diff options
| author | Chuck Lever <chuck.lever@oracle.com> | 2020-06-30 13:25:41 -0400 |
|---|---|---|
| committer | Chuck Lever <chuck.lever@oracle.com> | 2020-07-28 10:18:14 -0400 |
| commit | 365e9992b90fbbfda89f72866783fd52bbd58e64 (patch) | |
| tree | 3411338429110ca8c7eebaa35a8c6f4d2153882e /net/sunrpc/xprtrdma/svc_rdma_rw.c | |
| parent | 64d26422516b2e347b32e6d9b1d40b3c19a62aae (diff) | |
svcrdma: Remove transport reference counting
Jason tells me that a ULP cannot rely on getting an ESTABLISHED
and DISCONNECTED event pair for each connection, so transport
reference counting in the CM event handler will never be reliable.
Now that we have ib_drain_qp(), svcrdma should no longer need to
hold transport references while Sends and Receives are posted. So
remove the get/put call sites in the CM event handlers.
This eliminates a significant source of locked memory bus traffic.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Diffstat (limited to 'net/sunrpc/xprtrdma/svc_rdma_rw.c')
| -rw-r--r-- | net/sunrpc/xprtrdma/svc_rdma_rw.c | 2 |
1 files changed, 0 insertions, 2 deletions
diff --git a/net/sunrpc/xprtrdma/svc_rdma_rw.c b/net/sunrpc/xprtrdma/svc_rdma_rw.c index c16d10601d65..fe54cbe97a46 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_rw.c +++ b/net/sunrpc/xprtrdma/svc_rdma_rw.c @@ -164,7 +164,6 @@ static void svc_rdma_cc_init(struct svcxprt_rdma *rdma, { svc_rdma_cc_cid_init(rdma, &cc->cc_cid); cc->cc_rdma = rdma; - svc_xprt_get(&rdma->sc_xprt); INIT_LIST_HEAD(&cc->cc_rwctxts); cc->cc_sqecount = 0; @@ -184,7 +183,6 @@ static void svc_rdma_cc_release(struct svc_rdma_chunk_ctxt *cc, ctxt->rw_nents, dir); svc_rdma_put_rw_ctxt(rdma, ctxt); } - svc_xprt_put(&rdma->sc_xprt); } /* State for sending a Write or Reply chunk. |