IB/SA: Check dlid before SA agent queries for ClassPortInfo

SA queries SM for class port info when there is a LID_CHANGE event.

When a base lid is configured before fm is started ie when smlid is
not yet assigned, SA handles the LID_CHANGE event and tries query SM
with lid 0. This will cause an hang.

[ 1106.958820] INFO: task kworker/2:0:23 blocked for more than 120 seconds.
[ 1106.965082] Tainted: G O 4.12.0+ #1
[ 1106.969602] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables
 this message.
[ 1106.977227] kworker/2:0 D 0 23 2 0x00000000
[ 1106.977250] Workqueue: infiniband update_ib_cpi [ib_core]
[ 1106.977261] Call Trace:
[ 1106.977273] __schedule+0x28e/0x860
[ 1106.977285] schedule+0x36/0x80
[ 1106.977298] schedule_timeout+0x1a3/0x2e0
[ 1106.977310] ? radix_tree_iter_tag_clear+0x1b/0x20
[ 1106.977322] ? idr_alloc+0x64/0x90
[ 1106.977334] wait_for_completion+0xe3/0x140
[ 1106.977347] ? wake_up_q+0x80/0x80
[ 1106.977369] update_ib_cpi+0x163/0x210 [ib_core]
[ 1106.977381] process_one_work+0x147/0x370
[ 1106.977394] worker_thread+0x4a/0x390
[ 1106.977406] kthread+0x109/0x140
[ 1106.977418] ? process_one_work+0x370/0x370
[ 1106.977430] ? kthread_park+0x60/0x60
[ 1106.977443] ret_from_fork+0x22/0x30

Always ensure a proper smlid is assigned before querying SM for cpi.

Fixes: ee1c60b1bff ("IB/SA: Modify SA to implicitly cache Class Port info")
Reviewed-by: Ira Weiny <ira.weiny@intel.com>
Signed-off-by: Venkata Sandeep Dhanalakota <venkata.s.dhanalakota@intel.com>
Signed-off-by: Dennis Dalessandro <dennis.dalessandro@intel.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>

diff --git a/drivers/infiniband/core/sa_query.c b/drivers/infiniband/core/sa_query.c
index 7cd37e77debb7ec4892babdce1c4040c7ba46f2c..8cf15d4a8ac438db82971ad3d3bc16649a5ed6da 100644 (file)
--- a/drivers/infiniband/core/sa_query.c
+++ b/drivers/infiniband/core/sa_query.c
@@ -1345,6 +1345,7 @@ EXPORT_SYMBOL(ib_init_ah_attr_from_path);
 
 static int alloc_mad(struct ib_sa_query *query, gfp_t gfp_mask)
 {
+       struct rdma_ah_attr ah_attr;
        unsigned long flags;
 
        spin_lock_irqsave(&query->port->ah_lock, flags);
@@ -1356,6 +1357,15 @@ static int alloc_mad(struct ib_sa_query *query, gfp_t gfp_mask)
        query->sm_ah = query->port->sm_ah;
        spin_unlock_irqrestore(&query->port->ah_lock, flags);
 
+       /*
+        * Always check if sm_ah has valid dlid assigned,
+        * before querying for class port info
+        */
+       if ((rdma_query_ah(query->sm_ah->ah, &ah_attr) < 0) ||
+           !rdma_is_valid_unicast_lid(&ah_attr)) {
+               kref_put(&query->sm_ah->ref, free_sm_ah);
+               return -EAGAIN;
+       }
        query->mad_buf = ib_create_send_mad(query->port->agent, 1,
                                            query->sm_ah->pkey_index,
                                            0, IB_MGMT_SA_HDR, IB_MGMT_SA_DATA,

diff --git a/include/rdma/opa_addr.h b/include/rdma/opa_addr.h
index f68fca2966313002a216a1557428854f7ae22db3..2bbb7a67e643986354a1d6bf5b04402b539764d2 100644 (file)
--- a/include/rdma/opa_addr.h
+++ b/include/rdma/opa_addr.h
@@ -114,4 +114,20 @@ static inline u32 opa_get_mcast_base(u32 nr_top_bits)
        return (be32_to_cpu(OPA_LID_PERMISSIVE) << (32 - nr_top_bits));
 }
 
+/* Check for a valid unicast LID for non-SM traffic types */
+static inline bool rdma_is_valid_unicast_lid(struct rdma_ah_attr *attr)
+{
+       if (attr->type == RDMA_AH_ATTR_TYPE_IB) {
+               if (!rdma_ah_get_dlid(attr) ||
+                   rdma_ah_get_dlid(attr) >=
+                   be32_to_cpu(IB_MULTICAST_LID_BASE))
+                       return false;
+       } else if (attr->type == RDMA_AH_ATTR_TYPE_OPA) {
+               if (!rdma_ah_get_dlid(attr) ||
+                   rdma_ah_get_dlid(attr) >=
+                   opa_get_mcast_base(OPA_MCAST_NR))
+                       return false;
+       }
+       return true;
+}
 #endif /* OPA_ADDR_H */