Message-Id: <20250728082008.34091-1-byungchul@sk.com>
Date: Mon, 28 Jul 2025 17:20:08 +0900
From: Byungchul Park <byungchul@...com>
To: linux-mm@...ck.org,
	netdev@...r.kernel.org
Cc: linux-kernel@...r.kernel.org,
	kernel_team@...ynix.com,
	harry.yoo@...cle.com,
	ast@...nel.org,
	daniel@...earbox.net,
	davem@...emloft.net,
	kuba@...nel.org,
	hawk@...nel.org,
	john.fastabend@...il.com,
	sdf@...ichev.me,
	saeedm@...dia.com,
	leon@...nel.org,
	tariqt@...dia.com,
	mbloch@...dia.com,
	andrew+netdev@...n.ch,
	edumazet@...gle.com,
	pabeni@...hat.com,
	akpm@...ux-foundation.org,
	david@...hat.com,
	lorenzo.stoakes@...cle.com,
	Liam.Howlett@...cle.com,
	vbabka@...e.cz,
	rppt@...nel.org,
	surenb@...gle.com,
	mhocko@...e.com,
	horms@...nel.org,
	jackmanb@...gle.com,
	hannes@...xchg.org,
	ziy@...dia.com,
	ilias.apalodimas@...aro.org,
	willy@...radead.org,
	brauner@...nel.org,
	kas@...nel.org,
	yuzhao@...gle.com,
	usamaarif642@...il.com,
	baolin.wang@...ux.alibaba.com,
	almasrymina@...gle.com,
	toke@...hat.com,
	asml.silence@...il.com,
	bpf@...r.kernel.org,
	linux-rdma@...r.kernel.org
Subject: [PATCH v2 rebase as of Jul 28] mm, page_pool: introduce a new page type for page pool in page type

Rebasing on the latest linux-next/master is required.  Otherwise, a
build fail is observed.  Sorry about the noise.

Changes from v1:
	1. Rebase on linux-next.
	2. Initialize net_iov->pp = NULL when allocating net_iov in
	   net_devmem_bind_dmabuf() and io_zcrx_create_area().
	3. Use ->pp for net_iov to identify if it's pp rather than
	   always consider net_iov as pp.
	4. Add Suggested-by: David Hildenbrand <david@...hat.com>.

---8<---
>From 26c9a731f388b788d6ea972c313bc8da8831412b Mon Sep 17 00:00:00 2001
From: Byungchul Park <byungchul@...com>
Date: Mon, 28 Jul 2025 17:09:20 +0900
Subject: [PATCH v2 rebase as of Jul 28] mm, page_pool: introduce a new page type for page pool in page type

->pp_magic field in struct page is current used to identify if a page
belongs to a page pool.  However, ->pp_magic will be removed and page
type bit in struct page e.i. PGTY_netpp can be used for that 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().

For net_iov, use ->pp to identify if it's pp, with making sure that ->pp
is NULL for non-pp net_iov.

This work was inspired by the following link:

[1] https://lore.kernel.org/all/582f41c0-2742-4400-9c81-0d46bf4e8314@gmail.com/

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

Suggested-by: David Hildenbrand <david@...hat.com>
Signed-off-by: Byungchul Park <byungchul@...com>
---
 .../net/ethernet/mellanox/mlx5/core/en/xdp.c  |  2 +-
 include/linux/mm.h                            | 27 +++----------------
 include/linux/page-flags.h                    |  6 +++++
 include/net/netmem.h                          |  2 +-
 io_uring/zcrx.c                               |  1 +
 mm/page_alloc.c                               |  7 +++--
 net/core/devmem.c                             |  1 +
 net/core/netmem_priv.h                        | 23 +++++++---------
 net/core/page_pool.c                          | 10 +++++--
 9 files changed, 34 insertions(+), 45 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
index 5d51600935a6..def274f5c1ca 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
+++ b/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,
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 0d4ee569aa6b..d01b296e7184 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -4171,10 +4171,9 @@ 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.
  *
@@ -4205,26 +4204,6 @@ 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)
diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index 8d3fa3a91ce4..84247e39e9e7 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -933,6 +933,7 @@ enum pagetype {
 	PGTY_zsmalloc		= 0xf6,
 	PGTY_unaccepted		= 0xf7,
 	PGTY_large_kmalloc	= 0xf8,
+	PGTY_netpp		= 0xf9,
 
 	PGTY_mapcount_underflow = 0xff
 };
@@ -1077,6 +1078,11 @@ PAGE_TYPE_OPS(Zsmalloc, zsmalloc, zsmalloc)
 PAGE_TYPE_OPS(Unaccepted, unaccepted, unaccepted)
 FOLIO_TYPE_OPS(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.
diff --git a/include/net/netmem.h b/include/net/netmem.h
index f7dacc9e75fd..3667334e16e7 100644
--- a/include/net/netmem.h
+++ b/include/net/netmem.h
@@ -298,7 +298,7 @@ static inline struct net_iov *__netmem_clear_lsb(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);						\
 })
 
diff --git a/io_uring/zcrx.c b/io_uring/zcrx.c
index e5ff49f3425e..4cceb97ca26a 100644
--- a/io_uring/zcrx.c
+++ b/io_uring/zcrx.c
@@ -444,6 +444,7 @@ static int io_zcrx_create_area(struct io_zcrx_ifq *ifq,
 		area->freelist[i] = i;
 		atomic_set(&area->user_refs[i], 0);
 		niov->type = NET_IOV_IOURING;
+		niov->pp = NULL;
 	}
 
 	area->free_count = nr_iovs;
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index d1d037f97c5f..2f6a55fab942 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1042,7 +1042,6 @@ static inline bool page_expected_state(struct page *page,
 #ifdef CONFIG_MEMCG
 			page->memcg_data |
 #endif
-			page_pool_page_is_pp(page) |
 			(page->flags & check_flags)))
 		return false;
 
@@ -1069,8 +1068,6 @@ 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;
 }
 
@@ -1379,9 +1376,11 @@ __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))) {
+		WARN_ON_ONCE(PageNetpp(page));
 		/* Reset the page_type (which overlays _mapcount) */
 		page->page_type = UINT_MAX;
+	}
 
 	if (is_check_pages_enabled()) {
 		if (free_page_is_bad(page))
diff --git a/net/core/devmem.c b/net/core/devmem.c
index b3a62ca0df65..40e7a4ec9009 100644
--- a/net/core/devmem.c
+++ b/net/core/devmem.c
@@ -285,6 +285,7 @@ net_devmem_bind_dmabuf(struct net_device *dev,
 			niov = &owner->area.niovs[i];
 			niov->type = NET_IOV_DMABUF;
 			niov->owner = &owner->area;
+			niov->pp = NULL;
 			page_pool_set_dma_addr_netmem(net_iov_to_netmem(niov),
 						      net_devmem_get_dma_addr(niov));
 			if (direction == DMA_TO_DEVICE)
diff --git a/net/core/netmem_priv.h b/net/core/netmem_priv.h
index cd95394399b4..4b90332d6c64 100644
--- a/net/core/netmem_priv.h
+++ b/net/core/netmem_priv.h
@@ -8,21 +8,18 @@ static inline unsigned long netmem_get_pp_magic(netmem_ref netmem)
 	return __netmem_clear_lsb(netmem)->pp_magic & ~PP_DMA_INDEX_MASK;
 }
 
-static inline void netmem_or_pp_magic(netmem_ref netmem, unsigned long pp_magic)
-{
-	__netmem_clear_lsb(netmem)->pp_magic |= pp_magic;
-}
-
-static inline void netmem_clear_pp_magic(netmem_ref netmem)
-{
-	WARN_ON_ONCE(__netmem_clear_lsb(netmem)->pp_magic & PP_DMA_INDEX_MASK);
-
-	__netmem_clear_lsb(netmem)->pp_magic = 0;
-}
-
 static inline bool netmem_is_pp(netmem_ref netmem)
 {
-	return (netmem_get_pp_magic(netmem) & PP_MAGIC_MASK) == PP_SIGNATURE;
+	/* Use ->pp for net_iov to identify if it's pp, which requires
+	 * that non-pp net_iov should have ->pp NULL'd.
+	 */
+	if (netmem_is_net_iov(netmem))
+		return !!__netmem_clear_lsb(netmem)->pp;
+
+	/* For system memory, page type bit in struct page can be used
+	 * to identify if it's pp.
+	 */
+	return PageNetpp(__netmem_to_page(netmem));
 }
 
 static inline void netmem_set_pp(netmem_ref netmem, struct page_pool *pool)
diff --git a/net/core/page_pool.c b/net/core/page_pool.c
index 05e2e22a8f7c..0a10f3026faa 100644
--- a/net/core/page_pool.c
+++ b/net/core/page_pool.c
@@ -654,7 +654,6 @@ s32 page_pool_inflight(const struct page_pool *pool, bool strict)
 void page_pool_set_pp_info(struct page_pool *pool, netmem_ref netmem)
 {
 	netmem_set_pp(netmem, pool);
-	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
@@ -665,12 +664,19 @@ void page_pool_set_pp_info(struct page_pool *pool, netmem_ref netmem)
 	page_pool_fragment_netmem(netmem, 1);
 	if (pool->has_init_callback)
 		pool->slow.init_callback(netmem, pool->slow.init_arg);
+
+	if (netmem_is_net_iov(netmem))
+		return;
+	__SetPageNetpp(__netmem_to_page(netmem));
 }
 
 void page_pool_clear_pp_info(netmem_ref netmem)
 {
-	netmem_clear_pp_magic(netmem);
 	netmem_set_pp(netmem, NULL);
+
+	if (netmem_is_net_iov(netmem))
+		return;
+	__ClearPageNetpp(__netmem_to_page(netmem));
 }
 
 static __always_inline void __page_pool_release_netmem_dma(struct page_pool *pool,

base-commit: 0b90c3b6d76ea512dc3dac8fb30215e175b0019a
-- 
2.17.1

Powered by blists - more mailing lists