Re: fwdState patch + fix ideas?

On Sun, Feb 15, 2004, Adrian Chadd wrote:
>
> Hi,
>
> Here's a little patch which does three things:

.. needs to do four:

Index: comm.cc
===================================================================
RCS file: /server/cvs-server/squid/squid3/src/comm.cc,v
retrieving revision 1.391
diff -u -r1.391 comm.cc
--- comm.cc 20 Oct 2003 12:33:01 -0000 1.391
+++ comm.cc 16 Feb 2004 06:11:13 -0000
@@ -1302,7 +1302,7 @@
     cs->fd = fd;
     cs->host = xstrdup(host);
     cs->port = port;
- cs->callback = CallBack<CNCB>(callback,cbdataReference(data));
+ cs->callback = CallBack<CNCB>(callback, data);
     comm_add_close_handler(fd, commConnectFree, cs);
     cs->locks++;
     ipcache_nbgethostbyname(host, commConnectDnsHandle, cs);
@@ -1345,11 +1345,9 @@
     callback = CallBack<CNCB>();
     commSetTimeout(fd, -1, NULL, NULL);

- if (cbdataReferenceValid(aCallback.data))
+ if (aCallback.dataValid())
         aCallback.handler(fd, status, xerrno, aCallback.data);

- cbdataReferenceDone(aCallback.data);
-
     commConnectFree(fd, this);
 }

@@ -1358,7 +1356,7 @@
 {
     ConnectStateData *cs = (ConnectStateData *)data;
     debug(5, 3) ("commConnectFree: FD %d\n", fd);
- cbdataReferenceDone(cs->callback.data);
+ cs->callback = CallBack<CNCB>();
     safe_free(cs->host);
     delete cs;
 }

.. the last bit is in commConnectFree() - I guess I havent hit the
failed connect part yet but even if it did we shouldn't be poking
in cs->callback.data.

Gah.

Is there anything wrong with these patches? I'd like to commit it
and start working on finding other CallBack/cbdata macro bugs.

At least I'm not leaking memory anymore..

Adrian
Received on Sun Feb 15 2004 - 23:13:09 MST