From: Martin Wilck <mwilck@xxxxxxxx>
This reverts commit b2d2440430c0fdd5e0cad3efd6d1c9e3d3d02e5b.
It's true that creating rxe on top of 802.1q interfaces doesn't work.
Thus, commit fd49ddaf7e26 ("RDMA/rxe: prevent rxe creation on top of vlan interface")
was absolutely correct.
But b2d2440430c0 was incorrect assuming that with this change,
RDMA and VLAN don't work togehter at all. It just has to be
set up differently. Rather than creating rxe on top of the VLAN
interface, rxe must be created on top of the physical interface.
RDMA then works just fine through VLAN interfaces on top of that
physical interface, via the "upper device" logic.
I've tested this mainly with NVMe over RDMA and rping, but I don't
see why it wouldn't work just as well for other protocols. If there
are real issues, I'd like to know.
b2d2440430c0 broke this setup deliberately and should thus be
reverted.
Fixes: b2d2440430c0 ("RDMA/rxe: Remove VLAN code leftovers from RXE")
Cc: Zhu Yanjun <zyjzyj2000@xxxxxxxxx>
Cc: Mohammad Heib <goody698@xxxxxxxxx>
Cc: Vijay Immanuel <vijayi@xxxxxxxxxxxxxxxxx>
Cc: Nicolas Morey-Chaisemartin <nmoreychaisemartin@xxxxxxxx>
Signed-off-by: Martin Wilck <mwilck@xxxxxxxx>
---
Note: I'm currently not subscribed to linux-rdma.
---
drivers/infiniband/sw/rxe/rxe_net.c | 18 ++++++++++++++++++
drivers/infiniband/sw/rxe/rxe_resp.c | 5 +++++
2 files changed, 23 insertions(+)
diff --git a/drivers/infiniband/sw/rxe/rxe_net.c b/drivers/infiniband/sw/rxe/rxe_net.c
index c4b06ced30a7..34bef7d8e6b4 100644
--- a/drivers/infiniband/sw/rxe/rxe_net.c
+++ b/drivers/infiniband/sw/rxe/rxe_net.c
@@ -8,6 +8,7 @@
#include <linux/if_arp.h>
#include <linux/netdevice.h>
#include <linux/if.h>
+#include <linux/if_vlan.h>
#include <net/udp_tunnel.h>
#include <net/sch_generic.h>
#include <linux/netfilter.h>
@@ -19,6 +20,18 @@
static struct rxe_recv_sockets recv_sockets;
+struct device *rxe_dma_device(struct rxe_dev *rxe)
+{
+ struct net_device *ndev;
+
+ ndev = rxe->ndev;
+
+ if (is_vlan_dev(ndev))
+ ndev = vlan_dev_real_dev(ndev);
+
+ return ndev->dev.parent;
+}
+
int rxe_mcast_add(struct rxe_dev *rxe, union ib_gid *mgid)
{
int err;
@@ -153,9 +166,14 @@ static int rxe_udp_encap_recv(struct sock *sk, struct sk_buff *skb)
{
struct udphdr *udph;
struct net_device *ndev = skb->dev;
+ struct net_device *rdev = ndev;
struct rxe_dev *rxe = rxe_get_dev_from_net(ndev);
struct rxe_pkt_info *pkt = SKB_TO_PKT(skb);
+ if (!rxe && is_vlan_dev(rdev)) {
+ rdev = vlan_dev_real_dev(ndev);
+ rxe = rxe_get_dev_from_net(rdev);
+ }
if (!rxe)
goto drop;
diff --git a/drivers/infiniband/sw/rxe/rxe_resp.c b/drivers/infiniband/sw/rxe/rxe_resp.c
index 5a098083a9d2..c7e3b6a4af38 100644
--- a/drivers/infiniband/sw/rxe/rxe_resp.c
+++ b/drivers/infiniband/sw/rxe/rxe_resp.c
@@ -872,6 +872,11 @@ static enum resp_states do_complete(struct rxe_qp *qp,
else
wc->network_hdr_type = RDMA_NETWORK_IPV6;
+ if (is_vlan_dev(skb->dev)) {
+ wc->wc_flags |= IB_WC_WITH_VLAN;
+ wc->vlan_id = vlan_dev_vlan_id(skb->dev);
+ }
+
if (pkt->mask & RXE_IMMDT_MASK) {
wc->wc_flags |= IB_WC_WITH_IMM;
wc->ex.imm_data = immdt_imm(pkt);
--
2.29.2
