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

[Joe Damato <jdamato@xxxxxxxxxx>]

On Thu, Jan 25, 2024 at 03:22:34PM -0800, Greg Kroah-Hartman wrote:
> On Thu, Jan 25, 2024 at 10:56:59PM +0000, Joe Damato wrote:
> > Add an ioctl for getting and setting epoll_params. User programs can use
> > this ioctl to get and set the busy poll usec time or packet budget
> > params for a specific epoll context.
> > 
> > Signed-off-by: Joe Damato <jdamato@xxxxxxxxxx>
> > ---
> >  .../userspace-api/ioctl/ioctl-number.rst      |  1 +
> >  fs/eventpoll.c                                | 64 +++++++++++++++++++
> >  include/uapi/linux/eventpoll.h                | 12 ++++
> >  3 files changed, 77 insertions(+)
> > 
> > diff --git a/Documentation/userspace-api/ioctl/ioctl-number.rst b/Documentation/userspace-api/ioctl/ioctl-number.rst
> > index 457e16f06e04..b33918232f78 100644
> > --- a/Documentation/userspace-api/ioctl/ioctl-number.rst
> > +++ b/Documentation/userspace-api/ioctl/ioctl-number.rst
> > @@ -309,6 +309,7 @@ Code  Seq#    Include File                                           Comments
> >  0x89  0B-DF  linux/sockios.h
> >  0x89  E0-EF  linux/sockios.h                                         SIOCPROTOPRIVATE range
> >  0x89  F0-FF  linux/sockios.h                                         SIOCDEVPRIVATE range
> > +0x8A  00-1F  linux/eventpoll.h
> >  0x8B  all    linux/wireless.h
> >  0x8C  00-3F                                                          WiNRADiO driver
> >                                                                       <http://www.winradio.com.au/>
> > diff --git a/fs/eventpoll.c b/fs/eventpoll.c
> > index 40bd97477b91..73ae886efb8a 100644
> > --- a/fs/eventpoll.c
> > +++ b/fs/eventpoll.c
> > @@ -6,6 +6,8 @@
> >   *  Davide Libenzi <davidel@xxxxxxxxxxxxxxx>
> >   */
> >  
> > +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
> > +
> >  #include <linux/init.h>
> >  #include <linux/kernel.h>
> >  #include <linux/sched/signal.h>
> > @@ -37,6 +39,7 @@
> >  #include <linux/seq_file.h>
> >  #include <linux/compat.h>
> >  #include <linux/rculist.h>
> > +#include <linux/capability.h>
> >  #include <net/busy_poll.h>
> >  
> >  /*
> > @@ -495,6 +498,39 @@ static inline void ep_set_busy_poll_napi_id(struct epitem *epi)
> >  	ep->napi_id = napi_id;
> >  }
> >  
> > +static long ep_eventpoll_bp_ioctl(struct file *file, unsigned int cmd,
> > +				  unsigned long arg)
> > +{
> > +	struct eventpoll *ep;
> > +	struct epoll_params epoll_params;
> > +	void __user *uarg = (void __user *) arg;
> > +
> > +	ep = file->private_data;
> > +
> > +	switch (cmd) {
> > +	case EPIOCSPARAMS:
> > +		if (copy_from_user(&epoll_params, uarg, sizeof(epoll_params)))
> > +			return -EFAULT;
> > +
> > +		if (epoll_params.busy_poll_budget > NAPI_POLL_WEIGHT &&
> > +		    !capable(CAP_NET_ADMIN))
> > +			return -EPERM;
> > +
> > +		ep->busy_poll_usecs = epoll_params.busy_poll_usecs;
> > +		ep->busy_poll_budget = epoll_params.busy_poll_budget;
> > +		return 0;
> > +	case EPIOCGPARAMS:
> > +		memset(&epoll_params, 0, sizeof(epoll_params));
> > +		epoll_params.busy_poll_usecs = ep->busy_poll_usecs;
> > +		epoll_params.busy_poll_budget = ep->busy_poll_budget;
> > +		if (copy_to_user(uarg, &epoll_params, sizeof(epoll_params)))
> > +			return -EFAULT;
> > +		return 0;
> > +	default:
> > +		return -ENOIOCTLCMD;
> > +	}
> > +}
> > +
> >  #else
> >  
> >  static inline bool ep_busy_loop(struct eventpoll *ep, int nonblock)
> > @@ -510,6 +546,12 @@ static inline bool ep_busy_loop_on(struct eventpoll *ep)
> >  {
> >  	return false;
> >  }
> > +
> > +static long ep_eventpoll_bp_ioctl(struct file *file, unsigned int cmd,
> > +				  unsigned long arg)
> > +{
> > +	return -EOPNOTSUPP;
> > +}
> >  #endif /* CONFIG_NET_RX_BUSY_POLL */
> >  
> >  /*
> > @@ -869,6 +911,26 @@ static void ep_clear_and_put(struct eventpoll *ep)
> >  		ep_free(ep);
> >  }
> >  
> > +static long ep_eventpoll_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
> > +{
> > +	int ret;
> > +
> > +	if (!is_file_epoll(file))
> > +		return -EINVAL;
> > +
> > +	switch (cmd) {
> > +	case EPIOCSPARAMS:
> > +	case EPIOCGPARAMS:
> > +		ret = ep_eventpoll_bp_ioctl(file, cmd, arg);
> > +		break;
> > +	default:
> > +		ret = -EINVAL;
> > +		break;
> > +	}
> > +
> > +	return ret;
> > +}
> > +
> >  static int ep_eventpoll_release(struct inode *inode, struct file *file)
> >  {
> >  	struct eventpoll *ep = file->private_data;
> > @@ -975,6 +1037,8 @@ static const struct file_operations eventpoll_fops = {
> >  	.release	= ep_eventpoll_release,
> >  	.poll		= ep_eventpoll_poll,
> >  	.llseek		= noop_llseek,
> > +	.unlocked_ioctl	= ep_eventpoll_ioctl,
> > +	.compat_ioctl   = compat_ptr_ioctl,
> >  };
> >  
> >  /*
> > diff --git a/include/uapi/linux/eventpoll.h b/include/uapi/linux/eventpoll.h
> > index cfbcc4cc49ac..8eb0fdbce995 100644
> > --- a/include/uapi/linux/eventpoll.h
> > +++ b/include/uapi/linux/eventpoll.h
> > @@ -85,4 +85,16 @@ struct epoll_event {
> >  	__u64 data;
> >  } EPOLL_PACKED;
> >  
> > +struct epoll_params {
> > +	u64 busy_poll_usecs;
> > +	u16 busy_poll_budget;
> > +
> > +	/* for future fields */
> > +	u8 data[118];
> 
> You forgot to validate that "data" is set to 0, which means that this
> would be useless.  Why have this at all?

I included this because I (probably incorrectly) thought that there should
be some extra space in the struct for future additions if needed.

I am not sure if that is a recommended practice for this sort of thing or
not, but if it is I can add some validation.

Thanks for your time and effort in reviewing my code.