[PATCH mm-new 2/2] mm/khugepaged: merge PTE scanning logic into a new helper

[Lance Yang <lance.yang@linux.dev>]

From: Lance Yang <lance.yang@linux.dev>

As David suggested, the PTE scanning logic in hpage_collapse_scan_pmd()
and __collapse_huge_page_isolate() was almost duplicated.

This patch cleans things up by moving all the common PTE checking logic
into a new shared helper, thp_collapse_check_pte().

Suggested-by: David Hildenbrand <david@redhat.com>
Signed-off-by: Lance Yang <lance.yang@linux.dev>
---
 mm/khugepaged.c | 167 ++++++++++++++++++++++++++++++------------------
 1 file changed, 104 insertions(+), 63 deletions(-)

diff --git a/mm/khugepaged.c b/mm/khugepaged.c
index 808523f92c7b..2a897cfb1d03 100644
--- a/mm/khugepaged.c
+++ b/mm/khugepaged.c
@@ -61,6 +61,12 @@ enum scan_result {
 	SCAN_PAGE_FILLED,
 };
 
+enum pte_check_result {
+	PTE_CHECK_SUCCEED,
+	PTE_CHECK_CONTINUE,
+	PTE_CHECK_FAIL,
+};
+
 #define CREATE_TRACE_POINTS
 #include <trace/events/huge_memory.h>
 
@@ -533,6 +539,87 @@ static void release_pte_pages(pte_t *pte, pte_t *_pte,
 	}
 }
 
+/*
+ * thp_collapse_check_pte - Check if a PTE is suitable for THP collapse
+ * @pte:           PTE to check
+ * @vma:           VMA the PTE belongs to
+ * @cc:            Collapse control settings
+ * @scan_swap_pte: Allow scanning of swap PTEs if true
+ * @none_or_zero:  Counter for none/zero PTEs (must be non-NULL)
+ * @unmapped:      Counter for swap PTEs (must be non-NULL if scan_swap_pte
+ *                 is true)
+ * @scan_result:   Used to return the failure reason (SCAN_*) on a
+ *                 PTE_CHECK_FAIL return. Must be non-NULL
+ *
+ * Returns:
+ *   PTE_CHECK_SUCCEED  - Valid PTE, proceed with collapse
+ *   PTE_CHECK_CONTINUE - Skip this none/zero PTE but continue scanning
+ *   PTE_CHECK_FAIL     - Abort collapse scan
+ */
+static inline int thp_collapse_check_pte(pte_t pte, struct vm_area_struct *vma,
+		struct collapse_control *cc, bool scan_swap_pte,
+		int *none_or_zero, int *unmapped, int *scan_result)
+{
+	VM_BUG_ON(!none_or_zero || !scan_result);
+	VM_BUG_ON(scan_swap_pte && !unmapped);
+
+	if (pte_none(pte) || is_zero_pfn(pte_pfn(pte))) {
+		(*none_or_zero)++;
+		if (!userfaultfd_armed(vma) &&
+		    (!cc->is_khugepaged ||
+		     *none_or_zero <= khugepaged_max_ptes_none)) {
+			return PTE_CHECK_CONTINUE;
+		} else {
+			*scan_result = SCAN_EXCEED_NONE_PTE;
+			count_vm_event(THP_SCAN_EXCEED_NONE_PTE);
+			return PTE_CHECK_FAIL;
+		}
+	} else if (!pte_present(pte)) {
+		if (!scan_swap_pte) {
+			*scan_result = SCAN_PTE_NON_PRESENT;
+			return PTE_CHECK_FAIL;
+		}
+
+		if (non_swap_entry(pte_to_swp_entry(pte))) {
+			*scan_result = SCAN_PTE_NON_PRESENT;
+			return PTE_CHECK_FAIL;
+		}
+
+		(*unmapped)++;
+		if (!cc->is_khugepaged ||
+		    *unmapped <= khugepaged_max_ptes_swap) {
+			/*
+			 * Always be strict with uffd-wp
+			 * enabled swap entries. Please see
+			 * comment below for pte_uffd_wp().
+			 */
+			if (pte_swp_uffd_wp(pte)) {
+				*scan_result = SCAN_PTE_UFFD_WP;
+				return PTE_CHECK_FAIL;
+			}
+			return PTE_CHECK_CONTINUE;
+		} else {
+			*scan_result = SCAN_EXCEED_SWAP_PTE;
+			count_vm_event(THP_SCAN_EXCEED_SWAP_PTE);
+			return PTE_CHECK_FAIL;
+		}
+	} else if (pte_uffd_wp(pte)) {
+		/*
+		 * Don't collapse the page if any of the small
+		 * PTEs are armed with uffd write protection.
+		 * Here we can also mark the new huge pmd as
+		 * write protected if any of the small ones is
+		 * marked but that could bring unknown
+		 * userfault messages that falls outside of
+		 * the registered range.  So, just be simple.
+		 */
+		*scan_result = SCAN_PTE_UFFD_WP;
+		return PTE_CHECK_FAIL;
+	}
+
+	return PTE_CHECK_SUCCEED;
+}
+
 static int __collapse_huge_page_isolate(struct vm_area_struct *vma,
 					unsigned long start_addr,
 					pte_t *pte,
@@ -544,28 +631,20 @@ static int __collapse_huge_page_isolate(struct vm_area_struct *vma,
 	unsigned long addr = start_addr;
 	pte_t *_pte;
 	int none_or_zero = 0, shared = 0, result = SCAN_FAIL, referenced = 0;
+	int pte_check_res;
 
 	for (_pte = pte; _pte < pte + HPAGE_PMD_NR;
 	     _pte++, addr += PAGE_SIZE) {
 		pte_t pteval = ptep_get(_pte);
-		if (pte_none(pteval) || is_zero_pfn(pte_pfn(pteval))) {
-			++none_or_zero;
-			if (!userfaultfd_armed(vma) &&
-			    (!cc->is_khugepaged ||
-			     none_or_zero <= khugepaged_max_ptes_none)) {
-				continue;
-			} else {
-				result = SCAN_EXCEED_NONE_PTE;
-				count_vm_event(THP_SCAN_EXCEED_NONE_PTE);
-				goto out;
-			}
-		} else if (!pte_present(pteval)) {
-			result = SCAN_PTE_NON_PRESENT;
-			goto out;
-		} else if (pte_uffd_wp(pteval)) {
-			result = SCAN_PTE_UFFD_WP;
+		pte_check_res = thp_collapse_check_pte(
+			pteval, vma, cc, false, /* scan_swap_pte = false */
+			&none_or_zero, NULL, &result);
+
+		if (pte_check_res == PTE_CHECK_CONTINUE)
+			continue;
+		else if (pte_check_res == PTE_CHECK_FAIL)
 			goto out;
-		}
+
 		page = vm_normal_page(vma, addr, pteval);
 		if (unlikely(!page) || unlikely(is_zone_device_page(page))) {
 			result = SCAN_PAGE_NULL;
@@ -1260,6 +1339,7 @@ static int hpage_collapse_scan_pmd(struct mm_struct *mm,
 	unsigned long addr;
 	spinlock_t *ptl;
 	int node = NUMA_NO_NODE, unmapped = 0;
+	int pte_check_res;
 
 	VM_BUG_ON(start_addr & ~HPAGE_PMD_MASK);
 
@@ -1278,54 +1358,15 @@ static int hpage_collapse_scan_pmd(struct mm_struct *mm,
 	for (addr = start_addr, _pte = pte; _pte < pte + HPAGE_PMD_NR;
 	     _pte++, addr += PAGE_SIZE) {
 		pte_t pteval = ptep_get(_pte);
-		if (pte_none(pteval) || is_zero_pfn(pte_pfn(pteval))) {
-			++none_or_zero;
-			if (!userfaultfd_armed(vma) &&
-			    (!cc->is_khugepaged ||
-			     none_or_zero <= khugepaged_max_ptes_none)) {
-				continue;
-			} else {
-				result = SCAN_EXCEED_NONE_PTE;
-				count_vm_event(THP_SCAN_EXCEED_NONE_PTE);
-				goto out_unmap;
-			}
-		} else if (!pte_present(pteval)) {
-			if (non_swap_entry(pte_to_swp_entry(pteval))) {
-				result = SCAN_PTE_NON_PRESENT;
-				goto out_unmap;
-			}
 
-			++unmapped;
-			if (!cc->is_khugepaged ||
-			    unmapped <= khugepaged_max_ptes_swap) {
-				/*
-				 * Always be strict with uffd-wp
-				 * enabled swap entries.  Please see
-				 * comment below for pte_uffd_wp().
-				 */
-				if (pte_swp_uffd_wp(pteval)) {
-					result = SCAN_PTE_UFFD_WP;
-					goto out_unmap;
-				}
-				continue;
-			} else {
-				result = SCAN_EXCEED_SWAP_PTE;
-				count_vm_event(THP_SCAN_EXCEED_SWAP_PTE);
-				goto out_unmap;
-			}
-		} else if (pte_uffd_wp(pteval)) {
-			/*
-			 * Don't collapse the page if any of the small
-			 * PTEs are armed with uffd write protection.
-			 * Here we can also mark the new huge pmd as
-			 * write protected if any of the small ones is
-			 * marked but that could bring unknown
-			 * userfault messages that falls outside of
-			 * the registered range.  So, just be simple.
-			 */
-			result = SCAN_PTE_UFFD_WP;
+		pte_check_res = thp_collapse_check_pte(
+			pteval, vma, cc, true, /* scan_swap_pte = true */
+			&none_or_zero, &unmapped, &result);
+
+		if (pte_check_res == PTE_CHECK_CONTINUE)
+			continue;
+		else if (pte_check_res == PTE_CHECK_FAIL)
 			goto out_unmap;
-		}
 
 		page = vm_normal_page(vma, addr, pteval);
 		if (unlikely(!page) || unlikely(is_zone_device_page(page))) {
-- 
2.49.0