All of lore.kernel.org
 help / color / mirror / Atom feed
From: Chao Leng <lengchao@huawei.com>
To: <linux-nvme@lists.infradead.org>
Cc: <kbusch@kernel.org>, <axboe@fb.com>, <hch@lst.de>,
	<sagi@grimberg.me>, <linux-block@vger.kernel.org>,
	<axboe@kernel.dk>
Subject: [PATCH v4 4/5] nvme-rdma: avoid IO error for nvme native multipath
Date: Tue, 26 Jan 2021 16:15:38 +0800	[thread overview]
Message-ID: <20210126081539.13320-5-lengchao@huawei.com> (raw)
In-Reply-To: <20210126081539.13320-1-lengchao@huawei.com>

Work with nvme native multipath, if a path related error occurs when
queue_rq call HBA drive to send request, queue_rq will return
BLK_STS_IOERR to blk-mq. The request is completed with BLK_STS_IOERR
instead of fail over to retry.
queue_rq need call nvme_complete_rq to complete the request with
NVME_SC_HOST_PATH_ERROR, the request will fail over to retry if needed.

Signed-off-by: Chao Leng <lengchao@huawei.com>
---
 drivers/nvme/host/rdma.c | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c
index b7ce4f221d99..7c801132d5ed 100644
--- a/drivers/nvme/host/rdma.c
+++ b/drivers/nvme/host/rdma.c
@@ -2037,6 +2037,7 @@ static blk_status_t nvme_rdma_queue_rq(struct blk_mq_hw_ctx *hctx,
 	bool queue_ready = test_bit(NVME_RDMA_Q_LIVE, &queue->flags);
 	blk_status_t ret;
 	int err;
+	bool driver_error = false;
 
 	WARN_ON_ONCE(rq->tag < 0);
 
@@ -2084,8 +2085,10 @@ static blk_status_t nvme_rdma_queue_rq(struct blk_mq_hw_ctx *hctx,
 
 	err = nvme_rdma_post_send(queue, sqe, req->sge, req->num_sge,
 			req->mr ? &req->reg_wr.wr : NULL);
-	if (unlikely(err))
+	if (unlikely(err)) {
+		driver_error = true;
 		goto err_unmap;
+	}
 
 	return BLK_STS_OK;
 
@@ -2100,6 +2103,10 @@ static blk_status_t nvme_rdma_queue_rq(struct blk_mq_hw_ctx *hctx,
 unmap_qe:
 	ib_dma_unmap_single(dev, req->sqe.dma, sizeof(struct nvme_command),
 			    DMA_TO_DEVICE);
+	if (driver_error && ret == BLK_STS_IOERR) {
+		nvme_complete_failed_rq(rq, NVME_SC_HOST_PATH_ERROR);
+		ret = BLK_STS_OK;
+	}
 	return ret;
 }
 
-- 
2.16.4


WARNING: multiple messages have this Message-ID (diff)
From: Chao Leng <lengchao@huawei.com>
To: <linux-nvme@lists.infradead.org>
Cc: axboe@kernel.dk, linux-block@vger.kernel.org, sagi@grimberg.me,
	axboe@fb.com, kbusch@kernel.org, hch@lst.de
Subject: [PATCH v4 4/5] nvme-rdma: avoid IO error for nvme native multipath
Date: Tue, 26 Jan 2021 16:15:38 +0800	[thread overview]
Message-ID: <20210126081539.13320-5-lengchao@huawei.com> (raw)
In-Reply-To: <20210126081539.13320-1-lengchao@huawei.com>

Work with nvme native multipath, if a path related error occurs when
queue_rq call HBA drive to send request, queue_rq will return
BLK_STS_IOERR to blk-mq. The request is completed with BLK_STS_IOERR
instead of fail over to retry.
queue_rq need call nvme_complete_rq to complete the request with
NVME_SC_HOST_PATH_ERROR, the request will fail over to retry if needed.

Signed-off-by: Chao Leng <lengchao@huawei.com>
---
 drivers/nvme/host/rdma.c | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c
index b7ce4f221d99..7c801132d5ed 100644
--- a/drivers/nvme/host/rdma.c
+++ b/drivers/nvme/host/rdma.c
@@ -2037,6 +2037,7 @@ static blk_status_t nvme_rdma_queue_rq(struct blk_mq_hw_ctx *hctx,
 	bool queue_ready = test_bit(NVME_RDMA_Q_LIVE, &queue->flags);
 	blk_status_t ret;
 	int err;
+	bool driver_error = false;
 
 	WARN_ON_ONCE(rq->tag < 0);
 
@@ -2084,8 +2085,10 @@ static blk_status_t nvme_rdma_queue_rq(struct blk_mq_hw_ctx *hctx,
 
 	err = nvme_rdma_post_send(queue, sqe, req->sge, req->num_sge,
 			req->mr ? &req->reg_wr.wr : NULL);
-	if (unlikely(err))
+	if (unlikely(err)) {
+		driver_error = true;
 		goto err_unmap;
+	}
 
 	return BLK_STS_OK;
 
@@ -2100,6 +2103,10 @@ static blk_status_t nvme_rdma_queue_rq(struct blk_mq_hw_ctx *hctx,
 unmap_qe:
 	ib_dma_unmap_single(dev, req->sqe.dma, sizeof(struct nvme_command),
 			    DMA_TO_DEVICE);
+	if (driver_error && ret == BLK_STS_IOERR) {
+		nvme_complete_failed_rq(rq, NVME_SC_HOST_PATH_ERROR);
+		ret = BLK_STS_OK;
+	}
 	return ret;
 }
 
-- 
2.16.4


_______________________________________________
Linux-nvme mailing list
Linux-nvme@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-nvme

  parent reply	other threads:[~2021-01-26  8:18 UTC|newest]

Thread overview: 34+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-01-26  8:15 [PATCH v4 0/5] avoid double request completion and IO error Chao Leng
2021-01-26  8:15 ` Chao Leng
2021-01-26  8:15 ` [PATCH v4 1/5] blk-mq: introduce blk_mq_set_request_complete Chao Leng
2021-01-26  8:15   ` Chao Leng
2021-01-27 16:40   ` Christoph Hellwig
2021-01-27 16:40     ` Christoph Hellwig
2021-01-28  1:34     ` Chao Leng
2021-01-28  1:34       ` Chao Leng
2021-01-26  8:15 ` [PATCH v4 2/5] nvme-core: introduce complete failed request Chao Leng
2021-01-26  8:15   ` Chao Leng
2021-01-26  8:15 ` [PATCH v4 3/5] nvme-fabrics: avoid double request completion for nvmf_fail_nonready_command Chao Leng
2021-01-26  8:15   ` Chao Leng
2021-01-26  8:15 ` Chao Leng [this message]
2021-01-26  8:15   ` [PATCH v4 4/5] nvme-rdma: avoid IO error for nvme native multipath Chao Leng
2021-01-28  8:39   ` Sagi Grimberg
2021-01-28  8:39     ` Sagi Grimberg
2021-01-28  9:31     ` Chao Leng
2021-01-28  9:31       ` Chao Leng
2021-01-29  1:35       ` Sagi Grimberg
2021-01-29  1:35         ` Sagi Grimberg
2021-01-29  2:48         ` Chao Leng
2021-01-29  2:48           ` Chao Leng
2021-01-29  3:24           ` Sagi Grimberg
2021-01-29  3:24             ` Sagi Grimberg
2021-01-29  3:30             ` Chao Leng
2021-01-29  3:30               ` Chao Leng
2021-01-29  3:37               ` Sagi Grimberg
2021-01-29  3:37                 ` Sagi Grimberg
2021-01-29  3:50                 ` Chao Leng
2021-01-29  3:50                   ` Chao Leng
2021-01-29  3:37             ` Chao Leng
2021-01-29  3:37               ` Chao Leng
2021-01-26  8:15 ` [PATCH v4 5/5] nvme-fc: " Chao Leng
2021-01-26  8:15   ` Chao Leng

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=20210126081539.13320-5-lengchao@huawei.com \
    --to=lengchao@huawei.com \
    --cc=axboe@fb.com \
    --cc=axboe@kernel.dk \
    --cc=hch@lst.de \
    --cc=kbusch@kernel.org \
    --cc=linux-block@vger.kernel.org \
    --cc=linux-nvme@lists.infradead.org \
    --cc=sagi@grimberg.me \
    /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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.