[net-next,v4,3/3] eventpoll: Add epoll ioctl for epoll_params
Commit Message
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.
Parameters are limited:
- busy_poll_usecs is limited to <= u32_max
- busy_poll_budget is limited to <= NAPI_POLL_WEIGHT by unprivileged
users (!capable(CAP_NET_ADMIN)).
Signed-off-by: Joe Damato <jdamato@fastly.com>
---
.../userspace-api/ioctl/ioctl-number.rst | 1 +
fs/eventpoll.c | 65 +++++++++++++++++++
include/uapi/linux/eventpoll.h | 12 ++++
3 files changed, 78 insertions(+)
Comments
On Wed, Jan 31, 2024 at 01:47:33AM +0000, Joe Damato wrote:
> +struct epoll_params {
> + __aligned_u64 busy_poll_usecs;
> + __u16 busy_poll_budget;
> +
> + /* pad the struct to a multiple of 64bits for alignment on all arches */
> + __u8 __pad[6];
You HAVE to check this padding to be sure it is all 0, otherwise it can
never be used in the future for anything.
thanks,
greg k-h
On Tue, Jan 30, 2024 at 06:08:36PM -0800, Greg Kroah-Hartman wrote:
> On Wed, Jan 31, 2024 at 01:47:33AM +0000, Joe Damato wrote:
> > +struct epoll_params {
> > + __aligned_u64 busy_poll_usecs;
> > + __u16 busy_poll_budget;
> > +
> > + /* pad the struct to a multiple of 64bits for alignment on all arches */
> > + __u8 __pad[6];
>
> You HAVE to check this padding to be sure it is all 0, otherwise it can
> never be used in the future for anything.
Is there some preferred mechanism for this in the kernel that I should be
using or is this as simple as adding a for loop to check each u8 == 0 ?
Thanks.
On Tue, Jan 30, 2024 at 06:27:57PM -0800, Joe Damato wrote:
> On Tue, Jan 30, 2024 at 06:08:36PM -0800, Greg Kroah-Hartman wrote:
> > On Wed, Jan 31, 2024 at 01:47:33AM +0000, Joe Damato wrote:
> > > +struct epoll_params {
> > > + __aligned_u64 busy_poll_usecs;
> > > + __u16 busy_poll_budget;
> > > +
> > > + /* pad the struct to a multiple of 64bits for alignment on all arches */
> > > + __u8 __pad[6];
> >
> > You HAVE to check this padding to be sure it is all 0, otherwise it can
> > never be used in the future for anything.
>
> Is there some preferred mechanism for this in the kernel that I should be
> using or is this as simple as adding a for loop to check each u8 == 0 ?
It's as simple as a loop :)
On Wed, Jan 31, 2024 at 07:03:54AM +0100, Jiri Slaby wrote:
> On 31. 01. 24, 3:27, Joe Damato wrote:
> > On Tue, Jan 30, 2024 at 06:08:36PM -0800, Greg Kroah-Hartman wrote:
> > > On Wed, Jan 31, 2024 at 01:47:33AM +0000, Joe Damato wrote:
> > > > +struct epoll_params {
> > > > + __aligned_u64 busy_poll_usecs;
> > > > + __u16 busy_poll_budget;
> > > > +
> > > > + /* pad the struct to a multiple of 64bits for alignment on all arches */
> > > > + __u8 __pad[6];
> > >
> > > You HAVE to check this padding to be sure it is all 0, otherwise it can
> > > never be used in the future for anything.
> >
> > Is there some preferred mechanism for this in the kernel that I should be
> > using or is this as simple as adding a for loop to check each u8 == 0 ?
>
> You are likely looking for memchr_inv().
Ah, never noticed that, thanks!
@@ -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/>
@@ -37,6 +37,7 @@
#include <linux/seq_file.h>
#include <linux/compat.h>
#include <linux/rculist.h>
+#include <linux/capability.h>
#include <net/busy_poll.h>
/*
@@ -495,6 +496,42 @@ 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_usecs > U32_MAX)
+ return -EINVAL;
+
+ 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 +547,12 @@ 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 +912,26 @@ 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 +1038,8 @@ 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,
};
/*
@@ -85,4 +85,16 @@ struct epoll_event {
__u64 data;
} EPOLL_PACKED;
+struct epoll_params {
+ __aligned_u64 busy_poll_usecs;
+ __u16 busy_poll_budget;
+
+ /* pad the struct to a multiple of 64bits for alignment on all arches */
+ __u8 __pad[6];
+};
+
+#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 */