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

This reverts commit db359fccf2 ("mm: introduce a new page type for page
pool in page type") and a part of 735a309b4b ("net: add net_iov_init()
and use it to initialize ->page_type").

Netpp page_type'ed pages might be used in mapping so as to use @_mapcount.
However, since @page_type and @_mapcount are union'ed in struct page,
these two can't be used at the same time.  Revert the commit introducing
page_type for Netpp for now.

The patch will be retried once @page_type and @_mapcount get allowed to be
used at the same time.

The revert also includes removal of @page_type initialization part
introduced by commit 735a309b4b ("net: add net_iov_init() and use it
to initialize ->page_type"), which will be restored on the retry.

Link: https://lore.kernel.org/20260515034701.17027-1-byungchul@sk.com
Fixes: db359fccf2 ("mm: introduce a new page type for page pool in page type")
Signed-off-by: Byungchul Park <byungchul@sk.com>
Reported-by: Dragos Tatulea <dtatulea@nvidia.com>
Closes: https://lore.kernel.org/all/982b9bc1-0a0a-4fc5-8e3a-3672db2b29a1@nvidia.com
Acked-by: Jakub Kicinski <kuba@kernel.org>
Acked-by: David Hildenbrand (Arm) <david@kernel.org>
Acked-by: Harry Yoo (Oracle) <harry@kernel.org>
Reviewed-by: Lorenzo Stoakes <ljs@kernel.org>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Baolin Wang <baolin.wang@linux.alibaba.com>
Cc: Brendan Jackman <jackmanb@google.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Eric Dumazet <edumazet@google.com>
Cc: Ilias Apalodimas <ilias.apalodimas@linaro.org>
Cc: Jesper Dangaard Brouer <hawk@kernel.org>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: John Fastabend <john.fastabend@gmail.com>
Cc: Leon Romanovsky <leon@kernel.org>
Cc: Liam R. Howlett <liam@infradead.org>
Cc: Mark Bloch <mbloch@nvidia.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Mike Rapoport <rppt@kernel.org>
Cc: Paolo Abeni <pabeni@redhat.com>
Cc: Pavel Begunkov <asml.silence@gmail.com>
Cc: Saeed Mahameed <saeedm@nvidia.com>
Cc: Simon Horman <horms@kernel.org>
Cc: Stanislav Fomichev <sdf@fomichev.me>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Tariq Toukan <tariqt@nvidia.com>
Cc: Toke Hoiland-Jorgensen <toke@redhat.com>
Cc: Vlastimil Babka <vbabka@kernel.org>
Cc: Zi Yan <ziy@nvidia.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

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

@@ -708,7 +708,7 @@ 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 PageNetpp() as we
+				/* No need to check page_pool_page_is_pp() as we
 				 * know this is a page_pool page.
 				 */
 				page_pool_recycle_direct(pp_page_to_nmdesc(page)->pp,

include/linux/mm.h

@@ -5174,9 +5174,10 @@ 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. 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. 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
  * mistake a valid kernel pointer with any of the values we write into this
  * field.
  *
@@ -5211,6 +5212,26 @@ 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

@@ -923,7 +923,6 @@ enum pagetype {
 	PGTY_zsmalloc		= 0xf6,
 	PGTY_unaccepted		= 0xf7,
 	PGTY_large_kmalloc	= 0xf8,
-	PGTY_netpp		= 0xf9,
 
 	PGTY_mapcount_underflow = 0xff
 };
@@ -1056,11 +1055,6 @@ 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

@@ -94,20 +94,10 @@ enum net_iov_type {
  */
 struct net_iov {
 	struct netmem_desc desc;
-	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;
@@ -127,11 +117,7 @@ static inline unsigned int net_iov_idx(const struct net_iov *niov)
 	return niov - net_iov_owner(niov)->niovs;
 }
 
-/* Initialize a niov: stamp the owning area, the memory provider type,
- * and the page_type "no type" sentinel expected by the page-type API
- * (see PAGE_TYPE_OPS in <linux/page-flags.h>) so that
- * page_pool_set_pp_info() can later call __SetPageNetpp() on a niov
- * cast to struct page.
+/* Initialize a niov: stamp the owning area, the memory provider type.
  */
 static inline void net_iov_init(struct net_iov *niov,
 				struct net_iov_area *owner,
@@ -139,7 +125,6 @@ static inline void net_iov_init(struct net_iov *niov,
 {
 	niov->owner = owner;
 	niov->type = type;
-	niov->page_type = UINT_MAX;
 }
 
 /* netmem */
@@ -245,7 +230,7 @@ static inline unsigned long netmem_pfn_trace(netmem_ref netmem)
  */
 #define pp_page_to_nmdesc(p)						\
 ({									\
-	DEBUG_NET_WARN_ON_ONCE(!PageNetpp(p));				\
+	DEBUG_NET_WARN_ON_ONCE(!page_pool_page_is_pp(p));		\
 	__pp_page_to_nmdesc(p);						\
 })
 

mm/page_alloc.c

@@ -1035,6 +1035,7 @@ 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;
 
@@ -1061,6 +1062,8 @@ 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;
 }
 
@@ -1377,17 +1380,9 @@ __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))) {
-		/* 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;
-			}
-		}
+	if (unlikely(page_has_type(page)))
 		/* 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

@@ -8,18 +8,21 @@ 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)
 {
-	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);
+	return (netmem_get_pp_magic(netmem) & PP_MAGIC_MASK) == PP_SIGNATURE;
 }
 
 static inline void netmem_set_pp(netmem_ref netmem, struct page_pool *pool)

net/core/page_pool.c

@@ -707,18 +707,8 @@ 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);
-
-	/* 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);
+	netmem_or_pp_magic(netmem, PP_SIGNATURE);
 
 	/* Ensuring all pages have been split into one fragment initially:
 	 * page_pool_set_pp_info() is only called once for every page when it
@@ -733,17 +723,7 @@ void page_pool_set_pp_info(struct page_pool *pool, netmem_ref netmem)
 
 void page_pool_clear_pp_info(netmem_ref 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_clear_pp_magic(netmem);
 	netmem_set_pp(netmem, NULL);
 }