Re: [PATCH] net: tcp: Fix a PTO timing granularity issue

[Ido Yariv <ido@wizery.com>]

Hi Eric,

On Wed, May 27, 2015 at 10:24:16AM -0700, Eric Dumazet wrote:
> On Wed, 2015-05-27 at 12:54 -0400, Ido Yariv wrote:
> > Hi Eric,
> 
> > That's a nice optimization ;)
> > 
> > However, I think that with Nicholas Mc Guire's recent changes to
> > msecs_to_jiffies (http://marc.info/?l=linux-kernel&m=143195210010666),
> > we should get this for free, no?
> 
> Well, on net and net-next tree we currently have :
> 
> $ grep msecs_to_jiffies include/linux/jiffies.h
> extern unsigned long msecs_to_jiffies(const unsigned int m);
> 
> Given your patch is for stable, I would not mind having this done
> anyway.

I believe these changes are in tip, but not in net/net-next just yet.

I actually didn't think this patch is for stable, but we can certainly
do that.

Would you be fine with the patch below? Please note that I modified your
optimization a bit.

Cheers,
Ido.

>From 6b406d4746fe5523f29863c10e43ab8bba913307 Mon Sep 17 00:00:00 2001
From: Ido Yariv <ido@wizery.com>
Date: Thu, 21 May 2015 08:23:13 +0200
Subject: [PATCH v4] net: tcp: Fix a PTO timing granularity issue

The Tail Loss Probe RFC specifies that the PTO value should be set to
max(2 * SRTT, 10ms), where SRTT is the smoothed round-trip time.

The PTO value is converted to jiffies, so the timer may expire
prematurely.

This is especially problematic on systems in which HZ <= 100, so work
around this by setting the timeout to at least 2 jiffies on such
systems.

The 10ms figure was originally selected based on tests performed with
the current implementation and HZ = 1000. Thus, leave the behavior on
systems with HZ > 100 unchanged.

Signed-off-by: Ido Yariv <idox.yariv@intel.com>
---
 include/net/tcp.h     | 17 +++++++++++++++++
 net/ipv4/tcp_output.c |  2 +-
 2 files changed, 18 insertions(+), 1 deletion(-)

diff --git a/include/net/tcp.h b/include/net/tcp.h
index 2bb2bad..d22c93c 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -1751,4 +1751,21 @@ static inline void skb_set_tcp_pure_ack(struct sk_buff *skb)
 	skb->truesize = 2;
 }
 
+/* Convert msecs to jiffies, ensuring that the return value is always at least
+ * 2 jiffies.
+ * This can be used when setting tick-based timers to guarantee that they won't
+ * expire right away.
+ */
+static inline unsigned long tcp_safe_msecs_to_jiffies(const unsigned int m)
+{
+	if (__builtin_constant_p(m)) {
+		if (m * HZ > MSEC_PER_SEC)
+			return msecs_to_jiffies(m);
+
+		return 2;
+	}
+
+	return max_t(u32, 2, msecs_to_jiffies(m));
+}
+
 #endif	/* _TCP_H */
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 534e5fd..83021c5 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -2207,7 +2207,7 @@ bool tcp_schedule_loss_probe(struct sock *sk)
 	if (tp->packets_out == 1)
 		timeout = max_t(u32, timeout,
 				(rtt + (rtt >> 1) + TCP_DELACK_MAX));
-	timeout = max_t(u32, timeout, msecs_to_jiffies(10));
+	timeout = max_t(u32, timeout, tcp_safe_msecs_to_jiffies(10));
 
 	/* If RTO is shorter, just schedule TLP in its place. */
 	tlp_time_stamp = tcp_time_stamp + timeout;
-- 
2.1.0