mm: introduce a new page type for page pool in page type

Currently, the condition 'page->pp_magic == PP_SIGNATURE' is used to
determine if a page belongs to a page pool.  However, with the planned
removal of @pp_magic, we should instead leverage the page_type in struct
page, such as PGTY_netpp, for this purpose.

Introduce and use the page type APIs e.g.  PageNetpp(), __SetPageNetpp(),
and __ClearPageNetpp() instead, and remove the existing APIs accessing
@pp_magic e.g.  page_pool_page_is_pp(), netmem_or_pp_magic(), and
netmem_clear_pp_magic().

Plus, add @page_type to struct net_iov at the same offset as struct page
so as to use the page_type APIs for struct net_iov as well.  While at it,
reorder @type and @owner in struct net_iov to avoid a hole and increasing
the struct size.

This work was inspired by the following link:

  https://lore.kernel.org/all/[email protected]/

While at it, move the sanity check for page pool to on the free path.

[[email protected]: gate the sanity check, per Johannes]
  Link: https://lkml.kernel.org/r/[email protected]
Link: https://lkml.kernel.org/r/[email protected]
Co-developed-by: Pavel Begunkov <[email protected]>
Signed-off-by: Pavel Begunkov <[email protected]>
Signed-off-by: Byungchul Park <[email protected]>
Suggested-by: David Hildenbrand <[email protected]>
Acked-by: David Hildenbrand <[email protected]>
Acked-by: Zi Yan <[email protected]>
Acked-by: Vlastimil Babka <[email protected]>
Reviewed-by: Toke Høiland-Jørgensen <[email protected]>
Acked-by: Mike Rapoport (Microsoft) <[email protected]>
Acked-by: Johannes Weiner <[email protected]>
Acked-by: Jakub Kicinski <[email protected]>
Acked-by: Jesper Dangaard Brouer <[email protected]>
Acked-by: Ilias Apalodimas <[email protected]>
Cc: Alexei Starovoitov <[email protected]>
Cc: Andrew Lunn <[email protected]>
Cc: Baolin Wang <[email protected]>
Cc: Brendan Jackman <[email protected]>
Cc: Christian Brauner <[email protected]>
Cc: Daniel Borkmann <[email protected]>
Cc: David S. Miller <[email protected]>
Cc: David Wei <[email protected]>
Cc: Dragos Tatulea <[email protected]>
Cc: Eric Dumazet <[email protected]>
Cc: John Fastabend <[email protected]>
Cc: Leon Romanovsky <[email protected]>
Cc: Liam Howlett <[email protected]>
Cc: Lorenzo Stoakes (Oracle) <[email protected]>
Cc: Mark Bloch <[email protected]>
Cc: Matthew Wilcox (Oracle) <[email protected]>
Cc: Michal Hocko <[email protected]>
Cc: Mina Almasry <[email protected]>
Cc: Paolo Abeni <[email protected]>
Cc: Saeed Mahameed <[email protected]>
Cc: Simon Horman <[email protected]>
Cc: Stanislav Fomichev <[email protected]>
Cc: Stehen Rothwell <[email protected]>
Cc: Suren Baghdasaryan <[email protected]>
Cc: Taehee Yoo <[email protected]>
Cc: Tariq Toukan <[email protected]>
Cc: Usama Arif <[email protected]>
Cc: Yu Zhao <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>

drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c

@@ -707,7 +707,7 @@ static void mlx5e_free_xdpsq_desc(struct mlx5e_xdpsq *sq,
 				xdpi = mlx5e_xdpi_fifo_pop(xdpi_fifo);
 				page = xdpi.page.page;
 
-				/* No need to check page_pool_page_is_pp() as we
+				/* No need to check PageNetpp() as we
 				 * know this is a page_pool page.
 				 */
 				page_pool_recycle_direct(pp_page_to_nmdesc(page)->pp,

include/linux/mm.h

@@ -4840,10 +4840,9 @@ int arch_lock_shadow_stack_status(struct task_struct *t, unsigned long status);
  * DMA mapping IDs for page_pool
  *
  * When DMA-mapping a page, page_pool allocates an ID (from an xarray) and
- * stashes it in the upper bits of page->pp_magic. We always want to be able to
- * unambiguously identify page pool pages (using page_pool_page_is_pp()). Non-PP
- * pages can have arbitrary kernel pointers stored in the same field as pp_magic
- * (since it overlaps with page->lru.next), so we must ensure that we cannot
+ * stashes it in the upper bits of page->pp_magic. Non-PP pages can have
+ * arbitrary kernel pointers stored in the same field as pp_magic (since
+ * it overlaps with page->lru.next), so we must ensure that we cannot
  * mistake a valid kernel pointer with any of the values we write into this
  * field.
  *
@@ -4878,26 +4877,6 @@ int arch_lock_shadow_stack_status(struct task_struct *t, unsigned long status);
 #define PP_DMA_INDEX_MASK GENMASK(PP_DMA_INDEX_BITS + PP_DMA_INDEX_SHIFT - 1, \
 				  PP_DMA_INDEX_SHIFT)
 
-/* Mask used for checking in page_pool_page_is_pp() below. page->pp_magic is
- * OR'ed with PP_SIGNATURE after the allocation in order to preserve bit 0 for
- * the head page of compound page and bit 1 for pfmemalloc page, as well as the
- * bits used for the DMA index. page_is_pfmemalloc() is checked in
- * __page_pool_put_page() to avoid recycling the pfmemalloc page.
- */
-#define PP_MAGIC_MASK ~(PP_DMA_INDEX_MASK | 0x3UL)
-
-#ifdef CONFIG_PAGE_POOL
-static inline bool page_pool_page_is_pp(const struct page *page)
-{
-	return (page->pp_magic & PP_MAGIC_MASK) == PP_SIGNATURE;
-}
-#else
-static inline bool page_pool_page_is_pp(const struct page *page)
-{
-	return false;
-}
-#endif
-
 #define PAGE_SNAPSHOT_FAITHFUL (1 << 0)
 #define PAGE_SNAPSHOT_PG_BUDDY (1 << 1)
 #define PAGE_SNAPSHOT_PG_IDLE  (1 << 2)

include/linux/page-flags.h

@@ -923,6 +923,7 @@ enum pagetype {
 	PGTY_zsmalloc		= 0xf6,
 	PGTY_unaccepted		= 0xf7,
 	PGTY_large_kmalloc	= 0xf8,
+	PGTY_netpp		= 0xf9,
 
 	PGTY_mapcount_underflow = 0xff
 };
@@ -1055,6 +1056,11 @@ PAGE_TYPE_OPS(Zsmalloc, zsmalloc, zsmalloc)
 PAGE_TYPE_OPS(Unaccepted, unaccepted, unaccepted)
 PAGE_TYPE_OPS(LargeKmalloc, large_kmalloc, large_kmalloc)
 
+/*
+ * Marks page_pool allocated pages.
+ */
+PAGE_TYPE_OPS(Netpp, netpp, netpp)
+
 /**
  * PageHuge - Determine if the page belongs to hugetlbfs
  * @page: The page to test.

include/net/netmem.h

@@ -110,10 +110,21 @@ struct net_iov {
 			atomic_long_t pp_ref_count;
 		};
 	};
-	struct net_iov_area *owner;
+
+	unsigned int page_type;
 	enum net_iov_type type;
+	struct net_iov_area *owner;
 };
 
+/* Make sure 'the offset of page_type in struct page == the offset of
+ * type in struct net_iov'.
+ */
+#define NET_IOV_ASSERT_OFFSET(pg, iov)			\
+	static_assert(offsetof(struct page, pg) ==	\
+		      offsetof(struct net_iov, iov))
+NET_IOV_ASSERT_OFFSET(page_type, page_type);
+#undef NET_IOV_ASSERT_OFFSET
+
 struct net_iov_area {
 	/* Array of net_iovs for this area. */
 	struct net_iov *niovs;
@@ -256,7 +267,7 @@ static inline unsigned long netmem_pfn_trace(netmem_ref netmem)
  */
 #define pp_page_to_nmdesc(p)						\
 ({									\
-	DEBUG_NET_WARN_ON_ONCE(!page_pool_page_is_pp(p));		\
+	DEBUG_NET_WARN_ON_ONCE(!PageNetpp(p));				\
 	__pp_page_to_nmdesc(p);						\
 })
 

mm/page_alloc.c

@@ -1043,7 +1043,6 @@ static inline bool page_expected_state(struct page *page,
 #ifdef CONFIG_MEMCG
 			page->memcg_data |
 #endif
-			page_pool_page_is_pp(page) |
 			(page->flags.f & check_flags)))
 		return false;
 
@@ -1070,8 +1069,6 @@ static const char *page_bad_reason(struct page *page, unsigned long flags)
 	if (unlikely(page->memcg_data))
 		bad_reason = "page still charged to cgroup";
 #endif
-	if (unlikely(page_pool_page_is_pp(page)))
-		bad_reason = "page_pool leak";
 	return bad_reason;
 }
 
@@ -1380,9 +1377,17 @@ __always_inline bool __free_pages_prepare(struct page *page,
 		mod_mthp_stat(order, MTHP_STAT_NR_ANON, -1);
 		folio->mapping = NULL;
 	}
-	if (unlikely(page_has_type(page)))
+	if (unlikely(page_has_type(page))) {
+		/* networking expects to clear its page type before releasing */
+		if (is_check_pages_enabled()) {
+			if (unlikely(PageNetpp(page))) {
+				bad_page(page, "page_pool leak");
+				return false;
+			}
+		}
 		/* Reset the page_type (which overlays _mapcount) */
 		page->page_type = UINT_MAX;
+	}
 
 	if (is_check_pages_enabled()) {
 		if (free_page_is_bad(page))

net/core/netmem_priv.h

@@ -8,21 +8,18 @@ static inline unsigned long netmem_get_pp_magic(netmem_ref netmem)
 	return netmem_to_nmdesc(netmem)->pp_magic & ~PP_DMA_INDEX_MASK;
 }
 
-static inline void netmem_or_pp_magic(netmem_ref netmem, unsigned long pp_magic)
-{
-	netmem_to_nmdesc(netmem)->pp_magic |= pp_magic;
-}
-
-static inline void netmem_clear_pp_magic(netmem_ref netmem)
-{
-	WARN_ON_ONCE(netmem_to_nmdesc(netmem)->pp_magic & PP_DMA_INDEX_MASK);
-
-	netmem_to_nmdesc(netmem)->pp_magic = 0;
-}
-
 static inline bool netmem_is_pp(netmem_ref netmem)
 {
-	return (netmem_get_pp_magic(netmem) & PP_MAGIC_MASK) == PP_SIGNATURE;
+	struct page *page;
+
+	/* XXX: Now that the offset of page_type is shared between
+	 * struct page and net_iov, just cast the netmem to struct page
+	 * unconditionally by clearing NET_IOV if any, no matter whether
+	 * it comes from struct net_iov or struct page.  This should be
+	 * adjusted once the offset is no longer shared.
+	 */
+	page = (struct page *)((__force unsigned long)netmem & ~NET_IOV);
+	return PageNetpp(page);
 }
 
 static inline void netmem_set_pp(netmem_ref netmem, struct page_pool *pool)

net/core/page_pool.c

@@ -702,8 +702,18 @@ s32 page_pool_inflight(const struct page_pool *pool, bool strict)
 
 void page_pool_set_pp_info(struct page_pool *pool, netmem_ref netmem)
 {
+	struct page *page;
+
 	netmem_set_pp(netmem, pool);
-	netmem_or_pp_magic(netmem, PP_SIGNATURE);
+
+	/* XXX: Now that the offset of page_type is shared between
+	 * struct page and net_iov, just cast the netmem to struct page
+	 * unconditionally by clearing NET_IOV if any, no matter whether
+	 * it comes from struct net_iov or struct page.  This should be
+	 * adjusted once the offset is no longer shared.
+	 */
+	page = (struct page *)((__force unsigned long)netmem & ~NET_IOV);
+	__SetPageNetpp(page);
 
 	/* Ensuring all pages have been split into one fragment initially:
 	 * page_pool_set_pp_info() is only called once for every page when it
@@ -718,7 +728,17 @@ void page_pool_set_pp_info(struct page_pool *pool, netmem_ref netmem)
 
 void page_pool_clear_pp_info(netmem_ref netmem)
 {
-	netmem_clear_pp_magic(netmem);
+	struct page *page;
+
+	/* XXX: Now that the offset of page_type is shared between
+	 * struct page and net_iov, just cast the netmem to struct page
+	 * unconditionally by clearing NET_IOV if any, no matter whether
+	 * it comes from struct net_iov or struct page.  This should be
+	 * adjusted once the offset is no longer shared.
+	 */
+	page = (struct page *)((__force unsigned long)netmem & ~NET_IOV);
+	__ClearPageNetpp(page);
+
 	netmem_set_pp(netmem, NULL);
 }