[PATCH mm-new v4 2/6] mm: khugepaged: refine scan progress number

[Vernon Yang <vernon2gm@gmail.com>]

Currently, each scan always increases "progress" by HPAGE_PMD_NR,
even if only scanning a single pte.

This patch does not change the original semantics of "progress", it
simply uses the exact number of PTEs counted to replace HPAGE_PMD_NR.

Let me provide a detailed example:

static int hpage_collapse_scan_pmd()
{
	for (addr = start_addr, _pte = pte; _pte < pte + HPAGE_PMD_NR;
	     _pte++, addr += PAGE_SIZE) {
		pte_t pteval = ptep_get(_pte);
		...
		if (pte_uffd_wp(pteval)) { <-- first scan hit
			result = SCAN_PTE_UFFD_WP;
			goto out_unmap;
		}
	}
}

During the first scan, if pte_uffd_wp(pteval) is true, the loop exits
directly. In practice, only one PTE is scanned before termination.
Here, "progress += 1" reflects the actual number of PTEs scanned, but
previously "progress += HPAGE_PMD_NR" always.

Signed-off-by: Vernon Yang <yanglincheng@kylinos.cn>
---
 mm/khugepaged.c | 28 ++++++++++++++++++++++------
 1 file changed, 22 insertions(+), 6 deletions(-)

diff --git a/mm/khugepaged.c b/mm/khugepaged.c
index 2e570f83778c..5c6015ac7b5e 100644
--- a/mm/khugepaged.c
+++ b/mm/khugepaged.c
@@ -1249,6 +1249,7 @@ static enum scan_result collapse_huge_page(struct mm_struct *mm, unsigned long a
 static enum scan_result hpage_collapse_scan_pmd(struct mm_struct *mm,
 						struct vm_area_struct *vma,
 						unsigned long start_addr, bool *mmap_locked,
+						int *cur_progress,
 						struct collapse_control *cc)
 {
 	pmd_t *pmd;
@@ -1264,19 +1265,27 @@ static enum scan_result hpage_collapse_scan_pmd(struct mm_struct *mm,
 	VM_BUG_ON(start_addr & ~HPAGE_PMD_MASK);
 
 	result = find_pmd_or_thp_or_none(mm, start_addr, &pmd);
-	if (result != SCAN_SUCCEED)
+	if (result != SCAN_SUCCEED) {
+		if (cur_progress)
+			*cur_progress = HPAGE_PMD_NR;
 		goto out;
+	}
 
 	memset(cc->node_load, 0, sizeof(cc->node_load));
 	nodes_clear(cc->alloc_nmask);
 	pte = pte_offset_map_lock(mm, pmd, start_addr, &ptl);
 	if (!pte) {
+		if (cur_progress)
+			*cur_progress = HPAGE_PMD_NR;
 		result = SCAN_NO_PTE_TABLE;
 		goto out;
 	}
 
 	for (addr = start_addr, _pte = pte; _pte < pte + HPAGE_PMD_NR;
 	     _pte++, addr += PAGE_SIZE) {
+		if (cur_progress)
+			*cur_progress += 1;
+
 		pte_t pteval = ptep_get(_pte);
 		if (pte_none_or_zero(pteval)) {
 			++none_or_zero;
@@ -2297,6 +2306,7 @@ static enum scan_result collapse_file(struct mm_struct *mm, unsigned long addr,
 
 static enum scan_result hpage_collapse_scan_file(struct mm_struct *mm, unsigned long addr,
 						 struct file *file, pgoff_t start,
+						 int *cur_progress,
 						 struct collapse_control *cc)
 {
 	struct folio *folio = NULL;
@@ -2337,6 +2347,9 @@ static enum scan_result hpage_collapse_scan_file(struct mm_struct *mm, unsigned
 			continue;
 		}
 
+		if (cur_progress)
+			*cur_progress += folio_nr_pages(folio);
+
 		if (folio_order(folio) == HPAGE_PMD_ORDER &&
 		    folio->index == start) {
 			/* Maybe PMD-mapped */
@@ -2466,6 +2479,7 @@ static unsigned int khugepaged_scan_mm_slot(unsigned int pages, enum scan_result
 
 		while (khugepaged_scan.address < hend) {
 			bool mmap_locked = true;
+			int cur_progress = 0;
 
 			cond_resched();
 			if (unlikely(hpage_collapse_test_exit_or_disable(mm)))
@@ -2482,7 +2496,8 @@ static unsigned int khugepaged_scan_mm_slot(unsigned int pages, enum scan_result
 				mmap_read_unlock(mm);
 				mmap_locked = false;
 				*result = hpage_collapse_scan_file(mm,
-					khugepaged_scan.address, file, pgoff, cc);
+					khugepaged_scan.address, file, pgoff,
+					&cur_progress, cc);
 				fput(file);
 				if (*result == SCAN_PTE_MAPPED_HUGEPAGE) {
 					mmap_read_lock(mm);
@@ -2496,7 +2511,8 @@ static unsigned int khugepaged_scan_mm_slot(unsigned int pages, enum scan_result
 				}
 			} else {
 				*result = hpage_collapse_scan_pmd(mm, vma,
-					khugepaged_scan.address, &mmap_locked, cc);
+					khugepaged_scan.address, &mmap_locked,
+					&cur_progress, cc);
 			}
 
 			if (*result == SCAN_SUCCEED)
@@ -2504,7 +2520,7 @@ static unsigned int khugepaged_scan_mm_slot(unsigned int pages, enum scan_result
 
 			/* move to next address */
 			khugepaged_scan.address += HPAGE_PMD_SIZE;
-			progress += HPAGE_PMD_NR;
+			progress += cur_progress;
 			if (!mmap_locked)
 				/*
 				 * We released mmap_lock so break loop.  Note
@@ -2826,11 +2842,11 @@ int madvise_collapse(struct vm_area_struct *vma, unsigned long start,
 			mmap_read_unlock(mm);
 			mmap_locked = false;
 			result = hpage_collapse_scan_file(mm, addr, file, pgoff,
-							  cc);
+							  NULL, cc);
 			fput(file);
 		} else {
 			result = hpage_collapse_scan_pmd(mm, vma, addr,
-							 &mmap_locked, cc);
+							 &mmap_locked, NULL, cc);
 		}
 		if (!mmap_locked)
 			*lock_dropped = true;
-- 
2.51.0