Re: [PATCH net-next v3 3/3] eventpoll: Add epoll ioctl for epoll_params

[Christian Brauner <brauner@kernel.org>]

On Thu, Jan 25, 2024 at 06:36:30PM -0800, Joe Damato wrote:
> On Thu, Jan 25, 2024 at 04:23:58PM -0800, Greg Kroah-Hartman wrote:
> > On Thu, Jan 25, 2024 at 04:11:28PM -0800, Joe Damato wrote:
> > > On Thu, Jan 25, 2024 at 03:21:46PM -0800, Greg Kroah-Hartman wrote:
> > > > On Thu, Jan 25, 2024 at 10:56:59PM +0000, Joe Damato wrote:
> > > > > +struct epoll_params {
> > > > > +	u64 busy_poll_usecs;
> > > > > +	u16 busy_poll_budget;
> > > > > +
> > > > > +	/* for future fields */
> > > > > +	u8 data[118];
> > > > > +} EPOLL_PACKED;
> > > > 
> > > > variables that cross the user/kernel boundry need to be __u64, __u16,
> > > > and __u8 here.
> > > 
> > > I'll make that change for the next version, thank you.
> > > 
> > > > And why 118?
> > > 
> > > I chose this arbitrarily. I figured that a 128 byte struct would support 16
> > > u64s in the event that other fields needed to be added in the future. 118
> > > is what was left after the existing fields. There's almost certainly a
> > > better way to do this - or perhaps it is unnecessary as per your other
> > > message.
> > > 
> > > I am not sure if leaving extra space in the struct is a recommended
> > > practice for ioctls or not - I thought I noticed some code that did and
> > > some that didn't in the kernel so I err'd on the side of leaving the space
> > > and probably did it in the worst way possible.
> > 
> > It's not really a good idea unless you know exactly what you are going
> > to do with it.  Why not just have a new ioctl if you need new
> > information in the future?  That's simpler, right?
> 
> Sure, that makes sense to me. I'll remove it in the v4 alongside the other
> changes you've requested.

Fwiw, we do support extensible ioctls since they encode the size. Take a
look at kernel/seccomp.c. It's a clean extensible interface built on top
of the copy_struct_from_user() pattern we added for system calls
(openat(), clone3() etc.):

static long seccomp_notify_ioctl(struct file *file, unsigned int cmd,
                                 unsigned long arg)
{
        struct seccomp_filter *filter = file->private_data;
        void __user *buf = (void __user *)arg;

        /* Fixed-size ioctls */
        switch (cmd) {
        case SECCOMP_IOCTL_NOTIF_RECV:
                return seccomp_notify_recv(filter, buf);
        case SECCOMP_IOCTL_NOTIF_SEND:
                return seccomp_notify_send(filter, buf);
        case SECCOMP_IOCTL_NOTIF_ID_VALID_WRONG_DIR:
        case SECCOMP_IOCTL_NOTIF_ID_VALID:
                return seccomp_notify_id_valid(filter, buf);
        case SECCOMP_IOCTL_NOTIF_SET_FLAGS:
                return seccomp_notify_set_flags(filter, arg);
        }

        /* Extensible Argument ioctls */
#define EA_IOCTL(cmd)   ((cmd) & ~(IOC_INOUT | IOCSIZE_MASK))
        switch (EA_IOCTL(cmd)) {
        case EA_IOCTL(SECCOMP_IOCTL_NOTIF_ADDFD):
                return seccomp_notify_addfd(filter, buf, _IOC_SIZE(cmd));
        default:
                return -EINVAL;
        }
}

static long seccomp_notify_addfd(struct seccomp_filter *filter,
                                 struct seccomp_notif_addfd __user *uaddfd,
                                 unsigned int size)
{
        struct seccomp_notif_addfd addfd;
        struct seccomp_knotif *knotif;
        struct seccomp_kaddfd kaddfd;
        int ret;

        BUILD_BUG_ON(sizeof(addfd) < SECCOMP_NOTIFY_ADDFD_SIZE_VER0);
        BUILD_BUG_ON(sizeof(addfd) != SECCOMP_NOTIFY_ADDFD_SIZE_LATEST);

        if (size < SECCOMP_NOTIFY_ADDFD_SIZE_VER0 || size >= PAGE_SIZE)
                return -EINVAL;

        ret = copy_struct_from_user(&addfd, sizeof(addfd), uaddfd, size);
        if (ret)
                return ret;