[PATCH] optimize follow_hugetlb_page

follow_hugetlb_page() walks a range of user virtual address and then fills
in list of struct page * into an array that is passed from the argument
list.  It also gets a reference count via get_page().  For compound page,
get_page() actually traverse back to head page via page_private() macro and
then adds a reference count to the head page.  Since we are doing a virt to
pte look up, kernel already has a struct page pointer into the head page.
So instead of traverse into the small unit page struct and then follow a
link back to the head page, optimize that with incrementing the reference
count directly on the head page.

The benefit is that we don't take a cache miss on accessing page struct for
the corresponding user address and more importantly, not to pollute the
cache with a "not very useful" round trip of pointer chasing.  This adds a
moderate performance gain on an I/O intensive database transaction
workload.

Signed-off-by: Ken Chen <kenneth.w.chen@intel.com>
Cc: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 075877b..06699d8 100644 (file)
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -661,10 +661,10 @@ 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)
 {
-       unsigned long vpfn, vaddr = *position;
+       unsigned long pfn_offset;
+       unsigned long vaddr = *position;
        int remainder = *length;
 
-       vpfn = vaddr/PAGE_SIZE;
        spin_lock(&mm->page_table_lock);
        while (vaddr < vma->vm_end && remainder) {
                pte_t *pte;
@@ -692,19 +692,28 @@ int follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma,
                        break;
                }
 
-               if (pages) {
-                       page = &pte_page(*pte)[vpfn % (HPAGE_SIZE/PAGE_SIZE)];
-                       get_page(page);
-                       pages[i] = page;
-               }
+               pfn_offset = (vaddr & ~HPAGE_MASK) >> PAGE_SHIFT;
+               page = pte_page(*pte);
+same_page:
+               get_page(page);
+               if (pages)
+                       pages[i] = page + pfn_offset;
 
                if (vmas)
                        vmas[i] = vma;
 
                vaddr += PAGE_SIZE;
-               ++vpfn;
+               ++pfn_offset;
                --remainder;
                ++i;
+               if (vaddr < vma->vm_end && remainder &&
+                               pfn_offset < HPAGE_SIZE/PAGE_SIZE) {
+                       /*
+                        * We use pfn_offset to avoid touching the pageframes
+                        * of this compound page.
+                        */
+                       goto same_page;
+               }
        }
        spin_unlock(&mm->page_table_lock);
        *length = remainder;