summaryrefslogtreecommitdiffstats
path: root/mm
diff options
context:
space:
mode:
Diffstat (limited to 'mm')
-rw-r--r--mm/huge_memory.c55
1 files changed, 42 insertions, 13 deletions
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 29bc6e471df4..cb7be110cad3 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -2117,7 +2117,8 @@ static int __collapse_huge_page_isolate(struct vm_area_struct *vma,
{
struct page *page;
pte_t *_pte;
- int referenced = 0, none = 0;
+ int none = 0;
+ bool referenced = false, writable = false;
for (_pte = pte; _pte < pte+HPAGE_PMD_NR;
_pte++, address += PAGE_SIZE) {
pte_t pteval = *_pte;
@@ -2127,7 +2128,7 @@ static int __collapse_huge_page_isolate(struct vm_area_struct *vma,
else
goto out;
}
- if (!pte_present(pteval) || !pte_write(pteval))
+ if (!pte_present(pteval))
goto out;
page = vm_normal_page(vma, address, pteval);
if (unlikely(!page))
@@ -2137,9 +2138,6 @@ static int __collapse_huge_page_isolate(struct vm_area_struct *vma,
VM_BUG_ON_PAGE(!PageAnon(page), page);
VM_BUG_ON_PAGE(!PageSwapBacked(page), page);
- /* cannot use mapcount: can't collapse if there's a gup pin */
- if (page_count(page) != 1)
- goto out;
/*
* We can do it before isolate_lru_page because the
* page can't be freed from under us. NOTE: PG_lock
@@ -2148,6 +2146,29 @@ static int __collapse_huge_page_isolate(struct vm_area_struct *vma,
*/
if (!trylock_page(page))
goto out;
+
+ /*
+ * cannot use mapcount: can't collapse if there's a gup pin.
+ * The page must only be referenced by the scanned process
+ * and page swap cache.
+ */
+ if (page_count(page) != 1 + !!PageSwapCache(page)) {
+ unlock_page(page);
+ goto out;
+ }
+ if (pte_write(pteval)) {
+ writable = true;
+ } else {
+ if (PageSwapCache(page) && !reuse_swap_page(page)) {
+ unlock_page(page);
+ goto out;
+ }
+ /*
+ * Page is not in the swap cache. It can be collapsed
+ * into a THP.
+ */
+ }
+
/*
* Isolate the page to avoid collapsing an hugepage
* currently in use by the VM.
@@ -2164,9 +2185,9 @@ static int __collapse_huge_page_isolate(struct vm_area_struct *vma,
/* If there is no mapped pte young don't collapse the page */
if (pte_young(pteval) || PageReferenced(page) ||
mmu_notifier_test_young(vma->vm_mm, address))
- referenced = 1;
+ referenced = true;
}
- if (likely(referenced))
+ if (likely(referenced && writable))
return 1;
out:
release_pte_pages(pte, _pte);
@@ -2519,11 +2540,12 @@ static int khugepaged_scan_pmd(struct mm_struct *mm,
{
pmd_t *pmd;
pte_t *pte, *_pte;
- int ret = 0, referenced = 0, none = 0;
+ int ret = 0, none = 0;
struct page *page;
unsigned long _address;
spinlock_t *ptl;
int node = NUMA_NO_NODE;
+ bool writable = false, referenced = false;
VM_BUG_ON(address & ~HPAGE_PMD_MASK);
@@ -2542,8 +2564,11 @@ static int khugepaged_scan_pmd(struct mm_struct *mm,
else
goto out_unmap;
}
- if (!pte_present(pteval) || !pte_write(pteval))
+ if (!pte_present(pteval))
goto out_unmap;
+ if (pte_write(pteval))
+ writable = true;
+
page = vm_normal_page(vma, _address, pteval);
if (unlikely(!page))
goto out_unmap;
@@ -2560,14 +2585,18 @@ static int khugepaged_scan_pmd(struct mm_struct *mm,
VM_BUG_ON_PAGE(PageCompound(page), page);
if (!PageLRU(page) || PageLocked(page) || !PageAnon(page))
goto out_unmap;
- /* cannot use mapcount: can't collapse if there's a gup pin */
- if (page_count(page) != 1)
+ /*
+ * cannot use mapcount: can't collapse if there's a gup pin.
+ * The page must only be referenced by the scanned process
+ * and page swap cache.
+ */
+ if (page_count(page) != 1 + !!PageSwapCache(page))
goto out_unmap;
if (pte_young(pteval) || PageReferenced(page) ||
mmu_notifier_test_young(vma->vm_mm, address))
- referenced = 1;
+ referenced = true;
}
- if (referenced)
+ if (referenced && writable)
ret = 1;
out_unmap:
pte_unmap_unlock(pte, ptl);