When using RPCRDMA_MTHCAFMR memory registration, after a few
transport disconnect / reconnect cycles, ib_map_phys_fmr() starts to
return EINVAL because the provider has exhausted its map pool.
Make sure that all FMRs are unmapped during transport disconnect,
and that ->send_request remarshals them during an RPC retransmit.
This resets the transport's MRs to ensure that none are leaked
during a disconnect.
Signed-off-by: Chuck Lever <chuck.lever@xxxxxxxxxx>
---
net/sunrpc/xprtrdma/transport.c | 2 +-
net/sunrpc/xprtrdma/verbs.c | 40 ++++++++++++++++++++++++++++++++++++++-
2 files changed, 40 insertions(+), 2 deletions(-)
diff --git a/net/sunrpc/xprtrdma/transport.c b/net/sunrpc/xprtrdma/transport.c
index 6e9d0a7..61be0a0 100644
--- a/net/sunrpc/xprtrdma/transport.c
+++ b/net/sunrpc/xprtrdma/transport.c
@@ -601,7 +601,7 @@ xprt_rdma_send_request(struct rpc_task *task)
if (req->rl_niovs == 0)
rc = rpcrdma_marshal_req(rqst);
- else if (r_xprt->rx_ia.ri_memreg_strategy == RPCRDMA_FRMR)
+ else if (r_xprt->rx_ia.ri_memreg_strategy != RPCRDMA_ALLPHYSICAL)
rc = rpcrdma_marshal_chunks(rqst, 0);
if (rc < 0)
goto failed_marshal;
diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c
index 6fadb90..9105524 100644
--- a/net/sunrpc/xprtrdma/verbs.c
+++ b/net/sunrpc/xprtrdma/verbs.c
@@ -62,6 +62,7 @@
#endif
static void rpcrdma_reset_frmrs(struct rpcrdma_ia *);
+static void rpcrdma_reset_fmrs(struct rpcrdma_ia *);
/*
* internal functions
@@ -884,8 +885,17 @@ retry:
rpcrdma_ep_disconnect(ep, ia);
rpcrdma_flush_cqs(ep);
- if (ia->ri_memreg_strategy == RPCRDMA_FRMR)
+ switch (ia->ri_memreg_strategy) {
+ case RPCRDMA_FRMR:
rpcrdma_reset_frmrs(ia);
+ break;
+ case RPCRDMA_MTHCAFMR:
+ rpcrdma_reset_fmrs(ia);
+ break;
+ default:
+ rc = -EIO;
+ goto out;
+ }
xprt = container_of(ia, struct rpcrdma_xprt, rx_ia);
id = rpcrdma_create_id(xprt, ia,
@@ -1305,6 +1315,34 @@ rpcrdma_buffer_destroy(struct rpcrdma_buffer *buf)
kfree(buf->rb_pool);
}
+/* After a disconnect, unmap all FMRs.
+ *
+ * This is invoked only in the transport connect worker in order
+ * to serialize with rpcrdma_register_fmr_external().
+ */
+static void
+rpcrdma_reset_fmrs(struct rpcrdma_ia *ia)
+{
+ struct rpcrdma_xprt *r_xprt =
+ container_of(ia, struct rpcrdma_xprt, rx_ia);
+ struct rpcrdma_buffer *buf = &r_xprt->rx_buf;
+ struct list_head *pos;
+ struct rpcrdma_mw *r;
+ LIST_HEAD(l);
+ int rc;
+
+ list_for_each(pos, &buf->rb_all) {
+ r = list_entry(pos, struct rpcrdma_mw, mw_all);
+
+ INIT_LIST_HEAD(&l);
+ list_add(&r->r.fmr->list, &l);
+ rc = ib_unmap_fmr(&l);
+ if (rc)
+ dprintk("RPC: %s: ib_unmap_fmr failed %i\n",
+ __func__, rc);
+ }
+}
+
/* After a disconnect, a flushed FAST_REG_MR can leave an FRMR in
* an unusable state. Find FRMRs in this state and dereg / reg
* each. FRMRs that are VALID and attached to an rpcrdma_req are
--
To unsubscribe from this list: send the line "unsubscribe linux-nfs" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
