net: poll/select low latency socket support

select/poll busy-poll support.

Split sysctl value into two separate ones, one for read and one for poll.
updated Documentation/sysctl/net.txt

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: Eliezer Tamir <eliezer.tamir@linux.intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

2 files changed, 24 insertions, 13 deletions

diff --git a/include/net/ll_poll.h b/include/net/ll_poll.h
index fcc7c365cee5..5bf2b3a6129e 100644
--- a/include/net/ll_poll.h
+++ b/include/net/ll_poll.h
@@ -30,6 +30,7 @@
 #ifdef CONFIG_NET_LL_RX_POLL
 
 struct napi_struct;
+extern unsigned int sysctl_net_ll_read __read_mostly;
 extern unsigned int sysctl_net_ll_poll __read_mostly;
 
 /* return values from ndo_ll_poll */
@@ -38,17 +39,18 @@ 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 ((u64)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 ((u64)ACCESS_ONCE(sysctl_net_ll_poll) << 10) + sched_clock();
 }
 
 static inline bool sk_valid_ll(struct sock *sk)
@@ -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;
 
@@ -84,7 +89,6 @@ static inline bool sk_poll_ll(struct sock *sk, int nonblock)
                 goto out;
 
         do {
-
                 rc = ops->ndo_ll_poll(napi);
 
                 if (rc == LL_FLUSH_FAILED)
@@ -95,8 +99,8 @@ 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 +122,12 @@ 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 9ce7f44aebd2..4aee586979ca 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;