Currently, most of the userfaultfd features are implemented directly in the core mm. It will invoke VMA specific functions whenever necessary. So far it is fine because it almost only interacts with shmem and hugetlbfs. Introduce a generic userfaultfd API extension for vm_operations_struct, so that any code that implements vm_operations_struct (including kernel modules that can be compiled separately from the kernel core) can support userfaults without modifying the core files. With this API applied, if a module wants to support userfaultfd, the module should only need to properly define vm_uffd_ops and hook it to vm_operations_struct, instead of changing anything in core mm. This API will not work for anonymous memory. Handling of userfault operations for anonymous memory remains unchanged in core mm. Due to a security concern while reviewing older versions of this series [1], uffd_copy() will be temprorarily removed. IOW, MISSING-capable memory types can only be hard-coded and implemented in mm/. It would also affect UFFDIO_COPY and UFFDIO_ZEROPAGE. Other functions should still be able to be provided from vm_uffd_ops. Introduces the API only so that existing userfaultfd users can be moved over without breaking them. [1] https://lore.kernel.org/all/20250627154655.2085903-1-peterx@redhat.com/ Signed-off-by: Peter Xu --- include/linux/mm.h | 9 +++++++++ include/linux/userfaultfd_k.h | 29 +++++++++++++++++++++++++++++ 2 files changed, 38 insertions(+) diff --git a/include/linux/mm.h b/include/linux/mm.h index 5c01c4b59ca67..011962130c148 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -620,6 +620,8 @@ struct vm_fault { */ }; +struct vm_uffd_ops; + /* * These are the virtual MM functions - opening of an area, closing and * unmapping it (needed to keep files on disk up-to-date etc), pointer @@ -705,6 +707,13 @@ struct vm_operations_struct { struct page *(*find_normal_page)(struct vm_area_struct *vma, unsigned long addr); #endif /* CONFIG_FIND_NORMAL_PAGE */ +#ifdef CONFIG_USERFAULTFD + /* + * Userfaultfd related ops. Modules need to define this to support + * userfaultfd. + */ + const struct vm_uffd_ops *userfaultfd_ops; +#endif }; #ifdef CONFIG_NUMA_BALANCING diff --git a/include/linux/userfaultfd_k.h b/include/linux/userfaultfd_k.h index c0e716aec26aa..b5b4f3f174b32 100644 --- a/include/linux/userfaultfd_k.h +++ b/include/linux/userfaultfd_k.h @@ -92,6 +92,35 @@ enum mfill_atomic_mode { NR_MFILL_ATOMIC_MODES, }; +/* VMA userfaultfd operations */ +struct vm_uffd_ops { + /** + * @supported_ioctls: userfaultfd ioctls supported in bitmask. + * + * Userfaultfd ioctls supported by the module. Below will always + * be supported by default whenever a module provides vm_uffd_ops: + * + * _UFFDIO_API, _UFFDIO_REGISTER, _UFFDIO_UNREGISTER, _UFFDIO_WAKE + * + * The module needs to provide all the rest optionally supported + * ioctls as a bitmask. For example, a module needs to set the bit + * BIT(_UFFDIO_CONTINUE) to support userfaultfd minor faults. + */ + unsigned long supported_ioctls; + /** + * minor_get_folio: Handler to resolve UFFDIO_CONTINUE request. + * Must be specified if _UFFDIO_CONTINUE is set. + * + * @inode: the inode for folio lookup + * @pgoff: the pgoff of the folio + * @folio: returned folio pointer + * + * Return: zero if succeeded, negative for errors. + */ + int (*minor_get_folio)(struct inode *inode, pgoff_t pgoff, + struct folio **folio); +}; + #define MFILL_ATOMIC_MODE_BITS (const_ilog2(NR_MFILL_ATOMIC_MODES - 1) + 1) #define MFILL_ATOMIC_BIT(nr) BIT(MFILL_ATOMIC_MODE_BITS + (nr)) #define MFILL_ATOMIC_FLAG(nr) ((__force uffd_flags_t) MFILL_ATOMIC_BIT(nr)) -- 2.50.1