[PATCH] hugetlb: overcommit accounting check

Basic overcommit checking for hugetlb_file_map() based on an implementation
used with demand faulting in SLES9.

Since demand faulting can't guarantee the availability of pages at mmap
time, this patch implements a basic sanity check to ensure that the number
of huge pages required to satisfy the mmap are currently available.
Despite the obvious race, I think it is a good start on doing proper
accounting.  I'd like to work towards an accounting system that mimics the
semantics of normal pages (especially for the MAP_PRIVATE/COW case).  That
work is underway and builds on what this patch starts.

Huge page shared memory segments are simpler and still maintain their
commit on shmget semantics.

Signed-off-by: Adam Litke <agl@us.ibm.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index 2627efe767cf485257f381530ab8234cfb7a218d..e026c807e6b376fe57deb2dc2050d1d58d7c917a 100644 (file)
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -45,9 +45,58 @@ static struct backing_dev_info hugetlbfs_backing_dev_info = {
 
 int sysctl_hugetlb_shm_group;
 
+static void huge_pagevec_release(struct pagevec *pvec)
+{
+       int i;
+
+       for (i = 0; i < pagevec_count(pvec); ++i)
+               put_page(pvec->pages[i]);
+
+       pagevec_reinit(pvec);
+}
+
+/*
+ * huge_pages_needed tries to determine the number of new huge pages that
+ * will be required to fully populate this VMA.  This will be equal to
+ * the size of the VMA in huge pages minus the number of huge pages
+ * (covered by this VMA) that are found in the page cache.
+ *
+ * Result is in bytes to be compatible with is_hugepage_mem_enough()
+ */
+unsigned long
+huge_pages_needed(struct address_space *mapping, struct vm_area_struct *vma)
+{
+       int i;
+       struct pagevec pvec;
+       unsigned long start = vma->vm_start;
+       unsigned long end = vma->vm_end;
+       unsigned long hugepages = (end - start) >> HPAGE_SHIFT;
+       pgoff_t next = vma->vm_pgoff;
+       pgoff_t endpg = next + ((end - start) >> PAGE_SHIFT);
+
+       pagevec_init(&pvec, 0);
+       while (next < endpg) {
+               if (!pagevec_lookup(&pvec, mapping, next, PAGEVEC_SIZE))
+                       break;
+               for (i = 0; i < pagevec_count(&pvec); i++) {
+                       struct page *page = pvec.pages[i];
+                       if (page->index > next)
+                               next = page->index;
+                       if (page->index >= endpg)
+                               break;
+                       next++;
+                       hugepages--;
+               }
+               huge_pagevec_release(&pvec);
+       }
+       return hugepages << HPAGE_SHIFT;
+}
+
 static int hugetlbfs_file_mmap(struct file *file, struct vm_area_struct *vma)
 {
        struct inode *inode = file->f_dentry->d_inode;
+       struct address_space *mapping = inode->i_mapping;
+       unsigned long bytes;
        loff_t len, vma_len;
        int ret;
 
@@ -66,6 +115,10 @@ static int hugetlbfs_file_mmap(struct file *file, struct vm_area_struct *vma)
        if (vma->vm_end - vma->vm_start < HPAGE_SIZE)
                return -EINVAL;
 
+       bytes = huge_pages_needed(mapping, vma);
+       if (!is_hugepage_mem_enough(bytes))
+               return -ENOMEM;
+
        vma_len = (loff_t)(vma->vm_end - vma->vm_start);
 
        down(&inode->i_sem);
@@ -168,16 +221,6 @@ static int hugetlbfs_commit_write(struct file *file,
        return -EINVAL;
 }
 
-static void huge_pagevec_release(struct pagevec *pvec)
-{
-       int i;
-
-       for (i = 0; i < pagevec_count(pvec); ++i)
-               put_page(pvec->pages[i]);
-
-       pagevec_reinit(pvec);
-}
-
 static void truncate_huge_page(struct page *page)
 {
        clear_page_dirty(page);