From: sagi@grimberg.me (Sagi Grimberg)
Subject: [PATCH 5/7] nvme-rdma: Don't local invalidate if the queue is not live
Date: Wed, 11 Oct 2017 15:29:10 +0300 [thread overview]
Message-ID: <1507724952-13917-6-git-send-email-sagi@grimberg.me> (raw)
In-Reply-To: <1507724952-13917-1-git-send-email-sagi@grimberg.me>
No chance for the local invalidate to succeed if the queue-pair
is in error state. Most likely the target will do a remote
invalidation of our mr so not a big loss on the test_bit.
Signed-off-by: Sagi Grimberg <sagi at grimberg.me>
---
drivers/nvme/host/rdma.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c
index 93f4dd0b6f26..e3fe57011fcb 100644
--- a/drivers/nvme/host/rdma.c
+++ b/drivers/nvme/host/rdma.c
@@ -1055,7 +1055,7 @@ static void nvme_rdma_unmap_data(struct nvme_rdma_queue *queue,
if (!blk_rq_bytes(rq))
return;
- if (req->mr->need_inval) {
+ if (req->mr->need_inval && test_bit(NVME_RDMA_Q_LIVE, &req->queue->flags)) {
res = nvme_rdma_inv_rkey(queue, req);
if (unlikely(res < 0)) {
dev_err(ctrl->ctrl.device,
--
2.7.4
next prev parent reply other threads:[~2017-10-11 12:29 UTC|newest]
Thread overview: 17+ messages / expand[flat|nested] mbox.gz Atom feed top
2017-10-11 12:29 [PATCH 0/7] Some nvme-rdma host patches for 4.15 Sagi Grimberg
2017-10-11 12:29 ` [PATCH 1/7] nvme-rdma: pass tagset to directly nvme_rdma_free_tagset Sagi Grimberg
2017-10-11 13:33 ` Johannes Thumshirn
2017-10-11 18:38 ` Max Gurtovoy
2017-10-11 12:29 ` [PATCH 2/7] nvme-rdma: fix wrong logging message Sagi Grimberg
2017-10-11 13:34 ` Johannes Thumshirn
2017-10-11 18:40 ` Max Gurtovoy
2017-10-11 12:29 ` [PATCH 3/7] nvme-rdma: move assignment to declaration Sagi Grimberg
2017-10-11 13:34 ` Johannes Thumshirn
2017-10-11 18:44 ` Max Gurtovoy
2017-10-11 12:29 ` [PATCH 4/7] nvme-rdma: Check that reinit_request got a proper mr Sagi Grimberg
2017-10-11 13:35 ` Johannes Thumshirn
2017-10-11 12:29 ` Sagi Grimberg [this message]
2017-10-11 12:29 ` [PATCH 6/7] nvme-rdma: teardown admin/io queues once on error recovery Sagi Grimberg
2017-10-15 8:05 ` Nitzan Carmi
2017-10-11 12:29 ` [PATCH 7/7] nvme-rdma: change queue flag semantics DELETING -> ALLOCATED Sagi Grimberg
2017-10-17 6:51 ` [PATCH 0/7] Some nvme-rdma host patches for 4.15 Christoph Hellwig
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=1507724952-13917-6-git-send-email-sagi@grimberg.me \
--to=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 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).