diff options
Diffstat (limited to 'drivers/infiniband/ulp/ipoib')
| -rw-r--r-- | drivers/infiniband/ulp/ipoib/ipoib.h | 4 | ||||
| -rw-r--r-- | drivers/infiniband/ulp/ipoib/ipoib_cm.c | 23 | ||||
| -rw-r--r-- | drivers/infiniband/ulp/ipoib/ipoib_ib.c | 47 | ||||
| -rw-r--r-- | drivers/infiniband/ulp/ipoib/ipoib_main.c | 65 | ||||
| -rw-r--r-- | drivers/infiniband/ulp/ipoib/ipoib_multicast.c | 24 | ||||
| -rw-r--r-- | drivers/infiniband/ulp/ipoib/ipoib_verbs.c | 5 |
6 files changed, 146 insertions, 22 deletions
diff --git a/drivers/infiniband/ulp/ipoib/ipoib.h b/drivers/infiniband/ulp/ipoib/ipoib.h index a6f3eab0f350..caec8e9c4666 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib.h +++ b/drivers/infiniband/ulp/ipoib/ipoib.h @@ -244,6 +244,7 @@ struct ipoib_cm_tx { unsigned tx_tail; unsigned long flags; u32 mtu; + unsigned max_send_sge; }; struct ipoib_cm_rx_buf { @@ -387,9 +388,10 @@ struct ipoib_dev_priv { struct dentry *mcg_dentry; struct dentry *path_dentry; #endif - int hca_caps; + u64 hca_caps; struct ipoib_ethtool_st ethtool; struct timer_list poll_timer; + unsigned max_send_sge; }; struct ipoib_ah { diff --git a/drivers/infiniband/ulp/ipoib/ipoib_cm.c b/drivers/infiniband/ulp/ipoib/ipoib_cm.c index 917e46ea3bf6..c8ed53562c9b 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_cm.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_cm.c @@ -710,6 +710,7 @@ void ipoib_cm_send(struct net_device *dev, struct sk_buff *skb, struct ipoib_cm_ struct ipoib_dev_priv *priv = netdev_priv(dev); struct ipoib_tx_buf *tx_req; int rc; + unsigned usable_sge = tx->max_send_sge - !!skb_headlen(skb); if (unlikely(skb->len > tx->mtu)) { ipoib_warn(priv, "packet len %d (> %d) too long to send, dropping\n", @@ -719,7 +720,23 @@ void ipoib_cm_send(struct net_device *dev, struct sk_buff *skb, struct ipoib_cm_ ipoib_cm_skb_too_long(dev, skb, tx->mtu - IPOIB_ENCAP_LEN); return; } - + if (skb_shinfo(skb)->nr_frags > usable_sge) { + if (skb_linearize(skb) < 0) { + ipoib_warn(priv, "skb could not be linearized\n"); + ++dev->stats.tx_dropped; + ++dev->stats.tx_errors; + dev_kfree_skb_any(skb); + return; + } + /* Does skb_linearize return ok without reducing nr_frags? */ + if (skb_shinfo(skb)->nr_frags > usable_sge) { + ipoib_warn(priv, "too many frags after skb linearize\n"); + ++dev->stats.tx_dropped; + ++dev->stats.tx_errors; + dev_kfree_skb_any(skb); + return; + } + } ipoib_dbg_data(priv, "sending packet: head 0x%x length %d connection 0x%x\n", tx->tx_head, skb->len, tx->qp->qp_num); @@ -1031,7 +1048,8 @@ static struct ib_qp *ipoib_cm_create_tx_qp(struct net_device *dev, struct ipoib_ struct ib_qp *tx_qp; if (dev->features & NETIF_F_SG) - attr.cap.max_send_sge = MAX_SKB_FRAGS + 1; + attr.cap.max_send_sge = + min_t(u32, priv->ca->attrs.max_sge, MAX_SKB_FRAGS + 1); tx_qp = ib_create_qp(priv->pd, &attr); if (PTR_ERR(tx_qp) == -EINVAL) { @@ -1040,6 +1058,7 @@ static struct ib_qp *ipoib_cm_create_tx_qp(struct net_device *dev, struct ipoib_ attr.create_flags &= ~IB_QP_CREATE_USE_GFP_NOIO; tx_qp = ib_create_qp(priv->pd, &attr); } + tx->max_send_sge = attr.cap.max_send_sge; return tx_qp; } diff --git a/drivers/infiniband/ulp/ipoib/ipoib_ib.c b/drivers/infiniband/ulp/ipoib/ipoib_ib.c index 5ea0c14070d1..f0e55e47eb54 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_ib.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_ib.c @@ -180,6 +180,7 @@ static void ipoib_ib_handle_rx_wc(struct net_device *dev, struct ib_wc *wc) struct sk_buff *skb; u64 mapping[IPOIB_UD_RX_SG]; union ib_gid *dgid; + union ib_gid *sgid; ipoib_dbg_data(priv, "recv completion: id %d, status: %d\n", wr_id, wc->status); @@ -203,13 +204,6 @@ static void ipoib_ib_handle_rx_wc(struct net_device *dev, struct ib_wc *wc) return; } - /* - * Drop packets that this interface sent, ie multicast packets - * that the HCA has replicated. - */ - if (wc->slid == priv->local_lid && wc->src_qp == priv->qp->qp_num) - goto repost; - memcpy(mapping, priv->rx_ring[wr_id].mapping, IPOIB_UD_RX_SG * sizeof *mapping); @@ -239,14 +233,31 @@ static void ipoib_ib_handle_rx_wc(struct net_device *dev, struct ib_wc *wc) else skb->pkt_type = PACKET_MULTICAST; + sgid = &((struct ib_grh *)skb->data)->sgid; + + /* + * Drop packets that this interface sent, ie multicast packets + * that the HCA has replicated. + */ + if (wc->slid == priv->local_lid && wc->src_qp == priv->qp->qp_num) { + int need_repost = 1; + + if ((wc->wc_flags & IB_WC_GRH) && + sgid->global.interface_id != priv->local_gid.global.interface_id) + need_repost = 0; + + if (need_repost) { + dev_kfree_skb_any(skb); + goto repost; + } + } + skb_pull(skb, IB_GRH_BYTES); skb->protocol = ((struct ipoib_header *) skb->data)->proto; skb_reset_mac_header(skb); skb_pull(skb, IPOIB_ENCAP_LEN); - skb->truesize = SKB_TRUESIZE(skb->len); - ++dev->stats.rx_packets; dev->stats.rx_bytes += skb->len; @@ -540,6 +551,7 @@ void ipoib_send(struct net_device *dev, struct sk_buff *skb, struct ipoib_tx_buf *tx_req; int hlen, rc; void *phead; + unsigned usable_sge = priv->max_send_sge - !!skb_headlen(skb); if (skb_is_gso(skb)) { hlen = skb_transport_offset(skb) + tcp_hdrlen(skb); @@ -563,6 +575,23 @@ void ipoib_send(struct net_device *dev, struct sk_buff *skb, phead = NULL; hlen = 0; } + if (skb_shinfo(skb)->nr_frags > usable_sge) { + if (skb_linearize(skb) < 0) { + ipoib_warn(priv, "skb could not be linearized\n"); + ++dev->stats.tx_dropped; + ++dev->stats.tx_errors; + dev_kfree_skb_any(skb); + return; + } + /* Does skb_linearize return ok without reducing nr_frags? */ + if (skb_shinfo(skb)->nr_frags > usable_sge) { + ipoib_warn(priv, "too many frags after skb linearize\n"); + ++dev->stats.tx_dropped; + ++dev->stats.tx_errors; + dev_kfree_skb_any(skb); + return; + } + } ipoib_dbg_data(priv, "sending packet, length=%d address=%p qpn=0x%06x\n", skb->len, address, qpn); diff --git a/drivers/infiniband/ulp/ipoib/ipoib_main.c b/drivers/infiniband/ulp/ipoib/ipoib_main.c index 25509bbd4a05..80807d6e5c4c 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_main.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_main.c @@ -51,6 +51,7 @@ #include <net/addrconf.h> #include <linux/inetdevice.h> #include <rdma/ib_cache.h> +#include <linux/pci.h> #define DRV_VERSION "1.0.0" @@ -1590,11 +1591,67 @@ void ipoib_dev_cleanup(struct net_device *dev) priv->tx_ring = NULL; } +static int ipoib_set_vf_link_state(struct net_device *dev, int vf, int link_state) +{ + struct ipoib_dev_priv *priv = netdev_priv(dev); + + return ib_set_vf_link_state(priv->ca, vf, priv->port, link_state); +} + +static int ipoib_get_vf_config(struct net_device *dev, int vf, + struct ifla_vf_info *ivf) +{ + struct ipoib_dev_priv *priv = netdev_priv(dev); + int err; + + err = ib_get_vf_config(priv->ca, vf, priv->port, ivf); + if (err) + return err; + + ivf->vf = vf; + + return 0; +} + +static int ipoib_set_vf_guid(struct net_device *dev, int vf, u64 guid, int type) +{ + struct ipoib_dev_priv *priv = netdev_priv(dev); + + if (type != IFLA_VF_IB_NODE_GUID && type != IFLA_VF_IB_PORT_GUID) + return -EINVAL; + + return ib_set_vf_guid(priv->ca, vf, priv->port, guid, type); +} + +static int ipoib_get_vf_stats(struct net_device *dev, int vf, + struct ifla_vf_stats *vf_stats) +{ + struct ipoib_dev_priv *priv = netdev_priv(dev); + + return ib_get_vf_stats(priv->ca, vf, priv->port, vf_stats); +} + static const struct header_ops ipoib_header_ops = { .create = ipoib_hard_header, }; -static const struct net_device_ops ipoib_netdev_ops = { +static const struct net_device_ops ipoib_netdev_ops_pf = { + .ndo_uninit = ipoib_uninit, + .ndo_open = ipoib_open, + .ndo_stop = ipoib_stop, + .ndo_change_mtu = ipoib_change_mtu, + .ndo_fix_features = ipoib_fix_features, + .ndo_start_xmit = ipoib_start_xmit, + .ndo_tx_timeout = ipoib_timeout, + .ndo_set_rx_mode = ipoib_set_mcast_list, + .ndo_get_iflink = ipoib_get_iflink, + .ndo_set_vf_link_state = ipoib_set_vf_link_state, + .ndo_get_vf_config = ipoib_get_vf_config, + .ndo_get_vf_stats = ipoib_get_vf_stats, + .ndo_set_vf_guid = ipoib_set_vf_guid, +}; + +static const struct net_device_ops ipoib_netdev_ops_vf = { .ndo_uninit = ipoib_uninit, .ndo_open = ipoib_open, .ndo_stop = ipoib_stop, @@ -1610,7 +1667,11 @@ void ipoib_setup(struct net_device *dev) { struct ipoib_dev_priv *priv = netdev_priv(dev); - dev->netdev_ops = &ipoib_netdev_ops; + if (priv->hca_caps & IB_DEVICE_VIRTUAL_FUNCTION) + dev->netdev_ops = &ipoib_netdev_ops_vf; + else + dev->netdev_ops = &ipoib_netdev_ops_pf; + dev->header_ops = &ipoib_header_ops; ipoib_set_ethtool_ops(dev); diff --git a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c index 050dfa175d16..25889311b1e9 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c @@ -456,7 +456,10 @@ out_locked: return status; } -static void ipoib_mcast_join(struct net_device *dev, struct ipoib_mcast *mcast) +/* + * Caller must hold 'priv->lock' + */ +static int ipoib_mcast_join(struct net_device *dev, struct ipoib_mcast *mcast) { struct ipoib_dev_priv *priv = netdev_priv(dev); struct ib_sa_multicast *multicast; @@ -466,6 +469,10 @@ static void ipoib_mcast_join(struct net_device *dev, struct ipoib_mcast *mcast) ib_sa_comp_mask comp_mask; int ret = 0; + if (!priv->broadcast || + !test_bit(IPOIB_FLAG_OPER_UP, &priv->flags)) + return -EINVAL; + ipoib_dbg_mcast(priv, "joining MGID %pI6\n", mcast->mcmember.mgid.raw); rec.mgid = mcast->mcmember.mgid; @@ -525,20 +532,23 @@ static void ipoib_mcast_join(struct net_device *dev, struct ipoib_mcast *mcast) rec.join_state = 4; #endif } + spin_unlock_irq(&priv->lock); multicast = ib_sa_join_multicast(&ipoib_sa_client, priv->ca, priv->port, &rec, comp_mask, GFP_KERNEL, ipoib_mcast_join_complete, mcast); + spin_lock_irq(&priv->lock); if (IS_ERR(multicast)) { ret = PTR_ERR(multicast); ipoib_warn(priv, "ib_sa_join_multicast failed, status %d\n", ret); - spin_lock_irq(&priv->lock); /* Requeue this join task with a backoff delay */ __ipoib_mcast_schedule_join_thread(priv, mcast, 1); clear_bit(IPOIB_MCAST_FLAG_BUSY, &mcast->flags); spin_unlock_irq(&priv->lock); complete(&mcast->done); + spin_lock_irq(&priv->lock); } + return 0; } void ipoib_mcast_join_task(struct work_struct *work) @@ -620,9 +630,10 @@ void ipoib_mcast_join_task(struct work_struct *work) /* Found the next unjoined group */ init_completion(&mcast->done); set_bit(IPOIB_MCAST_FLAG_BUSY, &mcast->flags); - spin_unlock_irq(&priv->lock); - ipoib_mcast_join(dev, mcast); - spin_lock_irq(&priv->lock); + if (ipoib_mcast_join(dev, mcast)) { + spin_unlock_irq(&priv->lock); + return; + } } else if (!delay_until || time_before(mcast->delay_until, delay_until)) delay_until = mcast->delay_until; @@ -641,10 +652,9 @@ out: if (mcast) { init_completion(&mcast->done); set_bit(IPOIB_MCAST_FLAG_BUSY, &mcast->flags); + ipoib_mcast_join(dev, mcast); } spin_unlock_irq(&priv->lock); - if (mcast) - ipoib_mcast_join(dev, mcast); } int ipoib_mcast_start_thread(struct net_device *dev) diff --git a/drivers/infiniband/ulp/ipoib/ipoib_verbs.c b/drivers/infiniband/ulp/ipoib/ipoib_verbs.c index d48c5bae7877..b809c373e40e 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_verbs.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_verbs.c @@ -206,7 +206,8 @@ int ipoib_transport_dev_init(struct net_device *dev, struct ib_device *ca) init_attr.create_flags |= IB_QP_CREATE_NETIF_QP; if (dev->features & NETIF_F_SG) - init_attr.cap.max_send_sge = MAX_SKB_FRAGS + 1; + init_attr.cap.max_send_sge = + min_t(u32, priv->ca->attrs.max_sge, MAX_SKB_FRAGS + 1); priv->qp = ib_create_qp(priv->pd, &init_attr); if (IS_ERR(priv->qp)) { @@ -233,6 +234,8 @@ int ipoib_transport_dev_init(struct net_device *dev, struct ib_device *ca) priv->rx_wr.next = NULL; priv->rx_wr.sg_list = priv->rx_sge; + priv->max_send_sge = init_attr.cap.max_send_sge; + return 0; out_free_send_cq: |