From: Lokesh Gidra <lokeshgidra@google.com> mainline inclusion from mainline-v6.9-rc1 commit f91e6b41dd11daffb138e3afdb4804aefc3d4e1b category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IBLWTA CVE: CVE-2025-21696 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i... -------------------------------- Patch series "per-vma locks in userfaultfd", v7. Performing userfaultfd operations (like copy/move etc.) in critical section of mmap_lock (read-mode) causes significant contention on the lock when operations requiring the lock in write-mode are taking place concurrently. We can use per-vma locks instead to significantly reduce the contention issue. Android runtime's Garbage Collector uses userfaultfd for concurrent compaction. mmap-lock contention during compaction potentially causes jittery experience for the user. During one such reproducible scenario, we observed the following improvements with this patch-set: - Wall clock time of compaction phase came down from ~3s to <500ms - Uninterruptible sleep time (across all threads in the process) was ~10ms (none in mmap_lock) during compaction, instead of >20s This patch (of 4): Move the struct to userfaultfd_k.h to be accessible from mm/userfaultfd.c. There are no other changes in the struct. This is required to prepare for using per-vma locks in userfaultfd operations. Link: https://lkml.kernel.org/r/20240215182756.3448972-1-lokeshgidra@google.com Link: https://lkml.kernel.org/r/20240215182756.3448972-2-lokeshgidra@google.com Signed-off-by: Lokesh Gidra <lokeshgidra@google.com> Reviewed-by: Mike Rapoport (IBM) <rppt@kernel.org> Reviewed-by: Liam R. Howlett <Liam.Howlett@oracle.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Axel Rasmussen <axelrasmussen@google.com> Cc: Brian Geffon <bgeffon@google.com> Cc: David Hildenbrand <david@redhat.com> Cc: Jann Horn <jannh@google.com> Cc: Kalesh Singh <kaleshsingh@google.com> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Nicolas Geoffray <ngeoffray@google.com> Cc: Peter Xu <peterx@redhat.com> Cc: Ryan Roberts <ryan.roberts@arm.com> Cc: Suren Baghdasaryan <surenb@google.com> Cc: Tim Murray <timmurray@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Ze Zuo <zuoze1@huawei.com> --- fs/userfaultfd.c | 39 ----------------------------------- include/linux/userfaultfd_k.h | 39 +++++++++++++++++++++++++++++++++++ 2 files changed, 39 insertions(+), 39 deletions(-) diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c index d616b7777eef..c371f4aa42b0 100644 --- a/fs/userfaultfd.c +++ b/fs/userfaultfd.c @@ -52,45 +52,6 @@ static struct ctl_table vm_userfaultfd_table[] = { static struct kmem_cache *userfaultfd_ctx_cachep __read_mostly; -/* - * Start with fault_pending_wqh and fault_wqh so they're more likely - * to be in the same cacheline. - * - * Locking order: - * fd_wqh.lock - * fault_pending_wqh.lock - * fault_wqh.lock - * event_wqh.lock - * - * To avoid deadlocks, IRQs must be disabled when taking any of the above locks, - * since fd_wqh.lock is taken by aio_poll() while it's holding a lock that's - * also taken in IRQ context. - */ -struct userfaultfd_ctx { - /* waitqueue head for the pending (i.e. not read) userfaults */ - wait_queue_head_t fault_pending_wqh; - /* waitqueue head for the userfaults */ - wait_queue_head_t fault_wqh; - /* waitqueue head for the pseudo fd to wakeup poll/read */ - wait_queue_head_t fd_wqh; - /* waitqueue head for events */ - wait_queue_head_t event_wqh; - /* a refile sequence protected by fault_pending_wqh lock */ - seqcount_spinlock_t refile_seq; - /* pseudo fd refcounting */ - refcount_t refcount; - /* userfaultfd syscall flags */ - unsigned int flags; - /* features requested from the userspace */ - unsigned int features; - /* released */ - bool released; - /* memory mappings are changing because of non-cooperative event */ - atomic_t mmap_changing; - /* mm with one ore more vmas attached to this userfaultfd_ctx */ - struct mm_struct *mm; -}; - struct userfaultfd_fork_ctx { struct userfaultfd_ctx *orig; struct userfaultfd_ctx *new; diff --git a/include/linux/userfaultfd_k.h b/include/linux/userfaultfd_k.h index aa8e3725f103..9c3f06fd68c0 100644 --- a/include/linux/userfaultfd_k.h +++ b/include/linux/userfaultfd_k.h @@ -36,6 +36,45 @@ #define UFFD_SHARED_FCNTL_FLAGS (O_CLOEXEC | O_NONBLOCK) #define UFFD_FLAGS_SET (EFD_SHARED_FCNTL_FLAGS) +/* + * Start with fault_pending_wqh and fault_wqh so they're more likely + * to be in the same cacheline. + * + * Locking order: + * fd_wqh.lock + * fault_pending_wqh.lock + * fault_wqh.lock + * event_wqh.lock + * + * To avoid deadlocks, IRQs must be disabled when taking any of the above locks, + * since fd_wqh.lock is taken by aio_poll() while it's holding a lock that's + * also taken in IRQ context. + */ +struct userfaultfd_ctx { + /* waitqueue head for the pending (i.e. not read) userfaults */ + wait_queue_head_t fault_pending_wqh; + /* waitqueue head for the userfaults */ + wait_queue_head_t fault_wqh; + /* waitqueue head for the pseudo fd to wakeup poll/read */ + wait_queue_head_t fd_wqh; + /* waitqueue head for events */ + wait_queue_head_t event_wqh; + /* a refile sequence protected by fault_pending_wqh lock */ + seqcount_spinlock_t refile_seq; + /* pseudo fd refcounting */ + refcount_t refcount; + /* userfaultfd syscall flags */ + unsigned int flags; + /* features requested from the userspace */ + unsigned int features; + /* released */ + bool released; + /* memory mappings are changing because of non-cooperative event */ + atomic_t mmap_changing; + /* mm with one ore more vmas attached to this userfaultfd_ctx */ + struct mm_struct *mm; +}; + extern vm_fault_t handle_userfault(struct vm_fault *vmf, unsigned long reason); /* A combined operation mode + behavior flags. */ -- 2.25.1