From b7b4d8f37a4ff533dffeea9cbb08e9e4788b7742 Mon Sep 17 00:00:00 2001 From: "Lorenzo Stoakes (ARM)" Date: Tue, 13 Oct 2026 16:04:48 +0100 Subject: mm: add mmap action for discontiguous kernel page mapping The existing kernel page mapping mmap actions allow for partial and full mapping of an array of struct page pointers. However some drivers require the mapping of discontiguous ranges. Permit this by providing discontig_kernel_page_ops which allows a driver to specify how the operation should begin and how batches of pages should be retrieved. It uses the minimum exposed interface to do so, providing address, page offset and both vm_private_data state and a local private state object. ops->init can establish state for the operation, and ops->get outputs the pages to map and their count. Should an error arise the core unmaps the VMA, invoking vm_ops->close, which is therefore where any state established by ops->init is released. Also update the compatibility layer to do this too via compat_mmap_action_abort(). Batches may not exceed the VMA, but may map less than its full range in case the driver wishes to allow the user to map an area larger than the available data. To use it, users invoke mmap_action_map_discontig_kernel_pages() with initial local private state and a set of operations. Users can then use one of the provided helper functions to perform an action: * discontig_kernel_map_abort() - Abort and leave the mapping as it has been accumulated so far. * discontig_kernel_map_page() - Map a single page, or a compound page given its head page, as 1..N contiguous pages. * discontig_kernel_map_pages() - Map a struct page ** array of a specified count, mapping only those pages which fit in the VMA. The userland VMA tests are updated accordingly. Link: https://lore.kernel.org/20261013-b4-mmap-prepare-vma-flag-sanify-v6-8-1aa3c9b139f9@kernel.org Signed-off-by: Lorenzo Stoakes (ARM) Signed-off-by: Andrew Morton Acked-by: Zi Yan Acked-by: David Hildenbrand (Arm) Cc: Liam R. Howlett Cc: Vlastimil Babka Cc: Jann Horn Cc: Pedro Falcato Cc: Mike Rapoport Cc: Suren Baghdasaryan Cc: Michal Hocko Cc: Jonathan Corbet Cc: Greg Kroah-Hartman Cc: Dennis Dalessandro Cc: Jason Gunthorpe Cc: Leon Romanovsky Cc: Paul Moore Cc: Stephen Smalley Cc: Jaroslav Kysela Cc: Takashi Iwai Cc: Alexei Starovoitov Cc: Daniel Borkmann Cc: Andrii Nakryiko Cc: Eduard Zingerman Cc: Kumar Kartikeya Dwivedi Cc: Baolin Wang Cc: Nico Pache Cc: Ryan Roberts Cc: Dev Jain Cc: Barry Song Cc: Lance Yang Cc: Usama Arif Cc: Kiryl Shutsemau Cc: Doug Gilbert Cc: James Bottomley Cc: Martin K. Petersen Cc: Simona Vetter Cc: Helge Deller Cc: Sebastian Reichel Cc: John Hubbard Cc: Peter Xu Cc: Masami Hiramatsu Cc: Oleg Nesterov Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Ingo Molnar Cc: Borislav Petkov Cc: Dave Hansen Cc: Arnaldo Carvalho de Melo Cc: Namhyung Kim Cc: Mark Rutland Cc: Rik van Riel Cc: Harry Yoo Cc: Juri Lelli Cc: Vincent Guittot Cc: Maarten Lankhorst Cc: Maxime Ripard Cc: Thomas Zimmermann Cc: David Airlie Cc: Will Deacon Cc: Aneesh Kumar K.V Cc: Nicholas Piggin Cc: Arnd Bergmann Cc: Muchun Song Cc: Oscar Salvador Cc: Matthew Wilcox (Oracle) Cc: Jan Kara Cc: Marc Zyngier Cc: Oliver Upton Cc: Catalin Marinas Cc: Madhavan Srinivasan Cc: Anup Patel Cc: Paul Walmsley Cc: Palmer Dabbelt Cc: Albert Ou Cc: Christian Borntraeger Cc: Janosch Frank Cc: Claudio Imbrenda Cc: Alexander Gordeev Cc: Gerald Schaefer Cc: Heiko Carstens Cc: Vasily Gorbik Cc: David S. Miller Cc: Andreas Larsson Cc: Al Viro Cc: Christian Brauner Cc: Matthew Brost Cc: Joshua Hahn Cc: Rakie Kim Cc: Byungchul Park Cc: Gregory Price Cc: Ying Huang Cc: Alistair Popple Cc: Chris Li Cc: Kairui Song Cc: Kemeng Shi Cc: Nhat Pham Cc: Baoquan He Cc: Youngjun Park Cc: Johannes Weiner Cc: Qi Zheng Cc: Shakeel Butt Cc: Axel Rasmussen Cc: Yuanchu Xie Cc: Wei Xu Cc: Chengming Zhou Cc: Michal Hocko Cc: Miklos Szeredi Cc: Xu Xin Cc: Ihor Solodrai Cc: Bert Karwatzki --- include/linux/mm.h | 43 +++++++++++++++++++++++++++++++++++++++++++ include/linux/mm_types.h | 42 ++++++++++++++++++++++++++++++++++++++++-- 2 files changed, 83 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index d724c7401798..fc0d4c0a0cb6 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -4654,10 +4654,53 @@ static inline void mmap_action_map_kernel_pages_full(struct vm_area_desc *desc, vma_desc_pages(desc)); } +static inline +void mmap_action_map_discontig_kernel_pages(struct vm_area_desc *desc, + void *init_private, const struct discontig_kernel_page_ops *ops) +{ + struct mmap_action *action = &desc->action; + + action->type = MMAP_DISCONTIG_KERNEL_PAGES; + action->map_kernel_discontig.init_private = init_private; + action->map_kernel_discontig.ops = ops; +} + int mmap_action_prepare(struct vm_area_desc *desc); int mmap_action_complete(struct vm_area_struct *vma, struct mmap_action *action, bool is_compat); +static inline void +discontig_kernel_map_abort(struct discontig_kernel_page_state *state) +{ + state->action = DISCONTIG_KERNEL_PAGE_ABORT; +} + +static inline void +discontig_kernel_map_page(struct discontig_kernel_page_state *state, + struct page *page) +{ + struct folio *folio = page_folio(page); + unsigned long nr_pages = 1; + + if (folio_test_large(folio)) { + VM_WARN_ON_ONCE(page != folio_page(folio, 0)); + nr_pages = folio_nr_pages(folio); + } + + state->action = DISCONTIG_KERNEL_PAGE_MAP_CONTIG_PAGES; + state->__page = page; + state->__nr_pages = min(nr_pages, state->nr_pages_remain); +} + +static inline void +discontig_kernel_map_pages(struct discontig_kernel_page_state *state, + struct page **page_arr, unsigned long nr_pages) +{ + state->action = DISCONTIG_KERNEL_PAGE_MAP_PAGES; + state->__page_arr = page_arr; + state->__nr_pages = min(nr_pages, state->nr_pages_remain); +} + /* Look up the first VMA which exactly match the interval vm_start ... vm_end */ static inline struct vm_area_struct *find_exact_vma(struct mm_struct *mm, unsigned long vm_start, unsigned long vm_end) diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index bd5c8832d1af..0dead656d3e3 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -818,8 +818,42 @@ enum mmap_action_type { MMAP_NOTHING, MMAP_REMAP_PFN, MMAP_IO_REMAP_PFN, - MMAP_SIMPLE_IO_REMAP, /* I/O remap with guardrails. */ - MMAP_KERNEL_PAGES, /* Map kernel page range from array. */ + MMAP_SIMPLE_IO_REMAP, /* I/O remap with guardrails. */ + MMAP_KERNEL_PAGES, /* Map kernel page range from array. */ + MMAP_DISCONTIG_KERNEL_PAGES, /* Map kernel discontig page range. */ +}; + +enum discontig_kernel_page_action { + DISCONTIG_KERNEL_PAGE_ABORT, + DISCONTIG_KERNEL_PAGE_MAP_PAGES, /* Array of individual pages. */ + DISCONTIG_KERNEL_PAGE_MAP_CONTIG_PAGES, /* 1..N contiguous pages. */ +}; + +struct discontig_kernel_page_state { + /* Map state. */ + const unsigned long start; /* Start address of VMA. */ + const unsigned long end; /* End address of VMA. */ + unsigned long addr; /* The current address to be mapped. */ + pgoff_t pgoff; /* The current pgoff to be mapped. */ + unsigned long nr_pages_mapped; /* The number of pages mapped. */ + unsigned long nr_pages_remain; /* The number of pages remaining. */ + + /* User-defined state. */ + void *vm_private_data; /* VMA private data. */ + void *private; /* Mapping private data. */ + + /* Users should not touch these, use discontig_kernel_map_*() helpers. */ + enum discontig_kernel_page_action action; + union { + struct page *__page; + struct page **__page_arr; + }; + unsigned long __nr_pages; +}; + +struct discontig_kernel_page_ops { + int (*init)(void *vm_private_data, void **private); + int (*get)(struct discontig_kernel_page_state *state); }; /* @@ -844,6 +878,10 @@ struct mmap_action { unsigned long nr_pages; pgoff_t pgoff; } map_kernel; + struct { + void *init_private; + const struct discontig_kernel_page_ops *ops; + } map_kernel_discontig; }; enum mmap_action_type type; -- cgit v1.2.3