| Message ID | 1432019508-95824-1-git-send-email-matt@mellanox.com (mailing list archive) |
|---|---|
| State | Accepted |
| Headers | show |
> Resent due to mailer issues Next time, please put this comment under the '---', so that it doesn't end up in the patch description. > Support for using UD and AF_IB is currently broken. The > IB_CM_SIDR_REQ_RECEIVED > message is not handled properly in cma_save_net_info() and we end up > falling > into code that will try and process the request as ipv4/ipv6, which will > end > up failing. > > The resolution is to add a check for the SIDR_REQ and call > cma_save_ib_info() > with a NULL path record. Change cma_save_ib_info() to copy the src sib > info > from the listen_id when the path record is NULL. > > Reported-by: Hari Shankar <Hari.Shankar@netapp.com> > Signed-off-by: Matt Finlay <matt@mellanox.com> Acked-by: Sean Hefty <sean.hefty@intel.com> -- To unsubscribe from this list: send the line "unsubscribe linux-rdma" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
On Tue, May 19, 2015 at 8:06 PM, Hefty, Sean <sean.hefty@intel.com> wrote: >> Resent due to mailer issues > > Next time, please put this comment under the '---', so that it doesn't end up in the patch description. As long as Doug is OK to remove this manually before applying the patch... Doug? if not, Matt, please re-send again. -- To unsubscribe from this list: send the line "unsubscribe linux-rdma" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
On Tue, 2015-05-19 at 21:23 +0300, Or Gerlitz wrote: > On Tue, May 19, 2015 at 8:06 PM, Hefty, Sean <sean.hefty@intel.com> wrote: > >> Resent due to mailer issues > > > > Next time, please put this comment under the '---', so that it doesn't end up in the patch description. > > As long as Doug is OK to remove this manually before applying the > patch... Doug? if not, Matt, please re-send again. No, I don't need a resend for something little like that. It takes more time to grab the new patch and then copy over Sean's Acked-by: than it does to remove that line from the commit message.
diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c index 06441a4..38ffe09 100644 --- a/drivers/infiniband/core/cma.c +++ b/drivers/infiniband/core/cma.c @@ -845,18 +845,26 @@ static void cma_save_ib_info(struct rdma_cm_id *id, struct rdma_cm_id *listen_id listen_ib = (struct sockaddr_ib *) &listen_id->route.addr.src_addr; ib = (struct sockaddr_ib *) &id->route.addr.src_addr; ib->sib_family = listen_ib->sib_family; - ib->sib_pkey = path->pkey; - ib->sib_flowinfo = path->flow_label; - memcpy(&ib->sib_addr, &path->sgid, 16); + if (path) { + ib->sib_pkey = path->pkey; + ib->sib_flowinfo = path->flow_label; + memcpy(&ib->sib_addr, &path->sgid, 16); + } else { + ib->sib_pkey = listen_ib->sib_pkey; + ib->sib_flowinfo = listen_ib->sib_flowinfo; + ib->sib_addr = listen_ib->sib_addr; + } ib->sib_sid = listen_ib->sib_sid; ib->sib_sid_mask = cpu_to_be64(0xffffffffffffffffULL); ib->sib_scope_id = listen_ib->sib_scope_id; - ib = (struct sockaddr_ib *) &id->route.addr.dst_addr; - ib->sib_family = listen_ib->sib_family; - ib->sib_pkey = path->pkey; - ib->sib_flowinfo = path->flow_label; - memcpy(&ib->sib_addr, &path->dgid, 16); + if (path) { + ib = (struct sockaddr_ib *) &id->route.addr.dst_addr; + ib->sib_family = listen_ib->sib_family; + ib->sib_pkey = path->pkey; + ib->sib_flowinfo = path->flow_label; + memcpy(&ib->sib_addr, &path->dgid, 16); + } } static __be16 ss_get_port(const struct sockaddr_storage *ss) @@ -905,9 +913,11 @@ static int cma_save_net_info(struct rdma_cm_id *id, struct rdma_cm_id *listen_id { struct cma_hdr *hdr; - if ((listen_id->route.addr.src_addr.ss_family == AF_IB) && - (ib_event->event == IB_CM_REQ_RECEIVED)) { - cma_save_ib_info(id, listen_id, ib_event->param.req_rcvd.primary_path); + if (listen_id->route.addr.src_addr.ss_family == AF_IB) { + if (ib_event->event == IB_CM_REQ_RECEIVED) + cma_save_ib_info(id, listen_id, ib_event->param.req_rcvd.primary_path); + else if (ib_event->event == IB_CM_SIDR_REQ_RECEIVED) + cma_save_ib_info(id, listen_id, NULL); return 0; }
Resent due to mailer issues Support for using UD and AF_IB is currently broken. The IB_CM_SIDR_REQ_RECEIVED message is not handled properly in cma_save_net_info() and we end up falling into code that will try and process the request as ipv4/ipv6, which will end up failing. The resolution is to add a check for the SIDR_REQ and call cma_save_ib_info() with a NULL path record. Change cma_save_ib_info() to copy the src sib info from the listen_id when the path record is NULL. Reported-by: Hari Shankar <Hari.Shankar@netapp.com> Signed-off-by: Matt Finlay <matt@mellanox.com> --- drivers/infiniband/core/cma.c | 32 +++++++++++++++++++++----------- 1 file changed, 21 insertions(+), 11 deletions(-) -- To unsubscribe from this list: send the line "unsubscribe linux-rdma" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html