Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67;
From:   Sasha Levin <Alexander.Levin@microsoft.com>
To:     "linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
        "stable@vger.kernel.org" <stable@vger.kernel.org>
CC:     Sagi Grimberg <sagi@grimberg.me>, Christoph Hellwig <hch@lst.de>,
        "Sasha Levin" <Alexander.Levin@microsoft.com>
Subject: [PATCH AUTOSEL for 4.14 037/100] nvme-rdma: don't complete requests
 before a send work request has completed
Thread-Topic: [PATCH AUTOSEL for 4.14 037/100] nvme-rdma: don't complete
 requests before a send work request has completed
Thread-Index: AQHTlMnbvtRRfEgrakeckeoGFvHdZw==
Date:   Wed, 24 Jan 2018 04:14:42 +0000
Message-ID: <20180124041414.32065-37-alexander.levin@microsoft.com>
References: <20180124041414.32065-1-alexander.levin@microsoft.com>
In-Reply-To: <20180124041414.32065-1-alexander.levin@microsoft.com>
Accept-Language: en-US
Content-Language: en-US
received-spf: None (protection.outlook.com: microsoft.com does not designate
 permitted sender hosts)
spamdiagnosticoutput: 1:99
spamdiagnosticmetadata: NSPM
Content-Type: text/plain; charset="iso-8859-1"
Content-Transfer-Encoding: quoted-printable
MIME-Version: 1.0
X-MS-Exchange-CrossTenant-Network-Message-Id: 2f780e52-5ab8-477b-a37a-08d562e10ff7
X-MS-Exchange-CrossTenant-originalarrivaltime: 24 Jan 2018 04:14:42.3565
 (UTC)
X-MS-Exchange-CrossTenant-fromentityheader: Hosted
X-MS-Exchange-CrossTenant-id: 72f988bf-86f1-41af-91ab-2d7cd011db47
X-MS-Exchange-Transport-CrossTenantHeadersStamped: DM5PR2101MB0998
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk
List-ID: <linux-kernel.vger.kernel.org>
X-Mailing-List: linux-kernel@vger.kernel.org

From: Sagi Grimberg <sagi@grimberg.me>

[ Upstream commit 4af7f7ff92a42b6c713293c99e7982bcfcf51a70 ]

In order to guarantee that the HCA will never get an access violation
(either from invalidated rkey or from iommu) when retrying a send
operation we must complete a request only when both send completion and
the nvme cqe has arrived. We need to set the send/recv completions flags
atomically because we might have more than a single context accessing the
request concurrently (one is cq irq-poll context and the other is
user-polling used in IOCB_HIPRI).

Only then we are safe to invalidate the rkey (if needed), unmap the host
buffers, and complete the IO.

Signed-off-by: Sagi Grimberg <sagi@grimberg.me>
Reviewed-by: Max Gurtovoy <maxg@mellanox.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Sasha Levin <alexander.levin@microsoft.com>
---
 drivers/nvme/host/rdma.c | 28 ++++++++++++++++++++++++----
 1 file changed, 24 insertions(+), 4 deletions(-)

diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c
index 6de163e6c9eb..33d4431c2b4b 100644
--- a/drivers/nvme/host/rdma.c
+++ b/drivers/nvme/host/rdma.c
@@ -67,6 +67,9 @@ struct nvme_rdma_request {
 	struct nvme_request	req;
 	struct ib_mr		*mr;
 	struct nvme_rdma_qe	sqe;
+	union nvme_result	result;
+	__le16			status;
+	refcount_t		ref;
 	struct ib_sge		sge[1 + NVME_RDMA_MAX_INLINE_SEGMENTS];
 	u32			num_sge;
 	int			nents;
@@ -1177,6 +1180,7 @@ static int nvme_rdma_map_data(struct nvme_rdma_queue =
*queue,
 	req->num_sge =3D 1;
 	req->inline_data =3D false;
 	req->mr->need_inval =3D false;
+	refcount_set(&req->ref, 2); /* send and recv completions */
=20
 	c->common.flags |=3D NVME_CMD_SGL_METABUF;
=20
@@ -1213,8 +1217,19 @@ static int nvme_rdma_map_data(struct nvme_rdma_queue=
 *queue,
=20
 static void nvme_rdma_send_done(struct ib_cq *cq, struct ib_wc *wc)
 {
-	if (unlikely(wc->status !=3D IB_WC_SUCCESS))
+	struct nvme_rdma_qe *qe =3D
+		container_of(wc->wr_cqe, struct nvme_rdma_qe, cqe);
+	struct nvme_rdma_request *req =3D
+		container_of(qe, struct nvme_rdma_request, sqe);
+	struct request *rq =3D blk_mq_rq_from_pdu(req);
+
+	if (unlikely(wc->status !=3D IB_WC_SUCCESS)) {
 		nvme_rdma_wr_error(cq, wc, "SEND");
+		return;
+	}
+
+	if (refcount_dec_and_test(&req->ref))
+		nvme_end_request(rq, req->status, req->result);
 }
=20
 /*
@@ -1359,14 +1374,19 @@ static int nvme_rdma_process_nvme_rsp(struct nvme_r=
dma_queue *queue,
 	}
 	req =3D blk_mq_rq_to_pdu(rq);
=20
-	if (rq->tag =3D=3D tag)
-		ret =3D 1;
+	req->status =3D cqe->status;
+	req->result =3D cqe->result;
=20
 	if ((wc->wc_flags & IB_WC_WITH_INVALIDATE) &&
 	    wc->ex.invalidate_rkey =3D=3D req->mr->rkey)
 		req->mr->need_inval =3D false;
=20
-	nvme_end_request(rq, cqe->status, cqe->result);
+	if (refcount_dec_and_test(&req->ref)) {
+		if (rq->tag =3D=3D tag)
+			ret =3D 1;
+		nvme_end_request(rq, req->status, req->result);
+	}
+
 	return ret;
 }
=20
--=20
2.11.0