RDS: RDMA: Fix the composite message user notification

[ Upstream commit 941f8d55f6d613a460a5e080d25a38509f45eb75 ]

When application sends an RDS RDMA composite message consist of
RDMA transfer to be followed up by non RDMA payload, it expect to
be notified *only* when the full message gets delivered. RDS RDMA
notification doesn't behave this way though.

Thanks to Venkat for debug and root casuing the issue
where only first part of the message(RDMA) was
successfully delivered but remainder payload delivery failed.
In that case, application should not be notified with
a false positive of message delivery success.

Fix this case by making sure the user gets notified only after
the full message delivery.

Reviewed-by: Venkat Venkatsubra <venkat.x.venkatsubra@oracle.com>
Signed-off-by: Santosh Shilimkar <santosh.shilimkar@oracle.com>
Signed-off-by: Sasha Levin <alexander.levin@verizon.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

diff --git a/net/rds/ib_send.c b/net/rds/ib_send.c
index 84d90c97332f9178552f34f2e13973a351f6213a..19109817301812208a2f5589d750df40c93bf0ea 100644 (file)
--- a/net/rds/ib_send.c
+++ b/net/rds/ib_send.c
@@ -69,16 +69,6 @@ static void rds_ib_send_complete(struct rds_message *rm,
        complete(rm, notify_status);
 }
 
-static void rds_ib_send_unmap_data(struct rds_ib_connection *ic,
-                                  struct rm_data_op *op,
-                                  int wc_status)
-{
-       if (op->op_nents)
-               ib_dma_unmap_sg(ic->i_cm_id->device,
-                               op->op_sg, op->op_nents,
-                               DMA_TO_DEVICE);
-}
-
 static void rds_ib_send_unmap_rdma(struct rds_ib_connection *ic,
                                   struct rm_rdma_op *op,
                                   int wc_status)
@@ -139,6 +129,21 @@ static void rds_ib_send_unmap_atomic(struct rds_ib_connection *ic,
                rds_ib_stats_inc(s_ib_atomic_fadd);
 }
 
+static void rds_ib_send_unmap_data(struct rds_ib_connection *ic,
+                                  struct rm_data_op *op,
+                                  int wc_status)
+{
+       struct rds_message *rm = container_of(op, struct rds_message, data);
+
+       if (op->op_nents)
+               ib_dma_unmap_sg(ic->i_cm_id->device,
+                               op->op_sg, op->op_nents,
+                               DMA_TO_DEVICE);
+
+       if (rm->rdma.op_active && rm->data.op_notify)
+               rds_ib_send_unmap_rdma(ic, &rm->rdma, wc_status);
+}
+
 /*
  * Unmap the resources associated with a struct send_work.
  *

diff --git a/net/rds/rdma.c b/net/rds/rdma.c
index 4c93badeabf2236d3d90c933e6169174b3ba68d1..8d3a851a347697a0bf3c03666cad863d78962c3a 100644 (file)
--- a/net/rds/rdma.c
+++ b/net/rds/rdma.c
@@ -626,6 +626,16 @@ int rds_cmsg_rdma_args(struct rds_sock *rs, struct rds_message *rm,
                }
                op->op_notifier->n_user_token = args->user_token;
                op->op_notifier->n_status = RDS_RDMA_SUCCESS;
+
+               /* Enable rmda notification on data operation for composite
+                * rds messages and make sure notification is enabled only
+                * for the data operation which follows it so that application
+                * gets notified only after full message gets delivered.
+                */
+               if (rm->data.op_sg) {
+                       rm->rdma.op_notify = 0;
+                       rm->data.op_notify = !!(args->flags & RDS_RDMA_NOTIFY_ME);
+               }
        }
 
        /* The cookie contains the R_Key of the remote memory region, and

diff --git a/net/rds/rds.h b/net/rds/rds.h
index 67ba67c058b1b6b8e02631d664c41cac4deaadcc..f107a968ddffc1c61896dee4b2bd4037b7f83b71 100644 (file)
--- a/net/rds/rds.h
+++ b/net/rds/rds.h
@@ -414,6 +414,7 @@ struct rds_message {
                } rdma;
                struct rm_data_op {
                        unsigned int            op_active:1;
+                       unsigned int            op_notify:1;
                        unsigned int            op_nents;
                        unsigned int            op_count;
                        unsigned int            op_dmasg;

diff --git a/net/rds/send.c b/net/rds/send.c
index 896626b9a0efde321d64b7f2eef3b3e0200b872f..f28651b6ae833898b2a74b51362c2c41f8e697f9 100644 (file)
--- a/net/rds/send.c
+++ b/net/rds/send.c
@@ -475,12 +475,14 @@ void rds_rdma_send_complete(struct rds_message *rm, int status)
        struct rm_rdma_op *ro;
        struct rds_notifier *notifier;
        unsigned long flags;
+       unsigned int notify = 0;
 
        spin_lock_irqsave(&rm->m_rs_lock, flags);
 
+       notify =  rm->rdma.op_notify | rm->data.op_notify;
        ro = &rm->rdma;
        if (test_bit(RDS_MSG_ON_SOCK, &rm->m_flags) &&
-           ro->op_active && ro->op_notify && ro->op_notifier) {
+           ro->op_active && notify && ro->op_notifier) {
                notifier = ro->op_notifier;
                rs = rm->m_rs;
                sock_hold(rds_rs_to_sk(rs));