svcrdma: Revert 2a1e4f21d841 ("svcrdma: Normalize Send page handling")

Get rid of the completion wait in svc_rdma_sendto(), and release
pages in the send completion handler again. A subsequent patch will
handle releasing those pages more efficiently.

Reverted by hand: patch -R would not apply cleanly.

Reviewed-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>

diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h
index 8e654da..a5ee0af 100644 (file)
--- a/include/linux/sunrpc/svc_rdma.h
+++ b/include/linux/sunrpc/svc_rdma.h
@@ -154,7 +154,6 @@ struct svc_rdma_send_ctxt {
 
        struct ib_send_wr       sc_send_wr;
        struct ib_cqe           sc_cqe;
-       struct completion       sc_done;
        struct xdr_buf          sc_hdrbuf;
        struct xdr_stream       sc_stream;
        void                    *sc_xprt_buf;

diff --git a/net/sunrpc/xprtrdma/svc_rdma_backchannel.c b/net/sunrpc/xprtrdma/svc_rdma_backchannel.c
index aa2227a..7420a2c 100644 (file)
--- a/net/sunrpc/xprtrdma/svc_rdma_backchannel.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_backchannel.c
@@ -93,13 +93,7 @@ static int svc_rdma_bc_sendto(struct svcxprt_rdma *rdma,
         */
        get_page(virt_to_page(rqst->rq_buffer));
        sctxt->sc_send_wr.opcode = IB_WR_SEND;
-       ret = svc_rdma_send(rdma, sctxt);
-       if (ret < 0)
-               return ret;
-
-       ret = wait_for_completion_killable(&sctxt->sc_done);
-       svc_rdma_send_ctxt_put(rdma, sctxt);
-       return ret;
+       return svc_rdma_send(rdma, sctxt);
 }
 
 /* Server-side transport endpoint wants a whole page for its send

diff --git a/net/sunrpc/xprtrdma/svc_rdma_sendto.c b/net/sunrpc/xprtrdma/svc_rdma_sendto.c
index 4c62bc4..1ae4236 100644 (file)
--- a/net/sunrpc/xprtrdma/svc_rdma_sendto.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_sendto.c
@@ -147,7 +147,6 @@ svc_rdma_send_ctxt_alloc(struct svcxprt_rdma *rdma)
        ctxt->sc_send_wr.wr_cqe = &ctxt->sc_cqe;
        ctxt->sc_send_wr.sg_list = ctxt->sc_sges;
        ctxt->sc_send_wr.send_flags = IB_SEND_SIGNALED;
-       init_completion(&ctxt->sc_done);
        ctxt->sc_cqe.done = svc_rdma_wc_send;
        ctxt->sc_xprt_buf = buffer;
        xdr_buf_init(&ctxt->sc_hdrbuf, ctxt->sc_xprt_buf,
@@ -286,12 +285,12 @@ static void svc_rdma_wc_send(struct ib_cq *cq, struct ib_wc *wc)
                container_of(cqe, struct svc_rdma_send_ctxt, sc_cqe);
 
        svc_rdma_wake_send_waiters(rdma, 1);
-       complete(&ctxt->sc_done);
 
        if (unlikely(wc->status != IB_WC_SUCCESS))
                goto flushed;
 
        trace_svcrdma_wc_send(wc, &ctxt->sc_cid);
+       svc_rdma_send_ctxt_put(rdma, ctxt);
        return;
 
 flushed:
@@ -299,6 +298,7 @@ flushed:
                trace_svcrdma_wc_send_err(wc, &ctxt->sc_cid);
        else
                trace_svcrdma_wc_send_flush(wc, &ctxt->sc_cid);
+       svc_rdma_send_ctxt_put(rdma, ctxt);
        svc_xprt_deferred_close(&rdma->sc_xprt);
 }
 
@@ -315,8 +315,6 @@ int svc_rdma_send(struct svcxprt_rdma *rdma, struct svc_rdma_send_ctxt *ctxt)
        struct ib_send_wr *wr = &ctxt->sc_send_wr;
        int ret;
 
-       reinit_completion(&ctxt->sc_done);
-
        /* Sync the transport header buffer */
        ib_dma_sync_single_for_device(rdma->sc_pd->device,
                                      wr->sg_list[0].addr,
@@ -808,8 +806,8 @@ int svc_rdma_map_reply_msg(struct svcxprt_rdma *rdma,
  * svc_rdma_sendto returns. Transfer pages under I/O to the ctxt
  * so they are released by the Send completion handler.
  */
-static inline void svc_rdma_save_io_pages(struct svc_rqst *rqstp,
-                                         struct svc_rdma_send_ctxt *ctxt)
+static void svc_rdma_save_io_pages(struct svc_rqst *rqstp,
+                                  struct svc_rdma_send_ctxt *ctxt)
 {
        int i, pages = rqstp->rq_next_page - rqstp->rq_respages;
 
@@ -852,6 +850,8 @@ static int svc_rdma_send_reply_msg(struct svcxprt_rdma *rdma,
        if (ret < 0)
                return ret;
 
+       svc_rdma_save_io_pages(rqstp, sctxt);
+
        if (rctxt->rc_inv_rkey) {
                sctxt->sc_send_wr.opcode = IB_WR_SEND_WITH_INV;
                sctxt->sc_send_wr.ex.invalidate_rkey = rctxt->rc_inv_rkey;
@@ -859,13 +859,7 @@ static int svc_rdma_send_reply_msg(struct svcxprt_rdma *rdma,
                sctxt->sc_send_wr.opcode = IB_WR_SEND;
        }
 
-       ret = svc_rdma_send(rdma, sctxt);
-       if (ret < 0)
-               return ret;
-
-       ret = wait_for_completion_killable(&sctxt->sc_done);
-       svc_rdma_send_ctxt_put(rdma, sctxt);
-       return ret;
+       return svc_rdma_send(rdma, sctxt);
 }
 
 /**
@@ -931,8 +925,7 @@ void svc_rdma_send_error_msg(struct svcxprt_rdma *rdma,
        sctxt->sc_sges[0].length = sctxt->sc_hdrbuf.len;
        if (svc_rdma_send(rdma, sctxt))
                goto put_ctxt;
-
-       wait_for_completion_killable(&sctxt->sc_done);
+       return;
 
 put_ctxt:
        svc_rdma_send_ctxt_put(rdma, sctxt);
@@ -1006,6 +999,10 @@ reply_chunk:
        if (ret != -E2BIG && ret != -EINVAL)
                goto put_ctxt;
 
+       /* Send completion releases payload pages that were part
+        * of previously posted RDMA Writes.
+        */
+       svc_rdma_save_io_pages(rqstp, sctxt);
        svc_rdma_send_error_msg(rdma, sctxt, rctxt, ret);
        return 0;