[PATCH 7.2 v16 03/13] mm/khugepaged: rework max_ptes_* handling with helper functions

[Nico Pache <npache@redhat.com>]

The following cleanup reworks all the max_ptes_* handling into helper
functions. This increases the code readability and will later be used to
implement the mTHP handling of these variables.

With these changes we abstract all the madvise_collapse() special casing
(dont respect the sysctls) away from the functions that utilize them. And
will later in this series to cleanly restrict mTHP collapses behaviors.

Suggested-by: David Hildenbrand <david@kernel.org>
Signed-off-by: Nico Pache <npache@redhat.com>
---
 mm/khugepaged.c | 114 +++++++++++++++++++++++++++++++++---------------
 1 file changed, 78 insertions(+), 36 deletions(-)

diff --git a/mm/khugepaged.c b/mm/khugepaged.c
index afac6bc4e76d..f42b55421191 100644
--- a/mm/khugepaged.c
+++ b/mm/khugepaged.c
@@ -348,6 +348,58 @@ static bool pte_none_or_zero(pte_t pte)
 	return pte_present(pte) && is_zero_pfn(pte_pfn(pte));
 }
 
+/**
+ * collapse_max_ptes_none - Calculate maximum allowed empty PTEs for collapse
+ * @cc: The collapse control struct
+ * @vma: The vma to check for userfaultfd
+ *
+ * If we are not in khugepaged mode use HPAGE_PMD_NR to allow any
+ * empty page.
+ *
+ * Return: Maximum number of empty PTEs allowed for the collapse operation
+ */
+static unsigned int collapse_max_ptes_none(struct collapse_control *cc,
+		struct vm_area_struct *vma)
+{
+	if (vma && userfaultfd_armed(vma))
+		return 0;
+	if (!cc->is_khugepaged)
+		return HPAGE_PMD_NR;
+	return khugepaged_max_ptes_none;
+}
+
+/**
+ * collapse_max_ptes_shared - Calculate maximum allowed shared PTEs for collapse
+ * @cc: The collapse control struct
+ *
+ * If we are not in khugepaged mode use HPAGE_PMD_NR to allow any
+ * shared page.
+ *
+ * Return: Maximum number of shared PTEs allowed for the collapse operation
+ */
+static unsigned int collapse_max_ptes_shared(struct collapse_control *cc)
+{
+	if (!cc->is_khugepaged)
+		return HPAGE_PMD_NR;
+	return khugepaged_max_ptes_shared;
+}
+
+/**
+ * collapse_max_ptes_swap - Calculate maximum allowed swap PTEs for collapse
+ * @cc: The collapse control struct
+ *
+ * If we are not in khugepaged mode use HPAGE_PMD_NR to allow any
+ * swap page.
+ *
+ * Return: Maximum number of swap PTEs allowed for the collapse operation
+ */
+static unsigned int collapse_max_ptes_swap(struct collapse_control *cc)
+{
+	if (!cc->is_khugepaged)
+		return HPAGE_PMD_NR;
+	return khugepaged_max_ptes_swap;
+}
+
 int hugepage_madvise(struct vm_area_struct *vma,
 		     vm_flags_t *vm_flags, int advice)
 {
@@ -546,21 +598,19 @@ static enum scan_result __collapse_huge_page_isolate(struct vm_area_struct *vma,
 	pte_t *_pte;
 	int none_or_zero = 0, shared = 0, referenced = 0;
 	enum scan_result result = SCAN_FAIL;
+	unsigned int max_ptes_none = collapse_max_ptes_none(cc, vma);
+	unsigned int max_ptes_shared = collapse_max_ptes_shared(cc);
 
 	for (_pte = pte; _pte < pte + HPAGE_PMD_NR;
 	     _pte++, addr += PAGE_SIZE) {
 		pte_t pteval = ptep_get(_pte);
 		if (pte_none_or_zero(pteval)) {
-			++none_or_zero;
-			if (!userfaultfd_armed(vma) &&
-			    (!cc->is_khugepaged ||
-			     none_or_zero <= khugepaged_max_ptes_none)) {
-				continue;
-			} else {
+			if (++none_or_zero > max_ptes_none) {
 				result = SCAN_EXCEED_NONE_PTE;
 				count_vm_event(THP_SCAN_EXCEED_NONE_PTE);
 				goto out;
 			}
+			continue;
 		}
 		if (!pte_present(pteval)) {
 			result = SCAN_PTE_NON_PRESENT;
@@ -591,9 +641,7 @@ static enum scan_result __collapse_huge_page_isolate(struct vm_area_struct *vma,
 
 		/* See collapse_scan_pmd(). */
 		if (folio_maybe_mapped_shared(folio)) {
-			++shared;
-			if (cc->is_khugepaged &&
-			    shared > khugepaged_max_ptes_shared) {
+			if (++shared > max_ptes_shared) {
 				result = SCAN_EXCEED_SHARED_PTE;
 				count_vm_event(THP_SCAN_EXCEED_SHARED_PTE);
 				goto out;
@@ -1270,6 +1318,9 @@ static enum scan_result collapse_scan_pmd(struct mm_struct *mm,
 	unsigned long addr;
 	spinlock_t *ptl;
 	int node = NUMA_NO_NODE, unmapped = 0;
+	unsigned int max_ptes_none = collapse_max_ptes_none(cc, vma);
+	unsigned int max_ptes_shared = collapse_max_ptes_shared(cc);
+	unsigned int max_ptes_swap = collapse_max_ptes_swap(cc);
 
 	VM_BUG_ON(start_addr & ~HPAGE_PMD_MASK);
 
@@ -1294,36 +1345,29 @@ static enum scan_result collapse_scan_pmd(struct mm_struct *mm,
 
 		pte_t pteval = ptep_get(_pte);
 		if (pte_none_or_zero(pteval)) {
-			++none_or_zero;
-			if (!userfaultfd_armed(vma) &&
-			    (!cc->is_khugepaged ||
-			     none_or_zero <= khugepaged_max_ptes_none)) {
-				continue;
-			} else {
+			if (++none_or_zero > max_ptes_none) {
 				result = SCAN_EXCEED_NONE_PTE;
 				count_vm_event(THP_SCAN_EXCEED_NONE_PTE);
 				goto out_unmap;
 			}
+			continue;
 		}
 		if (!pte_present(pteval)) {
-			++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_any(pteval)) {
-					result = SCAN_PTE_UFFD_WP;
-					goto out_unmap;
-				}
-				continue;
-			} else {
+			if (++unmapped > max_ptes_swap) {
 				result = SCAN_EXCEED_SWAP_PTE;
 				count_vm_event(THP_SCAN_EXCEED_SWAP_PTE);
 				goto out_unmap;
 			}
+			/*
+			 * Always be strict with uffd-wp
+			 * enabled swap entries.  Please see
+			 * comment below for pte_uffd_wp().
+			 */
+			if (pte_swp_uffd_wp_any(pteval)) {
+				result = SCAN_PTE_UFFD_WP;
+				goto out_unmap;
+			}
+			continue;
 		}
 		if (pte_uffd_wp(pteval)) {
 			/*
@@ -1366,9 +1410,7 @@ static enum scan_result collapse_scan_pmd(struct mm_struct *mm,
 		 * is shared.
 		 */
 		if (folio_maybe_mapped_shared(folio)) {
-			++shared;
-			if (cc->is_khugepaged &&
-			    shared > khugepaged_max_ptes_shared) {
+			if (++shared > max_ptes_shared) {
 				result = SCAN_EXCEED_SHARED_PTE;
 				count_vm_event(THP_SCAN_EXCEED_SHARED_PTE);
 				goto out_unmap;
@@ -2329,6 +2371,8 @@ static enum scan_result collapse_scan_file(struct mm_struct *mm,
 	int present, swap;
 	int node = NUMA_NO_NODE;
 	enum scan_result result = SCAN_SUCCEED;
+	unsigned int max_ptes_none = collapse_max_ptes_none(cc, NULL);
+	unsigned int max_ptes_swap = collapse_max_ptes_swap(cc);
 
 	present = 0;
 	swap = 0;
@@ -2341,8 +2385,7 @@ static enum scan_result collapse_scan_file(struct mm_struct *mm,
 
 		if (xa_is_value(folio)) {
 			swap += 1 << xas_get_order(&xas);
-			if (cc->is_khugepaged &&
-			    swap > khugepaged_max_ptes_swap) {
+			if (swap > max_ptes_swap) {
 				result = SCAN_EXCEED_SWAP_PTE;
 				count_vm_event(THP_SCAN_EXCEED_SWAP_PTE);
 				break;
@@ -2413,8 +2456,7 @@ static enum scan_result collapse_scan_file(struct mm_struct *mm,
 		cc->progress += HPAGE_PMD_NR;
 
 	if (result == SCAN_SUCCEED) {
-		if (cc->is_khugepaged &&
-		    present < HPAGE_PMD_NR - khugepaged_max_ptes_none) {
+		if (present < HPAGE_PMD_NR - max_ptes_none) {
 			result = SCAN_EXCEED_NONE_PTE;
 			count_vm_event(THP_SCAN_EXCEED_NONE_PTE);
 		} else {
-- 
2.53.0