From: Alex Netes <alexne-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
To: Rolf Manderscheid
<rvm-ePGOBjL8dl3ta4EC/59zMFaTQe2KTcn/@public.gmane.org>
Cc: linux-rdma-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
Subject: Re: [PATCH] ibsim: support LID portions of directed-route SMPs
Date: Tue, 9 Aug 2011 17:50:18 +0300 [thread overview]
Message-ID: <20110809145018.GA2056@calypso.mtl.com> (raw)
In-Reply-To: <E1QpTpp-00026I-7p-nLM+XIojDeH72zTlGHhC+rDks+cytr/Z@public.gmane.org>
Hi Rolf,
On 17:29 Fri 05 Aug , Rolf Manderscheid wrote:
>
> Heed the DRSLID and DRDLID fields in DR SMPs.
>
> Signed-off-by: Rolf Manderscheid <rvm-ePGOBjL8dl3ta4EC/59zMFaTQe2KTcn/@public.gmane.org>
> ---
> ibsim/sim_mad.c | 35 +++++++++++++++++++++++++----------
> 1 files changed, 25 insertions(+), 10 deletions(-)
>
> diff --git a/ibsim/sim_mad.c b/ibsim/sim_mad.c
> index 61d4866..9396ca3 100644
> --- a/ibsim/sim_mad.c
> +++ b/ibsim/sim_mad.c
> @@ -152,11 +152,8 @@ static int decode_sim_MAD(Client * cl, struct sim_request * r, ib_rpc_t * rpc,
>
> if (rpc->mgtclass == 0x81) { // direct route
> // word 9
> - if (mad_get_field(buf, 0, IB_DRSMP_DRDLID_F) != 0xffff ||
> - mad_get_field(buf, 0, IB_DRSMP_DRSLID_F) != 0xffff) {
> - IBWARN("dr[ds]lids are used (not supported)");
> - return -1;
> - }
> + path->drslid = mad_get_field(buf, 0, IB_DRSMP_DRSLID_F);
> + path->drdlid = mad_get_field(buf, 0, IB_DRSMP_DRDLID_F);
> // bytes 128 - 256
> if (!response)
> mad_get_array(buf, 0, IB_DRSMP_PATH_F, path->p);
> @@ -1113,11 +1110,27 @@ static Port *direct_route_out_MAD(Port * port, ib_dr_path_t * path)
>
> static Port *route_MAD(Port * port, int response, int lid, ib_dr_path_t * path)
> {
> - if (lid >= 0 && lid < 0xffff)
> - return lid_route_MAD(port, lid);
> + if (lid >= 0 && lid < 0xffff) {
> + port = lid_route_MAD(port, lid);
> + if (!port)
> + return NULL;
> + if (!path)
> + return port;
> + } else if (!path)
> + return NULL; // permissive LID with no DR
> +
> + if (response) {
> + port = direct_route_in_MAD(port, path);
> + lid = path->drslid;
> + } else {
> + port = direct_route_out_MAD(port, path);
> + lid = path->drdlid;
> + }
>
> - return response ? direct_route_in_MAD(port, path) :
> - direct_route_out_MAD(port, path);
> + if (port && lid >= 0 && lid < 0xffff)
> + port = lid_route_MAD(port, lid);
> +
> + return port;
> }
route_MAD() breaks the LID route support.
>
> static Smpfn *get_handle_fn(ib_rpc_t rpc, int response)
> @@ -1176,7 +1189,9 @@ int process_packet(Client * cl, void *p, int size, Client ** dcl)
> return 0;
> }
>
> - if (!(port = route_MAD(cl->port, response, ntohs(r->dlid), &path))) {
> + port = route_MAD(cl->port, response, ntohs(r->dlid),
> + rpc.mgtclass == 0x81 ? &path : NULL);
> + if (!port) {
I guess you want to do the same for routing response mads.
> IBWARN("routing failed: no route to dest lid %u path %s",
> ntohs(r->dlid), pathstr(0, &path));
> goto _dropped;
> --
> 1.7.1
>
> --
> To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
> the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
> More majordomo info at http://vger.kernel.org/majordomo-info.html
--
-- Alex
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
next prev parent reply other threads:[~2011-08-09 14:50 UTC|newest]
Thread overview: 3+ messages / expand[flat|nested] mbox.gz Atom feed top
2011-08-05 23:29 [PATCH] ibsim: support LID portions of directed-route SMPs Rolf Manderscheid
[not found] ` <E1QpTpp-00026I-7p-nLM+XIojDeH72zTlGHhC+rDks+cytr/Z@public.gmane.org>
2011-08-09 14:50 ` Alex Netes [this message]
[not found] ` <20110809145018.GA2056-iQai9MGU/dze+A/uUDamNg@public.gmane.org>
2011-08-11 21:27 ` Rolf Manderscheid
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20110809145018.GA2056@calypso.mtl.com \
--to=alexne-vpraknaxozvwk0htik3j/w@public.gmane.org \
--cc=linux-rdma-u79uwXL29TY76Z2rM5mHXA@public.gmane.org \
--cc=rvm-ePGOBjL8dl3ta4EC/59zMFaTQe2KTcn/@public.gmane.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox