LU-7734 lnet: handle N NIs to 1 LND peer

[fs/lustre-release.git] / lnet / klnds / o2iblnd / o2iblnd.c

diff --git a/lnet/klnds/o2iblnd/o2iblnd.c b/lnet/klnds/o2iblnd/o2iblnd.c
index b1b3239..c07d4d1 100644 (file)
--- a/lnet/klnds/o2iblnd/o2iblnd.c
+++ b/lnet/klnds/o2iblnd/o2iblnd.c
@@ -23,7 +23,7 @@
  * Copyright (c) 2007, 2010, Oracle and/or its affiliates. All rights reserved.
  * Use is subject to license terms.
  *
- * Copyright (c) 2011, 2015, Intel Corporation.
+ * Copyright (c) 2011, 2016, Intel Corporation.
  */
 /*
  * This file is part of Lustre, http://www.lustre.org/
@@ -131,7 +131,6 @@ static int
 kiblnd_unpack_rd(kib_msg_t *msg, int flip)
 {
         kib_rdma_desc_t   *rd;
-       int msg_size;
         int                nob;
         int                n;
         int                i;
@@ -148,7 +147,14 @@ kiblnd_unpack_rd(kib_msg_t *msg, int flip)
                 __swab32s(&rd->rd_nfrags);
         }
 
-       n = rd->rd_nfrags;
+        n = rd->rd_nfrags;
+
+        if (n <= 0 || n > IBLND_MAX_RDMA_FRAGS) {
+                CERROR("Bad nfrags: %d, should be 0 < n <= %d\n",
+                       n, IBLND_MAX_RDMA_FRAGS);
+                return 1;
+        }
+
         nob = offsetof (kib_msg_t, ibm_u) +
               kiblnd_rd_msg_size(rd, msg->ibm_type, n);
 
@@ -158,13 +164,6 @@ kiblnd_unpack_rd(kib_msg_t *msg, int flip)
                 return 1;
         }
 
-       msg_size = kiblnd_rd_size(rd);
-       if (msg_size <= 0 || msg_size > LNET_MAX_PAYLOAD) {
-               CERROR("Bad msg_size: %d, should be 0 < n <= %d\n",
-                      msg_size, LNET_MAX_PAYLOAD);
-               return 1;
-       }
-
         if (!flip)
                 return 0;
 
@@ -318,7 +317,7 @@ kiblnd_create_peer(lnet_ni_t *ni, kib_peer_t **peerp, lnet_nid_t nid)
 {
        kib_peer_t      *peer;
        kib_net_t       *net = ni->ni_data;
-       int             cpt = lnet_cpt_of_nid(nid);
+       int             cpt = lnet_cpt_of_nid(nid, ni);
        unsigned long   flags;
 
        LASSERT(net != NULL);
@@ -335,7 +334,7 @@ kiblnd_create_peer(lnet_ni_t *ni, kib_peer_t **peerp, lnet_nid_t nid)
        peer->ibp_error = 0;
        peer->ibp_last_alive = 0;
        peer->ibp_max_frags = kiblnd_cfg_rdma_frags(peer->ibp_ni);
-       peer->ibp_queue_depth = ni->ni_peertxcredits;
+       peer->ibp_queue_depth = ni->ni_net->net_tunables.lct_peer_tx_credits;
        atomic_set(&peer->ibp_refcount, 1);     /* 1 ref for caller */
 
        INIT_LIST_HEAD(&peer->ibp_list);        /* not in the peer table yet */
@@ -377,7 +376,7 @@ kiblnd_destroy_peer (kib_peer_t *peer)
 }
 
 kib_peer_t *
-kiblnd_find_peer_locked (lnet_nid_t nid)
+kiblnd_find_peer_locked(struct lnet_ni *ni, lnet_nid_t nid)
 {
        /* the caller is responsible for accounting the additional reference
         * that this creates */
@@ -390,7 +389,14 @@ kiblnd_find_peer_locked (lnet_nid_t nid)
                peer = list_entry(tmp, kib_peer_t, ibp_list);
                LASSERT(!kiblnd_peer_idle(peer));
 
-               if (peer->ibp_nid != nid)
+               /*
+                * Match a peer if its NID and the NID of the local NI it
+                * communicates over are the same. Otherwise don't match
+                * the peer, which will result in a new lnd peer being
+                * created.
+                */
+               if (peer->ibp_nid != nid ||
+                   peer->ibp_ni->ni_nid != ni->ni_nid)
                        continue;
 
                CDEBUG(D_NET, "got peer [%p] -> %s (%d) version: %x\n",
@@ -723,7 +729,7 @@ kiblnd_create_conn(kib_peer_t *peer, struct rdma_cm_id *cmid,
 
        dev = net->ibn_dev;
 
-       cpt = lnet_cpt_of_nid(peer->ibp_nid);
+       cpt = lnet_cpt_of_nid(peer->ibp_nid, peer->ibp_ni);
        sched = kiblnd_data.kib_scheds[cpt];
 
        LASSERT(sched->ibs_nthreads > 0);
@@ -1150,7 +1156,7 @@ kiblnd_query(lnet_ni_t *ni, lnet_nid_t nid, cfs_time_t *when)
 
        read_lock_irqsave(glock, flags);
 
-       peer = kiblnd_find_peer_locked(nid);
+       peer = kiblnd_find_peer_locked(ni, nid);
        if (peer != NULL)
                last_alive = peer->ibp_last_alive;
 
@@ -1392,7 +1398,7 @@ kiblnd_find_rd_dma_mr(struct lnet_ni *ni, kib_rdma_desc_t *rd,
        int     mod;
        __u16   nfrags;
 
-       tunables = &ni->ni_lnd_tunables->lt_tun_u.lt_o2ib;
+       tunables = &ni->ni_lnd_tunables.lnd_tun_u.lnd_o2ib;
        mod = tunables->lnd_map_on_demand;
        nfrags = (negotiated_nfrags != -1) ? negotiated_nfrags : mod;
 
@@ -1537,7 +1543,10 @@ static int kiblnd_alloc_freg_pool(kib_fmr_poolset_t *fps, kib_fmr_pool_t *fpo)
                        goto out_middle;
                }
 
-               frd->frd_valid = true;
+               /* There appears to be a bug in MLX5 code where you must
+                * invalidate the rkey of a new FastReg pool before first
+                * using it. Thus, I am marking the FRD invalid here. */
+               frd->frd_valid = false;
 
                list_add_tail(&frd->frd_list, &fpo->fast_reg.fpo_pool_list);
                fpo->fast_reg.fpo_pool_size++;
@@ -2393,7 +2402,7 @@ kiblnd_net_init_pools(kib_net_t *net, lnet_ni_t *ni, __u32 *cpts, int ncpts)
        int             rc;
        int             i;
 
-       tunables = &ni->ni_lnd_tunables->lt_tun_u.lt_o2ib;
+       tunables = &ni->ni_lnd_tunables.lnd_tun_u.lnd_o2ib;
 
        read_lock_irqsave(&kiblnd_data.kib_global_lock, flags);
        if (tunables->lnd_map_on_demand == 0) {
@@ -3174,8 +3183,9 @@ kiblnd_startup (lnet_ni_t *ni)
         unsigned long             flags;
         int                       rc;
        int                       newdev;
+       int                       node_id;
 
-        LASSERT (ni->ni_lnd == &the_o2iblnd);
+        LASSERT (ni->ni_net->net_lnd == &the_o2iblnd);
 
         if (kiblnd_data.kib_init == IBLND_INIT_NOTHING) {
                 rc = kiblnd_base_startup();
@@ -3217,13 +3227,16 @@ kiblnd_startup (lnet_ni_t *ni)
        newdev = ibdev == NULL;
        /* hmm...create kib_dev even for alias */
        if (ibdev == NULL || strcmp(&ibdev->ibd_ifname[0], ifname) != 0)
-                ibdev = kiblnd_create_dev(ifname);
+               ibdev = kiblnd_create_dev(ifname);
 
-        if (ibdev == NULL)
-                goto failed;
+       if (ibdev == NULL)
+               goto failed;
+
+       node_id = dev_to_node(ibdev->ibd_hdev->ibh_ibdev->dma_device);
+       ni->dev_cpt = cfs_cpt_of_node(lnet_cpt_table(), node_id);
 
-        net->ibn_dev = ibdev;
-        ni->ni_nid = LNET_MKNID(LNET_NIDNET(ni->ni_nid), ibdev->ibd_ifip);
+       net->ibn_dev = ibdev;
+       ni->ni_nid = LNET_MKNID(LNET_NIDNET(ni->ni_nid), ibdev->ibd_ifip);
 
        rc = kiblnd_dev_start_threads(ibdev, newdev,
                                      ni->ni_cpts, ni->ni_ncpts);