Received-SPF: pass (google.com: domain of linux-kernel+bounces-37897-linux.lists.archive=gmail.com@vger.kernel.org designates 147.75.199.223 as permitted sender) client-ip=147.75.199.223;
Date: Wed, 24 Jan 2024 21:46:23 -0500
From: Willem de Bruijn <willemdebruijn.kernel@gmail.com>
To: Joe Damato <jdamato@fastly.com>, 
 netdev@vger.kernel.org, 
 linux-kernel@vger.kernel.org
Cc: chuck.lever@oracle.com, 
 jlayton@kernel.org, 
 linux-api@vger.kernel.org, 
 brauner@kernel.org, 
 edumazet@google.com, 
 davem@davemloft.net, 
 alexander.duyck@gmail.com, 
 sridhar.samudrala@intel.com, 
 kuba@kernel.org, 
 weiwan@google.com, 
 Joe Damato <jdamato@fastly.com>
Message-ID: <65b1cb7f73a6a_250560294bd@willemb.c.googlers.com.notmuch>
In-Reply-To: <20240125003014.43103-4-jdamato@fastly.com>
References: <20240125003014.43103-1-jdamato@fastly.com>
 <20240125003014.43103-4-jdamato@fastly.com>
Subject: Re: [net-next v2 3/4] eventpoll: Add epoll ioctl for epoll_params
Precedence: bulk
Mime-Version: 1.0
Content-Type: text/plain;
 charset=utf-8
Content-Transfer-Encoding: 7bit

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@fastly.com>

Please be sure to include the lists and people suggested by
`get_maintainer.pl -f fs/eventpoll.c`.

Adding ioctls is generally discouraged.

As this affects the behavior of epoll_wait, should this just be a
flag to (a new variant of) epoll_wait?

Speaking from some experience with adding epoll_pwait2. I initially
there added a stateful change that would affect wait behavior. The
sensible feedback as the time was to just change the behavior of the
syscall it affected. Even if that requires a syscall (which is not
that different from an ioctl, if better defined).

The discussion in that thread may be informative to decide on API:
https://lwn.net/ml/linux-kernel/20201116161001.1606608-1-willemdebruijn.kernel@gmail.com/

Agreed on the overall principle that it is preferable to be able to
enable busypolling selectively. We already do for SO_BUSY_POLL and
sysctl busy_read.

> ---
>  .../userspace-api/ioctl/ioctl-number.rst      |  1 +
>  fs/eventpoll.c                                | 47 +++++++++++++++++++
>  include/uapi/linux/eventpoll.h                | 12 +++++
>  3 files changed, 60 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..c1ee0fe01da1 100644
> --- a/fs/eventpoll.c
> +++ b/fs/eventpoll.c
> @@ -6,6 +6,8 @@
>   *  Davide Libenzi <davidel@xmailserver.org>
>   */
>  
> +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
> +
>  #include <linux/init.h>
>  #include <linux/kernel.h>
>  #include <linux/sched/signal.h>
> @@ -869,6 +871,49 @@ 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;
> +	struct eventpoll *ep;
> +	struct epoll_params epoll_params;
> +	void __user *uarg = (void __user *) arg;
> +
> +	if (!is_file_epoll(file))
> +		return -EINVAL;
> +
> +	ep = file->private_data;
> +
> +	switch (cmd) {
> +#ifdef CONFIG_NET_RX_BUSY_POLL
> +	case EPIOCSPARAMS:
> +		if (copy_from_user(&epoll_params, uarg, sizeof(epoll_params)))
> +			return -EFAULT;
> +
> +		if (epoll_params.busy_poll_budget > NAPI_POLL_WEIGHT)
> +			pr_err("busy poll budget %u exceeds suggested maximum %u\n",
> +					epoll_params.busy_poll_budget, NAPI_POLL_WEIGHT);
> +
> +		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;
> +#endif
> +	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 +1020,8 @@ 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];
> +} EPOLL_PACKED;
> +
> +#define EPOLL_IOC_TYPE 0x8A
> +#define EPIOCSPARAMS _IOW(EPOLL_IOC_TYPE, 0x01, struct epoll_params)
> +#define EPIOCGPARAMS _IOR(EPOLL_IOC_TYPE, 0x02, struct epoll_params)
> +
>  #endif /* _UAPI_LINUX_EVENTPOLL_H */
> -- 
> 2.25.1
>