summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
authorJason Gunthorpe <jgg@nvidia.com>2020-10-26 15:25:49 +0100
committerJason Gunthorpe <jgg@nvidia.com>2020-10-28 13:14:49 +0100
commit071ba4cc559de47160761b9500b72e8fa09d923d (patch)
tree0433f309f2aae8e868f09260cd1647671236af85
parentRDMA/uverbs: Fix false error in query gid IOCTL (diff)
downloadlinux-071ba4cc559de47160761b9500b72e8fa09d923d.tar.xz
linux-071ba4cc559de47160761b9500b72e8fa09d923d.zip
RDMA: Add rdma_connect_locked()
There are two flows for handling RDMA_CM_EVENT_ROUTE_RESOLVED, either the handler triggers a completion and another thread does rdma_connect() or the handler directly calls rdma_connect(). In all cases rdma_connect() needs to hold the handler_mutex, but when handler's are invoked this is already held by the core code. This causes ULPs using the 2nd method to deadlock. Provide a rdma_connect_locked() and have all ULPs call it from their handlers. Link: https://lore.kernel.org/r/0-v2-53c22d5c1405+33-rdma_connect_locking_jgg@nvidia.com Reported-and-tested-by: Guoqing Jiang <guoqing.jiang@cloud.ionos.com> Fixes: 2a7cec538169 ("RDMA/cma: Fix locking for the RDMA_CM_CONNECT state") Acked-by: Santosh Shilimkar <santosh.shilimkar@oracle.com> Acked-by: Jack Wang <jinpu.wang@cloud.ionos.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Max Gurtovoy <mgurtovoy@nvidia.com> Reviewed-by: Sagi Grimberg <sagi@grimberg.me> Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
-rw-r--r--drivers/infiniband/core/cma.c48
-rw-r--r--drivers/infiniband/ulp/iser/iser_verbs.c2
-rw-r--r--drivers/infiniband/ulp/rtrs/rtrs-clt.c4
-rw-r--r--drivers/nvme/host/rdma.c4
-rw-r--r--include/rdma/rdma_cm.h14
-rw-r--r--net/rds/ib_cm.c5
6 files changed, 48 insertions, 29 deletions
diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c
index 7c2ab1f2fbea..a77750b8954d 100644
--- a/drivers/infiniband/core/cma.c
+++ b/drivers/infiniband/core/cma.c
@@ -405,10 +405,10 @@ static int cma_comp_exch(struct rdma_id_private *id_priv,
/*
* The FSM uses a funny double locking where state is protected by both
* the handler_mutex and the spinlock. State is not allowed to change
- * away from a handler_mutex protected value without also holding
+ * to/from a handler_mutex protected value without also holding
* handler_mutex.
*/
- if (comp == RDMA_CM_CONNECT)
+ if (comp == RDMA_CM_CONNECT || exch == RDMA_CM_CONNECT)
lockdep_assert_held(&id_priv->handler_mutex);
spin_lock_irqsave(&id_priv->lock, flags);
@@ -4038,17 +4038,23 @@ out:
return ret;
}
-int rdma_connect(struct rdma_cm_id *id, struct rdma_conn_param *conn_param)
+/**
+ * rdma_connect_locked - Initiate an active connection request.
+ * @id: Connection identifier to connect.
+ * @conn_param: Connection information used for connected QPs.
+ *
+ * Same as rdma_connect() but can only be called from the
+ * RDMA_CM_EVENT_ROUTE_RESOLVED handler callback.
+ */
+int rdma_connect_locked(struct rdma_cm_id *id,
+ struct rdma_conn_param *conn_param)
{
struct rdma_id_private *id_priv =
container_of(id, struct rdma_id_private, id);
int ret;
- mutex_lock(&id_priv->handler_mutex);
- if (!cma_comp_exch(id_priv, RDMA_CM_ROUTE_RESOLVED, RDMA_CM_CONNECT)) {
- ret = -EINVAL;
- goto err_unlock;
- }
+ if (!cma_comp_exch(id_priv, RDMA_CM_ROUTE_RESOLVED, RDMA_CM_CONNECT))
+ return -EINVAL;
if (!id->qp) {
id_priv->qp_num = conn_param->qp_num;
@@ -4066,11 +4072,33 @@ int rdma_connect(struct rdma_cm_id *id, struct rdma_conn_param *conn_param)
ret = -ENOSYS;
if (ret)
goto err_state;
- mutex_unlock(&id_priv->handler_mutex);
return 0;
err_state:
cma_comp_exch(id_priv, RDMA_CM_CONNECT, RDMA_CM_ROUTE_RESOLVED);
-err_unlock:
+ return ret;
+}
+EXPORT_SYMBOL(rdma_connect_locked);
+
+/**
+ * rdma_connect - Initiate an active connection request.
+ * @id: Connection identifier to connect.
+ * @conn_param: Connection information used for connected QPs.
+ *
+ * Users must have resolved a route for the rdma_cm_id to connect with by having
+ * called rdma_resolve_route before calling this routine.
+ *
+ * This call will either connect to a remote QP or obtain remote QP information
+ * for unconnected rdma_cm_id's. The actual operation is based on the
+ * rdma_cm_id's port space.
+ */
+int rdma_connect(struct rdma_cm_id *id, struct rdma_conn_param *conn_param)
+{
+ struct rdma_id_private *id_priv =
+ container_of(id, struct rdma_id_private, id);
+ int ret;
+
+ mutex_lock(&id_priv->handler_mutex);
+ ret = rdma_connect_locked(id, conn_param);
mutex_unlock(&id_priv->handler_mutex);
return ret;
}
diff --git a/drivers/infiniband/ulp/iser/iser_verbs.c b/drivers/infiniband/ulp/iser/iser_verbs.c
index 2f3ebc0a75d9..2bd18b006893 100644
--- a/drivers/infiniband/ulp/iser/iser_verbs.c
+++ b/drivers/infiniband/ulp/iser/iser_verbs.c
@@ -620,7 +620,7 @@ static void iser_route_handler(struct rdma_cm_id *cma_id)
conn_param.private_data = (void *)&req_hdr;
conn_param.private_data_len = sizeof(struct iser_cm_hdr);
- ret = rdma_connect(cma_id, &conn_param);
+ ret = rdma_connect_locked(cma_id, &conn_param);
if (ret) {
iser_err("failure connecting: %d\n", ret);
goto failure;
diff --git a/drivers/infiniband/ulp/rtrs/rtrs-clt.c b/drivers/infiniband/ulp/rtrs/rtrs-clt.c
index 776e89231c52..f298adc02acb 100644
--- a/drivers/infiniband/ulp/rtrs/rtrs-clt.c
+++ b/drivers/infiniband/ulp/rtrs/rtrs-clt.c
@@ -1674,9 +1674,9 @@ static int rtrs_rdma_route_resolved(struct rtrs_clt_con *con)
uuid_copy(&msg.sess_uuid, &sess->s.uuid);
uuid_copy(&msg.paths_uuid, &clt->paths_uuid);
- err = rdma_connect(con->c.cm_id, &param);
+ err = rdma_connect_locked(con->c.cm_id, &param);
if (err)
- rtrs_err(clt, "rdma_connect(): %d\n", err);
+ rtrs_err(clt, "rdma_connect_locked(): %d\n", err);
return err;
}
diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c
index aad829a2b50d..8bbc48cc45dc 100644
--- a/drivers/nvme/host/rdma.c
+++ b/drivers/nvme/host/rdma.c
@@ -1890,10 +1890,10 @@ static int nvme_rdma_route_resolved(struct nvme_rdma_queue *queue)
priv.hsqsize = cpu_to_le16(queue->ctrl->ctrl.sqsize);
}
- ret = rdma_connect(queue->cm_id, &param);
+ ret = rdma_connect_locked(queue->cm_id, &param);
if (ret) {
dev_err(ctrl->ctrl.device,
- "rdma_connect failed (%d).\n", ret);
+ "rdma_connect_locked failed (%d).\n", ret);
goto out_destroy_queue_ib;
}
diff --git a/include/rdma/rdma_cm.h b/include/rdma/rdma_cm.h
index c672ae1da26b..32a67af18415 100644
--- a/include/rdma/rdma_cm.h
+++ b/include/rdma/rdma_cm.h
@@ -227,19 +227,9 @@ void rdma_destroy_qp(struct rdma_cm_id *id);
int rdma_init_qp_attr(struct rdma_cm_id *id, struct ib_qp_attr *qp_attr,
int *qp_attr_mask);
-/**
- * rdma_connect - Initiate an active connection request.
- * @id: Connection identifier to connect.
- * @conn_param: Connection information used for connected QPs.
- *
- * Users must have resolved a route for the rdma_cm_id to connect with
- * by having called rdma_resolve_route before calling this routine.
- *
- * This call will either connect to a remote QP or obtain remote QP
- * information for unconnected rdma_cm_id's. The actual operation is
- * based on the rdma_cm_id's port space.
- */
int rdma_connect(struct rdma_cm_id *id, struct rdma_conn_param *conn_param);
+int rdma_connect_locked(struct rdma_cm_id *id,
+ struct rdma_conn_param *conn_param);
int rdma_connect_ece(struct rdma_cm_id *id, struct rdma_conn_param *conn_param,
struct rdma_ucm_ece *ece);
diff --git a/net/rds/ib_cm.c b/net/rds/ib_cm.c
index 06603dd1c8aa..b36b60668b1d 100644
--- a/net/rds/ib_cm.c
+++ b/net/rds/ib_cm.c
@@ -956,9 +956,10 @@ int rds_ib_cm_initiate_connect(struct rdma_cm_id *cm_id, bool isv6)
rds_ib_cm_fill_conn_param(conn, &conn_param, &dp,
conn->c_proposed_version,
UINT_MAX, UINT_MAX, isv6);
- ret = rdma_connect(cm_id, &conn_param);
+ ret = rdma_connect_locked(cm_id, &conn_param);
if (ret)
- rds_ib_conn_error(conn, "rdma_connect failed (%d)\n", ret);
+ rds_ib_conn_error(conn, "rdma_connect_locked failed (%d)\n",
+ ret);
out:
/* Beware - returning non-zero tells the rdma_cm to destroy