[PATCH AUTOSEL 5.2 108/171] RDMA/i40iw: Set queue pair state when being queried

[PATCH AUTOSEL 5.2 108/171] RDMA/i40iw: Set queue pair state when being queried

[Sasha Levin]

From: "Liu, Changcheng" <changcheng.liu@intel.com>

[ Upstream commit 2e67e775845373905d2c2aecb9062c2c4352a535 ]

The API for ib_query_qp requires the driver to set qp_state and
cur_qp_state on return, add the missing sets.

Fixes: d37498417947 ("i40iw: add files for iwarp interface")
Signed-off-by: Changcheng Liu <changcheng.liu@aliyun.com>
Acked-by: Shiraz Saleem <shiraz.saleem@intel.com>
Reviewed-by: Jason Gunthorpe <jgg@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/infiniband/hw/i40iw/i40iw_verbs.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/infiniband/hw/i40iw/i40iw_verbs.c b/drivers/infiniband/hw/i40iw/i40iw_verbs.c
index 5689d742bafb..4c88d6f72574 100644
--- a/drivers/infiniband/hw/i40iw/i40iw_verbs.c
+++ b/drivers/infiniband/hw/i40iw/i40iw_verbs.c
@@ -772,6 +772,8 @@ static int i40iw_query_qp(struct ib_qp *ibqp,
 	struct i40iw_qp *iwqp = to_iwqp(ibqp);
 	struct i40iw_sc_qp *qp = &iwqp->sc_qp;
 
+	attr->qp_state = iwqp->ibqp_state;
+	attr->cur_qp_state = attr->qp_state;
 	attr->qp_access_flags = 0;
 	attr->cap.max_send_wr = qp->qp_uk.sq_size;
 	attr->cap.max_recv_wr = qp->qp_uk.rq_size;
-- 
2.20.1

[PATCH AUTOSEL 5.2 111/171] IB/mlx5: Fixed reporting counters on 2nd port for Dual port RoCE

[Sasha Levin]

From: Parav Pandit <parav@mellanox.com>

[ Upstream commit 2f40cf30c8644360d37287861d5288f00eab35e5 ]

Currently during dual port IB device registration in below code flow,

ib_register_device()
  ib_device_register_sysfs()
    ib_setup_port_attrs()
      add_port()
        get_counter_table()
          get_perf_mad()
            process_mad()
              mlx5_ib_process_mad()

mlx5_ib_process_mad() fails on 2nd port when both the ports are not fully
setup at the device level (because 2nd port is unaffiliated).

As a result, get_perf_mad() registers different PMA counter group for 1st
and 2nd port, namely pma_counter_ext and pma_counter. However both ports
have the same capability and counter offsets.

Due to this when counters are read by the user via sysfs in below code
flow, counters are queried from wrong location from the device mainly from
PPCNT instead of VPORT counters.

show_pma_counter()
  get_perf_mad()
    process_mad()
      mlx5_ib_process_mad()
        process_pma_cmd()

This shows all zero counters for 2nd port.

To overcome this, process_pma_cmd() is invoked, and when unaffiliated port
is not yet setup during device registration phase, make the query on the
first port.  while at it, only process_pma_cmd() needs to work on the
native port number and underlying mdev, so shift the get, put calls to
where its needed inside process_pma_cmd().

Fixes: 212f2a87b74f ("IB/mlx5: Route MADs for dual port RoCE")
Signed-off-by: Parav Pandit <parav@mellanox.com>
Reviewed-by: Daniel Jurgens <danielj@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/infiniband/hw/mlx5/mad.c | 60 +++++++++++++++++++-------------
 1 file changed, 36 insertions(+), 24 deletions(-)

diff --git a/drivers/infiniband/hw/mlx5/mad.c b/drivers/infiniband/hw/mlx5/mad.c
index 6c529e6f3a01..348c1df69cdc 100644
--- a/drivers/infiniband/hw/mlx5/mad.c
+++ b/drivers/infiniband/hw/mlx5/mad.c
@@ -200,19 +200,33 @@ static void pma_cnt_assign(struct ib_pma_portcounters *pma_cnt,
 			     vl_15_dropped);
 }
 
-static int process_pma_cmd(struct mlx5_core_dev *mdev, u8 port_num,
+static int process_pma_cmd(struct mlx5_ib_dev *dev, u8 port_num,
 			   const struct ib_mad *in_mad, struct ib_mad *out_mad)
 {
-	int err;
+	struct mlx5_core_dev *mdev;
+	bool native_port = true;
+	u8 mdev_port_num;
 	void *out_cnt;
+	int err;
 
+	mdev = mlx5_ib_get_native_port_mdev(dev, port_num, &mdev_port_num);
+	if (!mdev) {
+		/* Fail to get the native port, likely due to 2nd port is still
+		 * unaffiliated. In such case default to 1st port and attached
+		 * PF device.
+		 */
+		native_port = false;
+		mdev = dev->mdev;
+		mdev_port_num = 1;
+	}
 	/* Declaring support of extended counters */
 	if (in_mad->mad_hdr.attr_id == IB_PMA_CLASS_PORT_INFO) {
 		struct ib_class_port_info cpi = {};
 
 		cpi.capability_mask = IB_PMA_CLASS_CAP_EXT_WIDTH;
 		memcpy((out_mad->data + 40), &cpi, sizeof(cpi));
-		return IB_MAD_RESULT_SUCCESS | IB_MAD_RESULT_REPLY;
+		err = IB_MAD_RESULT_SUCCESS | IB_MAD_RESULT_REPLY;
+		goto done;
 	}
 
 	if (in_mad->mad_hdr.attr_id == IB_PMA_PORT_COUNTERS_EXT) {
@@ -221,11 +235,13 @@ static int process_pma_cmd(struct mlx5_core_dev *mdev, u8 port_num,
 		int sz = MLX5_ST_SZ_BYTES(query_vport_counter_out);
 
 		out_cnt = kvzalloc(sz, GFP_KERNEL);
-		if (!out_cnt)
-			return IB_MAD_RESULT_FAILURE;
+		if (!out_cnt) {
+			err = IB_MAD_RESULT_FAILURE;
+			goto done;
+		}
 
 		err = mlx5_core_query_vport_counter(mdev, 0, 0,
-						    port_num, out_cnt, sz);
+						    mdev_port_num, out_cnt, sz);
 		if (!err)
 			pma_cnt_ext_assign(pma_cnt_ext, out_cnt);
 	} else {
@@ -234,20 +250,23 @@ static int process_pma_cmd(struct mlx5_core_dev *mdev, u8 port_num,
 		int sz = MLX5_ST_SZ_BYTES(ppcnt_reg);
 
 		out_cnt = kvzalloc(sz, GFP_KERNEL);
-		if (!out_cnt)
-			return IB_MAD_RESULT_FAILURE;
+		if (!out_cnt) {
+			err = IB_MAD_RESULT_FAILURE;
+			goto done;
+		}
 
-		err = mlx5_core_query_ib_ppcnt(mdev, port_num,
+		err = mlx5_core_query_ib_ppcnt(mdev, mdev_port_num,
 					       out_cnt, sz);
 		if (!err)
 			pma_cnt_assign(pma_cnt, out_cnt);
-		}
-
+	}
 	kvfree(out_cnt);
-	if (err)
-		return IB_MAD_RESULT_FAILURE;
-
-	return IB_MAD_RESULT_SUCCESS | IB_MAD_RESULT_REPLY;
+	err = err ? IB_MAD_RESULT_FAILURE :
+		    IB_MAD_RESULT_SUCCESS | IB_MAD_RESULT_REPLY;
+done:
+	if (native_port)
+		mlx5_ib_put_native_port_mdev(dev, port_num);
+	return err;
 }
 
 int mlx5_ib_process_mad(struct ib_device *ibdev, int mad_flags, u8 port_num,
@@ -259,8 +278,6 @@ int mlx5_ib_process_mad(struct ib_device *ibdev, int mad_flags, u8 port_num,
 	struct mlx5_ib_dev *dev = to_mdev(ibdev);
 	const struct ib_mad *in_mad = (const struct ib_mad *)in;
 	struct ib_mad *out_mad = (struct ib_mad *)out;
-	struct mlx5_core_dev *mdev;
-	u8 mdev_port_num;
 	int ret;
 
 	if (WARN_ON_ONCE(in_mad_size != sizeof(*in_mad) ||
@@ -269,19 +286,14 @@ int mlx5_ib_process_mad(struct ib_device *ibdev, int mad_flags, u8 port_num,
 
 	memset(out_mad->data, 0, sizeof(out_mad->data));
 
-	mdev = mlx5_ib_get_native_port_mdev(dev, port_num, &mdev_port_num);
-	if (!mdev)
-		return IB_MAD_RESULT_FAILURE;
-
-	if (MLX5_CAP_GEN(mdev, vport_counters) &&
+	if (MLX5_CAP_GEN(dev->mdev, vport_counters) &&
 	    in_mad->mad_hdr.mgmt_class == IB_MGMT_CLASS_PERF_MGMT &&
 	    in_mad->mad_hdr.method == IB_MGMT_METHOD_GET) {
-		ret = process_pma_cmd(mdev, mdev_port_num, in_mad, out_mad);
+		ret = process_pma_cmd(dev, port_num, in_mad, out_mad);
 	} else {
 		ret =  process_mad(ibdev, mad_flags, port_num, in_wc, in_grh,
 				   in_mad, out_mad);
 	}
-	mlx5_ib_put_native_port_mdev(dev, port_num);
 	return ret;
 }
 
-- 
2.20.1

[PATCH AUTOSEL 5.2 113/171] IB/ipoib: Add child to parent list only if device initialized

[Sasha Levin]

From: Valentine Fatiev <valentinef@mellanox.com>

[ Upstream commit 91b01061fef9c57d2f5b712a6322ef51061f4efd ]

Despite failure in ipoib_dev_init() we continue with initialization flow
and creation of child device. It causes to the situation where this child
device is added too early to parent device list.

Change the logic, so in case of failure we properly return error from
ipoib_dev_init() and add child only in success path.

Fixes: eaeb39842508 ("IB/ipoib: Move init code to ndo_init")
Signed-off-by: Valentine Fatiev <valentinef@mellanox.com>
Reviewed-by: Feras Daoud <ferasda@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Reviewed-by: Jason Gunthorpe <jgg@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/infiniband/ulp/ipoib/ipoib_main.c | 34 +++++++++++++----------
 1 file changed, 20 insertions(+), 14 deletions(-)

diff --git a/drivers/infiniband/ulp/ipoib/ipoib_main.c b/drivers/infiniband/ulp/ipoib/ipoib_main.c
index 9b5e11d3fb85..bb904ec511be 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_main.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_main.c
@@ -1893,12 +1893,6 @@ static void ipoib_child_init(struct net_device *ndev)
 	struct ipoib_dev_priv *priv = ipoib_priv(ndev);
 	struct ipoib_dev_priv *ppriv = ipoib_priv(priv->parent);
 
-	dev_hold(priv->parent);
-
-	down_write(&ppriv->vlan_rwsem);
-	list_add_tail(&priv->list, &ppriv->child_intfs);
-	up_write(&ppriv->vlan_rwsem);
-
 	priv->max_ib_mtu = ppriv->max_ib_mtu;
 	set_bit(IPOIB_FLAG_SUBINTERFACE, &priv->flags);
 	memcpy(priv->dev->dev_addr, ppriv->dev->dev_addr, INFINIBAND_ALEN);
@@ -1941,6 +1935,17 @@ static int ipoib_ndo_init(struct net_device *ndev)
 	if (rc) {
 		pr_warn("%s: failed to initialize device: %s port %d (ret = %d)\n",
 			priv->ca->name, priv->dev->name, priv->port, rc);
+		return rc;
+	}
+
+	if (priv->parent) {
+		struct ipoib_dev_priv *ppriv = ipoib_priv(priv->parent);
+
+		dev_hold(priv->parent);
+
+		down_write(&ppriv->vlan_rwsem);
+		list_add_tail(&priv->list, &ppriv->child_intfs);
+		up_write(&ppriv->vlan_rwsem);
 	}
 
 	return 0;
@@ -1958,6 +1963,14 @@ static void ipoib_ndo_uninit(struct net_device *dev)
 	 */
 	WARN_ON(!list_empty(&priv->child_intfs));
 
+	if (priv->parent) {
+		struct ipoib_dev_priv *ppriv = ipoib_priv(priv->parent);
+
+		down_write(&ppriv->vlan_rwsem);
+		list_del(&priv->list);
+		up_write(&ppriv->vlan_rwsem);
+	}
+
 	ipoib_neigh_hash_uninit(dev);
 
 	ipoib_ib_dev_cleanup(dev);
@@ -1969,15 +1982,8 @@ static void ipoib_ndo_uninit(struct net_device *dev)
 		priv->wq = NULL;
 	}
 
-	if (priv->parent) {
-		struct ipoib_dev_priv *ppriv = ipoib_priv(priv->parent);
-
-		down_write(&ppriv->vlan_rwsem);
-		list_del(&priv->list);
-		up_write(&ppriv->vlan_rwsem);
-
+	if (priv->parent)
 		dev_put(priv->parent);
-	}
 }
 
 static int ipoib_set_vf_link_state(struct net_device *dev, int vf, int link_state)
-- 
2.20.1

[PATCH AUTOSEL 5.2 131/171] RDMA/rxe: Fill in wc byte_len with IB_WC_RECV_RDMA_WITH_IMM

[Sasha Levin]

From: Konstantin Taranov <konstantin.taranov@inf.ethz.ch>

[ Upstream commit bdce1290493caa3f8119f24b5dacc3fb7ca27389 ]

Calculate the correct byte_len on the receiving side when a work
completion is generated with IB_WC_RECV_RDMA_WITH_IMM opcode.

According to the IBA byte_len must indicate the number of written bytes,
whereas it was always equal to zero for the IB_WC_RECV_RDMA_WITH_IMM
opcode, even though data was transferred.

Fixes: 8700e3e7c485 ("Soft RoCE driver")
Signed-off-by: Konstantin Taranov <konstantin.taranov@inf.ethz.ch>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/infiniband/sw/rxe/rxe_resp.c  | 5 ++++-
 drivers/infiniband/sw/rxe/rxe_verbs.h | 1 +
 2 files changed, 5 insertions(+), 1 deletion(-)

diff --git a/drivers/infiniband/sw/rxe/rxe_resp.c b/drivers/infiniband/sw/rxe/rxe_resp.c
index aca9f60f9b21..1cbfbd98eb22 100644
--- a/drivers/infiniband/sw/rxe/rxe_resp.c
+++ b/drivers/infiniband/sw/rxe/rxe_resp.c
@@ -431,6 +431,7 @@ static enum resp_states check_rkey(struct rxe_qp *qp,
 			qp->resp.va = reth_va(pkt);
 			qp->resp.rkey = reth_rkey(pkt);
 			qp->resp.resid = reth_len(pkt);
+			qp->resp.length = reth_len(pkt);
 		}
 		access = (pkt->mask & RXE_READ_MASK) ? IB_ACCESS_REMOTE_READ
 						     : IB_ACCESS_REMOTE_WRITE;
@@ -856,7 +857,9 @@ static enum resp_states do_complete(struct rxe_qp *qp,
 				pkt->mask & RXE_WRITE_MASK) ?
 					IB_WC_RECV_RDMA_WITH_IMM : IB_WC_RECV;
 		wc->vendor_err = 0;
-		wc->byte_len = wqe->dma.length - wqe->dma.resid;
+		wc->byte_len = (pkt->mask & RXE_IMMDT_MASK &&
+				pkt->mask & RXE_WRITE_MASK) ?
+					qp->resp.length : wqe->dma.length - wqe->dma.resid;
 
 		/* fields after byte_len are different between kernel and user
 		 * space
diff --git a/drivers/infiniband/sw/rxe/rxe_verbs.h b/drivers/infiniband/sw/rxe/rxe_verbs.h
index e8be7f44e3be..28bfb3ece104 100644
--- a/drivers/infiniband/sw/rxe/rxe_verbs.h
+++ b/drivers/infiniband/sw/rxe/rxe_verbs.h
@@ -213,6 +213,7 @@ struct rxe_resp_info {
 	struct rxe_mem		*mr;
 	u32			resid;
 	u32			rkey;
+	u32			length;
 	u64			atomic_orig;
 
 	/* SRQ only */
-- 
2.20.1

[PATCH AUTOSEL 5.2 134/171] RDMA/core: Fix race when resolving IP address

[Sasha Levin]

From: Dag Moxnes <dag.moxnes@oracle.com>

[ Upstream commit d8d9ec7dc5abbb3f11d866e983c4984f5c2de9d6 ]

Use the neighbour lock when copying the MAC address from the neighbour
data struct in dst_fetch_ha.

When not using the lock, it is possible for the function to race with
neigh_update(), causing it to copy an torn MAC address:

rdma_resolve_addr()
  rdma_resolve_ip()
    addr_resolve()
      addr_resolve_neigh()
        fetch_ha()
          dst_fetch_ha()
	     memcpy(dev_addr->dst_dev_addr, n->ha, MAX_ADDR_LEN)

and

net_ioctl()
  arp_ioctl()
    arp_rec_delete()
      arp_invalidate()
        neigh_update()
          __neigh_update()
	    memcpy(&neigh->ha, lladdr, dev->addr_len)

It is possible to provoke this error by calling rdma_resolve_addr() in a
tight loop, while deleting the corresponding ARP entry in another tight
loop.

Fixes: 51d45974515c ("infiniband: addr: Consolidate code to fetch neighbour hardware address from dst.")
Signed-off-by: Dag Moxnes <dag.moxnes@oracle.com>
Signed-off-by: Håkon Bugge <haakon.bugge@oracle.com>
Reviewed-by: Jason Gunthorpe <jgg@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/infiniband/core/addr.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/infiniband/core/addr.c b/drivers/infiniband/core/addr.c
index 2f7d14159841..9b76a8fcdd24 100644
--- a/drivers/infiniband/core/addr.c
+++ b/drivers/infiniband/core/addr.c
@@ -337,7 +337,7 @@ static int dst_fetch_ha(const struct dst_entry *dst,
 		neigh_event_send(n, NULL);
 		ret = -ENODATA;
 	} else {
-		memcpy(dev_addr->dst_dev_addr, n->ha, MAX_ADDR_LEN);
+		neigh_ha_snapshot(dev_addr->dst_dev_addr, n, dst->dev);
 	}
 
 	neigh_release(n);
-- 
2.20.1

[PATCH AUTOSEL 5.2 143/171] rds: Accept peer connection reject messages due to incompatible version

[Sasha Levin]

From: Gerd Rausch <gerd.rausch@oracle.com>

[ Upstream commit 8c6166cfc9cd48e93d9176561e50b63cef4330d5 ]

Prior to
commit d021fabf525ff ("rds: rdma: add consumer reject")

function "rds_rdma_cm_event_handler_cmn" would always honor a rejected
connection attempt by issuing a "rds_conn_drop".

The commit mentioned above added a "break", eliminating
the "fallthrough" case and made the "rds_conn_drop" rather conditional:

Now it only happens if a "consumer defined" reject (i.e. "rdma_reject")
carries an integer-value of "1" inside "private_data":

  if (!conn)
    break;
    err = (int *)rdma_consumer_reject_data(cm_id, event, &len);
    if (!err || (err && ((*err) == RDS_RDMA_REJ_INCOMPAT))) {
      pr_warn("RDS/RDMA: conn <%pI6c, %pI6c> rejected, dropping connection\n",
              &conn->c_laddr, &conn->c_faddr);
              conn->c_proposed_version = RDS_PROTOCOL_COMPAT_VERSION;
              rds_conn_drop(conn);
    }
    rdsdebug("Connection rejected: %s\n",
             rdma_reject_msg(cm_id, event->status));
    break;
    /* FALLTHROUGH */
A number of issues are worth mentioning here:
   #1) Previous versions of the RDS code simply rejected a connection
       by calling "rdma_reject(cm_id, NULL, 0);"
       So the value of the payload in "private_data" will not be "1",
       but "0".

   #2) Now the code has become dependent on host byte order and sizing.
       If one peer is big-endian, the other is little-endian,
       or there's a difference in sizeof(int) (e.g. ILP64 vs LP64),
       the *err check does not work as intended.

   #3) There is no check for "len" to see if the data behind *err is even valid.
       Luckily, it appears that the "rdma_reject(cm_id, NULL, 0)" will always
       carry 148 bytes of zeroized payload.
       But that should probably not be relied upon here.

   #4) With the added "break;",
       we might as well drop the misleading "/* FALLTHROUGH */" comment.

This commit does _not_ address issue #2, as the sender would have to
agree on a byte order as well.

Here is the sequence of messages in this observed error-scenario:
   Host-A is pre-QoS changes (excluding the commit mentioned above)
   Host-B is post-QoS changes (including the commit mentioned above)

   #1 Host-B
      issues a connection request via function "rds_conn_path_transition"
      connection state transitions to "RDS_CONN_CONNECTING"

   #2 Host-A
      rejects the incompatible connection request (from #1)
      It does so by calling "rdma_reject(cm_id, NULL, 0);"

   #3 Host-B
      receives an "RDMA_CM_EVENT_REJECTED" event (from #2)
      But since the code is changed in the way described above,
      it won't drop the connection here, simply because "*err == 0".

   #4 Host-A
      issues a connection request

   #5 Host-B
      receives an "RDMA_CM_EVENT_CONNECT_REQUEST" event
      and ends up calling "rds_ib_cm_handle_connect".
      But since the state is already in "RDS_CONN_CONNECTING"
      (as of #1) it will end up issuing a "rdma_reject" without
      dropping the connection:
         if (rds_conn_state(conn) == RDS_CONN_CONNECTING) {
             /* Wait and see - our connect may still be succeeding */
             rds_ib_stats_inc(s_ib_connect_raced);
         }
         goto out;

   #6 Host-A
      receives an "RDMA_CM_EVENT_REJECTED" event (from #5),
      drops the connection and tries again (goto #4) until it gives up.

Tested-by: Zhu Yanjun <yanjun.zhu@oracle.com>
Signed-off-by: Gerd Rausch <gerd.rausch@oracle.com>
Signed-off-by: Santosh Shilimkar <santosh.shilimkar@oracle.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 net/rds/rdma_transport.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/net/rds/rdma_transport.c b/net/rds/rdma_transport.c
index 46bce8389066..9db455d02255 100644
--- a/net/rds/rdma_transport.c
+++ b/net/rds/rdma_transport.c
@@ -112,7 +112,9 @@ static int rds_rdma_cm_event_handler_cmn(struct rdma_cm_id *cm_id,
 		if (!conn)
 			break;
 		err = (int *)rdma_consumer_reject_data(cm_id, event, &len);
-		if (!err || (err && ((*err) == RDS_RDMA_REJ_INCOMPAT))) {
+		if (!err ||
+		    (err && len >= sizeof(*err) &&
+		     ((*err) <= RDS_RDMA_REJ_INCOMPAT))) {
 			pr_warn("RDS/RDMA: conn <%pI6c, %pI6c> rejected, dropping connection\n",
 				&conn->c_laddr, &conn->c_faddr);
 			conn->c_proposed_version = RDS_PROTOCOL_COMPAT_VERSION;
@@ -122,7 +124,6 @@ static int rds_rdma_cm_event_handler_cmn(struct rdma_cm_id *cm_id,
 		rdsdebug("Connection rejected: %s\n",
 			 rdma_reject_msg(cm_id, event->status));
 		break;
-		/* FALLTHROUGH */
 	case RDMA_CM_EVENT_ADDR_ERROR:
 	case RDMA_CM_EVENT_ROUTE_ERROR:
 	case RDMA_CM_EVENT_CONNECT_ERROR:
-- 
2.20.1

[PATCH AUTOSEL 5.2 150/171] net/mlx5e: IPoIB, Add error path in mlx5_rdma_setup_rn

[Sasha Levin]

From: Aya Levin <ayal@mellanox.com>

[ Upstream commit ef1ce7d7b67b46661091c7ccc0396186b7a247ef ]

Check return value from mlx5e_attach_netdev, add error path on failure.

Fixes: 48935bbb7ae8 ("net/mlx5e: IPoIB, Add netdevice profile skeleton")
Signed-off-by: Aya Levin <ayal@mellanox.com>
Reviewed-by: Feras Daoud <ferasda@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
index 9ca492b430d8..603d294757b4 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
@@ -698,7 +698,9 @@ static int mlx5_rdma_setup_rn(struct ib_device *ibdev, u8 port_num,
 
 	prof->init(mdev, netdev, prof, ipriv);
 
-	mlx5e_attach_netdev(epriv);
+	err = mlx5e_attach_netdev(epriv);
+	if (err)
+		goto detach;
 	netif_carrier_off(netdev);
 
 	/* set rdma_netdev func pointers */
@@ -714,6 +716,11 @@ static int mlx5_rdma_setup_rn(struct ib_device *ibdev, u8 port_num,
 
 	return 0;
 
+detach:
+	prof->cleanup(epriv);
+	if (ipriv->sub_interface)
+		return err;
+	mlx5e_destroy_mdev_resources(mdev);
 destroy_ht:
 	mlx5i_pkey_qpn_ht_cleanup(netdev);
 	return err;
-- 
2.20.1

[PATCH AUTOSEL 5.2 155/171] net/mlx5: E-Switch, Fix default encap mode

[Sasha Levin]

From: Maor Gottlieb <maorg@mellanox.com>

[ Upstream commit 9a64144d683a4395f57562d90247c61a0bf5105f ]

Encap mode is related to switchdev mode only. Move the init of
the encap mode to eswitch_offloads. Before this change, we reported
that eswitch supports encap, even tough the device was in non
SRIOV mode.

Fixes: 7768d1971de67 ('net/mlx5: E-Switch, Add control for encapsulation')
Signed-off-by: Maor Gottlieb <maorg@mellanox.com>
Reviewed-by: Roi Dayan <roid@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/net/ethernet/mellanox/mlx5/core/eswitch.c          | 5 -----
 drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c | 7 +++++++
 2 files changed, 7 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
index 6a921e24cd5e..e9339e7d6a18 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
@@ -1882,11 +1882,6 @@ int mlx5_eswitch_init(struct mlx5_core_dev *dev)
 	esw->enabled_vports = 0;
 	esw->mode = SRIOV_NONE;
 	esw->offloads.inline_mode = MLX5_INLINE_MODE_NONE;
-	if (MLX5_CAP_ESW_FLOWTABLE_FDB(dev, reformat) &&
-	    MLX5_CAP_ESW_FLOWTABLE_FDB(dev, decap))
-		esw->offloads.encap = DEVLINK_ESWITCH_ENCAP_MODE_BASIC;
-	else
-		esw->offloads.encap = DEVLINK_ESWITCH_ENCAP_MODE_NONE;
 
 	dev->priv.eswitch = esw;
 	return 0;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index 47b446d30f71..c2beadc41c40 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -1840,6 +1840,12 @@ int esw_offloads_init(struct mlx5_eswitch *esw, int vf_nvports,
 {
 	int err;
 
+	if (MLX5_CAP_ESW_FLOWTABLE_FDB(esw->dev, reformat) &&
+	    MLX5_CAP_ESW_FLOWTABLE_FDB(esw->dev, decap))
+		esw->offloads.encap = DEVLINK_ESWITCH_ENCAP_MODE_BASIC;
+	else
+		esw->offloads.encap = DEVLINK_ESWITCH_ENCAP_MODE_NONE;
+
 	err = esw_offloads_steering_init(esw, vf_nvports, total_nvports);
 	if (err)
 		return err;
@@ -1901,6 +1907,7 @@ void esw_offloads_cleanup(struct mlx5_eswitch *esw)
 	esw_offloads_devcom_cleanup(esw);
 	esw_offloads_unload_all_reps(esw, num_vfs);
 	esw_offloads_steering_cleanup(esw);
+	esw->offloads.encap = DEVLINK_ESWITCH_ENCAP_MODE_NONE;
 }
 
 static int esw_mode_from_devlink(u16 mode, u16 *mlx5_mode)
-- 
2.20.1