hugetlbfs: per mount huge page sizes

Add the ability to configure the hugetlb hstate used on a per mount basis.

- Add a new pagesize= option to the hugetlbfs mount that allows setting
  the page size
- This option causes the mount code to find the hstate corresponding to the
  specified size, and sets up a pointer to the hstate in the mount's
  superblock.
- Change the hstate accessors to use this information rather than the
  global_hstate they were using (requires a slight change in mm/memory.c
  so we don't NULL deref in the error-unmap path -- see comments).

[np: take hstate out of hugetlbfs inode and vma->vm_private_data]

Acked-by: Adam Litke <agl@us.ibm.com>
Acked-by: Nishanth Aravamudan <nacc@us.ibm.com>
Signed-off-by: Andi Kleen <ak@suse.de>
Signed-off-by: Nick Piggin <npiggin@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

2 files changed, 19 insertions, 15 deletions

diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 82378d44a0c5..4cf7a90e9140 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -1439,19 +1439,9 @@ void __unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start,
 void unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start,
                           unsigned long end, struct page *ref_page)
 {
-        /*
-         * It is undesirable to test vma->vm_file as it should be non-null
-         * for valid hugetlb area. However, vm_file will be NULL in the error
-         * cleanup path of do_mmap_pgoff. When hugetlbfs ->mmap method fails,
-         * do_mmap_pgoff() nullifies vma->vm_file before calling this function
-         * to clean up. Since no pte has actually been setup, it is safe to
-         * do nothing in this case.
-         */
-        if (vma->vm_file) {
-                spin_lock(&vma->vm_file->f_mapping->i_mmap_lock);
-                __unmap_hugepage_range(vma, start, end, ref_page);
-                spin_unlock(&vma->vm_file->f_mapping->i_mmap_lock);
-        }
+        spin_lock(&vma->vm_file->f_mapping->i_mmap_lock);
+        __unmap_hugepage_range(vma, start, end, ref_page);
+        spin_unlock(&vma->vm_file->f_mapping->i_mmap_lock);
 }
 
 /*
diff --git a/mm/memory.c b/mm/memory.c
index c1c1d6d8c22b..02fc6b1047b0 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -901,9 +901,23 @@ unsigned long unmap_vmas(struct mmu_gather **tlbp,
                         }
 
                         if (unlikely(is_vm_hugetlb_page(vma))) {
-                                unmap_hugepage_range(vma, start, end, NULL);
-                                zap_work -= (end - start) /
+                                /*
+                                 * It is undesirable to test vma->vm_file as it
+                                 * should be non-null for valid hugetlb area.
+                                 * However, vm_file will be NULL in the error
+                                 * cleanup path of do_mmap_pgoff. When
+                                 * hugetlbfs ->mmap method fails,
+                                 * do_mmap_pgoff() nullifies vma->vm_file
+                                 * before calling this function to clean up.
+                                 * Since no pte has actually been setup, it is
+                                 * safe to do nothing in this case.
+                                 */
+                                if (vma->vm_file) {
+                                        unmap_hugepage_range(vma, start, end, NULL);
+                                        zap_work -= (end - start) /
                                         pages_per_huge_page(hstate_vma(vma));
+                                }
+
                                 start = end;
                         } else
                                 start = unmap_page_range(*tlbp, vma,