From 68aa2fdbf57f769e552f472ddb762aba028a207e Mon Sep 17 00:00:00 2001 From: Lorenzo Stoakes Date: Mon, 10 Nov 2025 22:21:20 +0000 Subject: mm: introduce leaf entry type and use to simplify leaf entry logic The kernel maintains leaf page table entries which contain either: The kernel maintains leaf page table entries which contain either: - Nothing ('none' entries) - Present entries* - Everything else that will cause a fault which the kernel handles * Present entries are either entries the hardware can navigate without page fault or special cases like NUMA hint protnone or PMD with cleared present bit which contain hardware-valid entries modulo the present bit. In the 'everything else' group we include swap entries, but we also include a number of other things such as migration entries, device private entries and marker entries. Unfortunately this 'everything else' group expresses everything through a swp_entry_t type, and these entries are referred to swap entries even though they may well not contain a... swap entry. This is compounded by the rather mind-boggling concept of a non-swap swap entry (checked via non_swap_entry()) and the means by which we twist and turn to satisfy this. This patch lays the foundation for reducing this confusion. We refer to 'everything else' as a 'software-define leaf entry' or 'softleaf'. for short And in fact we scoop up the 'none' entries into this concept also so we are left with: - Present entries. - Softleaf entries (which may be empty). This allows for radical simplification across the board - one can simply convert any leaf page table entry to a leaf entry via softleaf_from_pte(). If the entry is present, we return an empty leaf entry, so it is assumed the caller is aware that they must differentiate between the two categories of page table entries, checking for the former via pte_present(). As a result, we can eliminate a number of places where we would otherwise need to use predicates to see if we can proceed with leaf page table entry conversion and instead just go ahead and do it unconditionally. We do so where we can, adjusting surrounding logic as necessary to integrate the new softleaf_t logic as far as seems reasonable at this stage. We typedef swp_entry_t to softleaf_t for the time being until the conversion can be complete, meaning everything remains compatible regardless of which type is used. We will eventually remove swp_entry_t when the conversion is complete. We introduce a new header file to keep things clear - leafops.h - this imports swapops.h so can direct replace swapops imports without issue, and we do so in all the files that require it. Additionally, add new leafops.h file to core mm maintainers entry. Link: https://lkml.kernel.org/r/c879383aac77d96a03e4d38f7daba893cd35fc76.1762812360.git.lorenzo.stoakes@oracle.com Signed-off-by: Lorenzo Stoakes Acked-by: Zi Yan Reviewed-by: Vlastimil Babka Cc: Alexander Gordeev Cc: Alistair Popple Cc: Al Viro Cc: Arnd Bergmann Cc: Axel Rasmussen Cc: Baolin Wang Cc: Baoquan He Cc: Barry Song Cc: Byungchul Park Cc: Chengming Zhou Cc: Chris Li Cc: Christian Borntraeger Cc: Christian Brauner Cc: Claudio Imbrenda Cc: David Hildenbrand Cc: Dev Jain Cc: Gerald Schaefer Cc: Gregory Price Cc: Heiko Carstens Cc: "Huang, Ying" Cc: Hugh Dickins Cc: Jan Kara Cc: Jann Horn Cc: Janosch Frank Cc: Jason Gunthorpe Cc: Joshua Hahn Cc: Kairui Song Cc: Kemeng Shi Cc: Lance Yang Cc: Leon Romanovsky Cc: Liam Howlett Cc: Mathew Brost Cc: Matthew Wilcox (Oracle) Cc: Miaohe Lin Cc: Michal Hocko Cc: Mike Rapoport Cc: Muchun Song Cc: Naoya Horiguchi Cc: Nhat Pham Cc: Nico Pache Cc: Oscar Salvador Cc: Pasha Tatashin Cc: Peter Xu Cc: Rakie Kim Cc: Rik van Riel Cc: Ryan Roberts Cc: SeongJae Park Cc: Suren Baghdasaryan Cc: Sven Schnelle Cc: Vasily Gorbik Cc: Wei Xu Cc: xu xin Cc: Yuanchu Xie Signed-off-by: Andrew Morton --- include/linux/mm_inline.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux/mm_inline.h') diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h index f6a2b2d20016..ca7a18351797 100644 --- a/include/linux/mm_inline.h +++ b/include/linux/mm_inline.h @@ -8,7 +8,7 @@ #include #include #include -#include +#include /** * folio_is_file_lru - Should the folio be on a file LRU or anon LRU? @@ -541,9 +541,9 @@ static inline bool mm_tlb_flush_nested(const struct mm_struct *mm) * The caller should insert a new pte created with make_pte_marker(). */ static inline pte_marker copy_pte_marker( - swp_entry_t entry, struct vm_area_struct *dst_vma) + softleaf_t entry, struct vm_area_struct *dst_vma) { - pte_marker srcm = pte_marker_get(entry); + const pte_marker srcm = softleaf_to_marker(entry); /* Always copy error entries. */ pte_marker dstm = srcm & (PTE_MARKER_POISONED | PTE_MARKER_GUARD); -- cgit v1.2.3 From 5b3eb779a20cf30d74bb346d2a1e525bc9072685 Mon Sep 17 00:00:00 2001 From: Shakeel Butt Date: Mon, 10 Nov 2025 15:20:07 -0800 Subject: memcg: remove __mod_lruvec_state __mod_lruvec_state() is already safe against irqs, so there is no need to have a separate interface (i.e. mod_lruvec_state) which wraps calls to it with irq disabling and reenabling. Let's rename __mod_lruvec_state() to mod_lruvec_state(). Link: https://lkml.kernel.org/r/20251110232008.1352063-4-shakeel.butt@linux.dev Signed-off-by: Shakeel Butt Reviewed-by: Harry Yoo Acked-by: Roman Gushchin Acked-by: Vlastimil Babka Cc: Johannes Weiner Cc: Michal Hocko Cc: Muchun Song Cc: Qi Zheng Signed-off-by: Andrew Morton --- include/linux/mm_inline.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux/mm_inline.h') diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h index ca7a18351797..b58f34c4fe92 100644 --- a/include/linux/mm_inline.h +++ b/include/linux/mm_inline.h @@ -44,7 +44,7 @@ static __always_inline void __update_lru_size(struct lruvec *lruvec, lockdep_assert_held(&lruvec->lru_lock); WARN_ON_ONCE(nr_pages != (int)nr_pages); - __mod_lruvec_state(lruvec, NR_LRU_BASE + lru, nr_pages); + mod_lruvec_state(lruvec, NR_LRU_BASE + lru, nr_pages); __mod_zone_page_state(&pgdat->node_zones[zid], NR_ZONE_LRU_BASE + lru, nr_pages); } -- cgit v1.2.3 From f59c0924d61aa2a2bb85936a593140f327112787 Mon Sep 17 00:00:00 2001 From: Chunyan Zhang Date: Thu, 13 Nov 2025 15:28:02 +0800 Subject: mm: userfaultfd: add pgtable_supports_uffd_wp() Some platforms can customize the PTE/PMD entry uffd-wp bit making it unavailable even if the architecture provides the resource. This patch adds a macro API pgtable_supports_uffd_wp() that allows architectures to define their specific implementations to check if the uffd-wp bit is available on which device the kernel is running. Also this patch is removing "ifdef CONFIG_HAVE_ARCH_USERFAULTFD_WP" and "ifdef CONFIG_PTE_MARKER_UFFD_WP" in favor of pgtable_supports_uffd_wp() and uffd_supports_wp_marker() checks respectively that default to IS_ENABLED(CONFIG_HAVE_ARCH_USERFAULTFD_WP) and "IS_ENABLED(CONFIG_HAVE_ARCH_USERFAULTFD_WP) && IS_ENABLED(CONFIG_PTE_MARKER_UFFD_WP)" if not overridden by the architecture, no change in behavior is expected. Link: https://lkml.kernel.org/r/20251113072806.795029-3-zhangchunyan@iscas.ac.cn Signed-off-by: Chunyan Zhang Acked-by: David Hildenbrand Cc: Albert Ou Cc: Alexandre Ghiti Cc: Alexandre Ghiti Cc: Al Viro Cc: Andrew Jones Cc: Arnd Bergmann Cc: Axel Rasmussen Cc: Christian Brauner Cc: Conor Dooley Cc: Conor Dooley Cc: Deepak Gupta Cc: Jan Kara Cc: Liam Howlett Cc: Lorenzo Stoakes Cc: Michal Hocko Cc: Mike Rapoport Cc: Palmer Dabbelt Cc: Paul Walmsley Cc: Peter Xu Cc: Rob Herring Cc: Suren Baghdasaryan Cc: Vlastimil Babka Cc: Yuanchu Xie Signed-off-by: Andrew Morton --- include/linux/mm_inline.h | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) (limited to 'include/linux/mm_inline.h') diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h index b58f34c4fe92..fa2d6ba811b5 100644 --- a/include/linux/mm_inline.h +++ b/include/linux/mm_inline.h @@ -553,7 +553,6 @@ static inline pte_marker copy_pte_marker( return dstm; } -#endif /* * If this pte is wr-protected by uffd-wp in any form, arm the special pte to @@ -571,9 +570,11 @@ static inline bool pte_install_uffd_wp_if_needed(struct vm_area_struct *vma, unsigned long addr, pte_t *pte, pte_t pteval) { -#ifdef CONFIG_PTE_MARKER_UFFD_WP bool arm_uffd_pte = false; + if (!uffd_supports_wp_marker()) + return false; + /* The current status of the pte should be "cleared" before calling */ WARN_ON_ONCE(!pte_none(ptep_get(pte))); @@ -602,7 +603,7 @@ pte_install_uffd_wp_if_needed(struct vm_area_struct *vma, unsigned long addr, make_pte_marker(PTE_MARKER_UFFD_WP)); return true; } -#endif + return false; } @@ -616,6 +617,7 @@ static inline bool vma_has_recency(const struct vm_area_struct *vma) return true; } +#endif /** * num_pages_contiguous() - determine the number of contiguous pages -- cgit v1.2.3