mm/util: introduce snapshot_page()

This commit refactors __dump_page() into snapshot_page().

snapshot_page() tries to take a faithful snapshot of a page and its folio
representation.  The snapshot is returned in the struct page_snapshot
parameter along with additional flags that are best retrieved at snapshot
creation time to reduce race windows.

This function is intended to be used by callers that need a stable
representation of a struct page and struct folio so that pointers or page
information doesn't change while working on a page.

The idea and original implementation of snapshot_page() comes from Matthew
Wilcox with suggestions for improvements from David Hildenbrand.  All bugs
and misconceptions are mine.

[[email protected]: fix set_ps_flags() commentary]
  Link: https://lkml.kernel.org/r/[email protected]
Link: https://lkml.kernel.org/r/637a03a05cb2e3df88f84ff9e9f9642374ef813a.1752499009.git.luizcap@redhat.com
Signed-off-by: Luiz Capitulino <[email protected]>
Reviewed-by: Shivank Garg <[email protected]>
Tested-by: Harry Yoo <[email protected]>
Acked-by: David Hildenbrand <[email protected]>
Cc: Matthew Wilcox (Oracle) <[email protected]>
Cc: Oscar Salvador <[email protected]>
Cc: SeongJae Park <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>

Author: luiz-cap

include/linux/mm.h

@@ -4199,4 +4199,23 @@ static inline bool page_pool_page_is_pp(struct page *page)
 }
 #endif
 
+#define PAGE_SNAPSHOT_FAITHFUL (1 << 0)
+#define PAGE_SNAPSHOT_PG_BUDDY (1 << 1)
+#define PAGE_SNAPSHOT_PG_IDLE  (1 << 2)
+
+struct page_snapshot {
+	struct folio folio_snapshot;
+	struct page page_snapshot;
+	unsigned long pfn;
+	unsigned long idx;
+	unsigned long flags;
+};
+
+static inline bool snapshot_page_is_faithful(const struct page_snapshot *ps)
+{
+	return ps->flags & PAGE_SNAPSHOT_FAITHFUL;
+}
+
+void snapshot_page(struct page_snapshot *ps, const struct page *page);
+
 #endif /* _LINUX_MM_H */

mm/debug.c

@@ -129,47 +129,13 @@ static void __dump_folio(struct folio *folio, struct page *page,
 
 static void __dump_page(const struct page *page)
 {
-	struct folio *foliop, folio;
-	struct page precise;
-	unsigned long head;
-	unsigned long pfn = page_to_pfn(page);
-	unsigned long idx, nr_pages = 1;
-	int loops = 5;
-
-again:
-	memcpy(&precise, page, sizeof(*page));
-	head = precise.compound_head;
-	if ((head & 1) == 0) {
-		foliop = (struct folio *)&precise;
-		idx = 0;
-		if (!folio_test_large(foliop))
-			goto dump;
-		foliop = (struct folio *)page;
-	} else {
-		foliop = (struct folio *)(head - 1);
-		idx = folio_page_idx(foliop, page);
-	}
+	struct page_snapshot ps;
 
-	if (idx < MAX_FOLIO_NR_PAGES) {
-		memcpy(&folio, foliop, 2 * sizeof(struct page));
-		nr_pages = folio_nr_pages(&folio);
-		if (nr_pages > 1)
-			memcpy(&folio.__page_2, &foliop->__page_2,
-			       sizeof(struct page));
-		foliop = &folio;
-	}
-
-	if (idx > nr_pages) {
-		if (loops-- > 0)
-			goto again;
+	snapshot_page(&ps, page);
+	if (!snapshot_page_is_faithful(&ps))
 		pr_warn("page does not match folio\n");
-		precise.compound_head &= ~1UL;
-		foliop = (struct folio *)&precise;
-		idx = 0;
-	}
 
-dump:
-	__dump_folio(foliop, &precise, pfn, idx);
+	__dump_folio(&ps.folio_snapshot, &ps.page_snapshot, ps.pfn, ps.idx);
 }
 
 void dump_page(const struct page *page, const char *reason)

mm/util.c

@@ -25,6 +25,7 @@
 #include <linux/sizes.h>
 #include <linux/compat.h>
 #include <linux/fsnotify.h>
+#include <linux/page_idle.h>
 
 #include <linux/uaccess.h>
 
@@ -1172,6 +1173,86 @@ int compat_vma_mmap_prepare(struct file *file, struct vm_area_struct *vma)
 }
 EXPORT_SYMBOL(compat_vma_mmap_prepare);
 
+static void set_ps_flags(struct page_snapshot *ps, const struct folio *folio,
+			 const struct page *page)
+{
+	/*
+	 * Only the first page of a high-order buddy page has PageBuddy() set.
+	 * So we have to check manually whether this page is part of a high-
+	 * order buddy page.
+	 */
+	if (PageBuddy(page))
+		ps->flags |= PAGE_SNAPSHOT_PG_BUDDY;
+	else if (page_count(page) == 0 && is_free_buddy_page(page))
+		ps->flags |= PAGE_SNAPSHOT_PG_BUDDY;
+
+	if (folio_test_idle(folio))
+		ps->flags |= PAGE_SNAPSHOT_PG_IDLE;
+}
+
+/**
+ * snapshot_page() - Create a snapshot of a struct page
+ * @ps: Pointer to a struct page_snapshot to store the page snapshot
+ * @page: The page to snapshot
+ *
+ * Create a snapshot of the page and store both its struct page and struct
+ * folio representations in @ps.
+ *
+ * A snapshot is marked as "faithful" if the compound state of @page was
+ * stable and allowed safe reconstruction of the folio representation. In
+ * rare cases where this is not possible (e.g. due to folio splitting),
+ * snapshot_page() falls back to treating @page as a single page and the
+ * snapshot is marked as "unfaithful". The snapshot_page_is_faithful()
+ * helper can be used to check for this condition.
+ */
+void snapshot_page(struct page_snapshot *ps, const struct page *page)
+{
+	unsigned long head, nr_pages = 1;
+	struct folio *foliop;
+	int loops = 5;
+
+	ps->pfn = page_to_pfn(page);
+	ps->flags = PAGE_SNAPSHOT_FAITHFUL;
+
+again:
+	memset(&ps->folio_snapshot, 0, sizeof(struct folio));
+	memcpy(&ps->page_snapshot, page, sizeof(*page));
+	head = ps->page_snapshot.compound_head;
+	if ((head & 1) == 0) {
+		ps->idx = 0;
+		foliop = (struct folio *)&ps->page_snapshot;
+		if (!folio_test_large(foliop)) {
+			set_ps_flags(ps, page_folio(page), page);
+			memcpy(&ps->folio_snapshot, foliop,
+			       sizeof(struct page));
+			return;
+		}
+		foliop = (struct folio *)page;
+	} else {
+		foliop = (struct folio *)(head - 1);
+		ps->idx = folio_page_idx(foliop, page);
+	}
+
+	if (ps->idx < MAX_FOLIO_NR_PAGES) {
+		memcpy(&ps->folio_snapshot, foliop, 2 * sizeof(struct page));
+		nr_pages = folio_nr_pages(&ps->folio_snapshot);
+		if (nr_pages > 1)
+			memcpy(&ps->folio_snapshot.__page_2, &foliop->__page_2,
+			       sizeof(struct page));
+		set_ps_flags(ps, foliop, page);
+	}
+
+	if (ps->idx > nr_pages) {
+		if (loops-- > 0)
+			goto again;
+		clear_compound_head(&ps->page_snapshot);
+		foliop = (struct folio *)&ps->page_snapshot;
+		memcpy(&ps->folio_snapshot, foliop, sizeof(struct page));
+		ps->flags = 0;
+		ps->idx = 0;
+	}
+}
+
 #ifdef CONFIG_MMU
 /**
  * folio_pte_batch - detect a PTE batch for a large folio