[PATCH v2 net-next] net: poll/select low latency socket support

From: Eliezer Tamir
Date: Tue Jun 18 2013 - 04:59:08 EST

select/poll busy-poll support.

Add a new poll flag POLL_LL. When this flag is set, sock poll will call
sk_poll_ll() if possible. sock_poll sets this flag in its return value
to indicate to select/poll when a socket that can busy poll is found.

When poll/select have nothing to report, call the low-level
sock_poll() again until we are out of time or we find something.

Once the system call finds something, it stops setting POLL_LL, so it can
return the result to the user ASAP.

Signed-off-by: Alexander Duyck <alexander.h.duyck@xxxxxxxxx>
Signed-off-by: Jesse Brandeburg <jesse.brandeburg@xxxxxxxxx>
Signed-off-by: Eliezer Tamir <eliezer.tamir@xxxxxxxxxxxxxxx>
---

fs/select.c | 40 +++++++++++++++++++++++++++++++++++++--
include/net/ll_poll.h | 34 +++++++++++++++++++++------------
include/uapi/asm-generic/poll.h | 2 ++
net/socket.c | 14 +++++++++++++-
4 files changed, 75 insertions(+), 15 deletions(-)

diff --git a/fs/select.c b/fs/select.c
index 8c1c96c..1d081f7 100644
--- a/fs/select.c
+++ b/fs/select.c
@@ -27,6 +27,7 @@
#include <linux/rcupdate.h>
#include <linux/hrtimer.h>
#include <linux/sched/rt.h>
+#include <net/ll_poll.h>

#include <asm/uaccess.h>

@@ -393,6 +394,15 @@ static inline void wait_key_set(poll_table *wait, unsigned long in,
wait->_key |= POLLOUT_SET;
}

+static inline void wait_key_set_lls(poll_table *wait, bool set)
+{
+ if (set)
+ wait->_key |= POLL_LL;
+ else
+ wait->_key &= ~POLL_LL;
+}
+
+
int do_select(int n, fd_set_bits *fds, struct timespec *end_time)
{
ktime_t expire, *to = NULL;
@@ -400,6 +410,9 @@ int do_select(int n, fd_set_bits *fds, struct timespec *end_time)
poll_table *wait;
int retval, i, timed_out = 0;
unsigned long slack = 0;
+ u64 ll_time = ll_end_time();
+ bool try_ll = true;
+ bool can_ll = false;

rcu_read_lock();
retval = max_select_fd(n, fds);
@@ -450,6 +463,7 @@ int do_select(int n, fd_set_bits *fds, struct timespec *end_time)
mask = DEFAULT_POLLMASK;
if (f_op && f_op->poll) {
wait_key_set(wait, in, out, bit);
+ wait_key_set_lls(wait, try_ll);
mask = (*f_op->poll)(f.file, wait);
}
fdput(f);
@@ -468,6 +482,10 @@ int do_select(int n, fd_set_bits *fds, struct timespec *end_time)
retval++;
wait->_qproc = NULL;
}
+ if (retval)
+ try_ll = false;
+ if (mask & POLL_LL)
+ can_ll = true;
}
}
if (res_in)
@@ -486,6 +504,11 @@ int do_select(int n, fd_set_bits *fds, struct timespec *end_time)
break;
}

+ if (can_poll_ll(ll_time) && can_ll) {
+ can_ll = false;
+ continue;
+ }
+
/*
* If this is the first loop and we have a timeout
* given, then we convert to ktime_t and set the to
@@ -717,7 +740,8 @@ struct poll_list {
* pwait poll_table will be used by the fd-provided poll handler for waiting,
* if pwait->_qproc is non-NULL.
*/
-static inline unsigned int do_pollfd(struct pollfd *pollfd, poll_table *pwait)
+static inline unsigned int do_pollfd(struct pollfd *pollfd, poll_table *pwait,
+ bool *can_ll, bool try_ll)
{
unsigned int mask;
int fd;
@@ -731,7 +755,11 @@ static inline unsigned int do_pollfd(struct pollfd *pollfd, poll_table *pwait)
mask = DEFAULT_POLLMASK;
if (f.file->f_op && f.file->f_op->poll) {
pwait->_key = pollfd->events|POLLERR|POLLHUP;
+ if (try_ll)
+ pwait->_key |= POLL_LL;
mask = f.file->f_op->poll(f.file, pwait);
+ if (mask & POLL_LL)
+ *can_ll = true;
}
/* Mask out unneeded events. */
mask &= pollfd->events | POLLERR | POLLHUP;
@@ -750,6 +778,9 @@ static int do_poll(unsigned int nfds, struct poll_list *list,
ktime_t expire, *to = NULL;
int timed_out = 0, count = 0;
unsigned long slack = 0;
+ u64 ll_time = ll_end_time();
+ bool can_ll = false;
+ bool try_ll = true;

/* Optimise the no-wait case */
if (end_time && !end_time->tv_sec && !end_time->tv_nsec) {
@@ -776,9 +807,10 @@ static int do_poll(unsigned int nfds, struct poll_list *list,
* this. They'll get immediately deregistered
* when we break out and return.
*/
- if (do_pollfd(pfd, pt)) {
+ if (do_pollfd(pfd, pt, &can_ll, try_ll)) {
count++;
pt->_qproc = NULL;
+ try_ll = false;
}
}
}
@@ -795,6 +827,10 @@ static int do_poll(unsigned int nfds, struct poll_list *list,
if (count || timed_out)
break;

+ if (can_poll_ll(ll_time) && can_ll) {
+ can_ll = false;
+ continue;
+ }
/*
* If this is the first loop and we have a timeout
* given, then we convert to ktime_t and set the to
diff --git a/include/net/ll_poll.h b/include/net/ll_poll.h
index fcc7c36..49b954c 100644
--- a/include/net/ll_poll.h
+++ b/include/net/ll_poll.h
@@ -38,19 +38,21 @@ extern unsigned int sysctl_net_ll_poll __read_mostly;

/* we can use sched_clock() because we don't care much about precision
* we only care that the average is bounded
+ * we don't mind a ~2.5% imprecision so <<10 instead of *1000
+ * sk->sk_ll_usec is a u_int so this can't overflow
*/
-static inline u64 ll_end_time(struct sock *sk)
+static inline u64 ll_sk_end_time(struct sock *sk)
{
- u64 end_time = ACCESS_ONCE(sk->sk_ll_usec);
-
- /* we don't mind a ~2.5% imprecision
- * sk->sk_ll_usec is a u_int so this can't overflow
- */
- end_time = (end_time << 10) + sched_clock();
+ return (ACCESS_ONCE(sk->sk_ll_usec) << 10) + sched_clock();
+}

- return end_time;
+/* in poll/select we use the global sysctl_net_ll_poll value */
+static inline u64 ll_end_time(void)
+{
+ return (ACCESS_ONCE(sysctl_net_ll_poll) << 10) + sched_clock();
}

+
static inline bool sk_valid_ll(struct sock *sk)
{
return sk->sk_ll_usec && sk->sk_napi_id &&
@@ -62,10 +64,13 @@ static inline bool can_poll_ll(u64 end_time)
return !time_after64(sched_clock(), end_time);
}

+/* when used in sock_poll() nonblock is known at compile time to be true
+ * so the loop and end_time will be optimized out
+ */
static inline bool sk_poll_ll(struct sock *sk, int nonblock)
{
+ u64 end_time = nonblock ? 0 : ll_sk_end_time(sk);
const struct net_device_ops *ops;
- u64 end_time = ll_end_time(sk);
struct napi_struct *napi;
int rc = false;

@@ -95,8 +100,8 @@ static inline bool sk_poll_ll(struct sock *sk, int nonblock)
NET_ADD_STATS_BH(sock_net(sk),
LINUX_MIB_LOWLATENCYRXPACKETS, rc);

- } while (skb_queue_empty(&sk->sk_receive_queue)
- && can_poll_ll(end_time) && !nonblock);
+ } while (!nonblock && skb_queue_empty(&sk->sk_receive_queue)
+ && can_poll_ll(end_time));

rc = !skb_queue_empty(&sk->sk_receive_queue);
out:
@@ -118,7 +123,12 @@ static inline void sk_mark_ll(struct sock *sk, struct sk_buff *skb)

#else /* CONFIG_NET_LL_RX_POLL */

-static inline u64 ll_end_time(struct sock *sk)
+static inline u64 sk_ll_end_time(struct sock *sk)
+{
+ return 0;
+}
+
+static inline u64 ll_end_time(void)
{
return 0;
}
diff --git a/include/uapi/asm-generic/poll.h b/include/uapi/asm-generic/poll.h
index 9ce7f44..4aee586 100644
--- a/include/uapi/asm-generic/poll.h
+++ b/include/uapi/asm-generic/poll.h
@@ -30,6 +30,8 @@

#define POLLFREE 0x4000 /* currently only for epoll */

+#define POLL_LL 0x8000
+
struct pollfd {
int fd;
short events;
diff --git a/net/socket.c b/net/socket.c
index 3eec3f7..a1c3ee8 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -1147,13 +1147,25 @@ EXPORT_SYMBOL(sock_create_lite);
/* No kernel lock held - perfect */
static unsigned int sock_poll(struct file *file, poll_table *wait)
{
+ unsigned int ll_flag = 0;
struct socket *sock;

/*
* We can't return errors to poll, so it's either yes or no.
*/
sock = file->private_data;
- return sock->ops->poll(file, sock, wait);
+
+ if (sk_valid_ll(sock->sk)) {
+
+ /* this socket can poll_ll so tell the system call */
+ ll_flag = POLL_LL;
+
+ /* only if requested by syscall */
+ if (wait && (wait->_key & POLL_LL))
+ sk_poll_ll(sock->sk, 1);
+ }
+
+ return ll_flag | sock->ops->poll(file, sock, wait);
}

static int sock_mmap(struct file *file, struct vm_area_struct *vma)

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/