Thread (34 messages) flat view 34 messages, 4 authors, 6d ago
COOLING6d

Revision v2 of 3 in this series.

Revisions (3)
  1. v1 [diff vs current]
  2. v2 current
  3. v3 [diff vs current]

[PATCH v2 11/12] mm/collapse: declare the collapse interface in collapse.h

From: Kiryl Shutsemau <hidden>
Date: 2026-09-10 12:03:37
Also in: lkml
Subsystem: memory management, memory management - thp (transparent huge page), the rest · Maintainers: Andrew Morton, David Hildenbrand, Linus Torvalds

From: "Kiryl Shutsemau (Meta)" <kas@kernel.org>

A collapse takes four calls:

  - collapse_control_init() - set up the control a caller carries;
  - collapse_scan_pmd() - scan one PTE table, under mmap_lock;
  - collapse_run_pmd() - collapse what the scan found, no mmap_lock;
  - collapse_control_release() - done with the control.

All four are static in khugepaged.c, as are collapse_possible_orders(),
which says what a VMA allows, and the revalidate a caller needs once a
collapse has given the mmap_lock up.  No other file can ask for a collapse
without them.

Declare them in collapse.h, with a comment stating the order they are
called in and who holds the lock over each step.

hugepage_vma_revalidate() becomes collapse_vma_revalidate(): it is part of
what a collapse offers now, not a helper of the daemon.

Preparation for implementing MADV_COLLAPSE in madvise.c.

No functional change.

Assisted-by: LLM
Signed-off-by: Kiryl Shutsemau (Meta) <kas@kernel.org>
---
 mm/collapse.h   | 44 ++++++++++++++++++++++++++++++++++++++++++++
 mm/khugepaged.c | 18 +++++++++---------
 2 files changed, 53 insertions(+), 9 deletions(-)
diff --git a/mm/collapse.h b/mm/collapse.h
index 346859a2184f..1ebbbf63fb25 100644
--- a/mm/collapse.h
+++ b/mm/collapse.h
@@ -106,4 +106,48 @@ struct collapse_control {
 	bool scan_retract_only;
 };
 
+/* Which orders a VMA may collapse to, zero when it may not collapse at all */
+unsigned long collapse_possible_orders(struct vm_area_struct *vma,
+		vm_flags_t vm_flags, enum tva_type tva_flags);
+
+/*
+ * A caller states what it allows in cc->policy and then hands over one PTE
+ * table's worth of a VMA at a time:
+ *
+ *     collapse_control_init(cc)         once, before the first table
+ *     collapse_scan_pmd(vma, addr, ...) per table
+ *     collapse_run_pmd(mm, addr, cc)    when a scan found work
+ *     collapse_control_release(cc)      once, when done with the control
+ *
+ * The caller holds mmap_lock for reading over the scan and passes an address
+ * within @vma, aligned to the PTE table the scan is to judge.
+ *
+ * The scan returns with that lock still held.  It only reads, and almost every
+ * table it is offered has nothing to collapse, so a caller walks a whole VMA
+ * under the one lock it took to get there.  SCAN_SUCCEED means there is
+ * something to collapse; anything else is why there is not.
+ *
+ * The run is called without the lock and returns without it, taking what it
+ * needs in between: what it does -- allocate, isolate, copy, flush -- is slow
+ * enough that a writer would wait behind it.  The caller gives the lock up
+ * first, and with it @vma and anything derived under it, so a caller carrying
+ * on has to look up again with collapse_vma_revalidate().  The run revalidates
+ * for itself rather than trusting what the scan saw.
+ *
+ * A scan that found something has to be run: the file side takes a reference on
+ * the file while it still has the VMA to take it from, and the run is what
+ * gives it back.
+ */
+void collapse_control_init(struct collapse_control *cc);
+void collapse_control_release(struct collapse_control *cc);
+enum scan_result collapse_scan_pmd(struct vm_area_struct *vma,
+		unsigned long addr, struct collapse_control *cc,
+		unsigned long orders);
+enum scan_result collapse_run_pmd(struct mm_struct *mm, unsigned long addr,
+		struct collapse_control *cc);
+enum scan_result collapse_vma_revalidate(struct mm_struct *mm,
+		unsigned long address, bool expect_anon,
+		struct vm_area_struct **vmap, struct collapse_control *cc,
+		unsigned int order);
+
 #endif	/* __MM_COLLAPSE_H */
diff --git a/mm/khugepaged.c b/mm/khugepaged.c
index 9e77f71a788d..77f34aedf0f2 100644
--- a/mm/khugepaged.c
+++ b/mm/khugepaged.c
@@ -498,7 +498,7 @@ void __khugepaged_enter(struct mm_struct *mm)
  * Check what orders are possible based on the vma and collapse type.
  * This is used to determine if mTHP collapse is a viable option.
  */
-static unsigned long collapse_possible_orders(struct vm_area_struct *vma,
+unsigned long collapse_possible_orders(struct vm_area_struct *vma,
 		vm_flags_t vm_flags, enum tva_type tva_flags)
 {
 	unsigned long orders;
@@ -1016,7 +1016,7 @@ static int collapse_find_target_node(struct collapse_control *cc)
  * Returns enum scan_result value.
  */
 
-static enum scan_result hugepage_vma_revalidate(struct mm_struct *mm, unsigned long address,
+enum scan_result collapse_vma_revalidate(struct mm_struct *mm, unsigned long address,
 		bool expect_anon, struct vm_area_struct **vmap,
 		struct collapse_control *cc, unsigned int order)
 {
@@ -1264,7 +1264,7 @@ static enum scan_result collapse_huge_page(struct mm_struct *mm, unsigned long s
 	}
 
 	mmap_read_lock(mm);
-	result = hugepage_vma_revalidate(mm, pmd_addr, /*expect_anon=*/ true,
+	result = collapse_vma_revalidate(mm, pmd_addr, /*expect_anon=*/ true,
 					 &vma, cc, order);
 	if (result != SCAN_SUCCEED) {
 		mmap_read_unlock(mm);
@@ -1299,7 +1299,7 @@ static enum scan_result collapse_huge_page(struct mm_struct *mm, unsigned long s
 	 * mmap_lock.
 	 */
 	mmap_write_lock(mm);
-	result = hugepage_vma_revalidate(mm, pmd_addr, /*expect_anon=*/ true,
+	result = collapse_vma_revalidate(mm, pmd_addr, /*expect_anon=*/ true,
 					 &vma, cc, order);
 	if (result != SCAN_SUCCEED)
 		goto out_up_write;
@@ -2743,13 +2743,13 @@ static enum scan_result collapse_scan_file(struct mm_struct *mm,
 	return result;
 }
 
-static void collapse_control_init(struct collapse_control *cc)
+void collapse_control_init(struct collapse_control *cc)
 {
 	cc->progress = 0;
 	cc->scan_file = NULL;
 }
 
-static void collapse_control_release(struct collapse_control *cc)
+void collapse_control_release(struct collapse_control *cc)
 {
 	/* A scan that took a file reference should have been run */
 	if (WARN_ON_ONCE(cc->scan_file)) {
@@ -2758,7 +2758,7 @@ static void collapse_control_release(struct collapse_control *cc)
 	}
 }
 
-static enum scan_result collapse_scan_pmd(struct vm_area_struct *vma,
+enum scan_result collapse_scan_pmd(struct vm_area_struct *vma,
 		unsigned long addr, struct collapse_control *cc,
 		unsigned long orders)
 {
@@ -2802,7 +2802,7 @@ static enum scan_result collapse_scan_pmd(struct vm_area_struct *vma,
 	return result;
 }
 
-static enum scan_result collapse_run_pmd(struct mm_struct *mm,
+enum scan_result collapse_run_pmd(struct mm_struct *mm,
 		unsigned long addr, struct collapse_control *cc)
 {
 	struct file *file = cc->scan_file;
@@ -3256,7 +3256,7 @@ int madvise_collapse(struct vm_area_struct *vma, unsigned long start,
 		if (!vma) {
 			cond_resched();
 			mmap_read_lock(mm);
-			result = hugepage_vma_revalidate(mm, addr, false, &found,
+			result = collapse_vma_revalidate(mm, addr, false, &found,
 							 cc, HPAGE_PMD_ORDER);
 			if (result != SCAN_SUCCEED) {
 				last_fail = result;
-- 
2.54.0

Keyboard shortcuts
hback out one level
jnext message in thread
kprevious message in thread
ldrill in
Escclose help / fold thread tree
?toggle this help