| Message ID | 20240209211528.51234-5-jdamato@fastly.com (mailing list archive) |
|---|---|
| State | Superseded |
| Delegated to: | Netdev Maintainers |
| Headers | show |
| Series | Per epoll context busy poll support | expand |
On Fri, Feb 9, 2024 at 10:15 PM Joe Damato <jdamato@fastly.com> 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, packet budget, and > prefer busy poll params for a specific epoll context. > > Parameters are limited: > - busy_poll_usecs is limited to <= s32_max > - busy_poll_budget is limited to <= NAPI_POLL_WEIGHT by unprivileged > users (!capable(CAP_NET_ADMIN)) > - prefer_busy_poll must be 0 or 1 > - __pad must be 0 > > Signed-off-by: Joe Damato <jdamato@fastly.com> > Acked-by: Stanislav Fomichev <sdf@google.com> > Reviewed-by: Jiri Slaby <jirislaby@kernel.org> > --- > .../userspace-api/ioctl/ioctl-number.rst | 1 + > fs/eventpoll.c | 72 +++++++++++++++++++ > include/uapi/linux/eventpoll.h | 13 ++++ > 3 files changed, 86 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 1b8d01af0c2c..aa58d42737e6 100644 > --- a/fs/eventpoll.c > +++ b/fs/eventpoll.c > @@ -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> > > /* > @@ -494,6 +495,49 @@ 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 = file->private_data; > + void __user *uarg = (void __user *)arg; > + struct epoll_params epoll_params; > + > + switch (cmd) { > + case EPIOCSPARAMS: > + if (copy_from_user(&epoll_params, uarg, sizeof(epoll_params))) > + return -EFAULT; > + > + /* pad byte must be zero */ > + if (epoll_params.__pad) > + return -EINVAL; > + > + if (epoll_params.busy_poll_usecs > S32_MAX) > + return -EINVAL; > + > + if (epoll_params.prefer_busy_poll > 1) > + 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; You need WRITE_ONCE(ep->XXX, val); for all these settings. > + ep->busy_poll_budget = epoll_params.busy_poll_budget; > + ep->prefer_busy_poll = epoll_params.prefer_busy_poll; > + return 0; > + case EPIOCGPARAMS: > + memset(&epoll_params, 0, sizeof(epoll_params)); > + epoll_params.busy_poll_usecs = ep->busy_poll_usecs; You need to use READ_ONCE(ep->XXXXX) for the three reads. > + epoll_params.busy_poll_budget = ep->busy_poll_budget; > + epoll_params.prefer_busy_poll = ep->prefer_busy_poll; > + if (copy_to_user(uarg, &epoll_params, sizeof(epoll_params))) > + return -EFAULT; > + return 0; > + default: > + return -ENOIOCTLCMD; > + } > +} >
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 1b8d01af0c2c..aa58d42737e6 100644 --- a/fs/eventpoll.c +++ b/fs/eventpoll.c @@ -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> /* @@ -494,6 +495,49 @@ 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 = file->private_data; + void __user *uarg = (void __user *)arg; + struct epoll_params epoll_params; + + switch (cmd) { + case EPIOCSPARAMS: + if (copy_from_user(&epoll_params, uarg, sizeof(epoll_params))) + return -EFAULT; + + /* pad byte must be zero */ + if (epoll_params.__pad) + return -EINVAL; + + if (epoll_params.busy_poll_usecs > S32_MAX) + return -EINVAL; + + if (epoll_params.prefer_busy_poll > 1) + 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; + ep->prefer_busy_poll = epoll_params.prefer_busy_poll; + 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; + epoll_params.prefer_busy_poll = ep->prefer_busy_poll; + 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) @@ -505,6 +549,12 @@ static inline void ep_set_busy_poll_napi_id(struct epitem *epi) { } +static long ep_eventpoll_bp_ioctl(struct file *file, unsigned int cmd, + unsigned long arg) +{ + return -EOPNOTSUPP; +} + #endif /* CONFIG_NET_RX_BUSY_POLL */ /* @@ -864,6 +914,26 @@ 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; @@ -970,6 +1040,8 @@ 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..4f4b948ef381 100644 --- a/include/uapi/linux/eventpoll.h +++ b/include/uapi/linux/eventpoll.h @@ -85,4 +85,17 @@ struct epoll_event { __u64 data; } EPOLL_PACKED; +struct epoll_params { + __u32 busy_poll_usecs; + __u16 busy_poll_budget; + __u8 prefer_busy_poll; + + /* pad the struct to a multiple of 64bits */ + __u8 __pad; +}; + +#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 */
Add an ioctl for getting and setting epoll_params. User programs can use this ioctl to get and set the busy poll usec time, packet budget, and prefer busy poll params for a specific epoll context. Parameters are limited: - busy_poll_usecs is limited to <= s32_max - busy_poll_budget is limited to <= NAPI_POLL_WEIGHT by unprivileged users (!capable(CAP_NET_ADMIN)) - prefer_busy_poll must be 0 or 1 - __pad must be 0 Signed-off-by: Joe Damato <jdamato@fastly.com> Acked-by: Stanislav Fomichev <sdf@google.com> Reviewed-by: Jiri Slaby <jirislaby@kernel.org> --- .../userspace-api/ioctl/ioctl-number.rst | 1 + fs/eventpoll.c | 72 +++++++++++++++++++ include/uapi/linux/eventpoll.h | 13 ++++ 3 files changed, 86 insertions(+)