[PATCH v2 07/10] thp: implement splitting pmd for huge zero page

From: Kirill A. Shutemov
Date: Mon Sep 10 2012 - 09:14:40 EST


From: "Kirill A. Shutemov" <kirill.shutemov@xxxxxxxxxxxxxxx>

We can't split huge zero page itself, but we can split the pmd which
points to it.

On splitting the pmd we create a table with all ptes set to normal zero
page.

Signed-off-by: Kirill A. Shutemov <kirill.shutemov@xxxxxxxxxxxxxxx>
---
mm/huge_memory.c | 32 ++++++++++++++++++++++++++++++++
1 files changed, 32 insertions(+), 0 deletions(-)

diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 48ecc46..995894f 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1599,6 +1599,7 @@ int split_huge_page(struct page *page)
struct anon_vma *anon_vma;
int ret = 1;

+ BUG_ON(is_huge_zero_pfn(page_to_pfn(page)));
BUG_ON(!PageAnon(page));
anon_vma = page_lock_anon_vma(page);
if (!anon_vma)
@@ -2503,6 +2504,32 @@ static int khugepaged(void *none)
return 0;
}

+static void __split_huge_zero_page_pmd(struct vm_area_struct *vma,
+ unsigned long haddr, pmd_t *pmd)
+{
+ pgtable_t pgtable;
+ pmd_t _pmd;
+ int i;
+
+ pmdp_clear_flush_notify(vma, haddr, pmd);
+ /* leave pmd empty until pte is filled */
+
+ pgtable = get_pmd_huge_pte(vma->vm_mm);
+ pmd_populate(vma->vm_mm, &_pmd, pgtable);
+
+ for (i = 0; i < HPAGE_PMD_NR; i++, haddr += PAGE_SIZE) {
+ pte_t *pte, entry;
+ entry = pfn_pte(my_zero_pfn(haddr), vma->vm_page_prot);
+ entry = pte_mkspecial(entry);
+ pte = pte_offset_map(&_pmd, haddr);
+ VM_BUG_ON(!pte_none(*pte));
+ set_pte_at(vma->vm_mm, haddr, pte, entry);
+ pte_unmap(pte);
+ }
+ smp_wmb(); /* make pte visible before pmd */
+ pmd_populate(vma->vm_mm, pmd, pgtable);
+}
+
void __split_huge_page_pmd(struct vm_area_struct *vma, unsigned long address,
pmd_t *pmd)
{
@@ -2516,6 +2543,11 @@ void __split_huge_page_pmd(struct vm_area_struct *vma, unsigned long address,
spin_unlock(&vma->vm_mm->page_table_lock);
return;
}
+ if (is_huge_zero_pmd(*pmd)) {
+ __split_huge_zero_page_pmd(vma, haddr, pmd);
+ spin_unlock(&vma->vm_mm->page_table_lock);
+ return;
+ }
page = pmd_page(*pmd);
VM_BUG_ON(!page_count(page));
get_page(page);
--
1.7.7.6

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/