@@ -144,6 +144,30 @@ void frwr_release_mr(struct rpcrdma_mr *mr)
frwr_release_mr(mr);
}
+/* frwr_reset - Place MRs back on the free list
+ * @req: request to reset
+ *
+ * Used after a failed marshal. For FRWR, this means the MRs
+ * don't have to be fully released and recreated.
+ *
+ * NB: This is safe only as long as none of @req's MRs are
+ * involved with an ongoing asynchronous FAST_REG or LOCAL_INV
+ * Work Request.
+ */
+void frwr_reset(struct rpcrdma_req *req)
+{
+ /* If this is a retransmit, discard previously registered
+ * chunks. Very likely the connection has been replaced,
+ * so these registrations are invalid and unusable.
+ */
+ while (!list_empty(&req->rl_registered)) {
+ struct rpcrdma_mr *mr;
+
+ mr = rpcrdma_mr_pop(&req->rl_registered);
+ rpcrdma_mr_unmap_and_put(mr);
+ }
+}
+
/**
* frwr_init_mr - Initialize one MR
* @ia: interface adapter
@@ -884,6 +884,7 @@ static bool rpcrdma_prepare_msg_sges(struct rpcrdma_xprt *r_xprt,
out_err:
trace_xprtrdma_marshal_failed(rqst, ret);
r_xprt->rx_stats.failed_marshal_count++;
+ frwr_reset(req);
return ret;
}
@@ -549,6 +549,7 @@ static inline bool rpcrdma_regbuf_dma_map(struct rpcrdma_xprt *r_xprt,
/* Memory registration calls xprtrdma/frwr_ops.c
*/
bool frwr_is_supported(struct ib_device *device);
+void frwr_reset(struct rpcrdma_req *req);
int frwr_open(struct rpcrdma_ia *ia, struct rpcrdma_ep *ep);
int frwr_init_mr(struct rpcrdma_ia *ia, struct rpcrdma_mr *mr);
void frwr_release_mr(struct rpcrdma_mr *mr);
A marshal operation can fail if there are not enough MRs or if the sendctx queue is empty. In this case, any MRs that were already set up for that request are recycled. Recycling releases MRs and creates new ones, which is expensive. Since commit f2877623082b ("xprtrdma: Chain Send to FastReg WRs") was merged, recycling FRWRs is unnecessary. This is because before that commit, frwr_map had already posted FAST_REG Work Requests, so the MRs were owned by the NIC and dealing with them had to be delayed. Since that commit, the FAST_REG WRs are posted at the same time as the Send WR. This means that if marshaling fails, we are certain the MRs are safe to simply unmap and place back on the free list because neither the Send nor the FAST_REG WRs have been posted yet. This reduces the total number of MRs that the xprt has to create under heavy workloads and makes the logic a bit less brittle. Signed-off-by: Chuck Lever <chuck.lever@oracle.com> --- net/sunrpc/xprtrdma/frwr_ops.c | 24 ++++++++++++++++++++++++ net/sunrpc/xprtrdma/rpc_rdma.c | 1 + net/sunrpc/xprtrdma/xprt_rdma.h | 1 + 3 files changed, 26 insertions(+)