diff options
Diffstat (limited to 'drivers/infiniband/ulp/ipoib')
-rw-r--r-- | drivers/infiniband/ulp/ipoib/ipoib.h | 44 | ||||
-rw-r--r-- | drivers/infiniband/ulp/ipoib/ipoib_cm.c | 73 | ||||
-rw-r--r-- | drivers/infiniband/ulp/ipoib/ipoib_ethtool.c | 65 | ||||
-rw-r--r-- | drivers/infiniband/ulp/ipoib/ipoib_fs.c | 13 | ||||
-rw-r--r-- | drivers/infiniband/ulp/ipoib/ipoib_ib.c | 364 | ||||
-rw-r--r-- | drivers/infiniband/ulp/ipoib/ipoib_main.c | 456 | ||||
-rw-r--r-- | drivers/infiniband/ulp/ipoib/ipoib_multicast.c | 120 | ||||
-rw-r--r-- | drivers/infiniband/ulp/ipoib/ipoib_netlink.c | 13 | ||||
-rw-r--r-- | drivers/infiniband/ulp/ipoib/ipoib_verbs.c | 64 | ||||
-rw-r--r-- | drivers/infiniband/ulp/ipoib/ipoib_vlan.c | 12 |
10 files changed, 712 insertions, 512 deletions
diff --git a/drivers/infiniband/ulp/ipoib/ipoib.h b/drivers/infiniband/ulp/ipoib/ipoib.h index bed233bf45c3..ff50a7bd66d8 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib.h +++ b/drivers/infiniband/ulp/ipoib/ipoib.h @@ -52,7 +52,6 @@ #include <rdma/ib_pack.h> #include <rdma/ib_sa.h> #include <linux/sched.h> - /* constants */ enum ipoib_flush_level { @@ -153,6 +152,13 @@ static inline void skb_add_pseudo_hdr(struct sk_buff *skb) skb_pull(skb, IPOIB_HARD_LEN); } +static inline struct ipoib_dev_priv *ipoib_priv(const struct net_device *dev) +{ + struct rdma_netdev *rn = netdev_priv(dev); + + return rn->clnt_priv; +} + /* Used for all multicast joins (broadcast, IPv4 mcast and IPv6 mcast) */ struct ipoib_mcast { struct ib_sa_mcmember_rec mcmember; @@ -404,6 +410,7 @@ struct ipoib_dev_priv { struct timer_list poll_timer; unsigned max_send_sge; bool sm_fullmember_sendonly_support; + const struct net_device_ops *rn_ops; }; struct ipoib_ah { @@ -416,7 +423,7 @@ struct ipoib_ah { struct ipoib_path { struct net_device *dev; - struct ib_sa_path_rec pathrec; + struct sa_path_rec pathrec; struct ipoib_ah *ah; struct sk_buff_head queue; @@ -472,7 +479,7 @@ void ipoib_ib_completion(struct ib_cq *cq, void *dev_ptr); void ipoib_send_comp_handler(struct ib_cq *cq, void *dev_ptr); struct ipoib_ah *ipoib_create_ah(struct net_device *dev, - struct ib_pd *pd, struct ib_ah_attr *attr); + struct ib_pd *pd, struct rdma_ah_attr *attr); void ipoib_free_ah(struct kref *kref); static inline void ipoib_put_ah(struct ipoib_ah *ah) { @@ -482,27 +489,28 @@ int ipoib_open(struct net_device *dev); int ipoib_add_pkey_attr(struct net_device *dev); int ipoib_add_umcast_attr(struct net_device *dev); -void ipoib_send(struct net_device *dev, struct sk_buff *skb, - struct ipoib_ah *address, u32 qpn); +int ipoib_send(struct net_device *dev, struct sk_buff *skb, + struct ib_ah *address, u32 dqpn); void ipoib_reap_ah(struct work_struct *work); struct ipoib_path *__path_find(struct net_device *dev, void *gid); void ipoib_mark_paths_invalid(struct net_device *dev); void ipoib_flush_paths(struct net_device *dev); -int ipoib_check_sm_sendonly_fullmember_support(struct ipoib_dev_priv *priv); -struct ipoib_dev_priv *ipoib_intf_alloc(const char *format); - -int ipoib_ib_dev_init(struct net_device *dev, struct ib_device *ca, int port); +struct ipoib_dev_priv *ipoib_intf_alloc(struct ib_device *hca, u8 port, + const char *format); +void ipoib_ib_tx_timer_func(unsigned long ctx); void ipoib_ib_dev_flush_light(struct work_struct *work); void ipoib_ib_dev_flush_normal(struct work_struct *work); void ipoib_ib_dev_flush_heavy(struct work_struct *work); void ipoib_pkey_event(struct work_struct *work); void ipoib_ib_dev_cleanup(struct net_device *dev); +int ipoib_ib_dev_open_default(struct net_device *dev); int ipoib_ib_dev_open(struct net_device *dev); +int ipoib_ib_dev_stop(struct net_device *dev); void ipoib_ib_dev_up(struct net_device *dev); void ipoib_ib_dev_down(struct net_device *dev); -void ipoib_ib_dev_stop(struct net_device *dev); +int ipoib_ib_dev_stop_default(struct net_device *dev); void ipoib_pkey_dev_check_presence(struct net_device *dev); int ipoib_dev_init(struct net_device *dev, struct ib_device *ca, int port); @@ -562,8 +570,10 @@ void ipoib_path_iter_read(struct ipoib_path_iter *iter, struct ipoib_path *path); #endif -int ipoib_mcast_attach(struct net_device *dev, u16 mlid, - union ib_gid *mgid, int set_qkey); +int ipoib_mcast_attach(struct net_device *dev, struct ib_device *hca, + union ib_gid *mgid, u16 mlid, int set_qkey, u32 qkey); +int ipoib_mcast_detach(struct net_device *dev, struct ib_device *hca, + union ib_gid *mgid, u16 mlid); void ipoib_mcast_remove_list(struct list_head *remove_list); void ipoib_check_and_add_mcast_sendonly(struct ipoib_dev_priv *priv, u8 *mgid, struct list_head *remove_list); @@ -587,7 +597,7 @@ void __exit ipoib_netlink_fini(void); void ipoib_set_umcast(struct net_device *ndev, int umcast_val); int ipoib_set_mode(struct net_device *dev, const char *buf); -void ipoib_setup(struct net_device *dev); +void ipoib_setup_common(struct net_device *dev); void ipoib_pkey_open(struct ipoib_dev_priv *priv); void ipoib_drain_cq(struct net_device *dev); @@ -607,14 +617,14 @@ extern int ipoib_max_conn_qp; static inline int ipoib_cm_admin_enabled(struct net_device *dev) { - struct ipoib_dev_priv *priv = netdev_priv(dev); + struct ipoib_dev_priv *priv = ipoib_priv(dev); return IPOIB_CM_SUPPORTED(dev->dev_addr) && test_bit(IPOIB_FLAG_ADMIN_CM, &priv->flags); } static inline int ipoib_cm_enabled(struct net_device *dev, u8 *hwaddr) { - struct ipoib_dev_priv *priv = netdev_priv(dev); + struct ipoib_dev_priv *priv = ipoib_priv(dev); return IPOIB_CM_SUPPORTED(hwaddr) && test_bit(IPOIB_FLAG_ADMIN_CM, &priv->flags); } @@ -637,13 +647,13 @@ static inline void ipoib_cm_set(struct ipoib_neigh *neigh, struct ipoib_cm_tx *t static inline int ipoib_cm_has_srq(struct net_device *dev) { - struct ipoib_dev_priv *priv = netdev_priv(dev); + struct ipoib_dev_priv *priv = ipoib_priv(dev); return !!priv->cm.srq; } static inline unsigned int ipoib_cm_max_mtu(struct net_device *dev) { - struct ipoib_dev_priv *priv = netdev_priv(dev); + struct ipoib_dev_priv *priv = ipoib_priv(dev); return priv->cm.max_cm_mtu; } diff --git a/drivers/infiniband/ulp/ipoib/ipoib_cm.c b/drivers/infiniband/ulp/ipoib/ipoib_cm.c index 0cdf2b7f272f..7cbcfdac6529 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_cm.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_cm.c @@ -92,7 +92,7 @@ static void ipoib_cm_dma_unmap_rx(struct ipoib_dev_priv *priv, int frags, static int ipoib_cm_post_receive_srq(struct net_device *dev, int id) { - struct ipoib_dev_priv *priv = netdev_priv(dev); + struct ipoib_dev_priv *priv = ipoib_priv(dev); struct ib_recv_wr *bad_wr; int i, ret; @@ -118,7 +118,7 @@ static int ipoib_cm_post_receive_nonsrq(struct net_device *dev, struct ib_recv_wr *wr, struct ib_sge *sge, int id) { - struct ipoib_dev_priv *priv = netdev_priv(dev); + struct ipoib_dev_priv *priv = ipoib_priv(dev); struct ib_recv_wr *bad_wr; int i, ret; @@ -145,7 +145,7 @@ static struct sk_buff *ipoib_cm_alloc_rx_skb(struct net_device *dev, u64 mapping[IPOIB_CM_RX_SG], gfp_t gfp) { - struct ipoib_dev_priv *priv = netdev_priv(dev); + struct ipoib_dev_priv *priv = ipoib_priv(dev); struct sk_buff *skb; int i; @@ -196,7 +196,7 @@ partial_error: static void ipoib_cm_free_rx_ring(struct net_device *dev, struct ipoib_cm_rx_buf *rx_ring) { - struct ipoib_dev_priv *priv = netdev_priv(dev); + struct ipoib_dev_priv *priv = ipoib_priv(dev); int i; for (i = 0; i < ipoib_recvq_size; ++i) @@ -235,7 +235,7 @@ static void ipoib_cm_start_rx_drain(struct ipoib_dev_priv *priv) static void ipoib_cm_rx_event_handler(struct ib_event *event, void *ctx) { struct ipoib_cm_rx *p = ctx; - struct ipoib_dev_priv *priv = netdev_priv(p->dev); + struct ipoib_dev_priv *priv = ipoib_priv(p->dev); unsigned long flags; if (event->event != IB_EVENT_QP_LAST_WQE_REACHED) @@ -251,7 +251,7 @@ static void ipoib_cm_rx_event_handler(struct ib_event *event, void *ctx) 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 ipoib_dev_priv *priv = ipoib_priv(dev); struct ib_qp_init_attr attr = { .event_handler = ipoib_cm_rx_event_handler, .send_cq = priv->recv_cq, /* For drain WR */ @@ -276,7 +276,7 @@ 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 ipoib_dev_priv *priv = ipoib_priv(dev); struct ib_qp_attr qp_attr; int qp_attr_mask, ret; @@ -331,7 +331,7 @@ 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); + struct ipoib_dev_priv *priv = ipoib_priv(dev); int i; for (i = 0; i < priv->cm.num_frags; ++i) @@ -349,7 +349,7 @@ static void ipoib_cm_init_rx_wr(struct net_device *dev, 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 ipoib_dev_priv *priv = ipoib_priv(dev); struct { struct ib_recv_wr wr; struct ib_sge sge[IPOIB_CM_RX_SG]; @@ -422,7 +422,7 @@ static int ipoib_cm_send_rep(struct net_device *dev, struct ib_cm_id *cm_id, struct ib_qp *qp, struct ib_cm_req_event_param *req, unsigned psn) { - struct ipoib_dev_priv *priv = netdev_priv(dev); + struct ipoib_dev_priv *priv = ipoib_priv(dev); struct ipoib_cm_data data = {}; struct ib_cm_rep_param rep = {}; @@ -442,7 +442,7 @@ static int ipoib_cm_send_rep(struct net_device *dev, struct ib_cm_id *cm_id, static int ipoib_cm_req_handler(struct ib_cm_id *cm_id, struct ib_cm_event *event) { struct net_device *dev = cm_id->context; - struct ipoib_dev_priv *priv = netdev_priv(dev); + struct ipoib_dev_priv *priv = ipoib_priv(dev); struct ipoib_cm_rx *p; unsigned psn; int ret; @@ -515,7 +515,7 @@ static int ipoib_cm_rx_handler(struct ib_cm_id *cm_id, /* Fall through */ case IB_CM_REJ_RECEIVED: p = cm_id->context; - priv = netdev_priv(p->dev); + priv = ipoib_priv(p->dev); if (ib_modify_qp(p->qp, &ipoib_cm_err_attr, IB_QP_STATE)) ipoib_warn(priv, "unable to move qp to error state\n"); /* Fall through */ @@ -559,7 +559,7 @@ static void skb_put_frags(struct sk_buff *skb, unsigned int hdr_space, void ipoib_cm_handle_rx_wc(struct net_device *dev, struct ib_wc *wc) { - struct ipoib_dev_priv *priv = netdev_priv(dev); + struct ipoib_dev_priv *priv = ipoib_priv(dev); struct ipoib_cm_rx_buf *rx_ring; unsigned int wr_id = wc->wr_id & ~(IPOIB_OP_CM | IPOIB_OP_RECV); struct sk_buff *skb, *newskb; @@ -708,7 +708,7 @@ static inline int post_send(struct ipoib_dev_priv *priv, void ipoib_cm_send(struct net_device *dev, struct sk_buff *skb, struct ipoib_cm_tx *tx) { - struct ipoib_dev_priv *priv = netdev_priv(dev); + struct ipoib_dev_priv *priv = ipoib_priv(dev); struct ipoib_tx_buf *tx_req; int rc; unsigned usable_sge = tx->max_send_sge - !!skb_headlen(skb); @@ -786,7 +786,7 @@ void ipoib_cm_send(struct net_device *dev, struct sk_buff *skb, struct ipoib_cm_ void ipoib_cm_handle_tx_wc(struct net_device *dev, struct ib_wc *wc) { - struct ipoib_dev_priv *priv = netdev_priv(dev); + struct ipoib_dev_priv *priv = ipoib_priv(dev); struct ipoib_cm_tx *tx = wc->qp->qp_context; unsigned int wr_id = wc->wr_id & ~IPOIB_OP_CM; struct ipoib_tx_buf *tx_req; @@ -855,7 +855,7 @@ void ipoib_cm_handle_tx_wc(struct net_device *dev, struct ib_wc *wc) int ipoib_cm_dev_open(struct net_device *dev) { - struct ipoib_dev_priv *priv = netdev_priv(dev); + struct ipoib_dev_priv *priv = ipoib_priv(dev); int ret; if (!IPOIB_CM_SUPPORTED(dev->dev_addr)) @@ -887,7 +887,7 @@ err_cm: static void ipoib_cm_free_rx_reap_list(struct net_device *dev) { - struct ipoib_dev_priv *priv = netdev_priv(dev); + struct ipoib_dev_priv *priv = ipoib_priv(dev); struct ipoib_cm_rx *rx, *n; LIST_HEAD(list); @@ -910,7 +910,7 @@ static void ipoib_cm_free_rx_reap_list(struct net_device *dev) void ipoib_cm_dev_stop(struct net_device *dev) { - struct ipoib_dev_priv *priv = netdev_priv(dev); + struct ipoib_dev_priv *priv = ipoib_priv(dev); struct ipoib_cm_rx *p; unsigned long begin; int ret; @@ -969,7 +969,7 @@ void ipoib_cm_dev_stop(struct net_device *dev) static int ipoib_cm_rep_handler(struct ib_cm_id *cm_id, struct ib_cm_event *event) { struct ipoib_cm_tx *p = cm_id->context; - struct ipoib_dev_priv *priv = netdev_priv(p->dev); + struct ipoib_dev_priv *priv = ipoib_priv(p->dev); struct ipoib_cm_data *data = event->private_data; struct sk_buff_head skqueue; struct ib_qp_attr qp_attr; @@ -1037,7 +1037,7 @@ static int ipoib_cm_rep_handler(struct ib_cm_id *cm_id, struct ib_cm_event *even static struct ib_qp *ipoib_cm_create_tx_qp(struct net_device *dev, struct ipoib_cm_tx *tx) { - struct ipoib_dev_priv *priv = netdev_priv(dev); + struct ipoib_dev_priv *priv = ipoib_priv(dev); struct ib_qp_init_attr attr = { .send_cq = priv->recv_cq, .recv_cq = priv->recv_cq, @@ -1068,9 +1068,9 @@ static struct ib_qp *ipoib_cm_create_tx_qp(struct net_device *dev, struct ipoib_ static int ipoib_cm_send_req(struct net_device *dev, struct ib_cm_id *id, struct ib_qp *qp, u32 qpn, - struct ib_sa_path_rec *pathrec) + struct sa_path_rec *pathrec) { - struct ipoib_dev_priv *priv = netdev_priv(dev); + struct ipoib_dev_priv *priv = ipoib_priv(dev); struct ipoib_cm_data data = {}; struct ib_cm_req_param req = {}; @@ -1105,7 +1105,7 @@ static int ipoib_cm_send_req(struct net_device *dev, static int ipoib_cm_modify_tx_init(struct net_device *dev, struct ib_cm_id *cm_id, struct ib_qp *qp) { - struct ipoib_dev_priv *priv = netdev_priv(dev); + struct ipoib_dev_priv *priv = ipoib_priv(dev); struct ib_qp_attr qp_attr; int qp_attr_mask, ret; ret = ib_find_pkey(priv->ca, priv->port, priv->pkey, &qp_attr.pkey_index); @@ -1128,9 +1128,9 @@ static int ipoib_cm_modify_tx_init(struct net_device *dev, } static int ipoib_cm_tx_init(struct ipoib_cm_tx *p, u32 qpn, - struct ib_sa_path_rec *pathrec) + struct sa_path_rec *pathrec) { - struct ipoib_dev_priv *priv = netdev_priv(p->dev); + struct ipoib_dev_priv *priv = ipoib_priv(p->dev); int ret; p->tx_ring = __vmalloc(ipoib_sendq_size * sizeof *p->tx_ring, @@ -1186,7 +1186,7 @@ err_tx: static void ipoib_cm_tx_destroy(struct ipoib_cm_tx *p) { - struct ipoib_dev_priv *priv = netdev_priv(p->dev); + struct ipoib_dev_priv *priv = ipoib_priv(p->dev); struct ipoib_tx_buf *tx_req; unsigned long begin; @@ -1236,7 +1236,7 @@ static int ipoib_cm_tx_handler(struct ib_cm_id *cm_id, struct ib_cm_event *event) { struct ipoib_cm_tx *tx = cm_id->context; - struct ipoib_dev_priv *priv = netdev_priv(tx->dev); + struct ipoib_dev_priv *priv = ipoib_priv(tx->dev); struct net_device *dev = priv->dev; struct ipoib_neigh *neigh; unsigned long flags; @@ -1287,7 +1287,7 @@ static int ipoib_cm_tx_handler(struct ib_cm_id *cm_id, struct ipoib_cm_tx *ipoib_cm_create_tx(struct net_device *dev, struct ipoib_path *path, struct ipoib_neigh *neigh) { - struct ipoib_dev_priv *priv = netdev_priv(dev); + struct ipoib_dev_priv *priv = ipoib_priv(dev); struct ipoib_cm_tx *tx; tx = kzalloc(sizeof *tx, GFP_ATOMIC); @@ -1306,7 +1306,7 @@ struct ipoib_cm_tx *ipoib_cm_create_tx(struct net_device *dev, struct ipoib_path void ipoib_cm_destroy_tx(struct ipoib_cm_tx *tx) { - struct ipoib_dev_priv *priv = netdev_priv(tx->dev); + struct ipoib_dev_priv *priv = ipoib_priv(tx->dev); unsigned long flags; if (test_and_clear_bit(IPOIB_FLAG_INITIALIZED, &tx->flags)) { spin_lock_irqsave(&priv->lock, flags); @@ -1332,7 +1332,7 @@ static void ipoib_cm_tx_start(struct work_struct *work) struct ipoib_path *path; int ret; - struct ib_sa_path_rec pathrec; + struct sa_path_rec pathrec; u32 qpn; netif_tx_lock_bh(dev); @@ -1441,7 +1441,7 @@ static void ipoib_cm_skb_reap(struct work_struct *work) void ipoib_cm_skb_too_long(struct net_device *dev, struct sk_buff *skb, unsigned int mtu) { - struct ipoib_dev_priv *priv = netdev_priv(dev); + struct ipoib_dev_priv *priv = ipoib_priv(dev); int e = skb_queue_empty(&priv->cm.skb_queue); if (skb_dst(skb)) @@ -1490,7 +1490,8 @@ static void ipoib_cm_stale_task(struct work_struct *work) static ssize_t show_mode(struct device *d, struct device_attribute *attr, char *buf) { - struct ipoib_dev_priv *priv = netdev_priv(to_net_dev(d)); + struct net_device *dev = to_net_dev(d); + struct ipoib_dev_priv *priv = ipoib_priv(dev); if (test_bit(IPOIB_FLAG_ADMIN_CM, &priv->flags)) return sprintf(buf, "connected\n"); @@ -1503,7 +1504,7 @@ static ssize_t set_mode(struct device *d, struct device_attribute *attr, { struct net_device *dev = to_net_dev(d); int ret; - struct ipoib_dev_priv *priv = netdev_priv(dev); + struct ipoib_dev_priv *priv = ipoib_priv(dev); if (test_bit(IPOIB_FLAG_GOING_DOWN, &priv->flags)) return -EPERM; @@ -1532,7 +1533,7 @@ int ipoib_cm_add_mode_attr(struct net_device *dev) static void ipoib_cm_create_srq(struct net_device *dev, int max_sge) { - struct ipoib_dev_priv *priv = netdev_priv(dev); + struct ipoib_dev_priv *priv = ipoib_priv(dev); struct ib_srq_init_attr srq_init_attr = { .srq_type = IB_SRQT_BASIC, .attr = { @@ -1561,7 +1562,7 @@ static void ipoib_cm_create_srq(struct net_device *dev, int max_sge) int ipoib_cm_dev_init(struct net_device *dev) { - struct ipoib_dev_priv *priv = netdev_priv(dev); + struct ipoib_dev_priv *priv = ipoib_priv(dev); int max_srq_sge, i; INIT_LIST_HEAD(&priv->cm.passive_ids); @@ -1622,7 +1623,7 @@ int ipoib_cm_dev_init(struct net_device *dev) void ipoib_cm_dev_cleanup(struct net_device *dev) { - struct ipoib_dev_priv *priv = netdev_priv(dev); + struct ipoib_dev_priv *priv = ipoib_priv(dev); int ret; if (!priv->cm.srq) diff --git a/drivers/infiniband/ulp/ipoib/ipoib_ethtool.c b/drivers/infiniband/ulp/ipoib/ipoib_ethtool.c index bac455a1942d..874b24366e4d 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_ethtool.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_ethtool.c @@ -60,7 +60,7 @@ static const struct ipoib_stats ipoib_gstrings_stats[] = { static void ipoib_get_drvinfo(struct net_device *netdev, struct ethtool_drvinfo *drvinfo) { - struct ipoib_dev_priv *priv = netdev_priv(netdev); + struct ipoib_dev_priv *priv = ipoib_priv(netdev); ib_get_device_fw_str(priv->ca, drvinfo->fw_version, sizeof(drvinfo->fw_version)); @@ -77,7 +77,7 @@ static void ipoib_get_drvinfo(struct net_device *netdev, static int ipoib_get_coalesce(struct net_device *dev, struct ethtool_coalesce *coal) { - struct ipoib_dev_priv *priv = netdev_priv(dev); + struct ipoib_dev_priv *priv = ipoib_priv(dev); coal->rx_coalesce_usecs = priv->ethtool.coalesce_usecs; coal->rx_max_coalesced_frames = priv->ethtool.max_coalesced_frames; @@ -88,7 +88,7 @@ static int ipoib_get_coalesce(struct net_device *dev, static int ipoib_set_coalesce(struct net_device *dev, struct ethtool_coalesce *coal) { - struct ipoib_dev_priv *priv = netdev_priv(dev); + struct ipoib_dev_priv *priv = ipoib_priv(dev); int ret; /* @@ -155,7 +155,66 @@ static int ipoib_get_sset_count(struct net_device __always_unused *dev, return -EOPNOTSUPP; } +/* Return lane speed in unit of 1e6 bit/sec */ +static inline int ib_speed_enum_to_int(int speed) +{ + switch (speed) { + case IB_SPEED_SDR: + return SPEED_2500; + case IB_SPEED_DDR: + return SPEED_5000; + case IB_SPEED_QDR: + case IB_SPEED_FDR10: + return SPEED_10000; + case IB_SPEED_FDR: + return SPEED_14000; + case IB_SPEED_EDR: + return SPEED_25000; + } + + return SPEED_UNKNOWN; +} + +static int ipoib_get_link_ksettings(struct net_device *netdev, + struct ethtool_link_ksettings *cmd) +{ + struct ipoib_dev_priv *priv = netdev_priv(netdev); + struct ib_port_attr attr; + int ret, speed, width; + + if (!netif_carrier_ok(netdev)) { + cmd->base.speed = SPEED_UNKNOWN; + cmd->base.duplex = DUPLEX_UNKNOWN; + return 0; + } + + ret = ib_query_port(priv->ca, priv->port, &attr); + if (ret < 0) + return -EINVAL; + + speed = ib_speed_enum_to_int(attr.active_speed); + width = ib_width_enum_to_int(attr.active_width); + + if (speed < 0 || width < 0) + return -EINVAL; + + /* Except the following are set, the other members of + * the struct ethtool_link_settings are initialized to + * zero in the function __ethtool_get_link_ksettings. + */ + cmd->base.speed = speed * width; + cmd->base.duplex = DUPLEX_FULL; + + cmd->base.phy_address = 0xFF; + + cmd->base.autoneg = AUTONEG_ENABLE; + cmd->base.port = PORT_OTHER; + + return 0; +} + static const struct ethtool_ops ipoib_ethtool_ops = { + .get_link_ksettings = ipoib_get_link_ksettings, .get_drvinfo = ipoib_get_drvinfo, .get_coalesce = ipoib_get_coalesce, .set_coalesce = ipoib_set_coalesce, diff --git a/drivers/infiniband/ulp/ipoib/ipoib_fs.c b/drivers/infiniband/ulp/ipoib/ipoib_fs.c index 6bd5740e2691..11f74cbe6660 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_fs.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_fs.c @@ -210,16 +210,16 @@ static int ipoib_path_seq_show(struct seq_file *file, void *iter_ptr) seq_printf(file, "GID: %s\n" " complete: %6s\n", - gid_buf, path.pathrec.dlid ? "yes" : "no"); + gid_buf, sa_path_get_dlid(&path.pathrec) ? "yes" : "no"); - if (path.pathrec.dlid) { + if (sa_path_get_dlid(&path.pathrec)) { rate = ib_rate_to_mbps(path.pathrec.rate); seq_printf(file, " DLID: 0x%04x\n" " SL: %12d\n" " rate: %8d.%d Gb/sec\n", - be16_to_cpu(path.pathrec.dlid), + be32_to_cpu(sa_path_get_dlid(&path.pathrec)), path.pathrec.sl, rate / 1000, rate % 1000); } @@ -261,7 +261,7 @@ static const struct file_operations ipoib_path_fops = { void ipoib_create_debug_files(struct net_device *dev) { - struct ipoib_dev_priv *priv = netdev_priv(dev); + struct ipoib_dev_priv *priv = ipoib_priv(dev); char name[IFNAMSIZ + sizeof "_path"]; snprintf(name, sizeof name, "%s_mcg", dev->name); @@ -279,10 +279,13 @@ void ipoib_create_debug_files(struct net_device *dev) void ipoib_delete_debug_files(struct net_device *dev) { - struct ipoib_dev_priv *priv = netdev_priv(dev); + struct ipoib_dev_priv *priv = ipoib_priv(dev); + WARN_ONCE(!priv->mcg_dentry, "null mcg debug file\n"); + WARN_ONCE(!priv->path_dentry, "null path debug file\n"); debugfs_remove(priv->mcg_dentry); debugfs_remove(priv->path_dentry); + priv->mcg_dentry = priv->path_dentry = NULL; } int ipoib_register_debugfs(void) diff --git a/drivers/infiniband/ulp/ipoib/ipoib_ib.c b/drivers/infiniband/ulp/ipoib/ipoib_ib.c index 12c4f84a6639..0060b2f9f659 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_ib.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_ib.c @@ -52,7 +52,7 @@ MODULE_PARM_DESC(data_debug_level, #endif struct ipoib_ah *ipoib_create_ah(struct net_device *dev, - struct ib_pd *pd, struct ib_ah_attr *attr) + struct ib_pd *pd, struct rdma_ah_attr *attr) { struct ipoib_ah *ah; struct ib_ah *vah; @@ -65,13 +65,13 @@ struct ipoib_ah *ipoib_create_ah(struct net_device *dev, ah->last_send = 0; kref_init(&ah->ref); - vah = ib_create_ah(pd, attr); + vah = rdma_create_ah(pd, attr); if (IS_ERR(vah)) { kfree(ah); ah = (struct ipoib_ah *)vah; } else { ah->ah = vah; - ipoib_dbg(netdev_priv(dev), "Created ah %p\n", ah->ah); + ipoib_dbg(ipoib_priv(dev), "Created ah %p\n", ah->ah); } return ah; @@ -80,7 +80,7 @@ struct ipoib_ah *ipoib_create_ah(struct net_device *dev, void ipoib_free_ah(struct kref *kref) { struct ipoib_ah *ah = container_of(kref, struct ipoib_ah, ref); - struct ipoib_dev_priv *priv = netdev_priv(ah->dev); + struct ipoib_dev_priv *priv = ipoib_priv(ah->dev); unsigned long flags; @@ -99,7 +99,7 @@ static void ipoib_ud_dma_unmap_rx(struct ipoib_dev_priv *priv, static int ipoib_ib_post_receive(struct net_device *dev, int id) { - struct ipoib_dev_priv *priv = netdev_priv(dev); + struct ipoib_dev_priv *priv = ipoib_priv(dev); struct ib_recv_wr *bad_wr; int ret; @@ -121,7 +121,7 @@ static int ipoib_ib_post_receive(struct net_device *dev, int id) static struct sk_buff *ipoib_alloc_rx_skb(struct net_device *dev, int id) { - struct ipoib_dev_priv *priv = netdev_priv(dev); + struct ipoib_dev_priv *priv = ipoib_priv(dev); struct sk_buff *skb; int buf_size; u64 *mapping; @@ -153,7 +153,7 @@ error: static int ipoib_ib_post_receives(struct net_device *dev) { - struct ipoib_dev_priv *priv = netdev_priv(dev); + struct ipoib_dev_priv *priv = ipoib_priv(dev); int i; for (i = 0; i < ipoib_recvq_size; ++i) { @@ -172,7 +172,7 @@ static int ipoib_ib_post_receives(struct net_device *dev) static void ipoib_ib_handle_rx_wc(struct net_device *dev, struct ib_wc *wc) { - struct ipoib_dev_priv *priv = netdev_priv(dev); + struct ipoib_dev_priv *priv = ipoib_priv(dev); unsigned int wr_id = wc->wr_id & ~IPOIB_OP_RECV; struct sk_buff *skb; u64 mapping[IPOIB_UD_RX_SG]; @@ -381,7 +381,7 @@ free_res: static void ipoib_ib_handle_tx_wc(struct net_device *dev, struct ib_wc *wc) { - struct ipoib_dev_priv *priv = netdev_priv(dev); + struct ipoib_dev_priv *priv = ipoib_priv(dev); unsigned int wr_id = wc->wr_id; struct ipoib_tx_buf *tx_req; @@ -485,14 +485,14 @@ poll_more: void ipoib_ib_completion(struct ib_cq *cq, void *dev_ptr) { struct net_device *dev = dev_ptr; - struct ipoib_dev_priv *priv = netdev_priv(dev); + struct ipoib_dev_priv *priv = ipoib_priv(dev); napi_schedule(&priv->napi); } static void drain_tx_cq(struct net_device *dev) { - struct ipoib_dev_priv *priv = netdev_priv(dev); + struct ipoib_dev_priv *priv = ipoib_priv(dev); netif_tx_lock(dev); while (poll_tx(priv)) @@ -506,14 +506,14 @@ static void drain_tx_cq(struct net_device *dev) void ipoib_send_comp_handler(struct ib_cq *cq, void *dev_ptr) { - struct ipoib_dev_priv *priv = netdev_priv(dev_ptr); + struct ipoib_dev_priv *priv = ipoib_priv(dev_ptr); mod_timer(&priv->poll_timer, jiffies); } static inline int post_send(struct ipoib_dev_priv *priv, unsigned int wr_id, - struct ib_ah *address, u32 qpn, + struct ib_ah *address, u32 dqpn, struct ipoib_tx_buf *tx_req, void *head, int hlen) { @@ -523,7 +523,7 @@ static inline int post_send(struct ipoib_dev_priv *priv, ipoib_build_sge(priv, tx_req); priv->tx_wr.wr.wr_id = wr_id; - priv->tx_wr.remote_qpn = qpn; + priv->tx_wr.remote_qpn = dqpn; priv->tx_wr.ah = address; if (head) { @@ -537,10 +537,10 @@ static inline int post_send(struct ipoib_dev_priv *priv, return ib_post_send(priv->qp, &priv->tx_wr.wr, &bad_wr); } -void ipoib_send(struct net_device *dev, struct sk_buff *skb, - struct ipoib_ah *address, u32 qpn) +int ipoib_send(struct net_device *dev, struct sk_buff *skb, + struct ib_ah *address, u32 dqpn) { - struct ipoib_dev_priv *priv = netdev_priv(dev); + struct ipoib_dev_priv *priv = ipoib_priv(dev); struct ipoib_tx_buf *tx_req; int hlen, rc; void *phead; @@ -554,7 +554,7 @@ void ipoib_send(struct net_device *dev, struct sk_buff *skb, ++dev->stats.tx_dropped; ++dev->stats.tx_errors; dev_kfree_skb_any(skb); - return; + return -1; } } else { if (unlikely(skb->len > priv->mcast_mtu + IPOIB_ENCAP_LEN)) { @@ -563,7 +563,7 @@ void ipoib_send(struct net_device *dev, struct sk_buff *skb, ++dev->stats.tx_dropped; ++dev->stats.tx_errors; ipoib_cm_skb_too_long(dev, skb, priv->mcast_mtu); - return; + return -1; } phead = NULL; hlen = 0; @@ -574,7 +574,7 @@ void ipoib_send(struct net_device *dev, struct sk_buff *skb, ++dev->stats.tx_dropped; ++dev->stats.tx_errors; dev_kfree_skb_any(skb); - return; + return -1; } /* Does skb_linearize return ok without reducing nr_frags? */ if (skb_shinfo(skb)->nr_frags > usable_sge) { @@ -582,12 +582,13 @@ void ipoib_send(struct net_device *dev, struct sk_buff *skb, ++dev->stats.tx_dropped; ++dev->stats.tx_errors; dev_kfree_skb_any(skb); - return; + return -1; } } - ipoib_dbg_data(priv, "sending packet, length=%d address=%p qpn=0x%06x\n", - skb->len, address, qpn); + ipoib_dbg_data(priv, + "sending packet, length=%d address=%p dqpn=0x%06x\n", + skb->len, address, dqpn); /* * We put the skb into the tx_ring _before_ we call post_send() @@ -601,7 +602,7 @@ void ipoib_send(struct net_device *dev, struct sk_buff *skb, if (unlikely(ipoib_dma_map_tx(priv->ca, tx_req))) { ++dev->stats.tx_errors; dev_kfree_skb_any(skb); - return; + return -1; } if (skb->ip_summed == CHECKSUM_PARTIAL) @@ -620,7 +621,7 @@ void ipoib_send(struct net_device *dev, struct sk_buff *skb, skb_dst_drop(skb); rc = post_send(priv, priv->tx_head & (ipoib_sendq_size - 1), - address->ah, qpn, tx_req, phead, hlen); + address, dqpn, tx_req, phead, hlen); if (unlikely(rc)) { ipoib_warn(priv, "post_send failed, error %d\n", rc); ++dev->stats.tx_errors; @@ -629,21 +630,24 @@ void ipoib_send(struct net_device *dev, struct sk_buff *skb, dev_kfree_skb_any(skb); if (netif_queue_stopped(dev)) netif_wake_queue(dev); + rc = 0; } else { netif_trans_update(dev); - address->last_send = priv->tx_head; + rc = priv->tx_head; ++priv->tx_head; } if (unlikely(priv->tx_outstanding > MAX_SEND_CQE)) while (poll_tx(priv)) ; /* nothing */ + + return rc; } static void __ipoib_reap_ah(struct net_device *dev) { - struct ipoib_dev_priv *priv = netdev_priv(dev); + struct ipoib_dev_priv *priv = ipoib_priv(dev); struct ipoib_ah *ah, *tah; LIST_HEAD(remove_list); unsigned long flags; @@ -654,7 +658,7 @@ static void __ipoib_reap_ah(struct net_device *dev) list_for_each_entry_safe(ah, tah, &priv->dead_ahs, list) if ((int) priv->tx_tail - (int) ah->last_send >= 0) { list_del(&ah->list); - ib_destroy_ah(ah->ah); + rdma_destroy_ah(ah->ah); kfree(ah); } @@ -677,7 +681,7 @@ void ipoib_reap_ah(struct work_struct *work) static void ipoib_flush_ah(struct net_device *dev) { - struct ipoib_dev_priv *priv = netdev_priv(dev); + struct ipoib_dev_priv *priv = ipoib_priv(dev); cancel_delayed_work(&priv->ah_reap_task); flush_workqueue(priv->wq); @@ -686,30 +690,124 @@ static void ipoib_flush_ah(struct net_device *dev) static void ipoib_stop_ah(struct net_device *dev) { - struct ipoib_dev_priv *priv = netdev_priv(dev); + struct ipoib_dev_priv *priv = ipoib_priv(dev); set_bit(IPOIB_STOP_REAPER, &priv->flags); ipoib_flush_ah(dev); } -static void ipoib_ib_tx_timer_func(unsigned long ctx) +static int recvs_pending(struct net_device *dev) { - drain_tx_cq((struct net_device *)ctx); + struct ipoib_dev_priv *priv = ipoib_priv(dev); + int pending = 0; + int i; + + for (i = 0; i < ipoib_recvq_size; ++i) + if (priv->rx_ring[i].skb) + ++pending; + + return pending; } -int ipoib_ib_dev_open(struct net_device *dev) +int ipoib_ib_dev_stop_default(struct net_device *dev) { - struct ipoib_dev_priv *priv = netdev_priv(dev); - int ret; + struct ipoib_dev_priv *priv = ipoib_priv(dev); + struct ib_qp_attr qp_attr; + unsigned long begin; + struct ipoib_tx_buf *tx_req; + int i; - ipoib_pkey_dev_check_presence(dev); + if (test_bit(IPOIB_FLAG_INITIALIZED, &priv->flags)) + napi_disable(&priv->napi); - if (!test_bit(IPOIB_PKEY_ASSIGNED, &priv->flags)) { - ipoib_warn(priv, "P_Key 0x%04x is %s\n", priv->pkey, - (!(priv->pkey & 0x7fff) ? "Invalid" : "not found")); - return -1; + ipoib_cm_dev_stop(dev); + + /* + * Move our QP to the error state and then reinitialize in + * when all work requests have completed or have been flushed. + */ + qp_attr.qp_state = IB_QPS_ERR; + if (ib_modify_qp(priv->qp, &qp_attr, IB_QP_STATE)) + ipoib_warn(priv, "Failed to modify QP to ERROR state\n"); + + /* Wait for all sends and receives to complete */ + begin = jiffies; + + while (priv->tx_head != priv->tx_tail || recvs_pending(dev)) { + if (time_after(jiffies, begin + 5 * HZ)) { + ipoib_warn(priv, + "timing out; %d sends %d receives not completed\n", + priv->tx_head - priv->tx_tail, + recvs_pending(dev)); + + /* + * assume the HW is wedged and just free up + * all our pending work requests. + */ + while ((int)priv->tx_tail - (int)priv->tx_head < 0) { + tx_req = &priv->tx_ring[priv->tx_tail & + (ipoib_sendq_size - 1)]; + ipoib_dma_unmap_tx(priv, tx_req); + dev_kfree_skb_any(tx_req->skb); + ++priv->tx_tail; + --priv->tx_outstanding; + } + + for (i = 0; i < ipoib_recvq_size; ++i) { + struct ipoib_rx_buf *rx_req; + + rx_req = &priv->rx_ring[i]; + if (!rx_req->skb) + continue; + ipoib_ud_dma_unmap_rx(priv, + priv->rx_ring[i].mapping); + dev_kfree_skb_any(rx_req->skb); + rx_req->skb = NULL; + } + + goto timeout; + } + + ipoib_drain_cq(dev); + + msleep(1); } + ipoib_dbg(priv, "All sends and receives done.\n"); + +timeout: + del_timer_sync(&priv->poll_timer); + 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"); + + ib_req_notify_cq(priv->recv_cq, IB_CQ_NEXT_COMP); + + return 0; +} + +int ipoib_ib_dev_stop(struct net_device *dev) +{ + struct ipoib_dev_priv *priv = ipoib_priv(dev); + + priv->rn_ops->ndo_stop(dev); + + clear_bit(IPOIB_FLAG_INITIALIZED, &priv->flags); + ipoib_flush_ah(dev); + + return 0; +} + +void ipoib_ib_tx_timer_func(unsigned long ctx) +{ + drain_tx_cq((struct net_device *)ctx); +} + +int ipoib_ib_dev_open_default(struct net_device *dev) +{ + struct ipoib_dev_priv *priv = ipoib_priv(dev); + int ret; + ret = ipoib_init_qp(dev); if (ret) { ipoib_warn(priv, "ipoib_init_qp returned %d\n", ret); @@ -719,33 +817,60 @@ int ipoib_ib_dev_open(struct net_device *dev) ret = ipoib_ib_post_receives(dev); if (ret) { ipoib_warn(priv, "ipoib_ib_post_receives returned %d\n", ret); - goto dev_stop; + goto out; } ret = ipoib_cm_dev_open(dev); if (ret) { ipoib_warn(priv, "ipoib_cm_dev_open returned %d\n", ret); - goto dev_stop; + goto out; + } + + if (!test_bit(IPOIB_FLAG_INITIALIZED, &priv->flags)) + napi_enable(&priv->napi); + + return 0; +out: + return -1; +} + +int ipoib_ib_dev_open(struct net_device *dev) +{ + struct ipoib_dev_priv *priv = ipoib_priv(dev); + + ipoib_pkey_dev_check_presence(dev); + + if (!test_bit(IPOIB_PKEY_ASSIGNED, &priv->flags)) { + ipoib_warn(priv, "P_Key 0x%04x is %s\n", priv->pkey, + (!(priv->pkey & 0x7fff) ? "Invalid" : "not found")); + return -1; } clear_bit(IPOIB_STOP_REAPER, &priv->flags); queue_delayed_work(priv->wq, &priv->ah_reap_task, round_jiffies_relative(HZ)); - if (!test_and_set_bit(IPOIB_FLAG_INITIALIZED, &priv->flags)) - napi_enable(&priv->napi); + if (priv->rn_ops->ndo_open(dev)) { + pr_warn("%s: Failed to open dev\n", dev->name); + goto dev_stop; + } + + set_bit(IPOIB_FLAG_INITIALIZED, &priv->flags); return 0; + dev_stop: - if (!test_and_set_bit(IPOIB_FLAG_INITIALIZED, &priv->flags)) - napi_enable(&priv->napi); + set_bit(IPOIB_STOP_REAPER, &priv->flags); + cancel_delayed_work(&priv->ah_reap_task); + set_bit(IPOIB_FLAG_INITIALIZED, &priv->flags); + napi_enable(&priv->napi); ipoib_ib_dev_stop(dev); return -1; } void ipoib_pkey_dev_check_presence(struct net_device *dev) { - struct ipoib_dev_priv *priv = netdev_priv(dev); + struct ipoib_dev_priv *priv = ipoib_priv(dev); if (!(priv->pkey & 0x7fff) || ib_find_pkey(priv->ca, priv->port, priv->pkey, @@ -757,7 +882,7 @@ void ipoib_pkey_dev_check_presence(struct net_device *dev) void ipoib_ib_dev_up(struct net_device *dev) { - struct ipoib_dev_priv *priv = netdev_priv(dev); + struct ipoib_dev_priv *priv = ipoib_priv(dev); ipoib_pkey_dev_check_presence(dev); @@ -773,7 +898,7 @@ void ipoib_ib_dev_up(struct net_device *dev) void ipoib_ib_dev_down(struct net_device *dev) { - struct ipoib_dev_priv *priv = netdev_priv(dev); + struct ipoib_dev_priv *priv = ipoib_priv(dev); ipoib_dbg(priv, "downing ib_dev\n"); @@ -786,22 +911,9 @@ void ipoib_ib_dev_down(struct net_device *dev) ipoib_flush_paths(dev); } -static int recvs_pending(struct net_device *dev) -{ - struct ipoib_dev_priv *priv = netdev_priv(dev); - int pending = 0; - int i; - - for (i = 0; i < ipoib_recvq_size; ++i) - if (priv->rx_ring[i].skb) - ++pending; - - return pending; -} - void ipoib_drain_cq(struct net_device *dev) { - struct ipoib_dev_priv *priv = netdev_priv(dev); + struct ipoib_dev_priv *priv = ipoib_priv(dev); int i, n; /* @@ -838,107 +950,6 @@ void ipoib_drain_cq(struct net_device *dev) local_bh_enable(); } -void ipoib_ib_dev_stop(struct net_device *dev) -{ - struct ipoib_dev_priv *priv = netdev_priv(dev); - struct ib_qp_attr qp_attr; - unsigned long begin; - struct ipoib_tx_buf *tx_req; - int i; - - if (test_and_clear_bit(IPOIB_FLAG_INITIALIZED, &priv->flags)) - napi_disable(&priv->napi); - - ipoib_cm_dev_stop(dev); - - /* - * Move our QP to the error state and then reinitialize in - * when all work requests have completed or have been flushed. - */ - qp_attr.qp_state = IB_QPS_ERR; - if (ib_modify_qp(priv->qp, &qp_attr, IB_QP_STATE)) - ipoib_warn(priv, "Failed to modify QP to ERROR state\n"); - - /* Wait for all sends and receives to complete */ - begin = jiffies; - - while (priv->tx_head != priv->tx_tail || recvs_pending(dev)) { - if (time_after(jiffies, begin + 5 * HZ)) { - ipoib_warn(priv, "timing out; %d sends %d receives not completed\n", - priv->tx_head - priv->tx_tail, recvs_pending(dev)); - - /* - * assume the HW is wedged and just free up - * all our pending work requests. - */ - while ((int) priv->tx_tail - (int) priv->tx_head < 0) { - tx_req = &priv->tx_ring[priv->tx_tail & - (ipoib_sendq_size - 1)]; - ipoib_dma_unmap_tx(priv, tx_req); - dev_kfree_skb_any(tx_req->skb); - ++priv->tx_tail; - --priv->tx_outstanding; - } - - for (i = 0; i < ipoib_recvq_size; ++i) { - struct ipoib_rx_buf *rx_req; - - rx_req = &priv->rx_ring[i]; - if (!rx_req->skb) - continue; - ipoib_ud_dma_unmap_rx(priv, - priv->rx_ring[i].mapping); - dev_kfree_skb_any(rx_req->skb); - rx_req->skb = NULL; - } - - goto timeout; - } - - ipoib_drain_cq(dev); - - msleep(1); - } - - ipoib_dbg(priv, "All sends and receives done.\n"); - -timeout: - del_timer_sync(&priv->poll_timer); - 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"); - - ipoib_flush_ah(dev); - - ib_req_notify_cq(priv->recv_cq, IB_CQ_NEXT_COMP); -} - -int ipoib_ib_dev_init(struct net_device *dev, struct ib_device *ca, int port) -{ - struct ipoib_dev_priv *priv = netdev_priv(dev); - - priv->ca = ca; - priv->port = port; - priv->qp = NULL; - - if (ipoib_transport_dev_init(dev, ca)) { - printk(KERN_WARNING "%s: ipoib_transport_dev_init failed\n", ca->name); - return -ENODEV; - } - - setup_timer(&priv->poll_timer, ipoib_ib_tx_timer_func, - (unsigned long) dev); - - if (dev->flags & IFF_UP) { - if (ipoib_ib_dev_open(dev)) { - ipoib_transport_dev_cleanup(dev); - return -ENODEV; - } - } - - return 0; -} - /* * Takes whatever value which is in pkey index 0 and updates priv->pkey * returns 0 if the pkey value was changed. @@ -967,6 +978,19 @@ static inline int update_parent_pkey(struct ipoib_dev_priv *priv) */ priv->dev->broadcast[8] = priv->pkey >> 8; priv->dev->broadcast[9] = priv->pkey & 0xff; + + /* + * Update the broadcast address in the priv->broadcast object, + * in case it already exists, otherwise no one will do that. + */ + if (priv->broadcast) { + spin_lock_irq(&priv->lock); + memcpy(priv->broadcast->mcmember.mgid.raw, + priv->dev->broadcast + 4, + sizeof(union ib_gid)); + spin_unlock_irq(&priv->lock); + } + return 0; } @@ -1216,7 +1240,7 @@ void ipoib_ib_dev_flush_heavy(struct work_struct *work) void ipoib_ib_dev_cleanup(struct net_device *dev) { - struct ipoib_dev_priv *priv = netdev_priv(dev); + struct ipoib_dev_priv *priv = ipoib_priv(dev); ipoib_dbg(priv, "cleaning up ib_dev\n"); /* @@ -1236,7 +1260,13 @@ void ipoib_ib_dev_cleanup(struct net_device *dev) */ ipoib_stop_ah(dev); - ipoib_transport_dev_cleanup(dev); -} + clear_bit(IPOIB_PKEY_ASSIGNED, &priv->flags); + priv->rn_ops->ndo_uninit(dev); + + if (priv->pd) { + ib_dealloc_pd(priv->pd); + priv->pd = NULL; + } +} diff --git a/drivers/infiniband/ulp/ipoib/ipoib_main.c b/drivers/infiniband/ulp/ipoib/ipoib_main.c index d1d3fb7a6127..2869d1adb1de 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_main.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_main.c @@ -108,9 +108,36 @@ static struct ib_client ipoib_client = { .get_net_dev_by_params = ipoib_get_net_dev_by_params, }; +#ifdef CONFIG_INFINIBAND_IPOIB_DEBUG +static int ipoib_netdev_event(struct notifier_block *this, + unsigned long event, void *ptr) +{ + struct netdev_notifier_info *ni = ptr; + struct net_device *dev = ni->dev; + + if (dev->netdev_ops->ndo_open != ipoib_open) + return NOTIFY_DONE; + + switch (event) { + case NETDEV_REGISTER: + ipoib_create_debug_files(dev); + break; + case NETDEV_CHANGENAME: + ipoib_delete_debug_files(dev); + ipoib_create_debug_files(dev); + break; + case NETDEV_UNREGISTER: + ipoib_delete_debug_files(dev); + break; + } + + return NOTIFY_DONE; +} +#endif + int ipoib_open(struct net_device *dev) { - struct ipoib_dev_priv *priv = netdev_priv(dev); + struct ipoib_dev_priv *priv = ipoib_priv(dev); ipoib_dbg(priv, "bringing up interface\n"); @@ -157,7 +184,7 @@ err_disable: static int ipoib_stop(struct net_device *dev) { - struct ipoib_dev_priv *priv = netdev_priv(dev); + struct ipoib_dev_priv *priv = ipoib_priv(dev); ipoib_dbg(priv, "stopping interface\n"); @@ -195,7 +222,7 @@ static void ipoib_uninit(struct net_device *dev) static netdev_features_t ipoib_fix_features(struct net_device *dev, netdev_features_t features) { - struct ipoib_dev_priv *priv = netdev_priv(dev); + struct ipoib_dev_priv *priv = ipoib_priv(dev); if (test_bit(IPOIB_FLAG_ADMIN_CM, &priv->flags)) features &= ~(NETIF_F_IP_CSUM | NETIF_F_TSO); @@ -205,7 +232,7 @@ static netdev_features_t ipoib_fix_features(struct net_device *dev, netdev_featu static int ipoib_change_mtu(struct net_device *dev, int new_mtu) { - struct ipoib_dev_priv *priv = netdev_priv(dev); + struct ipoib_dev_priv *priv = ipoib_priv(dev); /* dev->mtu > 2K ==> connected mode */ if (ipoib_cm_admin_enabled(dev)) { @@ -468,7 +495,7 @@ static struct net_device *ipoib_get_net_dev_by_params( int ipoib_set_mode(struct net_device *dev, const char *buf) { - struct ipoib_dev_priv *priv = netdev_priv(dev); + struct ipoib_dev_priv *priv = ipoib_priv(dev); if ((test_bit(IPOIB_FLAG_ADMIN_CM, &priv->flags) && !strcmp(buf, "connected\n")) || @@ -505,7 +532,7 @@ int ipoib_set_mode(struct net_device *dev, const char *buf) struct ipoib_path *__path_find(struct net_device *dev, void *gid) { - struct ipoib_dev_priv *priv = netdev_priv(dev); + struct ipoib_dev_priv *priv = ipoib_priv(dev); struct rb_node *n = priv->path_tree.rb_node; struct ipoib_path *path; int ret; @@ -529,7 +556,7 @@ struct ipoib_path *__path_find(struct net_device *dev, void *gid) static int __path_add(struct net_device *dev, struct ipoib_path *path) { - struct ipoib_dev_priv *priv = netdev_priv(dev); + struct ipoib_dev_priv *priv = ipoib_priv(dev); struct rb_node **n = &priv->path_tree.rb_node; struct rb_node *pn = NULL; struct ipoib_path *tpath; @@ -564,7 +591,7 @@ static void path_free(struct net_device *dev, struct ipoib_path *path) while ((skb = __skb_dequeue(&path->queue))) dev_kfree_skb_irq(skb); - ipoib_dbg(netdev_priv(dev), "path_free\n"); + ipoib_dbg(ipoib_priv(dev), "path_free\n"); /* remove all neigh connected to this path */ ipoib_del_neighs_by_gid(dev, path->pathrec.dgid.raw); @@ -598,7 +625,7 @@ struct ipoib_path_iter *ipoib_path_iter_init(struct net_device *dev) int ipoib_path_iter_next(struct ipoib_path_iter *iter) { - struct ipoib_dev_priv *priv = netdev_priv(iter->dev); + struct ipoib_dev_priv *priv = ipoib_priv(iter->dev); struct rb_node *n; struct ipoib_path *path; int ret = 1; @@ -635,92 +662,21 @@ void ipoib_path_iter_read(struct ipoib_path_iter *iter, void ipoib_mark_paths_invalid(struct net_device *dev) { - struct ipoib_dev_priv *priv = netdev_priv(dev); + struct ipoib_dev_priv *priv = ipoib_priv(dev); struct ipoib_path *path, *tp; spin_lock_irq(&priv->lock); list_for_each_entry_safe(path, tp, &priv->path_list, list) { - ipoib_dbg(priv, "mark path LID 0x%04x GID %pI6 invalid\n", - be16_to_cpu(path->pathrec.dlid), - path->pathrec.dgid.raw); + ipoib_dbg(priv, "mark path LID 0x%08x GID %pI6 invalid\n", + be32_to_cpu(sa_path_get_dlid(&path->pathrec)), + path->pathrec.dgid.raw); path->valid = 0; } spin_unlock_irq(&priv->lock); } -struct classport_info_context { - struct ipoib_dev_priv *priv; - struct completion done; - struct ib_sa_query *sa_query; -}; - -static void classport_info_query_cb(int status, struct ib_class_port_info *rec, - void *context) -{ - struct classport_info_context *cb_ctx = context; - struct ipoib_dev_priv *priv; - - WARN_ON(!context); - - priv = cb_ctx->priv; - - if (status || !rec) { - pr_debug("device: %s failed query classport_info status: %d\n", - priv->dev->name, status); - /* keeps the default, will try next mcast_restart */ - priv->sm_fullmember_sendonly_support = false; - goto out; - } - - if (ib_get_cpi_capmask2(rec) & - IB_SA_CAP_MASK2_SENDONLY_FULL_MEM_SUPPORT) { - pr_debug("device: %s enabled fullmember-sendonly for sendonly MCG\n", - priv->dev->name); - priv->sm_fullmember_sendonly_support = true; - } else { - pr_debug("device: %s disabled fullmember-sendonly for sendonly MCG\n", - priv->dev->name); - priv->sm_fullmember_sendonly_support = false; - } - -out: - complete(&cb_ctx->done); -} - -int ipoib_check_sm_sendonly_fullmember_support(struct ipoib_dev_priv *priv) -{ - struct classport_info_context *callback_context; - int ret; - - callback_context = kmalloc(sizeof(*callback_context), GFP_KERNEL); - if (!callback_context) - return -ENOMEM; - - callback_context->priv = priv; - init_completion(&callback_context->done); - - ret = ib_sa_classport_info_rec_query(&ipoib_sa_client, - priv->ca, priv->port, 3000, - GFP_KERNEL, - classport_info_query_cb, - callback_context, - &callback_context->sa_query); - if (ret < 0) { - pr_info("%s failed to send ib_sa_classport_info query, ret: %d\n", - priv->dev->name, ret); - kfree(callback_context); - return ret; - } - - /* waiting for the callback to finish before returnning */ - wait_for_completion(&callback_context->done); - kfree(callback_context); - - return ret; -} - static void push_pseudo_header(struct sk_buff *skb, const char *daddr) { struct ipoib_pseudo_header *phdr; @@ -731,7 +687,7 @@ static void push_pseudo_header(struct sk_buff *skb, const char *daddr) void ipoib_flush_paths(struct net_device *dev) { - struct ipoib_dev_priv *priv = netdev_priv(dev); + struct ipoib_dev_priv *priv = ipoib_priv(dev); struct ipoib_path *path, *tp; LIST_HEAD(remove_list); unsigned long flags; @@ -760,12 +716,12 @@ void ipoib_flush_paths(struct net_device *dev) } static void path_rec_completion(int status, - struct ib_sa_path_rec *pathrec, + struct sa_path_rec *pathrec, void *path_ptr) { struct ipoib_path *path = path_ptr; struct net_device *dev = path->dev; - struct ipoib_dev_priv *priv = netdev_priv(dev); + struct ipoib_dev_priv *priv = ipoib_priv(dev); struct ipoib_ah *ah = NULL; struct ipoib_ah *old_ah = NULL; struct ipoib_neigh *neigh, *tn; @@ -775,7 +731,8 @@ static void path_rec_completion(int status, if (!status) ipoib_dbg(priv, "PathRec LID 0x%04x for GID %pI6\n", - be16_to_cpu(pathrec->dlid), pathrec->dgid.raw); + be32_to_cpu(sa_path_get_dlid(pathrec)), + pathrec->dgid.raw); else ipoib_dbg(priv, "PathRec status %d for GID %pI6\n", status, path->pathrec.dgid.raw); @@ -783,7 +740,7 @@ static void path_rec_completion(int status, skb_queue_head_init(&skqueue); if (!status) { - struct ib_ah_attr av; + struct rdma_ah_attr av; if (!ib_init_ah_from_path(priv->ca, priv->port, pathrec, &av)) ah = ipoib_create_ah(dev, priv->pd, &av); @@ -798,7 +755,8 @@ static void path_rec_completion(int status, path->ah = ah; ipoib_dbg(priv, "created address handle %p for LID 0x%04x, SL %d\n", - ah, be16_to_cpu(pathrec->dlid), pathrec->sl); + ah, be32_to_cpu(sa_path_get_dlid(pathrec)), + pathrec->sl); while ((skb = __skb_dequeue(&path->queue))) __skb_queue_tail(&skqueue, skb); @@ -858,7 +816,7 @@ static void path_rec_completion(int status, static struct ipoib_path *path_rec_create(struct net_device *dev, void *gid) { - struct ipoib_dev_priv *priv = netdev_priv(dev); + struct ipoib_dev_priv *priv = ipoib_priv(dev); struct ipoib_path *path; if (!priv->broadcast) @@ -874,6 +832,10 @@ static struct ipoib_path *path_rec_create(struct net_device *dev, void *gid) INIT_LIST_HEAD(&path->neigh_list); + if (rdma_cap_opa_ah(priv->ca, priv->port)) + path->pathrec.rec_type = SA_PATH_REC_TYPE_OPA; + else + path->pathrec.rec_type = SA_PATH_REC_TYPE_IB; memcpy(path->pathrec.dgid.raw, gid, sizeof (union ib_gid)); path->pathrec.sgid = priv->local_gid; path->pathrec.pkey = cpu_to_be16(priv->pkey); @@ -886,7 +848,7 @@ static struct ipoib_path *path_rec_create(struct net_device *dev, void *gid) static int path_rec_start(struct net_device *dev, struct ipoib_path *path) { - struct ipoib_dev_priv *priv = netdev_priv(dev); + struct ipoib_dev_priv *priv = ipoib_priv(dev); ipoib_dbg(priv, "Start path record lookup for %pI6\n", path->pathrec.dgid.raw); @@ -917,7 +879,8 @@ static int path_rec_start(struct net_device *dev, static void neigh_add_path(struct sk_buff *skb, u8 *daddr, struct net_device *dev) { - struct ipoib_dev_priv *priv = netdev_priv(dev); + struct ipoib_dev_priv *priv = ipoib_priv(dev); + struct rdma_netdev *rn = netdev_priv(dev); struct ipoib_path *path; struct ipoib_neigh *neigh; unsigned long flags; @@ -964,7 +927,8 @@ static void neigh_add_path(struct sk_buff *skb, u8 *daddr, } } else { spin_unlock_irqrestore(&priv->lock, flags); - ipoib_send(dev, skb, path->ah, IPOIB_QPN(daddr)); + path->ah->last_send = rn->send(dev, skb, path->ah->ah, + IPOIB_QPN(daddr)); ipoib_neigh_put(neigh); return; } @@ -998,7 +962,8 @@ err_drop: static void unicast_arp_send(struct sk_buff *skb, struct net_device *dev, struct ipoib_pseudo_header *phdr) { - struct ipoib_dev_priv *priv = netdev_priv(dev); + struct ipoib_dev_priv *priv = ipoib_priv(dev); + struct rdma_netdev *rn = netdev_priv(dev); struct ipoib_path *path; unsigned long flags; @@ -1038,11 +1003,12 @@ static void unicast_arp_send(struct sk_buff *skb, struct net_device *dev, } if (path->ah) { - ipoib_dbg(priv, "Send unicast ARP to %04x\n", - be16_to_cpu(path->pathrec.dlid)); + ipoib_dbg(priv, "Send unicast ARP to %08x\n", + be32_to_cpu(sa_path_get_dlid(&path->pathrec))); spin_unlock_irqrestore(&priv->lock, flags); - ipoib_send(dev, skb, path->ah, IPOIB_QPN(phdr->hwaddr)); + path->ah->last_send = rn->send(dev, skb, path->ah->ah, + IPOIB_QPN(phdr->hwaddr)); return; } else if ((path->query || !path_rec_start(dev, path)) && skb_queue_len(&path->queue) < IPOIB_MAX_PATH_REC_QUEUE) { @@ -1058,7 +1024,8 @@ static void unicast_arp_send(struct sk_buff *skb, struct net_device *dev, static int ipoib_start_xmit(struct sk_buff *skb, struct net_device *dev) { - struct ipoib_dev_priv *priv = netdev_priv(dev); + struct ipoib_dev_priv *priv = ipoib_priv(dev); + struct rdma_netdev *rn = netdev_priv(dev); struct ipoib_neigh *neigh; struct ipoib_pseudo_header *phdr; struct ipoib_header *header; @@ -1122,7 +1089,8 @@ send_using_neigh: goto unref; } } else if (neigh->ah) { - ipoib_send(dev, skb, neigh->ah, IPOIB_QPN(phdr->hwaddr)); + neigh->ah->last_send = rn->send(dev, skb, neigh->ah->ah, + IPOIB_QPN(phdr->hwaddr)); goto unref; } @@ -1144,7 +1112,7 @@ unref: static void ipoib_timeout(struct net_device *dev) { - struct ipoib_dev_priv *priv = netdev_priv(dev); + struct ipoib_dev_priv *priv = ipoib_priv(dev); ipoib_warn(priv, "transmit timeout: latency %d msecs\n", jiffies_to_msecs(jiffies - dev_trans_start(dev))); @@ -1178,7 +1146,7 @@ static int ipoib_hard_header(struct sk_buff *skb, static void ipoib_set_mcast_list(struct net_device *dev) { - struct ipoib_dev_priv *priv = netdev_priv(dev); + struct ipoib_dev_priv *priv = ipoib_priv(dev); if (!test_bit(IPOIB_FLAG_OPER_UP, &priv->flags)) { ipoib_dbg(priv, "IPOIB_FLAG_OPER_UP not set"); @@ -1190,7 +1158,7 @@ static void ipoib_set_mcast_list(struct net_device *dev) static int ipoib_get_iflink(const struct net_device *dev) { - struct ipoib_dev_priv *priv = netdev_priv(dev); + struct ipoib_dev_priv *priv = ipoib_priv(dev); /* parent interface */ if (!test_bit(IPOIB_FLAG_SUBINTERFACE, &priv->flags)) @@ -1218,7 +1186,7 @@ static u32 ipoib_addr_hash(struct ipoib_neigh_hash *htbl, u8 *daddr) struct ipoib_neigh *ipoib_neigh_get(struct net_device *dev, u8 *daddr) { - struct ipoib_dev_priv *priv = netdev_priv(dev); + struct ipoib_dev_priv *priv = ipoib_priv(dev); struct ipoib_neigh_table *ntbl = &priv->ntbl; struct ipoib_neigh_hash *htbl; struct ipoib_neigh *neigh = NULL; @@ -1347,7 +1315,7 @@ static struct ipoib_neigh *ipoib_neigh_ctor(u8 *daddr, struct ipoib_neigh *ipoib_neigh_alloc(u8 *daddr, struct net_device *dev) { - struct ipoib_dev_priv *priv = netdev_priv(dev); + struct ipoib_dev_priv *priv = ipoib_priv(dev); struct ipoib_neigh_table *ntbl = &priv->ntbl; struct ipoib_neigh_hash *htbl; struct ipoib_neigh *neigh; @@ -1404,7 +1372,7 @@ void ipoib_neigh_dtor(struct ipoib_neigh *neigh) { /* neigh reference count was dropprd to zero */ struct net_device *dev = neigh->dev; - struct ipoib_dev_priv *priv = netdev_priv(dev); + struct ipoib_dev_priv *priv = ipoib_priv(dev); struct sk_buff *skb; if (neigh->ah) ipoib_put_ah(neigh->ah); @@ -1414,7 +1382,7 @@ void ipoib_neigh_dtor(struct ipoib_neigh *neigh) } if (ipoib_cm_get(neigh)) ipoib_cm_destroy_tx(ipoib_cm_get(neigh)); - ipoib_dbg(netdev_priv(dev), + ipoib_dbg(ipoib_priv(dev), "neigh free for %06x %pI6\n", IPOIB_QPN(neigh->daddr), neigh->daddr + 4); @@ -1436,7 +1404,7 @@ static void ipoib_neigh_reclaim(struct rcu_head *rp) void ipoib_neigh_free(struct ipoib_neigh *neigh) { struct net_device *dev = neigh->dev; - struct ipoib_dev_priv *priv = netdev_priv(dev); + struct ipoib_dev_priv *priv = ipoib_priv(dev); struct ipoib_neigh_table *ntbl = &priv->ntbl; struct ipoib_neigh_hash *htbl; struct ipoib_neigh __rcu **np; @@ -1519,7 +1487,7 @@ static void neigh_hash_free_rcu(struct rcu_head *head) void ipoib_del_neighs_by_gid(struct net_device *dev, u8 *gid) { - struct ipoib_dev_priv *priv = netdev_priv(dev); + struct ipoib_dev_priv *priv = ipoib_priv(dev); struct ipoib_neigh_table *ntbl = &priv->ntbl; struct ipoib_neigh_hash *htbl; unsigned long flags; @@ -1605,7 +1573,7 @@ out_unlock: static void ipoib_neigh_hash_uninit(struct net_device *dev) { - struct ipoib_dev_priv *priv = netdev_priv(dev); + struct ipoib_dev_priv *priv = ipoib_priv(dev); int stopped; ipoib_dbg(priv, "ipoib_neigh_hash_uninit\n"); @@ -1622,10 +1590,26 @@ static void ipoib_neigh_hash_uninit(struct net_device *dev) wait_for_completion(&priv->ntbl.deleted); } +void ipoib_dev_uninit_default(struct net_device *dev) +{ + struct ipoib_dev_priv *priv = ipoib_priv(dev); -int ipoib_dev_init(struct net_device *dev, struct ib_device *ca, int port) + ipoib_transport_dev_cleanup(dev); + + ipoib_cm_dev_cleanup(dev); + + kfree(priv->rx_ring); + vfree(priv->tx_ring); + + priv->rx_ring = NULL; + priv->tx_ring = NULL; +} + +static int ipoib_dev_init_default(struct net_device *dev) { - struct ipoib_dev_priv *priv = netdev_priv(dev); + struct ipoib_dev_priv *priv = ipoib_priv(dev); + + netif_napi_add(dev, &priv->napi, ipoib_poll, NAPI_POLL_WEIGHT); /* Allocate RX/TX "rings" to hold queued skbs */ priv->rx_ring = kzalloc(ipoib_recvq_size * sizeof *priv->rx_ring, @@ -1636,46 +1620,111 @@ int ipoib_dev_init(struct net_device *dev, struct ib_device *ca, int port) priv->tx_ring = vzalloc(ipoib_sendq_size * sizeof *priv->tx_ring); if (!priv->tx_ring) { printk(KERN_WARNING "%s: failed to allocate TX ring (%d entries)\n", - ca->name, ipoib_sendq_size); + priv->ca->name, ipoib_sendq_size); goto out_rx_ring_cleanup; } /* priv->tx_head, tx_tail & tx_outstanding are already 0 */ - if (ipoib_ib_dev_init(dev, ca, port)) + if (ipoib_transport_dev_init(dev, priv->ca)) { + pr_warn("%s: ipoib_transport_dev_init failed\n", + priv->ca->name); goto out_tx_ring_cleanup; + } + + /* after qp created set dev address */ + priv->dev->dev_addr[1] = (priv->qp->qp_num >> 16) & 0xff; + priv->dev->dev_addr[2] = (priv->qp->qp_num >> 8) & 0xff; + priv->dev->dev_addr[3] = (priv->qp->qp_num) & 0xff; + + setup_timer(&priv->poll_timer, ipoib_ib_tx_timer_func, + (unsigned long)dev); + + return 0; + +out_tx_ring_cleanup: + vfree(priv->tx_ring); + +out_rx_ring_cleanup: + kfree(priv->rx_ring); + +out: + return -ENOMEM; +} + +int ipoib_dev_init(struct net_device *dev, struct ib_device *ca, int port) +{ + struct ipoib_dev_priv *priv = ipoib_priv(dev); + int ret = -ENOMEM; + + priv->ca = ca; + priv->port = port; + priv->qp = NULL; /* - * Must be after ipoib_ib_dev_init so we can allocate a per - * device wq there and use it here + * the various IPoIB tasks assume they will never race against + * themselves, so always use a single thread workqueue */ - if (ipoib_neigh_hash_init(priv) < 0) + priv->wq = alloc_ordered_workqueue("ipoib_wq", WQ_MEM_RECLAIM); + if (!priv->wq) { + pr_warn("%s: failed to allocate device WQ\n", dev->name); + goto out; + } + + /* create pd, which used both for control and datapath*/ + priv->pd = ib_alloc_pd(priv->ca, 0); + if (IS_ERR(priv->pd)) { + pr_warn("%s: failed to allocate PD\n", ca->name); + goto clean_wq; + } + + ret = priv->rn_ops->ndo_init(dev); + if (ret) { + pr_warn("%s failed to init HW resource\n", dev->name); + goto out_free_pd; + } + + if (ipoib_neigh_hash_init(priv) < 0) { + pr_warn("%s failed to init neigh hash\n", dev->name); goto out_dev_uninit; + } + + if (dev->flags & IFF_UP) { + if (ipoib_ib_dev_open(dev)) { + pr_warn("%s failed to open device\n", dev->name); + ret = -ENODEV; + goto out_dev_uninit; + } + } return 0; out_dev_uninit: ipoib_ib_dev_cleanup(dev); -out_tx_ring_cleanup: - vfree(priv->tx_ring); +out_free_pd: + if (priv->pd) { + ib_dealloc_pd(priv->pd); + priv->pd = NULL; + } -out_rx_ring_cleanup: - kfree(priv->rx_ring); +clean_wq: + if (priv->wq) { + destroy_workqueue(priv->wq); + priv->wq = NULL; + } out: - return -ENOMEM; + return ret; } void ipoib_dev_cleanup(struct net_device *dev) { - struct ipoib_dev_priv *priv = netdev_priv(dev), *cpriv, *tcpriv; + struct ipoib_dev_priv *priv = ipoib_priv(dev), *cpriv, *tcpriv; LIST_HEAD(head); ASSERT_RTNL(); - ipoib_delete_debug_files(dev); - /* Delete any child interfaces first */ list_for_each_entry_safe(cpriv, tcpriv, &priv->child_intfs, list) { /* Stop GC on child */ @@ -1685,24 +1734,21 @@ void ipoib_dev_cleanup(struct net_device *dev) } unregister_netdevice_many(&head); - /* - * Must be before ipoib_ib_dev_cleanup or we delete an in use - * work queue - */ ipoib_neigh_hash_uninit(dev); ipoib_ib_dev_cleanup(dev); - kfree(priv->rx_ring); - vfree(priv->tx_ring); - - priv->rx_ring = NULL; - priv->tx_ring = NULL; + /* no more works over the priv->wq */ + if (priv->wq) { + flush_workqueue(priv->wq); + destroy_workqueue(priv->wq); + priv->wq = 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); + struct ipoib_dev_priv *priv = ipoib_priv(dev); return ib_set_vf_link_state(priv->ca, vf, priv->port, link_state); } @@ -1710,7 +1756,7 @@ static int ipoib_set_vf_link_state(struct net_device *dev, int vf, int link_stat 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); + struct ipoib_dev_priv *priv = ipoib_priv(dev); int err; err = ib_get_vf_config(priv->ca, vf, priv->port, ivf); @@ -1724,7 +1770,7 @@ static int ipoib_get_vf_config(struct net_device *dev, int vf, static int ipoib_set_vf_guid(struct net_device *dev, int vf, u64 guid, int type) { - struct ipoib_dev_priv *priv = netdev_priv(dev); + struct ipoib_dev_priv *priv = ipoib_priv(dev); if (type != IFLA_VF_IB_NODE_GUID && type != IFLA_VF_IB_PORT_GUID) return -EINVAL; @@ -1735,7 +1781,7 @@ static int ipoib_set_vf_guid(struct net_device *dev, int vf, u64 guid, int 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); + struct ipoib_dev_priv *priv = ipoib_priv(dev); return ib_get_vf_stats(priv->ca, vf, priv->port, vf_stats); } @@ -1773,21 +1819,12 @@ static const struct net_device_ops ipoib_netdev_ops_vf = { .ndo_get_iflink = ipoib_get_iflink, }; -void ipoib_setup(struct net_device *dev) +void ipoib_setup_common(struct net_device *dev) { - struct ipoib_dev_priv *priv = netdev_priv(dev); - - 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); - netif_napi_add(dev, &priv->napi, ipoib_poll, NAPI_POLL_WEIGHT); - dev->watchdog_timeo = HZ; dev->flags |= IFF_BROADCAST | IFF_MULTICAST; @@ -1801,11 +1838,14 @@ void ipoib_setup(struct net_device *dev) netif_keep_dst(dev); memcpy(dev->broadcast, ipv4_bcast_addr, INFINIBAND_ALEN); +} - priv->dev = dev; +static void ipoib_build_priv(struct net_device *dev) +{ + struct ipoib_dev_priv *priv = ipoib_priv(dev); + priv->dev = dev; spin_lock_init(&priv->lock); - init_rwsem(&priv->vlan_rwsem); INIT_LIST_HEAD(&priv->path_list); @@ -1823,22 +1863,99 @@ void ipoib_setup(struct net_device *dev) INIT_DELAYED_WORK(&priv->neigh_reap_task, ipoib_reap_neigh); } -struct ipoib_dev_priv *ipoib_intf_alloc(const char *name) +static const struct net_device_ops ipoib_netdev_default_pf = { + .ndo_init = ipoib_dev_init_default, + .ndo_uninit = ipoib_dev_uninit_default, + .ndo_open = ipoib_ib_dev_open_default, + .ndo_stop = ipoib_ib_dev_stop_default, +}; + +static struct net_device +*ipoib_create_netdev_default(struct ib_device *hca, + const char *name, + unsigned char name_assign_type, + void (*setup)(struct net_device *)) { struct net_device *dev; + struct rdma_netdev *rn; - dev = alloc_netdev((int)sizeof(struct ipoib_dev_priv), name, - NET_NAME_UNKNOWN, ipoib_setup); + dev = alloc_netdev((int)sizeof(struct rdma_netdev), + name, + name_assign_type, setup); if (!dev) return NULL; - return netdev_priv(dev); + rn = netdev_priv(dev); + + rn->send = ipoib_send; + rn->attach_mcast = ipoib_mcast_attach; + rn->detach_mcast = ipoib_mcast_detach; + rn->hca = hca; + + dev->netdev_ops = &ipoib_netdev_default_pf; + + return dev; +} + +static struct net_device *ipoib_get_netdev(struct ib_device *hca, u8 port, + const char *name) +{ + struct net_device *dev; + + if (hca->alloc_rdma_netdev) { + dev = hca->alloc_rdma_netdev(hca, port, + RDMA_NETDEV_IPOIB, name, + NET_NAME_UNKNOWN, + ipoib_setup_common); + if (IS_ERR_OR_NULL(dev) && PTR_ERR(dev) != -EOPNOTSUPP) + return NULL; + } + + if (!hca->alloc_rdma_netdev || PTR_ERR(dev) == -EOPNOTSUPP) + dev = ipoib_create_netdev_default(hca, name, NET_NAME_UNKNOWN, + ipoib_setup_common); + + return dev; +} + +struct ipoib_dev_priv *ipoib_intf_alloc(struct ib_device *hca, u8 port, + const char *name) +{ + struct net_device *dev; + struct ipoib_dev_priv *priv; + struct rdma_netdev *rn; + + priv = kzalloc(sizeof(*priv), GFP_KERNEL); + if (!priv) + return NULL; + + dev = ipoib_get_netdev(hca, port, name); + if (!dev) + goto free_priv; + + priv->rn_ops = dev->netdev_ops; + + /* fixme : should be after the query_cap */ + if (priv->hca_caps & IB_DEVICE_VIRTUAL_FUNCTION) + dev->netdev_ops = &ipoib_netdev_ops_vf; + else + dev->netdev_ops = &ipoib_netdev_ops_pf; + + rn = netdev_priv(dev); + rn->clnt_priv = priv; + ipoib_build_priv(dev); + + return priv; +free_priv: + kfree(priv); + return NULL; } static ssize_t show_pkey(struct device *dev, struct device_attribute *attr, char *buf) { - struct ipoib_dev_priv *priv = netdev_priv(to_net_dev(dev)); + struct net_device *ndev = to_net_dev(dev); + struct ipoib_dev_priv *priv = ipoib_priv(ndev); return sprintf(buf, "0x%04x\n", priv->pkey); } @@ -1847,14 +1964,15 @@ static DEVICE_ATTR(pkey, S_IRUGO, show_pkey, NULL); static ssize_t show_umcast(struct device *dev, struct device_attribute *attr, char *buf) { - struct ipoib_dev_priv *priv = netdev_priv(to_net_dev(dev)); + struct net_device *ndev = to_net_dev(dev); + struct ipoib_dev_priv *priv = ipoib_priv(ndev); return sprintf(buf, "%d\n", test_bit(IPOIB_FLAG_UMCAST, &priv->flags)); } void ipoib_set_umcast(struct net_device *ndev, int umcast_val) { - struct ipoib_dev_priv *priv = netdev_priv(ndev); + struct ipoib_dev_priv *priv = ipoib_priv(ndev); if (umcast_val > 0) { set_bit(IPOIB_FLAG_UMCAST, &priv->flags); @@ -1927,7 +2045,7 @@ static int ipoib_check_lladdr(struct net_device *dev, static int ipoib_set_mac(struct net_device *dev, void *addr) { - struct ipoib_dev_priv *priv = netdev_priv(dev); + struct ipoib_dev_priv *priv = ipoib_priv(dev); struct sockaddr_storage *ss = addr; int ret; @@ -2000,7 +2118,7 @@ void ipoib_set_dev_features(struct ipoib_dev_priv *priv, struct ib_device *hca) priv->hca_caps = hca->attrs.device_cap_flags; if (priv->hca_caps & IB_DEVICE_UD_IP_CSUM) { - priv->dev->hw_features = NETIF_F_IP_CSUM | NETIF_F_RXCSUM; + priv->dev->hw_features |= NETIF_F_IP_CSUM | NETIF_F_RXCSUM; if (priv->hca_caps & IB_DEVICE_UD_TSO) priv->dev->hw_features |= NETIF_F_TSO; @@ -2016,7 +2134,7 @@ static struct net_device *ipoib_add_port(const char *format, struct ib_port_attr attr; int result = -ENOMEM; - priv = ipoib_intf_alloc(format); + priv = ipoib_intf_alloc(hca, port, format); if (!priv) goto alloc_mem_failed; @@ -2090,8 +2208,6 @@ static struct net_device *ipoib_add_port(const char *format, goto register_failed; } - ipoib_create_debug_files(priv->dev); - if (ipoib_cm_add_mode_attr(priv->dev)) goto sysfs_failed; if (ipoib_add_pkey_attr(priv->dev)) @@ -2106,7 +2222,6 @@ static struct net_device *ipoib_add_port(const char *format, return priv->dev; sysfs_failed: - ipoib_delete_debug_files(priv->dev); unregister_netdev(priv->dev); register_failed: @@ -2146,7 +2261,7 @@ static void ipoib_add_one(struct ib_device *device) continue; dev = ipoib_add_port("ib%d", device, p); if (!IS_ERR(dev)) { - priv = netdev_priv(dev); + priv = ipoib_priv(dev); list_add_tail(&priv->list, dev_list); count++; } @@ -2186,11 +2301,18 @@ static void ipoib_remove_one(struct ib_device *device, void *client_data) unregister_netdev(priv->dev); free_netdev(priv->dev); + kfree(priv); } kfree(dev_list); } +#ifdef CONFIG_INFINIBAND_IPOIB_DEBUG +static struct notifier_block ipoib_netdev_notifier = { + .notifier_call = ipoib_netdev_event, +}; +#endif + static int __init ipoib_init_module(void) { int ret; @@ -2243,6 +2365,9 @@ static int __init ipoib_init_module(void) if (ret) goto err_client; +#ifdef CONFIG_INFINIBAND_IPOIB_DEBUG + register_netdevice_notifier(&ipoib_netdev_notifier); +#endif return 0; err_client: @@ -2260,6 +2385,9 @@ err_fs: static void __exit ipoib_cleanup_module(void) { +#ifdef CONFIG_INFINIBAND_IPOIB_DEBUG + unregister_netdevice_notifier(&ipoib_netdev_notifier); +#endif ipoib_netlink_fini(); ib_unregister_client(&ipoib_client); ib_sa_unregister_client(&ipoib_sa_client); diff --git a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c index 69e146cdc306..057f58e6afca 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c @@ -114,7 +114,7 @@ static void ipoib_mcast_free(struct ipoib_mcast *mcast) struct net_device *dev = mcast->dev; int tx_dropped = 0; - ipoib_dbg_mcast(netdev_priv(dev), "deleting multicast group %pI6\n", + ipoib_dbg_mcast(ipoib_priv(dev), "deleting multicast group %pI6\n", mcast->mcmember.mgid.raw); /* remove all neigh connected to this mcast */ @@ -158,7 +158,7 @@ static struct ipoib_mcast *ipoib_mcast_alloc(struct net_device *dev, static struct ipoib_mcast *__ipoib_mcast_find(struct net_device *dev, void *mgid) { - struct ipoib_dev_priv *priv = netdev_priv(dev); + struct ipoib_dev_priv *priv = ipoib_priv(dev); struct rb_node *n = priv->multicast_tree.rb_node; while (n) { @@ -182,7 +182,7 @@ static struct ipoib_mcast *__ipoib_mcast_find(struct net_device *dev, void *mgid static int __ipoib_mcast_add(struct net_device *dev, struct ipoib_mcast *mcast) { - struct ipoib_dev_priv *priv = netdev_priv(dev); + struct ipoib_dev_priv *priv = ipoib_priv(dev); struct rb_node **n = &priv->multicast_tree.rb_node, *pn = NULL; while (*n) { @@ -212,8 +212,10 @@ static int ipoib_mcast_join_finish(struct ipoib_mcast *mcast, struct ib_sa_mcmember_rec *mcmember) { struct net_device *dev = mcast->dev; - struct ipoib_dev_priv *priv = netdev_priv(dev); + struct ipoib_dev_priv *priv = ipoib_priv(dev); + struct rdma_netdev *rn = netdev_priv(dev); struct ipoib_ah *ah; + struct rdma_ah_attr av; int ret; int set_qkey = 0; @@ -260,8 +262,9 @@ static int ipoib_mcast_join_finish(struct ipoib_mcast *mcast, return 0; } - ret = ipoib_mcast_attach(dev, be16_to_cpu(mcast->mcmember.mlid), - &mcast->mcmember.mgid, set_qkey); + ret = rn->attach_mcast(dev, priv->ca, &mcast->mcmember.mgid, + be16_to_cpu(mcast->mcmember.mlid), + set_qkey, priv->qkey); if (ret < 0) { ipoib_warn(priv, "couldn't attach QP to multicast group %pI6\n", mcast->mcmember.mgid.raw); @@ -271,40 +274,34 @@ static int ipoib_mcast_join_finish(struct ipoib_mcast *mcast, } } - { - struct ib_ah_attr av = { - .dlid = be16_to_cpu(mcast->mcmember.mlid), - .port_num = priv->port, - .sl = mcast->mcmember.sl, - .ah_flags = IB_AH_GRH, - .static_rate = mcast->mcmember.rate, - .grh = { - .flow_label = be32_to_cpu(mcast->mcmember.flow_label), - .hop_limit = mcast->mcmember.hop_limit, - .sgid_index = 0, - .traffic_class = mcast->mcmember.traffic_class - } - }; - av.grh.dgid = mcast->mcmember.mgid; - - ah = ipoib_create_ah(dev, priv->pd, &av); - if (IS_ERR(ah)) { - ipoib_warn(priv, "ib_address_create failed %ld\n", - -PTR_ERR(ah)); - /* use original error */ - return PTR_ERR(ah); - } else { - spin_lock_irq(&priv->lock); - mcast->ah = ah; - spin_unlock_irq(&priv->lock); - - ipoib_dbg_mcast(priv, "MGID %pI6 AV %p, LID 0x%04x, SL %d\n", - mcast->mcmember.mgid.raw, - mcast->ah->ah, - be16_to_cpu(mcast->mcmember.mlid), - mcast->mcmember.sl); - } + memset(&av, 0, sizeof(av)); + av.type = rdma_ah_find_type(priv->ca, priv->port); + rdma_ah_set_dlid(&av, be16_to_cpu(mcast->mcmember.mlid)), + rdma_ah_set_port_num(&av, priv->port); + rdma_ah_set_sl(&av, mcast->mcmember.sl); + rdma_ah_set_static_rate(&av, mcast->mcmember.rate); + + rdma_ah_set_grh(&av, &mcast->mcmember.mgid, + be32_to_cpu(mcast->mcmember.flow_label), + 0, mcast->mcmember.hop_limit, + mcast->mcmember.traffic_class); + + ah = ipoib_create_ah(dev, priv->pd, &av); + if (IS_ERR(ah)) { + ipoib_warn(priv, "ib_address_create failed %ld\n", + -PTR_ERR(ah)); + /* use original error */ + return PTR_ERR(ah); } + spin_lock_irq(&priv->lock); + mcast->ah = ah; + spin_unlock_irq(&priv->lock); + + ipoib_dbg_mcast(priv, "MGID %pI6 AV %p, LID 0x%04x, SL %d\n", + mcast->mcmember.mgid.raw, + mcast->ah->ah, + be16_to_cpu(mcast->mcmember.mlid), + mcast->mcmember.sl); /* actually send any queued packets */ netif_tx_lock_bh(dev); @@ -331,7 +328,6 @@ void ipoib_mcast_carrier_on_task(struct work_struct *work) struct ipoib_dev_priv *priv = container_of(work, struct ipoib_dev_priv, carrier_on_task); struct ib_port_attr attr; - int ret; if (ib_query_port(priv->ca, priv->port, &attr) || attr.state != IB_PORT_ACTIVE) { @@ -344,11 +340,9 @@ void ipoib_mcast_carrier_on_task(struct work_struct *work) * because the broadcast group must always be joined first and is always * re-joined if the SM changes substantially. */ - ret = ipoib_check_sm_sendonly_fullmember_support(priv); - if (ret < 0) - pr_debug("%s failed query sm support for sendonly-fullmember (ret: %d)\n", - priv->dev->name, ret); - + priv->sm_fullmember_sendonly_support = + ib_sa_sendonly_fullmem_support(&ipoib_sa_client, + priv->ca, priv->port); /* * Take rtnl_lock to avoid racing with ipoib_stop() and * turning the carrier back on while a device is being @@ -375,7 +369,7 @@ static int ipoib_mcast_join_complete(int status, { struct ipoib_mcast *mcast = multicast->context; struct net_device *dev = mcast->dev; - struct ipoib_dev_priv *priv = netdev_priv(dev); + struct ipoib_dev_priv *priv = ipoib_priv(dev); ipoib_dbg_mcast(priv, "%sjoin completion for %pI6 (status %d)\n", test_bit(IPOIB_MCAST_FLAG_SENDONLY, &mcast->flags) ? @@ -477,7 +471,7 @@ out_locked: */ static int ipoib_mcast_join(struct net_device *dev, struct ipoib_mcast *mcast) { - struct ipoib_dev_priv *priv = netdev_priv(dev); + struct ipoib_dev_priv *priv = ipoib_priv(dev); struct ib_sa_multicast *multicast; struct ib_sa_mcmember_rec rec = { .join_state = 1 @@ -489,6 +483,9 @@ static int ipoib_mcast_join(struct net_device *dev, struct ipoib_mcast *mcast) !test_bit(IPOIB_FLAG_OPER_UP, &priv->flags)) return -EINVAL; + init_completion(&mcast->done); + set_bit(IPOIB_MCAST_FLAG_BUSY, &mcast->flags); + ipoib_dbg_mcast(priv, "joining MGID %pI6\n", mcast->mcmember.mgid.raw); rec.mgid = mcast->mcmember.mgid; @@ -647,8 +644,6 @@ void ipoib_mcast_join_task(struct work_struct *work) if (mcast->backoff == 1 || time_after_eq(jiffies, mcast->delay_until)) { /* Found the next unjoined group */ - init_completion(&mcast->done); - set_bit(IPOIB_MCAST_FLAG_BUSY, &mcast->flags); if (ipoib_mcast_join(dev, mcast)) { spin_unlock_irq(&priv->lock); return; @@ -668,17 +663,15 @@ out: queue_delayed_work(priv->wq, &priv->mcast_task, delay_until - jiffies); } - if (mcast) { - init_completion(&mcast->done); - set_bit(IPOIB_MCAST_FLAG_BUSY, &mcast->flags); + if (mcast) ipoib_mcast_join(dev, mcast); - } + spin_unlock_irq(&priv->lock); } void ipoib_mcast_start_thread(struct net_device *dev) { - struct ipoib_dev_priv *priv = netdev_priv(dev); + struct ipoib_dev_priv *priv = ipoib_priv(dev); unsigned long flags; ipoib_dbg_mcast(priv, "starting multicast thread\n"); @@ -690,7 +683,7 @@ void ipoib_mcast_start_thread(struct net_device *dev) int ipoib_mcast_stop_thread(struct net_device *dev) { - struct ipoib_dev_priv *priv = netdev_priv(dev); + struct ipoib_dev_priv *priv = ipoib_priv(dev); unsigned long flags; ipoib_dbg_mcast(priv, "stopping multicast thread\n"); @@ -706,7 +699,8 @@ int ipoib_mcast_stop_thread(struct net_device *dev) static int ipoib_mcast_leave(struct net_device *dev, struct ipoib_mcast *mcast) { - struct ipoib_dev_priv *priv = netdev_priv(dev); + struct ipoib_dev_priv *priv = ipoib_priv(dev); + struct rdma_netdev *rn = netdev_priv(dev); int ret = 0; if (test_and_clear_bit(IPOIB_MCAST_FLAG_BUSY, &mcast->flags)) @@ -720,8 +714,8 @@ static int ipoib_mcast_leave(struct net_device *dev, struct ipoib_mcast *mcast) mcast->mcmember.mgid.raw); /* Remove ourselves from the multicast group */ - ret = ib_detach_mcast(priv->qp, &mcast->mcmember.mgid, - be16_to_cpu(mcast->mcmember.mlid)); + ret = rn->detach_mcast(dev, priv->ca, &mcast->mcmember.mgid, + be16_to_cpu(mcast->mcmember.mlid)); if (ret) ipoib_warn(priv, "ib_detach_mcast failed (result = %d)\n", ret); } else if (!test_bit(IPOIB_MCAST_FLAG_SENDONLY, &mcast->flags)) @@ -762,7 +756,8 @@ void ipoib_mcast_remove_list(struct list_head *remove_list) void ipoib_mcast_send(struct net_device *dev, u8 *daddr, struct sk_buff *skb) { - struct ipoib_dev_priv *priv = netdev_priv(dev); + struct ipoib_dev_priv *priv = ipoib_priv(dev); + struct rdma_netdev *rn = netdev_priv(dev); struct ipoib_mcast *mcast; unsigned long flags; void *mgid = daddr + 4; @@ -825,7 +820,8 @@ void ipoib_mcast_send(struct net_device *dev, u8 *daddr, struct sk_buff *skb) } } spin_unlock_irqrestore(&priv->lock, flags); - ipoib_send(dev, skb, mcast->ah, IB_MULTICAST_QPN); + mcast->ah->last_send = rn->send(dev, skb, mcast->ah->ah, + IB_MULTICAST_QPN); if (neigh) ipoib_neigh_put(neigh); return; @@ -837,7 +833,7 @@ unlock: void ipoib_mcast_dev_flush(struct net_device *dev) { - struct ipoib_dev_priv *priv = netdev_priv(dev); + struct ipoib_dev_priv *priv = ipoib_priv(dev); LIST_HEAD(remove_list); struct ipoib_mcast *mcast, *tmcast; unsigned long flags; @@ -1029,7 +1025,7 @@ struct ipoib_mcast_iter *ipoib_mcast_iter_init(struct net_device *dev) int ipoib_mcast_iter_next(struct ipoib_mcast_iter *iter) { - struct ipoib_dev_priv *priv = netdev_priv(iter->dev); + struct ipoib_dev_priv *priv = ipoib_priv(iter->dev); struct rb_node *n; struct ipoib_mcast *mcast; int ret = 1; diff --git a/drivers/infiniband/ulp/ipoib/ipoib_netlink.c b/drivers/infiniband/ulp/ipoib/ipoib_netlink.c index cdc7df4fdb8a..28884781311b 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_netlink.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_netlink.c @@ -44,7 +44,7 @@ static const struct nla_policy ipoib_policy[IFLA_IPOIB_MAX + 1] = { static int ipoib_fill_info(struct sk_buff *skb, const struct net_device *dev) { - struct ipoib_dev_priv *priv = netdev_priv(dev); + struct ipoib_dev_priv *priv = ipoib_priv(dev); u16 val; if (nla_put_u16(skb, IFLA_IPOIB_PKEY, priv->pkey)) @@ -107,7 +107,7 @@ static int ipoib_new_child_link(struct net *src_net, struct net_device *dev, if (!pdev || pdev->type != ARPHRD_INFINIBAND) return -ENODEV; - ppriv = netdev_priv(pdev); + ppriv = ipoib_priv(pdev); if (test_bit(IPOIB_FLAG_SUBINTERFACE, &ppriv->flags)) { ipoib_warn(ppriv, "child creation disallowed for child devices\n"); @@ -129,7 +129,8 @@ static int ipoib_new_child_link(struct net *src_net, struct net_device *dev, */ child_pkey |= 0x8000; - err = __ipoib_vlan_add(ppriv, netdev_priv(dev), child_pkey, IPOIB_RTNL_CHILD); + err = __ipoib_vlan_add(ppriv, ipoib_priv(dev), + child_pkey, IPOIB_RTNL_CHILD); if (!err && data) err = ipoib_changelink(dev, tb, data); @@ -140,8 +141,8 @@ static void ipoib_unregister_child_dev(struct net_device *dev, struct list_head { struct ipoib_dev_priv *priv, *ppriv; - priv = netdev_priv(dev); - ppriv = netdev_priv(priv->parent); + priv = ipoib_priv(dev); + ppriv = ipoib_priv(priv->parent); down_write(&ppriv->vlan_rwsem); unregister_netdevice_queue(dev, head); @@ -161,7 +162,7 @@ static struct rtnl_link_ops ipoib_link_ops __read_mostly = { .maxtype = IFLA_IPOIB_MAX, .policy = ipoib_policy, .priv_size = sizeof(struct ipoib_dev_priv), - .setup = ipoib_setup, + .setup = ipoib_setup_common, .newlink = ipoib_new_child_link, .changelink = ipoib_changelink, .dellink = ipoib_unregister_child_dev, diff --git a/drivers/infiniband/ulp/ipoib/ipoib_verbs.c b/drivers/infiniband/ulp/ipoib/ipoib_verbs.c index 189dcd1709d2..bb64baf25309 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_verbs.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_verbs.c @@ -35,9 +35,10 @@ #include "ipoib.h" -int ipoib_mcast_attach(struct net_device *dev, u16 mlid, union ib_gid *mgid, int set_qkey) +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 = netdev_priv(dev); + struct ipoib_dev_priv *priv = ipoib_priv(dev); struct ib_qp_attr *qp_attr = NULL; int ret; u16 pkey_index; @@ -56,7 +57,7 @@ int ipoib_mcast_attach(struct net_device *dev, u16 mlid, union ib_gid *mgid, int goto out; /* set correct QKey for QP */ - qp_attr->qkey = priv->qkey; + 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); @@ -74,9 +75,20 @@ out: return ret; } +int ipoib_mcast_detach(struct net_device *dev, struct ib_device *hca, + union ib_gid *mgid, u16 mlid) +{ + struct ipoib_dev_priv *priv = ipoib_priv(dev); + int ret; + + ret = ib_detach_mcast(priv->qp, mgid, mlid); + + return ret; +} + int ipoib_init_qp(struct net_device *dev) { - struct ipoib_dev_priv *priv = netdev_priv(dev); + struct ipoib_dev_priv *priv = ipoib_priv(dev); int ret; struct ib_qp_attr qp_attr; int attr_mask; @@ -130,7 +142,7 @@ out_fail: int ipoib_transport_dev_init(struct net_device *dev, struct ib_device *ca) { - struct ipoib_dev_priv *priv = netdev_priv(dev); + struct ipoib_dev_priv *priv = ipoib_priv(dev); struct ib_qp_init_attr init_attr = { .cap = { .max_send_wr = ipoib_sendq_size, @@ -147,22 +159,6 @@ int ipoib_transport_dev_init(struct net_device *dev, struct ib_device *ca) int ret, size; int i; - priv->pd = ib_alloc_pd(priv->ca, 0); - if (IS_ERR(priv->pd)) { - printk(KERN_WARNING "%s: failed to allocate PD\n", ca->name); - return -ENODEV; - } - - /* - * the various IPoIB tasks assume they will never race against - * themselves, so always use a single thread workqueue - */ - priv->wq = alloc_ordered_workqueue("ipoib_wq", WQ_MEM_RECLAIM); - if (!priv->wq) { - printk(KERN_WARNING "ipoib: failed to allocate device WQ\n"); - goto out_free_pd; - } - size = ipoib_recvq_size + 1; ret = ipoib_cm_dev_init(dev); if (!ret) { @@ -173,7 +169,7 @@ int ipoib_transport_dev_init(struct net_device *dev, struct ib_device *ca) size += ipoib_recvq_size * ipoib_max_conn_qp; } else if (ret != -ENOSYS) - goto out_free_wq; + return -ENODEV; cq_attr.cqe = size; priv->recv_cq = ib_create_cq(priv->ca, ipoib_ib_completion, NULL, @@ -212,10 +208,6 @@ int ipoib_transport_dev_init(struct net_device *dev, struct ib_device *ca) goto out_free_send_cq; } - priv->dev->dev_addr[1] = (priv->qp->qp_num >> 16) & 0xff; - priv->dev->dev_addr[2] = (priv->qp->qp_num >> 8) & 0xff; - priv->dev->dev_addr[3] = (priv->qp->qp_num ) & 0xff; - for (i = 0; i < MAX_SKB_FRAGS + 1; ++i) priv->tx_sge[i].lkey = priv->pd->local_dma_lkey; @@ -247,26 +239,18 @@ out_free_recv_cq: out_cm_dev_cleanup: ipoib_cm_dev_cleanup(dev); -out_free_wq: - destroy_workqueue(priv->wq); - priv->wq = NULL; - -out_free_pd: - ib_dealloc_pd(priv->pd); - return -ENODEV; } void ipoib_transport_dev_cleanup(struct net_device *dev) { - struct ipoib_dev_priv *priv = netdev_priv(dev); + struct ipoib_dev_priv *priv = ipoib_priv(dev); if (priv->qp) { if (ib_destroy_qp(priv->qp)) ipoib_warn(priv, "ib_qp_destroy failed\n"); priv->qp = NULL; - clear_bit(IPOIB_PKEY_ASSIGNED, &priv->flags); } if (ib_destroy_cq(priv->send_cq)) @@ -274,16 +258,6 @@ void ipoib_transport_dev_cleanup(struct net_device *dev) if (ib_destroy_cq(priv->recv_cq)) ipoib_warn(priv, "ib_cq_destroy (recv) failed\n"); - - ipoib_cm_dev_cleanup(dev); - - if (priv->wq) { - flush_workqueue(priv->wq); - destroy_workqueue(priv->wq); - priv->wq = NULL; - } - - ib_dealloc_pd(priv->pd); } void ipoib_event(struct ib_event_handler *handler, diff --git a/drivers/infiniband/ulp/ipoib/ipoib_vlan.c b/drivers/infiniband/ulp/ipoib/ipoib_vlan.c index 3e10e3dac2e7..36dc4fcaa3cd 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_vlan.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_vlan.c @@ -44,7 +44,7 @@ static ssize_t show_parent(struct device *d, struct device_attribute *attr, char *buf) { struct net_device *dev = to_net_dev(d); - struct ipoib_dev_priv *priv = netdev_priv(dev); + struct ipoib_dev_priv *priv = ipoib_priv(dev); return sprintf(buf, "%s\n", priv->parent->name); } @@ -86,8 +86,6 @@ int __ipoib_vlan_add(struct ipoib_dev_priv *ppriv, struct ipoib_dev_priv *priv, goto register_failed; } - ipoib_create_debug_files(priv->dev); - /* RTNL childs don't need proprietary sysfs entries */ if (type == IPOIB_LEGACY_CHILD) { if (ipoib_cm_add_mode_attr(priv->dev)) @@ -108,7 +106,6 @@ int __ipoib_vlan_add(struct ipoib_dev_priv *ppriv, struct ipoib_dev_priv *priv, sysfs_failed: result = -ENOMEM; - ipoib_delete_debug_files(priv->dev); unregister_netdevice(priv->dev); register_failed: @@ -128,14 +125,15 @@ int ipoib_vlan_add(struct net_device *pdev, unsigned short pkey) if (!capable(CAP_NET_ADMIN)) return -EPERM; - ppriv = netdev_priv(pdev); + ppriv = ipoib_priv(pdev); if (test_bit(IPOIB_FLAG_GOING_DOWN, &ppriv->flags)) return -EPERM; snprintf(intf_name, sizeof intf_name, "%s.%04x", ppriv->dev->name, pkey); - priv = ipoib_intf_alloc(intf_name); + + priv = ipoib_intf_alloc(ppriv->ca, ppriv->port, intf_name); if (!priv) return -ENOMEM; @@ -183,7 +181,7 @@ int ipoib_vlan_delete(struct net_device *pdev, unsigned short pkey) if (!capable(CAP_NET_ADMIN)) return -EPERM; - ppriv = netdev_priv(pdev); + ppriv = ipoib_priv(pdev); if (test_bit(IPOIB_FLAG_GOING_DOWN, &ppriv->flags)) return -EPERM; |