Hi, I focused on converting the existing APIs accessing ->pp_magic field to page type APIs. However, yes. Additional works would better be considered on top like: 1. Adjust how to store and retrieve dma index. Maybe network guys can work better on top. 2. Move the sanity check for page pool in mm/page_alloc.c to on free. Byungchul ---8<--- From 7d207a1b3e9f4ff2a72f5b54b09e3ed0c4aaaca3 Mon Sep 17 00:00:00 2001 From: Byungchul Park Date: Mon, 21 Jul 2025 14:05:20 +0900 Subject: [PATCH] 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, page type e.i. PGTY_netpp can be used for that purpose. 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() since they are totally replaced. This work was inspired by the following link by Pavel: [1] https://lore.kernel.org/all/582f41c0-2742-4400-9c81-0d46bf4e8314@gmail.com/ Suggested-by: Pavel Begunkov Signed-off-by: Byungchul Park --- .../net/ethernet/mellanox/mlx5/core/en/xdp.c | 2 +- include/linux/mm.h | 28 ++----------------- include/linux/page-flags.h | 6 ++++ include/net/netmem.h | 2 +- mm/page_alloc.c | 4 +-- net/core/netmem_priv.h | 16 ++--------- net/core/page_pool.c | 10 +++++-- 7 files changed, 24 insertions(+), 44 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 ae50c1641bed..736061749535 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -4135,10 +4135,9 @@ 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. * @@ -4168,25 +4167,4 @@ 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 - #endif /* _LINUX_MM_H */ diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 4fe5ee67535b..906ba7c9e372 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -957,6 +957,7 @@ enum pagetype { PGTY_zsmalloc = 0xf6, PGTY_unaccepted = 0xf7, PGTY_large_kmalloc = 0xf8, + PGTY_netpp = 0xf9, PGTY_mapcount_underflow = 0xff }; @@ -1101,6 +1102,11 @@ 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/mm/page_alloc.c b/mm/page_alloc.c index 2ef3c07266b3..71c7666e48a9 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -898,7 +898,7 @@ static inline bool page_expected_state(struct page *page, #ifdef CONFIG_MEMCG page->memcg_data | #endif - page_pool_page_is_pp(page) | + PageNetpp(page) | (page->flags & check_flags))) return false; @@ -925,7 +925,7 @@ 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))) + if (unlikely(PageNetpp(page))) bad_reason = "page_pool leak"; return bad_reason; } diff --git a/net/core/netmem_priv.h b/net/core/netmem_priv.h index cd95394399b4..39a97703d9ed 100644 --- a/net/core/netmem_priv.h +++ b/net/core/netmem_priv.h @@ -8,21 +8,11 @@ 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; + if (netmem_is_net_iov(netmem)) + return true; + 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, -- 2.17.1