On Tue, May 19, 2009 at 09:31:36AM +0200, Eric Dumazet wrote:

Jarek Poplawski a écrit :

quoted

On Tue, May 19, 2009 at 01:59:55AM +0200, Eric Dumazet wrote:
...

quoted

diff --git a/net/core/gen_estimator.c b/net/core/gen_estimator.c

...

quoted

-		e->avbps += ((long)rate - (long)e->avbps) >> e->ewma_log;
+		e->avbps += ((s64)(brate - e->avbps)) >> e->ewma_log;

Btw., I'm a bit concerned about the syntax here: isn't such shifting
of signed ints implementation dependant?

You are right Jarek, I very often forget to never ever use signed quantities
at all ! (But also note original code has same undefined behavior)

Sure, I've meant the original code including 5 lines below.

Apparently gcc does the *right* thing on x86_32, but we probably want something
stronger here. I could not find gcc documentation statement on right shifts of 
negative values.

I guess gcc and most of others do this "right"; but it looks
"unkosher" anyway.

Jarek P.