int ipoib_init_qp(struct net_device *dev)
{
struct ipoib_dev_priv *priv = netdev_priv(dev);
int ret;
struct ib_qp_attr qp_attr;
int attr_mask;
if (!test_bit(IPOIB_PKEY_ASSIGNED, &priv->flags))
return -1;
qp_attr.qp_state = IB_QPS_INIT;
qp_attr.qkey = 0;
qp_attr.port_num = priv->port;
qp_attr.pkey_index = priv->pkey_index;
attr_mask =
IB_QP_QKEY |
IB_QP_PORT |
IB_QP_PKEY_INDEX |
IB_QP_STATE;
ret = ib_modify_qp(priv->qp, &qp_attr, attr_mask);
if (ret) {
ipoib_warn(priv, "failed to modify QP to init, ret = %d\n", ret);
goto out_fail;
}
qp_attr.qp_state = IB_QPS_RTR;
/* Can't set this in a INIT->RTR transition */
attr_mask &= ~IB_QP_PORT;
ret = ib_modify_qp(priv->qp, &qp_attr, attr_mask);
if (ret) {
ipoib_warn(priv, "failed to modify QP to RTR, ret = %d\n", ret);
goto out_fail;
}
qp_attr.qp_state = IB_QPS_RTS;
qp_attr.sq_psn = 0;
attr_mask |= IB_QP_SQ_PSN;
attr_mask &= ~IB_QP_PKEY_INDEX;
ret = ib_modify_qp(priv->qp, &qp_attr, attr_mask);
if (ret) {
ipoib_warn(priv, "failed to modify QP to RTS, ret = %d\n", ret);
goto out_fail;
}
return 0;
out_fail:
qp_attr.qp_state = IB_QPS_RESET;
if (ib_modify_qp(priv->qp, &qp_attr, IB_QP_STATE))
ipoib_warn(priv, "Failed to modify QP to RESET state\n");
return ret;
}
static int ipoib_new_child_link(struct net *src_net, struct net_device *dev,
struct nlattr *tb[], struct nlattr *data[],
struct netlink_ext_ack *extack)
{
struct net_device *pdev;
struct ipoib_dev_priv *ppriv;
u16 child_pkey;
int err;
if (!tb[IFLA_LINK])
return -EINVAL;
pdev = __dev_get_by_index(src_net, nla_get_u32(tb[IFLA_LINK]));
if (!pdev || pdev->type != ARPHRD_INFINIBAND)
return -ENODEV;
ppriv = ipoib_priv(pdev);
if (test_bit(IPOIB_FLAG_SUBINTERFACE, &ppriv->flags)) {
ipoib_warn(ppriv, "child creation disallowed for child devices\n");
return -EINVAL;
}
if (!data || !data[IFLA_IPOIB_PKEY]) {
ipoib_dbg(ppriv, "no pkey specified, using parent pkey\n");
child_pkey = ppriv->pkey;
} else
child_pkey = nla_get_u16(data[IFLA_IPOIB_PKEY]);
err = ipoib_intf_init(ppriv->ca, ppriv->port, dev->name, dev);
if (err) {
ipoib_warn(ppriv, "failed to initialize pkey device\n");
return err;
}
err = __ipoib_vlan_add(ppriv, ipoib_priv(dev),
child_pkey, IPOIB_RTNL_CHILD);
if (err)
return err;
if (data) {
err = ipoib_changelink(dev, tb, data, extack);
if (err) {
unregister_netdevice(dev);
return err;
}
}
return 0;
}
static int ipoib_set_coalesce(struct net_device *dev,
struct ethtool_coalesce *coal)
{
struct ipoib_dev_priv *priv = netdev_priv(dev);
int ret;
/*
* These values are saved in the private data and returned
* when ipoib_get_coalesce() is called
*/
if (coal->rx_coalesce_usecs > 0xffff ||
coal->rx_max_coalesced_frames > 0xffff)
return -EINVAL;
ret = ib_modify_cq(priv->recv_cq, coal->rx_max_coalesced_frames,
coal->rx_coalesce_usecs);
if (ret && ret != -ENOSYS) {
ipoib_warn(priv, "failed modifying CQ (%d)\n", ret);
return ret;
}
priv->ethtool.coalesce_usecs = coal->rx_coalesce_usecs;
priv->ethtool.max_coalesced_frames = coal->rx_max_coalesced_frames;
return 0;
}
static int ipoib_set_coalesce(struct net_device *dev,
struct ethtool_coalesce *coal)
{
struct ipoib_dev_priv *priv = netdev_priv(dev);
int ret;
/*
* Since IPoIB uses a single CQ for both rx and tx, we assume
* that rx params dictate the configuration. These values are
* saved in the private data and returned when ipoib_get_coalesce()
* is called.
*/
if (coal->rx_coalesce_usecs > 0xffff ||
coal->rx_max_coalesced_frames > 0xffff)
return -EINVAL;
ret = ib_modify_cq(priv->recv_cq, coal->rx_max_coalesced_frames,
coal->rx_coalesce_usecs);
if (ret && ret != -ENOSYS) {
ipoib_warn(priv, "failed modifying CQ (%d)\n", ret);
return ret;
}
coal->tx_coalesce_usecs = coal->rx_coalesce_usecs;
coal->tx_max_coalesced_frames = coal->rx_max_coalesced_frames;
priv->ethtool.coalesce_usecs = coal->rx_coalesce_usecs;
priv->ethtool.max_coalesced_frames = coal->rx_max_coalesced_frames;
return 0;
}
static int ipoib_cm_post_receive_nonsrq(struct net_device *dev,
struct ipoib_cm_rx *rx,
struct ib_recv_wr *wr,
struct ib_sge *sge, int id)
{
struct ipoib_dev_priv *priv = netdev_priv(dev);
struct ib_recv_wr *bad_wr;
int i, ret;
wr->wr_id = id | IPOIB_OP_CM | IPOIB_OP_RECV;
for (i = 0; i < IPOIB_CM_RX_SG; ++i)
sge[i].addr = rx->rx_ring[id].mapping[i];
ret = ib_post_recv(rx->qp, wr, &bad_wr);
if (unlikely(ret)) {
ipoib_warn(priv, "post recv failed for buf %d (%d)\n", id, ret);
ipoib_cm_dma_unmap_rx(priv, IPOIB_CM_RX_SG - 1,
rx->rx_ring[id].mapping);
dev_kfree_skb_any(rx->rx_ring[id].skb);
rx->rx_ring[id].skb = NULL;
}
return ret;
}
int ipoib_mcast_attach(struct net_device *dev, u16 mlid, union ib_gid *mgid)
{
struct ipoib_dev_priv *priv = netdev_priv(dev);
struct ib_qp_attr *qp_attr;
int attr_mask;
int ret;
u16 pkey_index;
ret = -ENOMEM;
qp_attr = kmalloc(sizeof *qp_attr, GFP_KERNEL);
if (!qp_attr)
goto out;
if (ib_find_cached_pkey(priv->ca, priv->port, priv->pkey, &pkey_index)) {
clear_bit(IPOIB_PKEY_ASSIGNED, &priv->flags);
ret = -ENXIO;
goto out;
}
set_bit(IPOIB_PKEY_ASSIGNED, &priv->flags);
/* set correct QKey for QP */
qp_attr->qkey = priv->qkey;
attr_mask = IB_QP_QKEY;
ret = ib_modify_qp(priv->qp, qp_attr, attr_mask);
if (ret) {
ipoib_warn(priv, "failed to modify QP, ret = %d\n", ret);
goto out;
}
/* attach QP to multicast group */
down(&priv->mcast_mutex);
ret = ib_attach_mcast(priv->qp, mgid, mlid);
up(&priv->mcast_mutex);
if (ret)
ipoib_warn(priv, "failed to attach to multicast group, ret = %d\n", ret);
out:
kfree(qp_attr);
return ret;
}
int ipoib_mcast_detach(struct net_device *dev, u16 mlid, union ib_gid *mgid)
{
struct ipoib_dev_priv *priv = netdev_priv(dev);
int ret;
mutex_lock(&priv->mcast_mutex);
ret = ib_detach_mcast(priv->qp, mgid, mlid);
mutex_unlock(&priv->mcast_mutex);
if (ret)
ipoib_warn(priv, "ib_detach_mcast failed (result = %d)\n", ret);
return ret;
}
int ipoib_mcast_attach(struct net_device *dev, struct ib_device *hca,
union ib_gid *mgid, u16 mlid, int set_qkey, u32 qkey)
{
struct ipoib_dev_priv *priv = ipoib_priv(dev);
struct ib_qp_attr *qp_attr = NULL;
int ret;
u16 pkey_index;
if (ib_find_pkey(priv->ca, priv->port, priv->pkey, &pkey_index)) {
clear_bit(IPOIB_PKEY_ASSIGNED, &priv->flags);
ret = -ENXIO;
goto out;
}
set_bit(IPOIB_PKEY_ASSIGNED, &priv->flags);
if (set_qkey) {
ret = -ENOMEM;
qp_attr = kmalloc(sizeof(*qp_attr), GFP_KERNEL);
if (!qp_attr)
goto out;
/* set correct QKey for QP */
qp_attr->qkey = qkey;
ret = ib_modify_qp(priv->qp, qp_attr, IB_QP_QKEY);
if (ret) {
ipoib_warn(priv, "failed to modify QP, ret = %d\n", ret);
goto out;
}
}
/* attach QP to multicast group */
ret = ib_attach_mcast(priv->qp, mgid, mlid);
if (ret)
ipoib_warn(priv, "failed to attach to multicast group, ret = %d\n", ret);
out:
kfree(qp_attr);
return ret;
}
static int ipoib_set_tso(struct net_device *dev, u32 data)
{
struct ipoib_dev_priv *priv = netdev_priv(dev);
if (data) {
if (!test_bit(IPOIB_FLAG_ADMIN_CM, &priv->flags) &&
(dev->features & NETIF_F_SG) &&
(priv->hca_caps & IB_DEVICE_UD_TSO)) {
dev->features |= NETIF_F_TSO;
} else {
ipoib_warn(priv, "can't set TSO on\n");
return -EOPNOTSUPP;
}
} else
dev->features &= ~NETIF_F_TSO;
return 0;
}
static int ipoib_new_child_link(struct net *src_net, struct net_device *dev,
struct nlattr *tb[], struct nlattr *data[])
{
struct net_device *pdev;
struct ipoib_dev_priv *ppriv;
u16 child_pkey;
int err;
if (!tb[IFLA_LINK])
return -EINVAL;
pdev = __dev_get_by_index(src_net, nla_get_u32(tb[IFLA_LINK]));
if (!pdev)
return -ENODEV;
ppriv = netdev_priv(pdev);
if (test_bit(IPOIB_FLAG_SUBINTERFACE, &ppriv->flags)) {
ipoib_warn(ppriv, "child creation disallowed for child devices\n");
return -EINVAL;
}
if (!data || !data[IFLA_IPOIB_PKEY]) {
ipoib_dbg(ppriv, "no pkey specified, using parent pkey\n");
child_pkey = ppriv->pkey;
} else
child_pkey = nla_get_u16(data[IFLA_IPOIB_PKEY]);
if (child_pkey == 0 || child_pkey == 0x8000)
return -EINVAL;
/*
* Set the full membership bit, so that we join the right
* broadcast group, etc.
*/
child_pkey |= 0x8000;
err = __ipoib_vlan_add(ppriv, netdev_priv(dev), child_pkey, IPOIB_RTNL_CHILD);
if (!err && data)
err = ipoib_changelink(dev, tb, data);
return err;
}
static void ipoib_cm_start_rx_drain(struct ipoib_dev_priv *priv)
{
struct ib_send_wr *bad_wr;
struct ipoib_cm_rx *p;
/* We only reserved 1 extra slot in CQ for drain WRs, so
* make sure we have at most 1 outstanding WR. */
if (list_empty(&priv->cm.rx_flush_list) ||
!list_empty(&priv->cm.rx_drain_list))
return;
/*
* QPs on flush list are error state. This way, a "flush
* error" WC will be immediately generated for each WR we post.
*/
p = list_entry(priv->cm.rx_flush_list.next, typeof(*p), list);
if (ib_post_send(p->qp, &ipoib_cm_rx_drain_wr, &bad_wr))
ipoib_warn(priv, "failed to post drain wr\n");
list_splice_init(&priv->cm.rx_flush_list, &priv->cm.rx_drain_list);
}
static int ipoib_set_coalesce(struct net_device *dev,
struct ethtool_coalesce *coal)
{
struct ipoib_dev_priv *priv = netdev_priv(dev);
int ret;
if (coal->rx_coalesce_usecs > 0xffff ||
coal->rx_max_coalesced_frames > 0xffff)
return -EINVAL;
ret = ib_modify_cq(priv->recv_cq, coal->rx_max_coalesced_frames,
coal->rx_coalesce_usecs);
if (ret && ret != -ENOSYS) {
ipoib_warn(priv, "failed modifying CQ (%d)\n", ret);
return ret;
}
priv->ethtool.coalesce_usecs = coal->rx_coalesce_usecs;
priv->ethtool.max_coalesced_frames = coal->rx_max_coalesced_frames;
return 0;
}
static int ipoib_cm_post_receive_srq(struct net_device *dev, int id)
{
struct ipoib_dev_priv *priv = netdev_priv(dev);
struct ib_recv_wr *bad_wr;
int i, ret;
priv->cm.rx_wr.wr_id = id | IPOIB_OP_CM | IPOIB_OP_RECV;
for (i = 0; i < priv->cm.num_frags; ++i)
priv->cm.rx_sge[i].addr = priv->cm.srq_ring[id].mapping[i];
ret = ib_post_srq_recv(priv->cm.srq, &priv->cm.rx_wr, &bad_wr);
if (unlikely(ret)) {
ipoib_warn(priv, "post srq failed for buf %d (%d)\n", id, ret);
ipoib_cm_dma_unmap_rx(priv, priv->cm.num_frags - 1,
priv->cm.srq_ring[id].mapping);
dev_kfree_skb_any(priv->cm.srq_ring[id].skb);
priv->cm.srq_ring[id].skb = NULL;
}
return ret;
}
int ipoib_init_qp(struct net_device *dev)
{
struct ipoib_dev_priv *priv = netdev_priv(dev);
int ret;
u16 pkey_index;
struct ib_qp_attr qp_attr;
int attr_mask;
/*
* Search through the port P_Key table for the requested pkey value.
* The port has to be assigned to the respective IB partition in
* advance.
*/
ret = ib_find_cached_pkey(priv->ca, priv->port, priv->pkey, &pkey_index);
if (ret) {
clear_bit(IPOIB_PKEY_ASSIGNED, &priv->flags);
return ret;
}
set_bit(IPOIB_PKEY_ASSIGNED, &priv->flags);
qp_attr.qp_state = IB_QPS_INIT;
qp_attr.qkey = 0;
qp_attr.port_num = priv->port;
qp_attr.pkey_index = pkey_index;
attr_mask =
IB_QP_QKEY |
IB_QP_PORT |
IB_QP_PKEY_INDEX |
IB_QP_STATE;
ret = ib_modify_qp(priv->qp, &qp_attr, attr_mask);
if (ret) {
ipoib_warn(priv, "failed to modify QP to init, ret = %d\n", ret);
goto out_fail;
}
qp_attr.qp_state = IB_QPS_RTR;
/* Can't set this in a INIT->RTR transition */
attr_mask &= ~IB_QP_PORT;
ret = ib_modify_qp(priv->qp, &qp_attr, attr_mask);
if (ret) {
ipoib_warn(priv, "failed to modify QP to RTR, ret = %d\n", ret);
goto out_fail;
}
qp_attr.qp_state = IB_QPS_RTS;
qp_attr.sq_psn = 0;
attr_mask |= IB_QP_SQ_PSN;
attr_mask &= ~IB_QP_PKEY_INDEX;
ret = ib_modify_qp(priv->qp, &qp_attr, attr_mask);
if (ret) {
ipoib_warn(priv, "failed to modify QP to RTS, ret = %d\n", ret);
goto out_fail;
}
return 0;
out_fail:
qp_attr.qp_state = IB_QPS_RESET;
if (ib_modify_qp(priv->qp, &qp_attr, IB_QP_STATE))
ipoib_warn(priv, "Failed to modify QP to RESET state\n");
return ret;
}
static struct ib_qp *ipoib_cm_create_rx_qp(struct net_device *dev,
struct ipoib_cm_rx *p)
{
struct ipoib_dev_priv *priv = netdev_priv(dev);
struct ib_qp_init_attr attr = {
.event_handler = ipoib_cm_rx_event_handler,
.send_cq = priv->recv_cq, /* For drain WR */
.recv_cq = priv->recv_cq,
.srq = priv->cm.srq,
.cap.max_send_wr = 1, /* For drain WR */
.cap.max_send_sge = 1, /* FIXME: 0 Seems not to work */
.sq_sig_type = IB_SIGNAL_ALL_WR,
.qp_type = IB_QPT_RC,
.qp_context = p,
};
if (!ipoib_cm_has_srq(dev)) {
attr.cap.max_recv_wr = ipoib_recvq_size;
attr.cap.max_recv_sge = IPOIB_CM_RX_SG;
}
return ib_create_qp(priv->pd, &attr);
}
static int ipoib_cm_modify_rx_qp(struct net_device *dev,
struct ib_cm_id *cm_id, struct ib_qp *qp,
unsigned psn)
{
struct ipoib_dev_priv *priv = netdev_priv(dev);
struct ib_qp_attr qp_attr;
int qp_attr_mask, ret;
qp_attr.qp_state = IB_QPS_INIT;
ret = ib_cm_init_qp_attr(cm_id, &qp_attr, &qp_attr_mask);
if (ret) {
ipoib_warn(priv, "failed to init QP attr for INIT: %d\n", ret);
return ret;
}
ret = ib_modify_qp(qp, &qp_attr, qp_attr_mask);
if (ret) {
ipoib_warn(priv, "failed to modify QP to INIT: %d\n", ret);
return ret;
}
qp_attr.qp_state = IB_QPS_RTR;
ret = ib_cm_init_qp_attr(cm_id, &qp_attr, &qp_attr_mask);
if (ret) {
ipoib_warn(priv, "failed to init QP attr for RTR: %d\n", ret);
return ret;
}
qp_attr.rq_psn = psn;
ret = ib_modify_qp(qp, &qp_attr, qp_attr_mask);
if (ret) {
ipoib_warn(priv, "failed to modify QP to RTR: %d\n", ret);
return ret;
}
/*
* Current Mellanox HCA firmware won't generate completions
* with error for drain WRs unless the QP has been moved to
* RTS first. This work-around leaves a window where a QP has
* moved to error asynchronously, but this will eventually get
* fixed in firmware, so let's not error out if modify QP
* fails.
*/
qp_attr.qp_state = IB_QPS_RTS;
ret = ib_cm_init_qp_attr(cm_id, &qp_attr, &qp_attr_mask);
if (ret) {
ipoib_warn(priv, "failed to init QP attr for RTS: %d\n", ret);
return 0;
}
ret = ib_modify_qp(qp, &qp_attr, qp_attr_mask);
if (ret) {
ipoib_warn(priv, "failed to modify QP to RTS: %d\n", ret);
return 0;
}
return 0;
}
static void ipoib_cm_init_rx_wr(struct net_device *dev,
struct ib_recv_wr *wr,
struct ib_sge *sge)
{
struct ipoib_dev_priv *priv = netdev_priv(dev);
int i;
for (i = 0; i < priv->cm.num_frags; ++i)
sge[i].lkey = priv->mr->lkey;
sge[0].length = IPOIB_CM_HEAD_SIZE;
for (i = 1; i < priv->cm.num_frags; ++i)
sge[i].length = PAGE_SIZE;
wr->next = NULL;
wr->sg_list = sge;
wr->num_sge = priv->cm.num_frags;
}
static int ipoib_cm_nonsrq_init_rx(struct net_device *dev, struct ib_cm_id *cm_id,
struct ipoib_cm_rx *rx)
{
struct ipoib_dev_priv *priv = netdev_priv(dev);
struct {
struct ib_recv_wr wr;
struct ib_sge sge[IPOIB_CM_RX_SG];
} *t;
int ret;
int i;
<<<<<<< HEAD
rx->rx_ring = vzalloc(ipoib_recvq_size * sizeof *rx->rx_ring);
=======
