[PATCH v3 05/14] mm/khugepaged: Break COW PTE before scanning pte

[Chih-En Lin]

We should not allow THP to collapse COW-ed PTE. So, break COW PTE
before collapse_pte_mapped_thp() collapse to THP. Also, break COW
PTE before khugepaged_scan_pmd() scan PTE.

Signed-off-by: Chih-En Lin <shiyn.lin@xxxxxxxxx>
---
 include/trace/events/huge_memory.h |  1 +
 mm/khugepaged.c                    | 23 +++++++++++++++++++++++
 2 files changed, 24 insertions(+)

diff --git a/include/trace/events/huge_memory.h b/include/trace/events/huge_memory.h
index 760455dfa8600..881553aa0f2f2 100644
--- a/include/trace/events/huge_memory.h
+++ b/include/trace/events/huge_memory.h
@@ -13,6 +13,7 @@
 	EM( SCAN_PMD_NULL,		"pmd_null")			\
 	EM( SCAN_PMD_NONE,		"pmd_none")			\
 	EM( SCAN_PMD_MAPPED,		"page_pmd_mapped")		\
+	EM( SCAN_COW_PTE,		"cowed_pte")			\
 	EM( SCAN_EXCEED_NONE_PTE,	"exceed_none_pte")		\
 	EM( SCAN_EXCEED_SWAP_PTE,	"exceed_swap_pte")		\
 	EM( SCAN_EXCEED_SHARED_PTE,	"exceed_shared_pte")		\
diff --git a/mm/khugepaged.c b/mm/khugepaged.c
index a8d5ef2a77d24..106e1ce3931f7 100644
--- a/mm/khugepaged.c
+++ b/mm/khugepaged.c
@@ -31,6 +31,7 @@ enum scan_result {
 	SCAN_PMD_NULL,
 	SCAN_PMD_NONE,
 	SCAN_PMD_MAPPED,
+	SCAN_COW_PTE,
 	SCAN_EXCEED_NONE_PTE,
 	SCAN_EXCEED_SWAP_PTE,
 	SCAN_EXCEED_SHARED_PTE,
@@ -1030,6 +1031,9 @@ static int collapse_huge_page(struct mm_struct *mm, unsigned long address,
 	if (result != SCAN_SUCCEED)
 		goto out_up_write;
 
+	/* We should already handled COW-ed PTE. */
+	VM_WARN_ON(test_bit(MMF_COW_PTE, &mm->flags) && !pmd_write(*pmd));
+
 	anon_vma_lock_write(vma->anon_vma);
 
 	mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, NULL, mm,
@@ -1139,6 +1143,16 @@ static int hpage_collapse_scan_pmd(struct mm_struct *mm,
 
 	memset(cc->node_load, 0, sizeof(cc->node_load));
 	nodes_clear(cc->alloc_nmask);
+
+	/*
+	 * Before we scan each pte entry, we should first check PTE
+	 * could be modified. So, we break COW if PTE is COW-ed.
+	 */
+	if (break_cow_pte(vma, pmd, address) < 0) {
+		result = SCAN_COW_PTE;
+		goto out;
+	}
+
 	pte = pte_offset_map_lock(mm, pmd, address, &ptl);
 	for (_address = address, _pte = pte; _pte < pte + HPAGE_PMD_NR;
 	     _pte++, _address += PAGE_SIZE) {
@@ -1197,6 +1211,10 @@ static int hpage_collapse_scan_pmd(struct mm_struct *mm,
 			goto out_unmap;
 		}
 
+		/*
+		 * If we only trigger the break COW PTE, the page usually
+		 * still in COW mapping, which it still be shared.
+		 */
 		if (page_mapcount(page) > 1) {
 			++shared;
 			if (cc->is_khugepaged &&
@@ -1472,6 +1490,11 @@ int collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr,
 		goto drop_hpage;
 	}
 
+	/* We shouldn't let COW-ed PTE collapse. */
+	if (break_cow_pte(vma, pmd, haddr) < 0)
+		goto drop_hpage;
+	VM_WARN_ON(test_bit(MMF_COW_PTE, &mm->flags) && !pmd_write(*pmd));
+
 	start_pte = pte_offset_map_lock(mm, pmd, haddr, &ptl);
 	result = SCAN_FAIL;
 
-- 
2.37.3