If any of the ptes that khugepaged is collapsing was a pte_numa, the
resulting trans huge pmd will be a pmd_numa too.
See the comment inline for why we require just one pte_numa pte to
make a pmd_numa pmd. If needed later we could change the number of
pte_numa ptes required to create a pmd_numa and make it tunable with
sysfs too.
Signed-off-by: Andrea Arcangeli <aarcange@xxxxxxxxxx>
---
mm/huge_memory.c | 33 +++++++++++++++++++++++++++++++--
1 files changed, 31 insertions(+), 2 deletions(-)
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 152d4dd..1023e67 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1833,12 +1833,19 @@ out:
return isolated;
}
-static void __collapse_huge_page_copy(pte_t *pte, struct page *page,
+/*
+ * Do the actual data copy for mapped ptes and release the mapped
+ * pages, or alternatively zero out the transparent hugepage in the
+ * mapping holes. Transfer the page_autonuma information in the
+ * process. Return true if any of the mapped ptes was of numa type.
+ */
+static bool __collapse_huge_page_copy(pte_t *pte, struct page *page,
struct vm_area_struct *vma,
unsigned long address,
spinlock_t *ptl)
{
pte_t *_pte;
+ bool mknuma = false;
for (_pte = pte; _pte < pte+HPAGE_PMD_NR; _pte++) {
pte_t pteval = *_pte;
struct page *src_page;
@@ -1865,11 +1872,29 @@ static void __collapse_huge_page_copy(pte_t *pte, struct page *page,
page_remove_rmap(src_page);
spin_unlock(ptl);
free_page_and_swap_cache(src_page);
+
+ /*
+ * Only require one pte_numa mapped by a pmd
+ * to make it a pmd_numa, too. To avoid the
+ * risk of losing NUMA hinting page faults, it
+ * is better to overestimate the NUMA node
+ * affinity with a node where we just
+ * collapsed a hugepage, rather than
+ * underestimate it.
+ *
+ * Note: if AUTONUMA_SCAN_PMD_FLAG is set, we
+ * won't find any pte_numa ptes since we're
+ * only setting NUMA hinting at the pmd
+ * level.
+ */
+ mknuma |= pte_numa(pteval);
}
address += PAGE_SIZE;
page++;
}
+
+ return mknuma;
}
static void collapse_huge_page(struct mm_struct *mm,
@@ -1887,6 +1912,7 @@ static void collapse_huge_page(struct mm_struct *mm,
spinlock_t *ptl;
int isolated;
unsigned long hstart, hend;
+ bool mknuma = false;
VM_BUG_ON(address & ~HPAGE_PMD_MASK);
#ifndef CONFIG_NUMA
@@ -2005,7 +2031,8 @@ static void collapse_huge_page(struct mm_struct *mm,
*/
anon_vma_unlock(vma->anon_vma);
- __collapse_huge_page_copy(pte, new_page, vma, address, ptl);
+ mknuma = pmd_numa(_pmd);
+ mknuma |= __collapse_huge_page_copy(pte, new_page, vma, address, ptl);
pte_unmap(pte);
__SetPageUptodate(new_page);
pgtable = pmd_pgtable(_pmd);
@@ -2015,6 +2042,8 @@ static void collapse_huge_page(struct mm_struct *mm,
_pmd = mk_pmd(new_page, vma->vm_page_prot);
_pmd = maybe_pmd_mkwrite(pmd_mkdirty(_pmd), vma);
_pmd = pmd_mkhuge(_pmd);
+ if (mknuma)
+ _pmd = pmd_mknuma(_pmd);
/*
* spin_lock() below is not the equivalent of smp_wmb(), so
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@xxxxxxxxx. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@xxxxxxxxx";> email@xxxxxxxxx </a>