linux-nvme.lists.infradead.org archive mirror
 help / color / mirror / Atom feed
From: swise@opengridcomputing.com (Steve Wise)
Subject: [PATCH v5 4/6] nvme-rdma: destroy nvme queue rdma resources on connect failure
Date: Fri, 2 Sep 2016 09:01:27 -0700	[thread overview]
Message-ID: <7f9c2b9ac54d158d825dae89b48abdc5ed85043a.1472833420.git.swise@opengridcomputing.com> (raw)
In-Reply-To: <cover.1472833420.git.swise@opengridcomputing.com>

After address resolution, the nvme_rdma_queue rdma resources are
allocated.  If rdma route resolution or the connect fails, or the
controller reconnect times out and gives up, then the rdma resources
need to be freed.  Otherwise, rdma resources are leaked.

Reviewed-by: Christoph Hellwig <hch at lst.de>
Reviewed-by: Sagi Grimberg <sagi at grimbrg.me>
Signed-off-by: Steve Wise <swise at opengridcomputing.com>
---
 drivers/nvme/host/rdma.c | 14 +++++++++++---
 1 file changed, 11 insertions(+), 3 deletions(-)

diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c
index 15b0c1d..a9d43f0 100644
--- a/drivers/nvme/host/rdma.c
+++ b/drivers/nvme/host/rdma.c
@@ -82,6 +82,7 @@ struct nvme_rdma_request {
 
 enum nvme_rdma_queue_flags {
 	NVME_RDMA_Q_CONNECTED = (1 << 0),
+	NVME_RDMA_IB_QUEUE_ALLOCATED = (1 << 1),
 };
 
 struct nvme_rdma_queue {
@@ -480,9 +481,14 @@ out_err:
 
 static void nvme_rdma_destroy_queue_ib(struct nvme_rdma_queue *queue)
 {
-	struct nvme_rdma_device *dev = queue->device;
-	struct ib_device *ibdev = dev->dev;
+	struct nvme_rdma_device *dev;
+	struct ib_device *ibdev;
 
+	if (!test_and_clear_bit(NVME_RDMA_IB_QUEUE_ALLOCATED, &queue->flags))
+		return;
+
+	dev = queue->device;
+	ibdev = dev->dev;
 	rdma_destroy_qp(queue->cm_id);
 	ib_free_cq(queue->ib_cq);
 
@@ -533,6 +539,7 @@ static int nvme_rdma_create_queue_ib(struct nvme_rdma_queue *queue,
 		ret = -ENOMEM;
 		goto out_destroy_qp;
 	}
+	set_bit(NVME_RDMA_IB_QUEUE_ALLOCATED, &queue->flags);
 
 	return 0;
 
@@ -590,6 +597,7 @@ static int nvme_rdma_init_queue(struct nvme_rdma_ctrl *ctrl,
 	return 0;
 
 out_destroy_cm_id:
+	nvme_rdma_destroy_queue_ib(queue);
 	rdma_destroy_id(queue->cm_id);
 	return ret;
 }
@@ -652,7 +660,7 @@ static int nvme_rdma_init_io_queues(struct nvme_rdma_ctrl *ctrl)
 	return 0;
 
 out_free_queues:
-	for (; i >= 1; i--)
+	for (i--; i >= 1; i--)
 		nvme_rdma_stop_and_free_queue(&ctrl->queues[i]);
 
 	return ret;
-- 
2.7.0

  parent reply	other threads:[~2016-09-02 16:01 UTC|newest]

Thread overview: 11+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2016-09-02 16:23 [PATCH v5 0/6] nvme-rdma device removal fixes Steve Wise
2016-09-01 13:43 ` [PATCH v5 1/6] iw_cxgb4: call dev_put() on l2t allocation failure Steve Wise
2016-09-01 13:44 ` [PATCH v5 2/6] iw_cxgb4: block module unload until all ep resources are released Steve Wise
2016-09-01 16:12 ` [PATCH v5 3/6] nvme_rdma: keep a ref on the ctrl during delete/flush Steve Wise
2016-09-02 16:01 ` Steve Wise [this message]
2016-09-02 16:01 ` [PATCH v5 5/6] nvme-rdma: add DELETING queue flag Steve Wise
2016-09-02 16:01 ` [PATCH v5 6/6] nvme-rdma: use ib_client API to detect device removal Steve Wise
2016-09-04  7:01 ` [PATCH v5 0/6] nvme-rdma device removal fixes Sagi Grimberg
2016-09-12 14:49   ` Steve Wise
2016-09-12 14:58     ` Sagi Grimberg
2016-09-12 15:00       ` Steve Wise

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=7f9c2b9ac54d158d825dae89b48abdc5ed85043a.1472833420.git.swise@opengridcomputing.com \
    --to=swise@opengridcomputing.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).