[PATCH v3 10/12] mm/collapse: work out the orders a VMA allows once per VMA

[Kiryl Shutsemau]

From: "Kiryl Shutsemau (Meta)" <kas@xxxxxxxxxx>

The scan asked collapse_possible_orders() for every PTE table, for an
answer that is a property of the VMA.  Both callers walk a VMA a table at
a time, so let them work it out once and pass the mask in.  It is only
good while the lock that produced it is held, so madvise_collapse() takes
it again after every collapse.

The mask is then sampled once per VMA rather than once per table.  A thp
enabled knob written during a walk takes effect one VMA later, and cannot
widen a collapse: hugepage_vma_revalidate() tests the order again under
the lock the collapse retakes.

Assisted-by: LLM
Reviewed-by: Zi Yan <ziy@xxxxxxxxxx>
Reviewed-by: Baolin Wang <baolin.wang@xxxxxxxxxxxxxxxxx>
Signed-off-by: Kiryl Shutsemau (Meta) <kas@xxxxxxxxxx>
---
 mm/khugepaged.c | 32 ++++++++++++++++++--------------
 1 file changed, 18 insertions(+), 14 deletions(-)

diff --git a/mm/khugepaged.c b/mm/khugepaged.c
index 9e6b2af6519e..12cb67d8df32 100644
--- a/mm/khugepaged.c
+++ b/mm/khugepaged.c
@@ -1549,12 +1549,12 @@ static enum scan_result mthp_collapse(struct mm_struct *mm, unsigned long addres
 }
 
 static enum scan_result collapse_scan_anon_pmd(struct vm_area_struct *vma,
-		unsigned long start_addr, struct collapse_control *cc)
+		unsigned long start_addr, struct collapse_control *cc,
+		unsigned long enabled_orders)
 {
 	const unsigned int max_ptes_shared = collapse_max_ptes_shared(cc, HPAGE_PMD_ORDER);
 	const unsigned int max_ptes_swap = collapse_max_ptes_swap(cc, HPAGE_PMD_ORDER);
 	unsigned int max_ptes_none = collapse_max_ptes_none(cc, vma, HPAGE_PMD_ORDER);
-	enum tva_type tva_flags = cc->policy.tva_type;
 	struct mm_struct *mm = vma->vm_mm;
 	pmd_t *pmd;
 	pte_t *pte, *_pte, pteval;
@@ -1565,7 +1565,6 @@ static enum scan_result collapse_scan_anon_pmd(struct vm_area_struct *vma,
 	struct folio *folio = NULL;
 	unsigned long failed_pfn = -1;
 	unsigned long addr;
-	unsigned long enabled_orders;
 	spinlock_t *ptl;
 	int node = NUMA_NO_NODE, unmapped = 0;
 
@@ -1579,8 +1578,6 @@ static enum scan_result collapse_scan_anon_pmd(struct vm_area_struct *vma,
 
 	collapse_scan_reset(cc);
 
-	enabled_orders = collapse_possible_orders(vma, vma->vm_flags, tva_flags);
-
 	/*
 	 * If PMD is the only enabled order, enforce max_ptes_none, otherwise
 	 * scan all pages to populate the bitmap for mTHP collapse. The bitmap
@@ -2765,7 +2762,8 @@ static void collapse_control_release(struct collapse_control *cc)
 }
 
 static enum scan_result collapse_scan_pmd(struct vm_area_struct *vma,
-		unsigned long addr, struct collapse_control *cc)
+		unsigned long addr, struct collapse_control *cc,
+		unsigned long orders)
 {
 	enum scan_result result;
 	pgoff_t pgoff;
@@ -2775,7 +2773,7 @@ static enum scan_result collapse_scan_pmd(struct vm_area_struct *vma,
 	collapse_put_scan_file(cc);
 
 	if (vma_is_anonymous(vma))
-		return collapse_scan_anon_pmd(vma, addr, cc);
+		return collapse_scan_anon_pmd(vma, addr, cc, orders);
 
 	pgoff = linear_page_index(vma, addr);
 	result = collapse_scan_file(vma->vm_mm, addr, vma->vm_file, pgoff, cc);
@@ -2885,15 +2883,17 @@ static void collapse_scan_mm_slot(unsigned int progress_max,
 
 	vma_iter_init(&vmi, mm, khugepaged_scan.address);
 	for_each_vma(vmi, vma) {
-		unsigned long hstart, hend;
+		unsigned long hstart, hend, orders;
 
 		cond_resched();
 		if (unlikely(collapse_test_exit_or_disable(mm))) {
 			cc->progress++;
 			break;
 		}
-		if (!collapse_possible_orders(vma, vma->vm_flags,
-					      TVA_KHUGEPAGED)) {
+		/* One mask for the whole VMA */
+		orders = collapse_possible_orders(vma, vma->vm_flags,
+						  cc->policy.tva_type);
+		if (!orders) {
 			cc->progress++;
 			continue;
 		}
@@ -2922,7 +2922,7 @@ static void collapse_scan_mm_slot(unsigned int progress_max,
 			/* move to next address */
 			khugepaged_scan.address += HPAGE_PMD_SIZE;
 
-			*result = collapse_scan_pmd(vma, addr, cc);
+			*result = collapse_scan_pmd(vma, addr, cc, orders);
 			/* Nothing to do here, and the lock is still ours */
 			if (*result != SCAN_SUCCEED &&
 			    *result != SCAN_PTE_MAPPED_HUGEPAGE) {
@@ -3207,14 +3207,16 @@ int madvise_collapse(struct vm_area_struct *vma, unsigned long start,
 {
 	struct collapse_control *cc;
 	struct mm_struct *mm = vma->vm_mm;
-	unsigned long hstart, hend, addr;
+	unsigned long hstart, hend, addr, orders;
 	enum scan_result last_fail = SCAN_FAIL;
 	int thps = 0;
 
 	BUG_ON(vma->vm_start > start);
 	BUG_ON(vma->vm_end < end);
 
-	if (!collapse_possible_orders(vma, vma->vm_flags, TVA_FORCED_COLLAPSE))
+	orders = collapse_possible_orders(vma, vma->vm_flags,
+					  TVA_FORCED_COLLAPSE);
+	if (!orders)
 		return -EINVAL;
 
 	hstart = ALIGN(start, HPAGE_PMD_SIZE);
@@ -3252,9 +3254,11 @@ int madvise_collapse(struct vm_area_struct *vma, unsigned long start,
 			}
 			vma = found;
 			hend = min(hend, vma->vm_end & HPAGE_PMD_MASK);
+			orders = collapse_possible_orders(vma, vma->vm_flags,
+							  cc->policy.tva_type);
 		}
 
-		result = collapse_scan_pmd(vma, addr, cc);
+		result = collapse_scan_pmd(vma, addr, cc, orders);
 		/* Nothing to do here, and the lock is still ours */
 		if (result != SCAN_SUCCEED && result != SCAN_PTE_MAPPED_HUGEPAGE)
 			goto tally;
-- 
2.54.0