Merge branch 'master'

11 files changed, 112 insertions, 65 deletions

diff --git a/mm/bootmem.c b/mm/bootmem.c
index c1330cc19783..a58699b6579e 100644
--- a/mm/bootmem.c
+++ b/mm/bootmem.c
@@ -154,10 +154,10 @@ static void __init free_bootmem_core(bootmem_data_t *bdata, unsigned long addr,
  */
 static void * __init
 __alloc_bootmem_core(struct bootmem_data *bdata, unsigned long size,
-                unsigned long align, unsigned long goal)
+              unsigned long align, unsigned long goal, unsigned long limit)
 {
         unsigned long offset, remaining_size, areasize, preferred;
-        unsigned long i, start = 0, incr, eidx;
+        unsigned long i, start = 0, incr, eidx, end_pfn = bdata->node_low_pfn;
         void *ret;
 
         if(!size) {
@@ -166,7 +166,14 @@ __alloc_bootmem_core(struct bootmem_data *bdata, unsigned long size,
         }
         BUG_ON(align & (align-1));
 
-        eidx = bdata->node_low_pfn - (bdata->node_boot_start >> PAGE_SHIFT);
+        if (limit && bdata->node_boot_start >= limit)
+                return NULL;
+
+        limit >>=PAGE_SHIFT;
+        if (limit && end_pfn > limit)
+                end_pfn = limit;
+
+        eidx = end_pfn - (bdata->node_boot_start >> PAGE_SHIFT);
         offset = 0;
         if (align &&
             (bdata->node_boot_start & (align - 1UL)) != 0)
@@ -178,11 +185,12 @@ __alloc_bootmem_core(struct bootmem_data *bdata, unsigned long size,
          * first, then we try to allocate lower pages.
          */
         if (goal && (goal >= bdata->node_boot_start) && 
-            ((goal >> PAGE_SHIFT) < bdata->node_low_pfn)) {
+            ((goal >> PAGE_SHIFT) < end_pfn)) {
                 preferred = goal - bdata->node_boot_start;
 
                 if (bdata->last_success >= preferred)
-                        preferred = bdata->last_success;
+                        if (!limit || (limit && limit > bdata->last_success))
+                                preferred = bdata->last_success;
         } else
                 preferred = 0;
 
@@ -382,14 +390,15 @@ unsigned long __init free_all_bootmem (void)
         return(free_all_bootmem_core(NODE_DATA(0)));
 }
 
-void * __init __alloc_bootmem (unsigned long size, unsigned long align, unsigned long goal)
+void * __init __alloc_bootmem_limit (unsigned long size, unsigned long align, unsigned long goal,
+                                unsigned long limit)
 {
         pg_data_t *pgdat = pgdat_list;
         void *ptr;
 
         for_each_pgdat(pgdat)
                 if ((ptr = __alloc_bootmem_core(pgdat->bdata, size,
-                                                align, goal)))
+                                                 align, goal, limit)))
                         return(ptr);
 
         /*
@@ -400,14 +409,16 @@ void * __init __alloc_bootmem (unsigned long size, unsigned long align, unsigned
         return NULL;
 }
 
-void * __init __alloc_bootmem_node (pg_data_t *pgdat, unsigned long size, unsigned long align, unsigned long goal)
+
+void * __init __alloc_bootmem_node_limit (pg_data_t *pgdat, unsigned long size, unsigned long align,
+                                     unsigned long goal, unsigned long limit)
 {
         void *ptr;
 
-        ptr = __alloc_bootmem_core(pgdat->bdata, size, align, goal);
+        ptr = __alloc_bootmem_core(pgdat->bdata, size, align, goal, limit);
         if (ptr)
                 return (ptr);
 
-        return __alloc_bootmem(size, align, goal);
+        return __alloc_bootmem_limit(size, align, goal, limit);
 }
 
diff --git a/mm/filemap.c b/mm/filemap.c
index b5346576e58d..1c31b2fd2ca5 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -377,7 +377,7 @@ int filemap_write_and_wait_range(struct address_space *mapping,
  * This function does not add the page to the LRU.  The caller must do that.
  */
 int add_to_page_cache(struct page *page, struct address_space *mapping,
-                pgoff_t offset, int gfp_mask)
+                pgoff_t offset, gfp_t gfp_mask)
 {
         int error = radix_tree_preload(gfp_mask & ~__GFP_HIGHMEM);
 
@@ -401,7 +401,7 @@ int add_to_page_cache(struct page *page, struct address_space *mapping,
 EXPORT_SYMBOL(add_to_page_cache);
 
 int add_to_page_cache_lru(struct page *page, struct address_space *mapping,
-                                pgoff_t offset, int gfp_mask)
+                                pgoff_t offset, gfp_t gfp_mask)
 {
         int ret = add_to_page_cache(page, mapping, offset, gfp_mask);
         if (ret == 0)
@@ -591,7 +591,7 @@ EXPORT_SYMBOL(find_lock_page);
  * memory exhaustion.
  */
 struct page *find_or_create_page(struct address_space *mapping,
-                unsigned long index, unsigned int gfp_mask)
+                unsigned long index, gfp_t gfp_mask)
 {
         struct page *page, *cached_page = NULL;
         int err;
@@ -683,7 +683,7 @@ struct page *
 grab_cache_page_nowait(struct address_space *mapping, unsigned long index)
 {
         struct page *page = find_get_page(mapping, index);
-        unsigned int gfp_mask;
+        gfp_t gfp_mask;
 
         if (page) {
                 if (!TestSetPageLocked(page))
diff --git a/mm/highmem.c b/mm/highmem.c
index 90e1861e2da0..ce2e7e8bbfa7 100644
--- a/mm/highmem.c
+++ b/mm/highmem.c
@@ -30,11 +30,9 @@
 
 static mempool_t *page_pool, *isa_page_pool;
 
-static void *page_pool_alloc(gfp_t gfp_mask, void *data)
+static void *page_pool_alloc_isa(gfp_t gfp_mask, void *data)
 {
-        unsigned int gfp = gfp_mask | (unsigned int) (long) data;
-
-        return alloc_page(gfp);
+        return alloc_page(gfp_mask | GFP_DMA);
 }
 
 static void page_pool_free(void *page, void *data)
@@ -51,6 +49,12 @@ static void page_pool_free(void *page, void *data)
  *  n means that there are (n-1) current users of it.
  */
 #ifdef CONFIG_HIGHMEM
+
+static void *page_pool_alloc(gfp_t gfp_mask, void *data)
+{
+        return alloc_page(gfp_mask);
+}
+
 static int pkmap_count[LAST_PKMAP];
 static unsigned int last_pkmap_nr;
 static  __cacheline_aligned_in_smp DEFINE_SPINLOCK(kmap_lock);
@@ -267,7 +271,7 @@ int init_emergency_isa_pool(void)
         if (isa_page_pool)
                 return 0;
 
-        isa_page_pool = mempool_create(ISA_POOL_SIZE, page_pool_alloc, page_pool_free, (void *) __GFP_DMA);
+        isa_page_pool = mempool_create(ISA_POOL_SIZE, page_pool_alloc_isa, page_pool_free, NULL);
         if (!isa_page_pool)
                 BUG();
 
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 901ac523a1c3..61d380678030 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -274,21 +274,22 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src,
 {
         pte_t *src_pte, *dst_pte, entry;
         struct page *ptepage;
-        unsigned long addr = vma->vm_start;
-        unsigned long end = vma->vm_end;
+        unsigned long addr;
 
-        while (addr < end) {
+        for (addr = vma->vm_start; addr < vma->vm_end; addr += HPAGE_SIZE) {
                 dst_pte = huge_pte_alloc(dst, addr);
                 if (!dst_pte)
                         goto nomem;
+                spin_lock(&src->page_table_lock);
                 src_pte = huge_pte_offset(src, addr);
-                BUG_ON(!src_pte || pte_none(*src_pte)); /* prefaulted */
-                entry = *src_pte;
-                ptepage = pte_page(entry);
-                get_page(ptepage);
-                add_mm_counter(dst, rss, HPAGE_SIZE / PAGE_SIZE);
-                set_huge_pte_at(dst, addr, dst_pte, entry);
-                addr += HPAGE_SIZE;
+                if (src_pte && !pte_none(*src_pte)) {
+                        entry = *src_pte;
+                        ptepage = pte_page(entry);
+                        get_page(ptepage);
+                        add_mm_counter(dst, rss, HPAGE_SIZE / PAGE_SIZE);
+                        set_huge_pte_at(dst, addr, dst_pte, entry);
+                }
+                spin_unlock(&src->page_table_lock);
         }
         return 0;
 
@@ -323,8 +324,8 @@ void unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start,
 
                 page = pte_page(pte);
                 put_page(page);
+                add_mm_counter(mm, rss,  - (HPAGE_SIZE / PAGE_SIZE));
         }
-        add_mm_counter(mm, rss,  -((end - start) >> PAGE_SHIFT));
         flush_tlb_range(vma, start, end);
 }
 
@@ -393,6 +394,28 @@ out:
         return ret;
 }
 
+/*
+ * On ia64 at least, it is possible to receive a hugetlb fault from a
+ * stale zero entry left in the TLB from earlier hardware prefetching.
+ * Low-level arch code should already have flushed the stale entry as
+ * part of its fault handling, but we do need to accept this minor fault
+ * and return successfully.  Whereas the "normal" case is that this is
+ * an access to a hugetlb page which has been truncated off since mmap.
+ */
+int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
+                        unsigned long address, int write_access)
+{
+        int ret = VM_FAULT_SIGBUS;
+        pte_t *pte;
+
+        spin_lock(&mm->page_table_lock);
+        pte = huge_pte_offset(mm, address);
+        if (pte && !pte_none(*pte))
+                ret = VM_FAULT_MINOR;
+        spin_unlock(&mm->page_table_lock);
+        return ret;
+}
+
 int follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma,
                         struct page **pages, struct vm_area_struct **vmas,
                         unsigned long *position, int *length, int i)
@@ -403,6 +426,7 @@ int follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma,
         BUG_ON(!is_vm_hugetlb_page(vma));
 
         vpfn = vaddr/PAGE_SIZE;
+        spin_lock(&mm->page_table_lock);
         while (vaddr < vma->vm_end && remainder) {
 
                 if (pages) {
@@ -415,8 +439,13 @@ int follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma,
                          * indexing below to work. */
                         pte = huge_pte_offset(mm, vaddr & HPAGE_MASK);
 
-                        /* hugetlb should be locked, and hence, prefaulted */
-                        WARN_ON(!pte || pte_none(*pte));
+                        /* the hugetlb file might have been truncated */
+                        if (!pte || pte_none(*pte)) {
+                                remainder = 0;
+                                if (!i)
+                                        i = -EFAULT;
+                                break;
+                        }
 
                         page = &pte_page(*pte)[vpfn % (HPAGE_SIZE/PAGE_SIZE)];
 
@@ -434,7 +463,7 @@ int follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma,
                 --remainder;
                 ++i;
         }
-
+        spin_unlock(&mm->page_table_lock);
         *length = remainder;
         *position = vaddr;
 
diff --git a/mm/memory.c b/mm/memory.c
index ae8161f1f459..1db40e935e55 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -2045,8 +2045,8 @@ int __handle_mm_fault(struct mm_struct *mm, struct vm_area_struct * vma,
 
         inc_page_state(pgfault);
 
-        if (is_vm_hugetlb_page(vma))
-                return VM_FAULT_SIGBUS; /* mapping truncation does this. */
+        if (unlikely(is_vm_hugetlb_page(vma)))
+                return hugetlb_fault(mm, vma, address, write_access);
 
         /*
          * We need the page table lock to synchronize with kswapd
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 37af443eb094..1d5c64df1653 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -700,7 +700,7 @@ static struct zonelist *zonelist_policy(gfp_t gfp, struct mempolicy *policy)
         case MPOL_BIND:
                 /* Lower zones don't get a policy applied */
                 /* Careful: current->mems_allowed might have moved */
-                if ((gfp & GFP_ZONEMASK) >= policy_zone)
+                if (gfp_zone(gfp) >= policy_zone)
                         if (cpuset_zonelist_valid_mems_allowed(policy->v.zonelist))
                                 return policy->v.zonelist;
                 /*FALL THROUGH*/
@@ -712,7 +712,7 @@ static struct zonelist *zonelist_policy(gfp_t gfp, struct mempolicy *policy)
                 nd = 0;
                 BUG();
         }
-        return NODE_DATA(nd)->node_zonelists + (gfp & GFP_ZONEMASK);
+        return NODE_DATA(nd)->node_zonelists + gfp_zone(gfp);
 }
 
 /* Do dynamic interleaving for a process */
@@ -757,7 +757,7 @@ static struct page *alloc_page_interleave(gfp_t gfp, unsigned order, unsigned ni
         struct page *page;
 
         BUG_ON(!node_online(nid));
-        zl = NODE_DATA(nid)->node_zonelists + (gfp & GFP_ZONEMASK);
+        zl = NODE_DATA(nid)->node_zonelists + gfp_zone(gfp);
         page = __alloc_pages(gfp, order, zl);
         if (page && page_zone(page) == zl->zones[0]) {
                 zone_pcp(zl->zones[0],get_cpu())->interleave_hit++;
diff --git a/mm/mempool.c b/mm/mempool.c
index 9e377ea700b2..1a99b80480d3 100644
--- a/mm/mempool.c
+++ b/mm/mempool.c
@@ -205,7 +205,7 @@ void * mempool_alloc(mempool_t *pool, gfp_t gfp_mask)
         void *element;
         unsigned long flags;
         wait_queue_t wait;
-        unsigned int gfp_temp;
+        gfp_t gfp_temp;
 
         might_sleep_if(gfp_mask & __GFP_WAIT);
 
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index cc1fe2672a31..94c864eac9c4 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -734,7 +734,7 @@ buffered_rmqueue(struct zone *zone, int order, gfp_t gfp_flags)
  * of the allocation.
  */
 int zone_watermark_ok(struct zone *z, int order, unsigned long mark,
-                      int classzone_idx, int can_try_harder, int gfp_high)
+                      int classzone_idx, int can_try_harder, gfp_t gfp_high)
 {
         /* free_pages my go negative - that's OK */
         long min = mark, free_pages = z->free_pages - (1 << order) + 1;
@@ -777,7 +777,7 @@ struct page * fastcall
 __alloc_pages(gfp_t gfp_mask, unsigned int order,
                 struct zonelist *zonelist)
 {
-        const int wait = gfp_mask & __GFP_WAIT;
+        const gfp_t wait = gfp_mask & __GFP_WAIT;
         struct zone **zones, *z;
         struct page *page;
         struct reclaim_state reclaim_state;
@@ -996,7 +996,7 @@ fastcall unsigned long get_zeroed_page(gfp_t gfp_mask)
          * get_zeroed_page() returns a 32-bit address, which cannot represent
          * a highmem page
          */
-        BUG_ON(gfp_mask & __GFP_HIGHMEM);
+        BUG_ON((gfp_mask & __GFP_HIGHMEM) != 0);
 
         page = alloc_pages(gfp_mask | __GFP_ZERO, 0);
         if (page)
@@ -1089,7 +1089,7 @@ static unsigned int nr_free_zone_pages(int offset)
  */
 unsigned int nr_free_buffer_pages(void)
 {
-        return nr_free_zone_pages(GFP_USER & GFP_ZONEMASK);
+        return nr_free_zone_pages(gfp_zone(GFP_USER));
 }
 
 /*
@@ -1097,7 +1097,7 @@ unsigned int nr_free_buffer_pages(void)
  */
 unsigned int nr_free_pagecache_pages(void)
 {
-        return nr_free_zone_pages(GFP_HIGHUSER & GFP_ZONEMASK);
+        return nr_free_zone_pages(gfp_zone(GFP_HIGHUSER));
 }
 
 #ifdef CONFIG_HIGHMEM
@@ -1428,6 +1428,16 @@ static int __init build_zonelists_node(pg_data_t *pgdat, struct zonelist *zoneli
         return j;
 }
 
+static inline int highest_zone(int zone_bits)
+{
+        int res = ZONE_NORMAL;
+        if (zone_bits & (__force int)__GFP_HIGHMEM)
+                res = ZONE_HIGHMEM;
+        if (zone_bits & (__force int)__GFP_DMA)
+                res = ZONE_DMA;
+        return res;
+}
+
 #ifdef CONFIG_NUMA
 #define MAX_NODE_LOAD (num_online_nodes())
 static int __initdata node_load[MAX_NUMNODES];
@@ -1524,11 +1534,7 @@ static void __init build_zonelists(pg_data_t *pgdat)
                         zonelist = pgdat->node_zonelists + i;
                         for (j = 0; zonelist->zones[j] != NULL; j++);
 
-                        k = ZONE_NORMAL;
-                        if (i & __GFP_HIGHMEM)
-                                k = ZONE_HIGHMEM;
-                        if (i & __GFP_DMA)
-                                k = ZONE_DMA;
+                        k = highest_zone(i);
 
                         j = build_zonelists_node(NODE_DATA(node), zonelist, j, k);
                         zonelist->zones[j] = NULL;
@@ -1549,12 +1555,7 @@ static void __init build_zonelists(pg_data_t *pgdat)
                 zonelist = pgdat->node_zonelists + i;
 
                 j = 0;
-                k = ZONE_NORMAL;
-                if (i & __GFP_HIGHMEM)
-                        k = ZONE_HIGHMEM;
-                if (i & __GFP_DMA)
-                        k = ZONE_DMA;
-
+                k = highest_zone(i);
                 j = build_zonelists_node(pgdat, zonelist, j, k);
                 /*
                  * Now we build the zonelist so that it contains the zones
@@ -1750,6 +1751,8 @@ inline void setup_pageset(struct per_cpu_pageset *p, unsigned long batch)
 {
         struct per_cpu_pages *pcp;
 
+        memset(p, 0, sizeof(*p));
+
         pcp = &p->pcp[0];               /* hot */
         pcp->count = 0;
         pcp->low = 2 * batch;
diff --git a/mm/shmem.c b/mm/shmem.c
index ea064d89cda9..55e04a0734c1 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -85,7 +85,7 @@ enum sgp_type {
 static int shmem_getpage(struct inode *inode, unsigned long idx,
                          struct page **pagep, enum sgp_type sgp, int *type);
 
-static inline struct page *shmem_dir_alloc(unsigned int gfp_mask)
+static inline struct page *shmem_dir_alloc(gfp_t gfp_mask)
 {
         /*
          * The above definition of ENTRIES_PER_PAGE, and the use of
@@ -898,7 +898,7 @@ struct page *shmem_swapin(struct shmem_inode_info *info, swp_entry_t entry,
 }
 
 static struct page *
-shmem_alloc_page(unsigned long gfp, struct shmem_inode_info *info,
+shmem_alloc_page(gfp_t gfp, struct shmem_inode_info *info,
                  unsigned long idx)
 {
         struct vm_area_struct pvma;
diff --git a/mm/slab.c b/mm/slab.c
index d05c678bceb3..d30423f167a2 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -386,7 +386,7 @@ struct kmem_cache_s {
         unsigned int            gfporder;
 
         /* force GFP flags, e.g. GFP_DMA */
-        unsigned int            gfpflags;
+        gfp_t                   gfpflags;
 
         size_t                  colour;         /* cache colouring range */
         unsigned int            colour_off;     /* colour offset */
@@ -2117,7 +2117,7 @@ static void cache_init_objs(kmem_cache_t *cachep,
         slabp->free = 0;
 }
 
-static void kmem_flagcheck(kmem_cache_t *cachep, unsigned int flags)
+static void kmem_flagcheck(kmem_cache_t *cachep, gfp_t flags)
 {
         if (flags & SLAB_DMA) {
                 if (!(cachep->gfpflags & GFP_DMA))
@@ -2152,7 +2152,7 @@ static int cache_grow(kmem_cache_t *cachep, gfp_t flags, int nodeid)
         struct slab     *slabp;
         void            *objp;
         size_t           offset;
-        unsigned int     local_flags;
+        gfp_t            local_flags;
         unsigned long    ctor_flags;
         struct kmem_list3 *l3;
 
@@ -2546,7 +2546,7 @@ static inline void *__cache_alloc(kmem_cache_t *cachep, gfp_t flags)
 /*
  * A interface to enable slab creation on nodeid
  */
-static void *__cache_alloc_node(kmem_cache_t *cachep, int flags, int nodeid)
+static void *__cache_alloc_node(kmem_cache_t *cachep, gfp_t flags, int nodeid)
 {
         struct list_head *entry;
         struct slab *slabp;
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 64f9570cff56..843c87d1e61f 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -70,7 +70,7 @@ struct scan_control {
         unsigned int priority;
 
         /* This context's GFP mask */
-        unsigned int gfp_mask;
+        gfp_t gfp_mask;
 
         int may_writepage;
 
@@ -186,7 +186,7 @@ EXPORT_SYMBOL(remove_shrinker);
  *
  * Returns the number of slab objects which we shrunk.
  */
-static int shrink_slab(unsigned long scanned, unsigned int gfp_mask,
+static int shrink_slab(unsigned long scanned, gfp_t gfp_mask,
                         unsigned long lru_pages)
 {
         struct shrinker *shrinker;
@@ -926,7 +926,7 @@ shrink_caches(struct zone **zones, struct scan_control *sc)
  * holds filesystem locks which prevent writeout this might not work, and the
  * allocation attempt will fail.
  */
-int try_to_free_pages(struct zone **zones, unsigned int gfp_mask)
+int try_to_free_pages(struct zone **zones, gfp_t gfp_mask)
 {
         int priority;
         int ret = 0;
@@ -1338,7 +1338,7 @@ module_init(kswapd_init)
 /*
  * Try to free up some pages from this zone through reclaim.
  */
-int zone_reclaim(struct zone *zone, unsigned int gfp_mask, unsigned int order)
+int zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order)
 {
         struct scan_control sc;
         int nr_pages = 1 << order;