[PATCH 1/6] mm/page_owner: extract page_owner_next_eligible() from read loop

[Zhen Ni <zhen.ni@easystack.cn>]

Move the page scanning logic out of read_page_owner() into a dedicated
helper, in preparation for using it in the page_owner bpf_iter target.

The helper advances a struct page_owner_scan cursor to the next page
eligible for page_owner output and returns true on a hit. On a hit it
takes a snapshot of the page_owner record inside the page_ext RCU
window.

No change to the output is intended. handle is read from the snapshot,
taken before the non-zero check, so the validated and reported handle
are the same value.

Signed-off-by: Zhen Ni <zhen.ni@easystack.cn>
---
 mm/page_owner.c | 105 ++++++++++++++++++++++++++++++------------------
 1 file changed, 66 insertions(+), 39 deletions(-)

diff --git a/mm/page_owner.c b/mm/page_owner.c
index fbbda7ba914b..bafe474f3360 100644
--- a/mm/page_owner.c
+++ b/mm/page_owner.c
@@ -36,6 +36,16 @@ struct page_owner {
 	pid_t free_tgid;
 };
 
+/*
+ * Cursor and per-page result of page_owner_next_eligible().
+ */
+struct page_owner_scan {
+	/* resume point */
+	unsigned long pfn;
+	struct page *page;
+	struct page_owner po_snap;
+};
+
 struct stack {
 	struct stack_record *stack_record;
 	struct stack *next;
@@ -725,37 +735,24 @@ void __dump_page_owner(const struct page *page)
 	page_ext_put(page_ext);
 }
 
-static ssize_t
-read_page_owner(struct file *file, char __user *buf, size_t count, loff_t *ppos)
+/*
+ * Advance @scan to the next page eligible for page_owner output.
+ * On a hit, fill scan->pfn/page/po_snap and return true; the caller
+ * must advance scan->pfn past the hit before calling again to resume
+ * the scan.
+ */
+static bool page_owner_next_eligible(struct page_owner_scan *scan)
 {
-	unsigned long pfn;
-	struct page *page;
-	struct page_ext *page_ext;
-	struct page_owner *page_owner;
-	depot_stack_handle_t handle;
-	struct page_owner_filter_state *state = file->private_data;
+	unsigned long pfn = scan->pfn;
 
-	if (!static_branch_unlikely(&page_owner_inited))
-		return -EINVAL;
-
-	page = NULL;
-	if (*ppos == 0)
-		pfn = min_low_pfn;
-	else
-		pfn = *ppos;
 	/* Find a valid PFN or the start of a MAX_ORDER_NR_PAGES area */
 	while (!pfn_valid(pfn) && (pfn & (MAX_ORDER_NR_PAGES - 1)) != 0)
 		pfn++;
 
-	/* Find an allocated page */
 	for (; pfn < max_pfn; pfn++) {
-		/*
-		 * This temporary page_owner is required so
-		 * that we can avoid the context switches while holding
-		 * the rcu lock and copying the page owner information to
-		 * user through copy_to_user() or GFP_KERNEL allocations.
-		 */
-		struct page_owner page_owner_tmp;
+		struct page_owner *page_owner;
+		struct page_ext *page_ext;
+		struct page *page;
 
 		/*
 		 * If the new page is in a new MAX_ORDER_NR_PAGES area,
@@ -798,37 +795,67 @@ read_page_owner(struct file *file, char __user *buf, size_t count, loff_t *ppos)
 			goto ext_put_continue;
 
 		/*
-		 * Access to page_ext->handle isn't synchronous so we should
-		 * be careful to access it.
+		 * Take a snapshot of the page_owner record inside the RCU
+		 * window, then validate it, so that print_page_owner()
+		 * reads the checked handle from the same snapshot.
 		 */
-		handle = READ_ONCE(page_owner->handle);
-		if (!handle)
-			goto ext_put_continue;
+		scan->pfn = pfn;
+		scan->page = page;
+		scan->po_snap = *page_owner;
+		page_ext_put(page_ext);
 
+		if (!scan->po_snap.handle)
+			continue;
+
+		return true;
+
+ext_put_continue:
+		page_ext_put(page_ext);
+		cond_resched();
+	}
+
+	return false;
+}
+
+static ssize_t
+read_page_owner(struct file *file, char __user *buf, size_t count, loff_t *ppos)
+{
+	struct page_owner_scan scan;
+	struct page_owner_filter_state *state = file->private_data;
+
+	if (!static_branch_unlikely(&page_owner_inited))
+		return -EINVAL;
+
+	if (*ppos == 0)
+		scan.pfn = min_low_pfn;
+	else
+		scan.pfn = *ppos;
+
+	/* Find an allocated page */
+	while (page_owner_next_eligible(&scan)) {
 		if (state->nid_filter_enabled) {
 			int nid;
-			memdesc_flags_t page_flags = READ_ONCE(page->flags);
+			memdesc_flags_t page_flags =
+				READ_ONCE(scan.page->flags);
 
 			/*
 			 * Bypass PF_POISONED_CHECK() in page_to_nid() to avoid
 			 * VM_BUG_ON when accessing poisoned pages.
 			 */
 			if (page_flags.f == PAGE_POISON_PATTERN)
-				goto ext_put_continue;
+				goto skip_continue;
 			nid = memdesc_nid(&page_flags);
 			if (!node_isset(nid, state->nid_filter))
-				goto ext_put_continue;
+				goto skip_continue;
 		}
 
 		/* Record the next PFN to read in the file offset */
-		*ppos = pfn + 1;
+		*ppos = scan.pfn + 1;
 
-		page_owner_tmp = *page_owner;
-		page_ext_put(page_ext);
-		return print_page_owner(buf, count, pfn, page,
-				&page_owner_tmp, handle, state);
-ext_put_continue:
-		page_ext_put(page_ext);
+		return print_page_owner(buf, count, scan.pfn, scan.page,
+				&scan.po_snap, scan.po_snap.handle, state);
+skip_continue:
+		scan.pfn++;
 		cond_resched();
 	}
 
-- 
2.20.1