and changed files

[powerpc.git] / mm / hugetlb.c

diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 0ccc7f2..eb7180d 100644 (file)
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -44,14 +44,14 @@ static void clear_huge_page(struct page *page, unsigned long addr)
 }
 
 static void copy_huge_page(struct page *dst, struct page *src,
-                          unsigned long addr)
+                          unsigned long addr, struct vm_area_struct *vma)
 {
        int i;
 
        might_sleep();
        for (i = 0; i < HPAGE_SIZE/PAGE_SIZE; i++) {
                cond_resched();
-               copy_user_highpage(dst + i, src + i, addr + i*PAGE_SIZE);
+               copy_user_highpage(dst + i, src + i, addr + i*PAGE_SIZE, vma);
        }
 }
 
@@ -73,7 +73,7 @@ static struct page *dequeue_huge_page(struct vm_area_struct *vma,
 
        for (z = zonelist->zones; *z; z++) {
                nid = zone_to_nid(*z);
-               if (cpuset_zone_allowed(*z, GFP_HIGHUSER) &&
+               if (cpuset_zone_allowed_softwall(*z, GFP_HIGHUSER) &&
                    !list_empty(&hugepage_freelists[nid]))
                        break;
        }
@@ -140,6 +140,8 @@ static struct page *alloc_huge_page(struct vm_area_struct *vma,
        return page;
 
 fail:
+       if (vma->vm_flags & VM_MAYSHARE)
+               resv_huge_pages++;
        spin_unlock(&hugetlb_lock);
        return NULL;
 }
@@ -172,6 +174,17 @@ static int __init hugetlb_setup(char *s)
 }
 __setup("hugepages=", hugetlb_setup);
 
+static unsigned int cpuset_mems_nr(unsigned int *array)
+{
+       int node;
+       unsigned int nr = 0;
+
+       for_each_node_mask(node, cpuset_current_mems_allowed)
+               nr += array[node];
+
+       return nr;
+}
+
 #ifdef CONFIG_SYSCTL
 static void update_and_free_page(struct page *page)
 {
@@ -389,6 +402,8 @@ void __unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start,
                        continue;
 
                page = pte_page(pte);
+               if (pte_dirty(pte))
+                       set_page_dirty(page);
                list_add(&page->lru, &page_list);
        }
        spin_unlock(&mm->page_table_lock);
@@ -442,7 +457,7 @@ static int hugetlb_cow(struct mm_struct *mm, struct vm_area_struct *vma,
        }
 
        spin_unlock(&mm->page_table_lock);
-       copy_huge_page(new_page, old_page, address);
+       copy_huge_page(new_page, old_page, address, vma);
        spin_lock(&mm->page_table_lock);
 
        ptep = huge_pte_offset(mm, address & HPAGE_MASK);
@@ -815,6 +830,26 @@ int hugetlb_reserve_pages(struct inode *inode, long from, long to)
        chg = region_chg(&inode->i_mapping->private_list, from, to);
        if (chg < 0)
                return chg;
+       /*
+        * When cpuset is configured, it breaks the strict hugetlb page
+        * reservation as the accounting is done on a global variable. Such
+        * reservation is completely rubbish in the presence of cpuset because
+        * the reservation is not checked against page availability for the
+        * current cpuset. Application can still potentially OOM'ed by kernel
+        * with lack of free htlb page in cpuset that the task is in.
+        * Attempt to enforce strict accounting with cpuset is almost
+        * impossible (or too ugly) because cpuset is too fluid that
+        * task or memory node can be dynamically moved between cpusets.
+        *
+        * The change of semantics for shared hugetlb mapping with cpuset is
+        * undesirable. However, in order to preserve some of the semantics,
+        * we fall back to check against current free page availability as
+        * a best attempt and hopefully to minimize the impact of changing
+        * semantics that cpuset has.
+        */
+       if (chg > cpuset_mems_nr(free_huge_pages_node))
+               return -ENOMEM;
+
        ret = hugetlb_acct_memory(chg);
        if (ret < 0)
                return ret;