[RESEND RFC PATCH v2 2/5] mm/khugepaged: add damon_collapse_folio_range() for external callers

[Lian Wang <lianux.mm@gmail.com>]

Export a thin wrapper around collapse_huge_page() that allows external
subsystems such as DAMON to trigger THP collapse on a target address
range.

Currently restricted to PMD order (HPAGE_PMD_ORDER), since
collapse_huge_page() does not yet support arbitrary mTHP orders.
The restriction can be relaxed when khugepaged gains mTHP support.

The caller must hold a reference to @mm.  Do not hold mmap lock:
collapse_huge_page() acquires mmap_read_lock for validation, releases
it, then acquires mmap_write_lock for the actual collapse.  Holding
an outer mmap_read_lock would cause a self-deadlock when the same
thread attempts the inner mmap_write_lock.

Co-developed-by: Kunwu Chan <kunwu.chan@gmail.com>
Signed-off-by: Kunwu Chan <kunwu.chan@gmail.com>
Signed-off-by: Lian Wang <lianux.mm@gmail.com>
Signed-off-by: Lian Wang <lianux.wang@processmission.com>
---
 include/linux/khugepaged.h |  9 ++++++++
 mm/khugepaged.c            | 46 ++++++++++++++++++++++++++++++++++++++
 2 files changed, 55 insertions(+)

diff --git a/include/linux/khugepaged.h b/include/linux/khugepaged.h
index d7a9053ff4fe..f7d49cba712f 100644
--- a/include/linux/khugepaged.h
+++ b/include/linux/khugepaged.h
@@ -20,6 +20,9 @@ extern bool current_is_khugepaged(void);
 void collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr,
 		bool install_pmd);
 
+int damon_collapse_folio_range(struct mm_struct *mm, unsigned long start_addr,
+			       unsigned int target_order);
+
 static inline void khugepaged_fork(struct mm_struct *mm, struct mm_struct *oldmm)
 {
 	if (mm_flags_test(MMF_VM_HUGEPAGE, oldmm))
@@ -47,6 +50,12 @@ static inline void collapse_pte_mapped_thp(struct mm_struct *mm,
 {
 }
 
+static inline int damon_collapse_folio_range(struct mm_struct *mm,
+		unsigned long start_addr, unsigned int target_order)
+{
+	return -EINVAL;
+}
+
 static inline void khugepaged_min_free_kbytes_update(void)
 {
 }
diff --git a/mm/khugepaged.c b/mm/khugepaged.c
index 617bca76db49..7fe9ce1e0533 100644
--- a/mm/khugepaged.c
+++ b/mm/khugepaged.c
@@ -3272,3 +3272,49 @@ int madvise_collapse(struct vm_area_struct *vma, unsigned long start,
 	return thps == ((hend - hstart) >> HPAGE_PMD_SHIFT) ? 0
 			: madvise_collapse_errno(last_fail);
 }
+
+/**
+ * damon_collapse_folio_range() - Collapse base pages in range into a THP
+ * @mm:         mm_struct of the target process
+ * @start_addr: start address (must be order-aligned)
+ * @target_order: page order of the collapse result (currently only
+ *                HPAGE_PMD_ORDER is supported)
+ *
+ * Thin wrapper around collapse_huge_page() for external callers such as
+ * DAMON.  The caller must hold a reference to @mm.  Do not hold mmap
+ * lock: collapse_huge_page() acquires mmap_read_lock for validation,
+ * releases it, then acquires mmap_write_lock for the collapse.  Holding
+ * an outer mmap_read_lock would self-deadlock.
+ *
+ * Return: 0 on success, -EINVAL on bad arguments, negative error from
+ *         madvise_collapse_errno() otherwise.
+ */
+int damon_collapse_folio_range(struct mm_struct *mm, unsigned long start_addr,
+			       unsigned int target_order)
+{
+	struct collapse_control *cc;
+	enum scan_result result;
+
+	if (target_order != HPAGE_PMD_ORDER) {
+		pr_warn_once("%s: only PMD order (%u) is supported, got %u\n",
+			     __func__, HPAGE_PMD_ORDER, target_order);
+		return -EINVAL;
+	}
+	if (start_addr & ((PAGE_SIZE << target_order) - 1))
+		return -EINVAL;
+
+	cc = kmalloc_obj(*cc);
+	if (!cc)
+		return -ENOMEM;
+	cc->is_khugepaged = false;
+	cc->progress = 0;
+
+	lru_add_drain_all();
+
+	result = collapse_huge_page(mm, start_addr, 1, 0, cc, target_order);
+	kfree(cc);
+	if (result == SCAN_SUCCEED || result == SCAN_PMD_MAPPED)
+		return 0;
+	return madvise_collapse_errno(result);
+}
+EXPORT_SYMBOL_GPL(damon_collapse_folio_range);