        pgdat->pgdat_next = pgdat_list;
+        pgdat_list = pgdat;
 
         mapsize = ALIGN(mapsize, sizeof(long));
         bdata->node_bootmem_map = phys_to_virt(mapstart << PAGE_SHIFT);
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index afa06e184d88..9033f0859aa8 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -333,8 +333,13 @@ check_range(struct mm_struct *mm, unsigned long start, unsigned long end,
                 if (prev && prev->vm_end < vma->vm_start)
                         return ERR_PTR(-EFAULT);
                 if ((flags & MPOL_MF_STRICT) && !is_vm_hugetlb_page(vma)) {
+                        unsigned long endvma = vma->vm_end;
+                        if (endvma > end)
+                                endvma = end;
+                        if (vma->vm_start > start)
+                                start = vma->vm_start;
                         err = check_pgd_range(vma->vm_mm,
-                                           vma->vm_start, vma->vm_end, nodes);
+                                           start, endvma, nodes);
                         if (err) {
                                 first = ERR_PTR(err);
                                 break;
diff --git a/mm/mmap.c b/mm/mmap.c
index 12334aecf8ad..fa11d91242e8 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -1640,7 +1640,7 @@ static void unmap_vma_list(struct mm_struct *mm, struct vm_area_struct *vma)
 /*
  * Get rid of page table information in the indicated region.
  *
- * Called with the page table lock held.
+ * Called with the mm semaphore held.
  */
 static void unmap_region(struct mm_struct *mm,
                 struct vm_area_struct *vma, struct vm_area_struct *prev,
@@ -1993,6 +1993,9 @@ int insert_vm_struct(struct mm_struct * mm, struct vm_area_struct * vma)
         __vma = find_vma_prepare(mm,vma->vm_start,&prev,&rb_link,&rb_parent);
         if (__vma && __vma->vm_start < vma->vm_end)
                 return -ENOMEM;
+        if ((vma->vm_flags & VM_ACCOUNT) &&
+             security_vm_enough_memory(vma_pages(vma)))
+                return -ENOMEM;
         vma_link(mm, vma, prev, rb_link, rb_parent);
         return 0;
 }
diff --git a/mm/mprotect.c b/mm/mprotect.c
index e9fbd013ad9a..57577f63b305 100644
--- a/mm/mprotect.c
+++ b/mm/mprotect.c
@@ -248,7 +248,8 @@ sys_mprotect(unsigned long start, size_t len, unsigned long prot)
 
                 newflags = vm_flags | (vma->vm_flags & ~(VM_READ | VM_WRITE | VM_EXEC));
 
-                if ((newflags & ~(newflags >> 4)) & 0xf) {
+                /* newflags >> 4 shift VM_MAY% in place of VM_% */
+                if ((newflags & ~(newflags >> 4)) & (VM_READ | VM_WRITE | VM_EXEC)) {
                         error = -EACCES;
                         goto out;
                 }
diff --git a/mm/mremap.c b/mm/mremap.c
index a32fed454bd7..f343fc73a8bd 100644
--- a/mm/mremap.c
+++ b/mm/mremap.c
@@ -141,10 +141,10 @@ move_one_page(struct vm_area_struct *vma, unsigned long old_addr,
                         if (dst) {
                                 pte_t pte;
                                 pte = ptep_clear_flush(vma, old_addr, src);
+
                                 /* ZERO_PAGE can be dependant on virtual addr */
-                                if (pfn_valid(pte_pfn(pte)) &&
-                                        pte_page(pte) == ZERO_PAGE(old_addr))
-                                        pte = pte_wrprotect(mk_pte(ZERO_PAGE(new_addr), new_vma->vm_page_prot));
+                                pte = move_pte(pte, new_vma->vm_page_prot,
+                                                        old_addr, new_addr);
                                 set_pte_at(mm, new_addr, dst, pte);
                         } else
                                 error = -ENOMEM;
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index c5823c395f71..ae2903339e71 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -22,6 +22,7 @@
 #include <linux/pagemap.h>
 #include <linux/bootmem.h>
 #include <linux/compiler.h>
+#include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/suspend.h>
 #include <linux/pagevec.h>
@@ -117,7 +118,7 @@ static void bad_page(const char *function, struct page *page)
         set_page_count(page, 0);
         reset_page_mapcount(page);
         page->mapping = NULL;
-        tainted |= TAINT_BAD_PAGE;
+        add_taint(TAINT_BAD_PAGE);
 }
 
 #ifndef CONFIG_HUGETLB_PAGE
diff --git a/mm/slab.c b/mm/slab.c
index 9e876d6dfad9..5cbbdfa6dd0e 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -308,12 +308,12 @@ struct kmem_list3 __initdata initkmem_list3[NUM_INIT_LISTS];
 #define SIZE_L3 (1 + MAX_NUMNODES)
 
 /*
- * This function may be completely optimized away if
+ * This function must be completely optimized away if
  * a constant is passed to it. Mostly the same as
  * what is in linux/slab.h except it returns an
  * index.
  */
-static inline int index_of(const size_t size)
+static __always_inline int index_of(const size_t size)
 {
         if (__builtin_constant_p(size)) {
                 int i = 0;
@@ -329,7 +329,8 @@ static inline int index_of(const size_t size)
                         extern void __bad_size(void);
                         __bad_size();
                 }
-        }
+        } else
+                BUG();
         return 0;
 }
 
@@ -639,7 +640,7 @@ static enum {
 
 static DEFINE_PER_CPU(struct work_struct, reap_work);
 
-static void free_block(kmem_cache_t* cachep, void** objpp, int len);
+static void free_block(kmem_cache_t* cachep, void** objpp, int len, int node);
 static void enable_cpucache (kmem_cache_t *cachep);
 static void cache_reap (void *unused);
 static int __node_shrink(kmem_cache_t *cachep, int node);
@@ -659,7 +660,7 @@ static inline kmem_cache_t *__find_general_cachep(size_t size,
         * kmem_cache_create(), or __kmalloc(), before
         * the generic caches are initialized.
         */
-        BUG_ON(csizep->cs_cachep == NULL);
+        BUG_ON(malloc_sizes[INDEX_AC].cs_cachep == NULL);
 #endif
         while (size > csizep->cs_size)
                 csizep++;
@@ -804,7 +805,7 @@ static inline void __drain_alien_cache(kmem_cache_t *cachep, struct array_cache
 
         if (ac->avail) {
                 spin_lock(&rl3->list_lock);
-                free_block(cachep, ac->entry, ac->avail);
+                free_block(cachep, ac->entry, ac->avail, node);
                 ac->avail = 0;
                 spin_unlock(&rl3->list_lock);
         }
@@ -925,7 +926,7 @@ static int __devinit cpuup_callback(struct notifier_block *nfb,
                         /* Free limit for this kmem_list3 */
                         l3->free_limit -= cachep->batchcount;
                         if (nc)
-                                free_block(cachep, nc->entry, nc->avail);
+                                free_block(cachep, nc->entry, nc->avail, node);
 
                         if (!cpus_empty(mask)) {
                                 spin_unlock(&l3->list_lock);
@@ -934,7 +935,7 @@ static int __devinit cpuup_callback(struct notifier_block *nfb,
 
                         if (l3->shared) {
                                 free_block(cachep, l3->shared->entry,
-                                                l3->shared->avail);
+                                                l3->shared->avail, node);
                                 kfree(l3->shared);
                                 l3->shared = NULL;
                         }
@@ -1882,12 +1883,13 @@ static void do_drain(void *arg)
 {
         kmem_cache_t *cachep = (kmem_cache_t*)arg;
         struct array_cache *ac;
+        int node = numa_node_id();
 
         check_irq_off();
         ac = ac_data(cachep);
-        spin_lock(&cachep->nodelists[numa_node_id()]->list_lock);
-        free_block(cachep, ac->entry, ac->avail);
-        spin_unlock(&cachep->nodelists[numa_node_id()]->list_lock);
+        spin_lock(&cachep->nodelists[node]->list_lock);
+        free_block(cachep, ac->entry, ac->avail, node);
+        spin_unlock(&cachep->nodelists[node]->list_lock);
         ac->avail = 0;
 }
 
@@ -2508,16 +2510,12 @@ cache_alloc_debugcheck_after(kmem_cache_t *cachep,
 #define cache_alloc_debugcheck_after(a,b,objp,d) (objp)
 #endif
 
-
-static inline void *__cache_alloc(kmem_cache_t *cachep, unsigned int __nocast flags)
+static inline void *____cache_alloc(kmem_cache_t *cachep, unsigned int __nocast flags)
 {
-        unsigned long save_flags;
         void* objp;
         struct array_cache *ac;
 
-        cache_alloc_debugcheck_before(cachep, flags);
-
-        local_irq_save(save_flags);
+        check_irq_off();
         ac = ac_data(cachep);
         if (likely(ac->avail)) {
                 STATS_INC_ALLOCHIT(cachep);
@@ -2527,6 +2525,18 @@ static inline void *__cache_alloc(kmem_cache_t *cachep, unsigned int __nocast fl
                 STATS_INC_ALLOCMISS(cachep);
                 objp = cache_alloc_refill(cachep, flags);
         }
+        return objp;
+}
+
+static inline void *__cache_alloc(kmem_cache_t *cachep, unsigned int __nocast flags)
+{
+        unsigned long save_flags;
+        void* objp;
+
+        cache_alloc_debugcheck_before(cachep, flags);
+
+        local_irq_save(save_flags);
+        objp = ____cache_alloc(cachep, flags);
         local_irq_restore(save_flags);
         objp = cache_alloc_debugcheck_after(cachep, flags, objp,
                                         __builtin_return_address(0));
@@ -2608,7 +2618,7 @@ done:
 /*
  * Caller needs to acquire correct kmem_list's list_lock
  */
-static void free_block(kmem_cache_t *cachep, void **objpp, int nr_objects)
+static void free_block(kmem_cache_t *cachep, void **objpp, int nr_objects, int node)
 {
         int i;
         struct kmem_list3 *l3;
@@ -2617,14 +2627,12 @@ static void free_block(kmem_cache_t *cachep, void **objpp, int nr_objects)
                 void *objp = objpp[i];
                 struct slab *slabp;
                 unsigned int objnr;
-                int nodeid = 0;
 
                 slabp = GET_PAGE_SLAB(virt_to_page(objp));
-                nodeid = slabp->nodeid;
-                l3 = cachep->nodelists[nodeid];
+                l3 = cachep->nodelists[node];
                 list_del(&slabp->list);
                 objnr = (objp - slabp->s_mem) / cachep->objsize;
-                check_spinlock_acquired_node(cachep, nodeid);
+                check_spinlock_acquired_node(cachep, node);
                 check_slabp(cachep, slabp);
 
 
@@ -2664,13 +2672,14 @@ static void cache_flusharray(kmem_cache_t *cachep, struct array_cache *ac)
 {
         int batchcount;
         struct kmem_list3 *l3;
+        int node = numa_node_id();
 
         batchcount = ac->batchcount;
 #if DEBUG
         BUG_ON(!batchcount || batchcount > ac->avail);
 #endif
         check_irq_off();
-        l3 = cachep->nodelists[numa_node_id()];
+        l3 = cachep->nodelists[node];
         spin_lock(&l3->list_lock);
         if (l3->shared) {
                 struct array_cache *shared_array = l3->shared;
@@ -2686,7 +2695,7 @@ static void cache_flusharray(kmem_cache_t *cachep, struct array_cache *ac)
                 }
         }
 
-        free_block(cachep, ac->entry, batchcount);
+        free_block(cachep, ac->entry, batchcount, node);
 free_done:
 #if STATS
         {
@@ -2751,7 +2760,7 @@ static inline void __cache_free(kmem_cache_t *cachep, void *objp)
                         } else {
                                 spin_lock(&(cachep->nodelists[nodeid])->
                                                 list_lock);
-                                free_block(cachep, &objp, 1);
+                                free_block(cachep, &objp, 1, nodeid);
                                 spin_unlock(&(cachep->nodelists[nodeid])->
                                                 list_lock);
                         }
@@ -2844,7 +2853,7 @@ void *kmem_cache_alloc_node(kmem_cache_t *cachep, unsigned int __nocast flags, i
         unsigned long save_flags;
         void *ptr;
 
-        if (nodeid == numa_node_id() || nodeid == -1)
+        if (nodeid == -1)
                 return __cache_alloc(cachep, flags);
 
         if (unlikely(!cachep->nodelists[nodeid])) {
@@ -2855,7 +2864,10 @@ void *kmem_cache_alloc_node(kmem_cache_t *cachep, unsigned int __nocast flags, i
 
         cache_alloc_debugcheck_before(cachep, flags);
         local_irq_save(save_flags);
-        ptr = __cache_alloc_node(cachep, flags, nodeid);
+        if (nodeid == numa_node_id())
+                ptr = ____cache_alloc(cachep, flags);
+        else
+                ptr = __cache_alloc_node(cachep, flags, nodeid);
         local_irq_restore(save_flags);
         ptr = cache_alloc_debugcheck_after(cachep, flags, ptr, __builtin_return_address(0));
 
@@ -3079,7 +3091,7 @@ static int alloc_kmemlist(kmem_cache_t *cachep)
 
                         if ((nc = cachep->nodelists[node]->shared))
                                 free_block(cachep, nc->entry,
-                                                        nc->avail);
+                                                        nc->avail, node);
 
                         l3->shared = new;
                         if (!cachep->nodelists[node]->alien) {
@@ -3160,7 +3172,7 @@ static int do_tune_cpucache(kmem_cache_t *cachep, int limit, int batchcount,
                 if (!ccold)
                         continue;
                 spin_lock_irq(&cachep->nodelists[cpu_to_node(i)]->list_lock);
-                free_block(cachep, ccold->entry, ccold->avail);
+                free_block(cachep, ccold->entry, ccold->avail, cpu_to_node(i));
                 spin_unlock_irq(&cachep->nodelists[cpu_to_node(i)]->list_lock);
                 kfree(ccold);
         }
@@ -3240,7 +3252,7 @@ static void drain_array_locked(kmem_cache_t *cachep,
                 if (tofree > ac->avail) {
                         tofree = (ac->avail+1)/2;
                 }
-                free_block(cachep, ac->entry, tofree);
+                free_block(cachep, ac->entry, tofree, node);
                 ac->avail -= tofree;
                 memmove(ac->entry, &(ac->entry[tofree]),
                                         sizeof(void*)*ac->avail);
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 0184f510aace..1dcaeda039f4 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -1381,6 +1381,7 @@ asmlinkage long sys_swapon(const char __user * specialfile, int swap_flags)
                 error = bd_claim(bdev, sys_swapon);
                 if (error < 0) {
                         bdev = NULL;
+                        error = -EINVAL;
                         goto bad_swap;
                 }
                 p->old_block_size = block_size(bdev);
diff --git a/mm/vmscan.c b/mm/vmscan.c
index a740778f688d..0ea71e887bb6 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1258,9 +1258,9 @@ void wakeup_kswapd(struct zone *zone, int order)
                 pgdat->kswapd_max_order = order;
         if (!cpuset_zone_allowed(zone, __GFP_HARDWALL))
                 return;
-        if (!waitqueue_active(&zone->zone_pgdat->kswapd_wait))
+        if (!waitqueue_active(&pgdat->kswapd_wait))
                 return;
-        wake_up_interruptible(&zone->zone_pgdat->kswapd_wait);
+        wake_up_interruptible(&pgdat->kswapd_wait);
 }
 
 #ifdef CONFIG_PM