From: jmoyer@redhat.com (Jeff Moyer)
Subject: [PATCH 04/47] block: provide a new BLK_EH_QUIESCED timeout return value
Date: Tue, 24 Nov 2015 11:34:22 -0500 [thread overview]
Message-ID: <x49wpt71hm9.fsf@segfault.boston.devel.redhat.com> (raw)
In-Reply-To: <20151124155609.GA6251@lst.de> (Christoph Hellwig's message of "Tue, 24 Nov 2015 16:56:09 +0100")
Christoph Hellwig <hch at lst.de> writes:
> We always set REQ_ATOM_COMPLETE before calling into ->timeout and thus
> even having a chance to REQ_ATOM_QUIESCED. Maybe we're talking past
> each other, so if it feels like I'm off track try to explain the
> race in a bit more detail.
Sure.
CPU 0 executes the following:
blk_rq_check_expired():
if (!blk_mark_rq_complete(rq)) // this succeeds, so we call blk_rq_timed_out
blk_rq_timed_out(rq);
blk_rq_timed_out():
if (q->rq_timed_out_fn)
ret = q->rq_timed_out_fn(req);
switch (ret) { // QUIESCED is returned
...
case BLK_EH_QUIESCED:
set_bit(REQ_ATOM_QUIESCED, &req->atomic_flags);
break;
CPU 1 takes an interrupt for the completion of the same request:
blk_complete_request():
if (!blk_mark_rq_complete(req) || // this fails, as it's already marked complete
test_and_clear_bit(REQ_ATOM_QUIESCED, &req->atomic_flags)) // this succeeds
__blk_complete_request(req); // so we complete the request
Later, after the adapter reset is finished, you mentioned that all
requests will be completed. My question is: will this result in a
double completion for this particular request?
I hope that's more clear.
-Jeff
next prev parent reply other threads:[~2015-11-24 16:34 UTC|newest]
Thread overview: 63+ messages / expand[flat|nested] mbox.gz Atom feed top
2015-11-20 16:34 NVMe mega patchbomb for Linux 4.5-rc Christoph Hellwig
2015-11-20 16:34 ` [PATCH 01/47] nvme: add missing unmaps in nvme_queue_rq Christoph Hellwig
2015-11-20 16:34 ` [PATCH 02/47] block: fix blk_abort_request for blk-mq drivers Christoph Hellwig
2015-11-20 21:43 ` Jeff Moyer
2015-11-20 21:47 ` Jens Axboe
2015-11-20 21:54 ` Jeff Moyer
2015-11-20 22:20 ` Jeff Moyer
2015-11-21 7:34 ` Christoph Hellwig
2015-11-20 16:34 ` [PATCH 03/47] block: defer timeouts to a workqueue Christoph Hellwig
2015-11-23 20:31 ` Jeff Moyer
2015-11-23 20:48 ` Christoph Hellwig
2015-11-23 20:59 ` Jeff Moyer
2015-11-20 16:34 ` [PATCH 04/47] block: provide a new BLK_EH_QUIESCED timeout return value Christoph Hellwig
2015-11-24 15:16 ` Jeff Moyer
2015-11-24 15:40 ` Christoph Hellwig
2015-11-24 15:51 ` Jeff Moyer
2015-11-24 15:56 ` Christoph Hellwig
2015-11-24 16:34 ` Jeff Moyer [this message]
2015-11-24 16:47 ` Keith Busch
2015-11-24 17:56 ` Christoph Hellwig
2015-11-24 18:12 ` Jeff Moyer
2015-11-24 19:40 ` Christoph Hellwig
2015-11-20 16:35 ` [PATCH 05/47] block: remoe REQ_ATOM_COMPLETE wrappers Christoph Hellwig
2015-11-23 21:23 ` Jeff Moyer
2015-11-24 21:22 ` Jens Axboe
2015-11-20 16:35 ` [PATCH 06/47] blk-mq: add a flags parameter to blk_mq_alloc_request Christoph Hellwig
2015-11-24 15:19 ` Jeff Moyer
2015-11-24 15:32 ` Christoph Hellwig
2015-11-24 21:21 ` Jens Axboe
2015-11-24 22:22 ` Christoph Hellwig
2015-11-24 22:25 ` Jens Axboe
2015-11-20 16:35 ` [PATCH 07/47] nvme: move struct nvme_iod to pci.c Christoph Hellwig
2015-11-20 16:35 ` [PATCH 08/47] nvme: split command submission helpers out of pci.c Christoph Hellwig
2015-11-20 16:35 ` [PATCH 09/47] nvme: add a vendor field to struct nvme_dev Christoph Hellwig
2015-11-20 16:35 ` [PATCH 10/47] nvme: use offset instead of a struct for registers Christoph Hellwig
2015-11-20 16:35 ` [PATCH 11/47] nvme: split a new struct nvme_ctrl out of struct nvme_dev Christoph Hellwig
2015-11-20 16:35 ` [PATCH 12/47] nvme: simplify nvme_setup_prps calling convention Christoph Hellwig
2015-11-20 16:35 ` [PATCH 13/47] nvme: refactor nvme_queue_rq Christoph Hellwig
2015-11-20 16:35 ` [PATCH 14/47] nvme: move nvme_error_status to common code Christoph Hellwig
2015-11-20 16:35 ` [PATCH 15/47] nvme: move nvme_setup_flush and nvme_setup_rw " Christoph Hellwig
2015-11-20 16:35 ` [PATCH 16/47] nvme: split __nvme_submit_sync_cmd Christoph Hellwig
2015-11-20 16:35 ` [PATCH 17/47] nvme: use the block layer for userspace passthrough metadata Christoph Hellwig
2015-11-20 16:35 ` [PATCH 18/47] nvme: move block_device_operations and ns/ctrl freeing to common code Christoph Hellwig
2015-11-20 16:35 ` [PATCH 19/47] nvme: add explicit quirk handling Christoph Hellwig
2015-11-20 16:35 ` [PATCH 20/47] nvme: add a common helper to read Identify Controller data Christoph Hellwig
2015-11-20 16:35 ` [PATCH 21/47] nvme: move the call to nvme_init_identify earlier Christoph Hellwig
2015-11-20 16:35 ` [PATCH 22/47] nvme: move namespace scanning to common code Christoph Hellwig
2015-11-20 16:35 ` [PATCH 23/47] nvme: move chardev and sysfs interface " Christoph Hellwig
2015-11-20 16:35 ` [PATCH 24/47] nvme: only add a controller to dev_list after it's been fully initialized Christoph Hellwig
2015-11-20 16:35 ` [PATCH 25/47] nvme: don't take the I/O queue q_lock in nvme_timeout Christoph Hellwig
2017-03-10 12:51 ` David Woodhouse
2017-03-10 14:24 ` Christoph Hellwig
2015-11-20 16:35 ` [PATCH 26/47] nvme: merge nvme_abort_req and nvme_timeout Christoph Hellwig
2015-11-20 16:35 ` [PATCH 27/47] nvme: do not restart the request timeout if we're resetting the controller Christoph Hellwig
2015-11-20 16:35 ` [PATCH 28/47] nvme: simplify resets Christoph Hellwig
2015-11-20 16:35 ` [PATCH 29/47] nvme: merge probe_work and reset_work Christoph Hellwig
2015-11-20 16:35 ` [PATCH 30/47] nvme: remove dead controllers from a work item Christoph Hellwig
2015-11-20 16:35 ` [PATCH 31/47] nvme: switch abort_limit to an atomic_t Christoph Hellwig
2015-11-20 16:35 ` [PATCH 32/47] NVMe: Implement namespace list scanning Christoph Hellwig
2015-11-20 16:35 ` [PATCH 33/47] NVMe: Use unbounded work queue for all work Christoph Hellwig
2015-11-20 16:35 ` [PATCH 34/47] NVMe: Remove device management handles on remove Christoph Hellwig
2015-11-20 16:50 ` NVMe mega patchbomb for Linux 4.5-rc Christoph Hellwig
2015-11-21 7:19 NVMe mega patchbomb for Linux 4.5-rc (resend) Christoph Hellwig
2015-11-21 7:19 ` [PATCH 04/47] block: provide a new BLK_EH_QUIESCED timeout return value 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=x49wpt71hm9.fsf@segfault.boston.devel.redhat.com \
--to=jmoyer@redhat.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).