Re: [PATCH v2 1/3] userfaultfd: move userfaultfd_ctx struct to header file

[Mike Rapoport <rppt@kernel.org>]

On Mon, Jan 29, 2024 at 11:35:10AM -0800, Lokesh Gidra wrote:
> Moving the struct to userfaultfd_k.h to be accessible from
> mm/userfaultfd.c. There are no other changes in the struct.

Just a thought, it maybe worth to move all of fs/userfaultfd.c to
mm/userfaultfd.c ...
 
> This is required to prepare for using per-vma locks in userfaultfd
> operations.
> 
> Signed-off-by: Lokesh Gidra <lokeshgidra@google.com>

Reviewed-by: Mike Rapoport (IBM) <rppt@kernel.org>

> ---
>  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 05c8e8a05427..58331b83d648 100644
> --- a/fs/userfaultfd.c
> +++ b/fs/userfaultfd.c
> @@ -50,45 +50,6 @@ static struct ctl_table vm_userfaultfd_table[] = {
>  
>  static struct kmem_cache *userfaultfd_ctx_cachep __ro_after_init;
>  
> -/*
> - * 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 e4056547fbe6..691d928ee864 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. */
> -- 
> 2.43.0.429.g432eaa2c6b-goog
> 

-- 
Sincerely yours,
Mike.