Patchwork [net-next,2/2] net: avoid calling sched_clock when LLS is off

login
register
mail settings
Submitter Eliezer Tamir
Date June 28, 2013, 12:59 p.m.
Message ID <20130628125934.14419.38109.stgit@ladj378.jer.intel.com>
Download mbox | patch
Permalink /patch/255361/
State Accepted
Delegated to: David Miller
Headers show

Comments

Eliezer Tamir - June 28, 2013, 12:59 p.m.
Change Low Latency Sockets code for select and poll so that
when LLS is disabled sched_clock() is never called.

Also, avoid sending POLL_LL to sockets if disabled.

Reported-by: Andi Kleen <andi@firstfloor.org>
Signed-off-by: Eliezer Tamir <eliezer.tamir@linux.intel.com>
---

 fs/select.c           |   11 +++++++----
 include/net/ll_poll.h |   17 +++++++++++++++--
 2 files changed, 22 insertions(+), 6 deletions(-)


--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Andi Kleen - June 28, 2013, 2:38 p.m.
> diff --git a/fs/select.c b/fs/select.c
> index 79b876e..3654075 100644
> --- a/fs/select.c
> +++ b/fs/select.c
> @@ -402,7 +402,7 @@ 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;
> -	unsigned int ll_flag = POLL_LL;
> +	unsigned int ll_flag = ll_get_flag();

Is that a global flag? That's still the wrong level. It should
look at something in the file descriptor (preferably without
fetching any new cache lines)

-Andi

>  
> +static inline unsigned int ll_get_flag(void)
> +{
> +	return sysctl_net_ll_poll ? POLL_LL : 0;
> +}
--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Eliezer Tamir - June 28, 2013, 2:54 p.m.
On 28/06/2013 17:38, Andi Kleen wrote:
>> diff --git a/fs/select.c b/fs/select.c
>> index 79b876e..3654075 100644
>> --- a/fs/select.c
>> +++ b/fs/select.c
>> @@ -402,7 +402,7 @@ 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;
>> -	unsigned int ll_flag = POLL_LL;
>> +	unsigned int ll_flag = ll_get_flag();
>
> Is that a global flag? That's still the wrong level. It should
> look at something in the file descriptor (preferably without
> fetching any new cache lines)
>

There is a global flag that decides if we even try to find supported
files (sockets).

If it is on we look to see if anyone will return POLL_LL.
at the individual socket level, you need both the socket option to
be on, and the queue data to be available for it to return POLL_LL.

I wanted to find a way to control this at the time the user calls poll().
I was not able to find any simple way of doing it that way.
I'm open to suggestion.
--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Patch

diff --git a/fs/select.c b/fs/select.c
index 79b876e..3654075 100644
--- a/fs/select.c
+++ b/fs/select.c
@@ -402,7 +402,7 @@  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;
-	unsigned int ll_flag = POLL_LL;
+	unsigned int ll_flag = ll_get_flag();
 	u64 ll_time = ll_end_time();
 
 	rcu_read_lock();
@@ -497,7 +497,8 @@  int do_select(int n, fd_set_bits *fds, struct timespec *end_time)
 			break;
 		}
 
-		if (can_ll && can_poll_ll(ll_time))
+		/* only if on, have sockets with POLL_LL and not out of time */
+		if (ll_flag && can_ll && can_poll_ll(ll_time))
 			continue;
 
 		/*
@@ -768,7 +769,7 @@  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;
-	unsigned int ll_flag = POLL_LL;
+	unsigned int ll_flag = ll_get_flag();
 	u64 ll_time = ll_end_time();
 
 	/* Optimise the no-wait case */
@@ -817,8 +818,10 @@  static int do_poll(unsigned int nfds,  struct poll_list *list,
 		if (count || timed_out)
 			break;
 
-		if (can_ll && can_poll_ll(ll_time))
+		/* only if on, have sockets with POLL_LL and not out of time */
+		if (ll_flag && can_ll && can_poll_ll(ll_time))
 			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 6d45e6f..6c06f7c 100644
--- a/include/net/ll_poll.h
+++ b/include/net/ll_poll.h
@@ -37,6 +37,11 @@  extern unsigned int sysctl_net_ll_poll __read_mostly;
 #define LL_FLUSH_FAILED		-1
 #define LL_FLUSH_BUSY		-2
 
+static inline unsigned int ll_get_flag(void)
+{
+	return sysctl_net_ll_poll ? POLL_LL : 0;
+}
+
 /* a wrapper to make debug_smp_processor_id() happy
  * we can use sched_clock() because we don't care much about precision
  * we only care that the average is bounded
@@ -67,10 +72,14 @@  static inline u64 ll_sk_end_time(struct sock *sk)
 	return ((u64)ACCESS_ONCE(sk->sk_ll_usec) << 10) + ll_sched_clock();
 }
 
-/* in poll/select we use the global sysctl_net_ll_poll value */
+/* in poll/select we use the global sysctl_net_ll_poll value
+ * only call sched_clock() if enabled
+ */
 static inline u64 ll_end_time(void)
 {
-	return ((u64)ACCESS_ONCE(sysctl_net_ll_poll) << 10) + ll_sched_clock();
+	u64 end_time = ACCESS_ONCE(sysctl_net_ll_poll);
+
+	return end_time ? (end_time << 10) + ll_sched_clock() : 0;
 }
 
 static inline bool sk_valid_ll(struct sock *sk)
@@ -141,6 +150,10 @@  static inline void sk_mark_ll(struct sock *sk, struct sk_buff *skb)
 }
 
 #else /* CONFIG_NET_LL_RX_POLL */
+static inline unsigned long ll_get_flag(void)
+{
+	return 0;
+}
 
 static inline u64 sk_ll_end_time(struct sock *sk)
 {