IB/mad: Use IDR for agent IDs

Allocate agent IDs from a global IDR instead of an atomic variable.
This eliminates the possibility of reusing an ID which is already in
use after 4 billion registrations.  We limit the assigned ID to be less
than 2^24 as the mlx4 driver uses the most significant byte of the agent
ID to store the slave number.  Users unlucky enough to see a collision
between agent numbers and slave numbers see messages like:

 mlx4_ib: egress mad has non-null tid msb:1 class:4 slave:0

and the MAD layer stops working.

We look up the agent under protection of the RCU lock, which means we
have to free the agent using kfree_rcu, and only increment the reference
counter if it is not 0.

Signed-off-by: Matthew Wilcox <mawilcox@microsoft.com>
Reported-by: Hans Westgaard Ry <hans.westgaard.ry@oracle.com>
Acked-by: Jack Morgenstein <jackm@dev.mellanox.co.il>
Tested-by: Jack Morgenstein <jackm@dev.mellanox.co.il>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>

1 files changed, 4 insertions, 3 deletions

diff --git a/drivers/infiniband/core/mad_priv.h b/drivers/infiniband/core/mad_priv.h
index 28669f6419e1..d84ae1671898 100644
--- a/drivers/infiniband/core/mad_priv.h
+++ b/drivers/infiniband/core/mad_priv.h
@@ -89,7 +89,6 @@ struct ib_rmpp_segment {
 };
 
 struct ib_mad_agent_private {
-	struct list_head agent_list;
 	struct ib_mad_agent agent;
 	struct ib_mad_reg_req *reg_req;
 	struct ib_mad_qp_info *qp_info;
@@ -105,7 +104,10 @@ struct ib_mad_agent_private {
 	struct list_head rmpp_list;
 
 	atomic_t refcount;
-	struct completion comp;
+	union {
+		struct completion comp;
+		struct rcu_head rcu;
+	};
 };
 
 struct ib_mad_snoop_private {
@@ -203,7 +205,6 @@ struct ib_mad_port_private {
 
 	spinlock_t reg_lock;
 	struct ib_mad_mgmt_version_table version[MAX_MGMT_VERSION];
-	struct list_head agent_list;
 	struct workqueue_struct *wq;
 	struct ib_mad_qp_info qp_info[IB_MAD_QPS_CORE];
 };