[PATCH AUTOSEL 4.19 058/101] RDMA/i40iw: Set queue pair state when being queried

[PATCH AUTOSEL 4.19 058/101] 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 e2e6c74a7452..a5e3349b8a7c 100644
--- a/drivers/infiniband/hw/i40iw/i40iw_verbs.c
+++ b/drivers/infiniband/hw/i40iw/i40iw_verbs.c
@@ -806,6 +806,8 @@ 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 4.19 061/101] 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 32a9e9228b13..cdf6e26ebc87 100644
--- a/drivers/infiniband/hw/mlx5/mad.c
+++ b/drivers/infiniband/hw/mlx5/mad.c
@@ -197,19 +197,33 @@ 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) {
@@ -218,11 +232,13 @@ 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 {
@@ -231,20 +247,23 @@ 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,
@@ -256,8 +275,6 @@ 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) ||
@@ -266,19 +283,14 @@ 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 4.19 063/101] 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 30f840f874b3..453695f7d457 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_main.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_main.c
@@ -1892,12 +1892,6 @@ 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);
@@ -1940,6 +1934,17 @@ 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;
@@ -1957,6 +1962,14 @@ 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);
@@ -1968,15 +1981,8 @@ 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 4.19 077/101] 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 4111b798fd3c..681d8e0913d0 100644
--- a/drivers/infiniband/sw/rxe/rxe_resp.c
+++ b/drivers/infiniband/sw/rxe/rxe_resp.c
@@ -435,6 +435,7 @@ 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;
@@ -859,7 +860,9 @@ 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 332a16dad2a7..3b731c7682e5 100644
--- a/drivers/infiniband/sw/rxe/rxe_verbs.h
+++ b/drivers/infiniband/sw/rxe/rxe_verbs.h
@@ -212,6 +212,7 @@ struct rxe_resp_info {
 	struct rxe_mem		*mr;
 	u32			resid;
 	u32			rkey;
+	u32			length;
 	u64			atomic_orig;
 
 	/* SRQ only */
-- 
2.20.1