LU-7734 lnet: fix routing selection

[fs/lustre-release.git] / lnet / lnet / lib-ptl.c

diff --git a/lnet/lnet/lib-ptl.c b/lnet/lnet/lib-ptl.c
index c89e013..0b31878 100644 (file)
--- a/lnet/lnet/lib-ptl.c
+++ b/lnet/lnet/lib-ptl.c
@@ -39,9 +39,9 @@
 #include <lnet/lib-lnet.h>
 
 /* NB: add /proc interfaces in upcoming patches */
-int    portal_rotor    = LNET_PTL_ROTOR_HASH_RT;
-CFS_MODULE_PARM(portal_rotor, "i", int, 0644,
-               "redirect PUTs to different cpu-partitions");
+int portal_rotor = LNET_PTL_ROTOR_HASH_RT;
+module_param(portal_rotor, int, 0644);
+MODULE_PARM_DESC(portal_rotor, "redirect PUTs to different cpu-partitions");
 
 static int
 lnet_ptl_match_type(unsigned int index, lnet_process_id_t match_id,
@@ -184,7 +184,7 @@ lnet_try_match_md(lnet_libmd_t *md,
                mlength = info->mi_rlength;
        } else if ((md->md_options & LNET_MD_TRUNCATE) == 0) {
                /* this packet _really_ is too big */
-               CERROR("Matching packet from %s, match "LPU64
+               CERROR("Matching packet from %s, match %llu"
                       " length %d too big: %d left, %d allowed\n",
                       libcfs_id2str(info->mi_id), info->mi_mbits,
                       info->mi_rlength, md->md_length - offset, mlength);
@@ -194,7 +194,7 @@ lnet_try_match_md(lnet_libmd_t *md,
 
        /* Commit to this ME/MD */
        CDEBUG(D_NET, "Incoming %s index %x from %s of "
-              "length %d/%d into md "LPX64" [%d] + %d\n",
+              "length %d/%d into md %#llx [%d] + %d\n",
               (info->mi_opc == LNET_MD_OP_PUT) ? "put" : "get",
               info->mi_portal, libcfs_id2str(info->mi_id), mlength,
               info->mi_rlength, md->md_lh.lh_cookie, md->md_niov, offset);
@@ -222,7 +222,7 @@ lnet_match2mt(struct lnet_portal *ptl, lnet_process_id_t id, __u64 mbits)
 
        /* if it's a unique portal, return match-table hashed by NID */
        return lnet_ptl_is_unique(ptl) ?
-              ptl->ptl_mtables[lnet_cpt_of_nid(id.nid)] : NULL;
+              ptl->ptl_mtables[lnet_cpt_of_nid(id.nid, NULL)] : NULL;
 }
 
 struct lnet_match_table *
@@ -292,7 +292,7 @@ lnet_mt_of_match(struct lnet_match_info *info, struct lnet_msg *msg)
 
        rotor = ptl->ptl_rotor++; /* get round-robin factor */
        if (portal_rotor == LNET_PTL_ROTOR_HASH_RT && routed)
-               cpt = lnet_cpt_of_nid(msg->msg_hdr.src_nid);
+               cpt = info->mi_cpt;
        else
                cpt = rotor % LNET_CPT_NUMBER;
 
@@ -367,7 +367,7 @@ lnet_mt_match_head(struct lnet_match_table *mtable,
 
                LASSERT(lnet_ptl_is_unique(ptl));
                hash = hash_long(hash, LNET_MT_HASH_BITS);
-               return &mtable->mt_mhash[hash];
+               return &mtable->mt_mhash[hash & LNET_MT_HASH_MASK];
        }
 }
 
@@ -567,7 +567,7 @@ lnet_ptl_match_md(struct lnet_match_info *info, struct lnet_msg *msg)
        int                     rc;
 
        CDEBUG(D_NET, "Request from %s of length %d into portal %d "
-              "MB="LPX64"\n", libcfs_id2str(info->mi_id),
+              "MB=%#llx\n", libcfs_id2str(info->mi_id),
               info->mi_rlength, info->mi_portal, info->mi_mbits);
 
        if (info->mi_portal >= the_lnet.ln_nportals) {
@@ -615,7 +615,7 @@ lnet_ptl_match_md(struct lnet_match_info *info, struct lnet_msg *msg)
                lnet_ptl_unlock(ptl);
                lnet_res_unlock(mtable->mt_cpt);
                rc = LNET_MATCHMD_NONE;
-       } else  {
+       } else  {
                lnet_res_unlock(mtable->mt_cpt);
                rc = lnet_ptl_match_delay(ptl, info, msg);
        }
@@ -623,7 +623,7 @@ lnet_ptl_match_md(struct lnet_match_info *info, struct lnet_msg *msg)
        /* LNET_MATCHMD_NONE means msg was added to the delay queue */
        if (rc & LNET_MATCHMD_NONE) {
                CDEBUG(D_NET,
-                      "Delaying %s from %s ptl %d MB "LPX64" off %d len %d\n",
+                      "Delaying %s from %s ptl %d MB %#llx off %d len %d\n",
                       info->mi_opc == LNET_MD_OP_PUT ? "PUT" : "GET",
                       libcfs_id2str(info->mi_id), info->mi_portal,
                       info->mi_mbits, info->mi_roffset, info->mi_rlength);
@@ -682,7 +682,8 @@ lnet_ptl_attach_md(lnet_me_t *me, lnet_libmd_t *md,
                LASSERT(msg->msg_rx_delayed || head == &ptl->ptl_msg_stealing);
 
                hdr   = &msg->msg_hdr;
-               info.mi_id.nid  = hdr->src_nid;
+               /* Multi-Rail: Primary peer NID */
+               info.mi_id.nid  = msg->msg_initiator;
                info.mi_id.pid  = hdr->src_pid;
                info.mi_opc     = LNET_MD_OP_PUT;
                info.mi_portal  = hdr->msg.put.ptl_index;
@@ -714,7 +715,7 @@ lnet_ptl_attach_md(lnet_me_t *me, lnet_libmd_t *md,
                        list_add_tail(&msg->msg_list, matches);
 
                        CDEBUG(D_NET, "Resuming delayed PUT from %s portal %d "
-                              "match "LPU64" offset %d length %d.\n",
+                              "match %llu offset %d length %d.\n",
                               libcfs_id2str(info.mi_id),
                               info.mi_portal, info.mi_mbits,
                               info.mi_roffset, info.mi_rlength);
@@ -889,7 +890,7 @@ lnet_portals_create(void)
  *
  * \param portal Index of the portal to enable the lazy attribute on.
  *
- * \retval 0       On success.
+ * \retval 0      On success.
  * \retval -EINVAL If \a portal is not a valid index.
  */
 int
@@ -941,7 +942,7 @@ lnet_clear_lazy_portal(struct lnet_ni *ni, int portal, char *reason)
                /* grab all messages which are on the NI passed in */
                list_for_each_entry_safe(msg, tmp, &ptl->ptl_msg_delayed,
                                         msg_list) {
-                       if (msg->msg_rxpeer->lp_ni == ni)
+                       if (msg->msg_txni == ni || msg->msg_rxni == ni)
                                list_move(&msg->msg_list, &zombies);
                }
        } else {
@@ -970,7 +971,7 @@ lnet_clear_lazy_portal(struct lnet_ni *ni, int portal, char *reason)
  *
  * \param portal Index of the portal to disable the lazy attribute on.
  *
- * \retval 0       On success.
+ * \retval 0      On success.
  * \retval -EINVAL If \a portal is not a valid index.
  */
 int