From: Ming Lei <ming.lei@redhat.com>
To: Jens Axboe <axboe@kernel.dk>, Christoph Hellwig <hch@lst.de>,
linux-block@vger.kernel.org
Cc: Sagi Grimberg <sagi@grimberg.me>,
linux-nvme@lists.infradead.org, Keith Busch <kbusch@kernel.org>,
Ming Lei <ming.lei@redhat.com>
Subject: [PATCH 4/5] nvme: paring quiesce/unquiesce
Date: Wed, 29 Sep 2021 12:15:58 +0800 [thread overview]
Message-ID: <20210929041559.701102-5-ming.lei@redhat.com> (raw)
In-Reply-To: <20210929041559.701102-1-ming.lei@redhat.com>
The current blk_mq_quiesce_queue() and blk_mq_unquiesce_queue() always
stops and starts the queue unconditionally. And there can be concurrent
quiesce/unquiesce coming from different unrelated code paths, so
unquiesce may come unexpectedly and start queue too early.
Prepare for supporting nested / concurrent quiesce/unquiesce, so that we
can address the above issue.
NVMe has very complicated quiesce/unquiesce use pattern, add one mutex
and queue stopped state in nvme_ctrl, so that we can make sure that
quiece/unquiesce is called in pair.
Signed-off-by: Ming Lei <ming.lei@redhat.com>
---
drivers/nvme/host/core.c | 51 ++++++++++++++++++++++++++++++++++++----
drivers/nvme/host/nvme.h | 4 ++++
2 files changed, 50 insertions(+), 5 deletions(-)
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 23fb746a8970..5d0b2eb38e43 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -4375,6 +4375,7 @@ int nvme_init_ctrl(struct nvme_ctrl *ctrl, struct device *dev,
clear_bit(NVME_CTRL_FAILFAST_EXPIRED, &ctrl->flags);
spin_lock_init(&ctrl->lock);
mutex_init(&ctrl->scan_lock);
+ mutex_init(&ctrl->queues_stop_lock);
INIT_LIST_HEAD(&ctrl->namespaces);
xa_init(&ctrl->cels);
init_rwsem(&ctrl->namespaces_rwsem);
@@ -4450,14 +4451,44 @@ int nvme_init_ctrl(struct nvme_ctrl *ctrl, struct device *dev,
}
EXPORT_SYMBOL_GPL(nvme_init_ctrl);
+static void __nvme_stop_admin_queue(struct nvme_ctrl *ctrl)
+{
+ lockdep_assert_held(&ctrl->queues_stop_lock);
+
+ if (!ctrl->admin_queue_stopped) {
+ blk_mq_quiesce_queue(ctrl->admin_q);
+ ctrl->admin_queue_stopped = true;
+ }
+}
+
+static void __nvme_start_admin_queue(struct nvme_ctrl *ctrl)
+{
+ lockdep_assert_held(&ctrl->queues_stop_lock);
+
+ if (ctrl->admin_queue_stopped) {
+ blk_mq_unquiesce_queue(ctrl->admin_q);
+ ctrl->admin_queue_stopped = false;
+ }
+}
+
static void nvme_start_ns_queue(struct nvme_ns *ns)
{
- blk_mq_unquiesce_queue(ns->queue);
+ lockdep_assert_held(&ns->ctrl->queues_stop_lock);
+
+ if (test_bit(NVME_NS_STOPPED, &ns->flags)) {
+ blk_mq_unquiesce_queue(ns->queue);
+ clear_bit(NVME_NS_STOPPED, &ns->flags);
+ }
}
static void nvme_stop_ns_queue(struct nvme_ns *ns)
{
- blk_mq_quiesce_queue(ns->queue);
+ lockdep_assert_held(&ns->ctrl->queues_stop_lock);
+
+ if (!test_bit(NVME_NS_STOPPED, &ns->flags)) {
+ blk_mq_quiesce_queue(ns->queue);
+ set_bit(NVME_NS_STOPPED, &ns->flags);
+ }
}
/*
@@ -4490,16 +4521,18 @@ void nvme_kill_queues(struct nvme_ctrl *ctrl)
{
struct nvme_ns *ns;
+ mutex_lock(&ctrl->queues_stop_lock);
down_read(&ctrl->namespaces_rwsem);
/* Forcibly unquiesce queues to avoid blocking dispatch */
if (ctrl->admin_q && !blk_queue_dying(ctrl->admin_q))
- nvme_start_admin_queue(ctrl);
+ __nvme_start_admin_queue(ctrl);
list_for_each_entry(ns, &ctrl->namespaces, list)
nvme_set_queue_dying(ns);
up_read(&ctrl->namespaces_rwsem);
+ mutex_unlock(&ctrl->queues_stop_lock);
}
EXPORT_SYMBOL_GPL(nvme_kill_queues);
@@ -4555,10 +4588,12 @@ void nvme_stop_queues(struct nvme_ctrl *ctrl)
{
struct nvme_ns *ns;
+ mutex_lock(&ctrl->queues_stop_lock);
down_read(&ctrl->namespaces_rwsem);
list_for_each_entry(ns, &ctrl->namespaces, list)
nvme_stop_ns_queue(ns);
up_read(&ctrl->namespaces_rwsem);
+ mutex_unlock(&ctrl->queues_stop_lock);
}
EXPORT_SYMBOL_GPL(nvme_stop_queues);
@@ -4566,22 +4601,28 @@ void nvme_start_queues(struct nvme_ctrl *ctrl)
{
struct nvme_ns *ns;
+ mutex_lock(&ctrl->queues_stop_lock);
down_read(&ctrl->namespaces_rwsem);
list_for_each_entry(ns, &ctrl->namespaces, list)
nvme_start_ns_queue(ns);
up_read(&ctrl->namespaces_rwsem);
+ mutex_unlock(&ctrl->queues_stop_lock);
}
EXPORT_SYMBOL_GPL(nvme_start_queues);
void nvme_stop_admin_queue(struct nvme_ctrl *ctrl)
{
- blk_mq_quiesce_queue(ctrl->admin_q);
+ mutex_lock(&ctrl->queues_stop_lock);
+ __nvme_stop_admin_queue(ctrl);
+ mutex_unlock(&ctrl->queues_stop_lock);
}
EXPORT_SYMBOL_GPL(nvme_stop_admin_queue);
void nvme_start_admin_queue(struct nvme_ctrl *ctrl)
{
- blk_mq_unquiesce_queue(ctrl->admin_q);
+ mutex_lock(&ctrl->queues_stop_lock);
+ __nvme_start_admin_queue(ctrl);
+ mutex_unlock(&ctrl->queues_stop_lock);
}
EXPORT_SYMBOL_GPL(nvme_start_admin_queue);
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index 47877a5f1515..3a02a370f025 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -341,6 +341,9 @@ struct nvme_ctrl {
struct page *discard_page;
unsigned long discard_page_busy;
+ bool admin_queue_stopped;
+ struct mutex queues_stop_lock;
+
struct nvme_fault_inject fault_inject;
};
@@ -457,6 +460,7 @@ struct nvme_ns {
#define NVME_NS_ANA_PENDING 2
#define NVME_NS_FORCE_RO 3
#define NVME_NS_READY 4
+#define NVME_NS_STOPPED 5
struct cdev cdev;
struct device cdev_device;
--
2.31.1
next prev parent reply other threads:[~2021-09-29 4:17 UTC|newest]
Thread overview: 10+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-09-29 4:15 [PATCH 0/5] blk-mq: support nested queue quiescing Ming Lei
2021-09-29 4:15 ` [PATCH 1/5] nvme: add APIs for stopping/starting admin queue Ming Lei
2021-09-29 4:15 ` [PATCH 2/5] nvme: apply nvme API to quiesce/unquiesce " Ming Lei
2021-09-29 4:15 ` [PATCH 3/5] nvme: prepare for pairing quiescing and unquiescing Ming Lei
2021-09-29 4:15 ` Ming Lei [this message]
2021-09-29 11:49 ` [PATCH 4/5] nvme: paring quiesce/unquiesce Sagi Grimberg
2021-09-29 15:28 ` Ming Lei
2021-09-29 4:15 ` [PATCH 5/5] blk-mq: support nested blk_mq_quiesce_queue() Ming Lei
2021-09-29 11:53 ` Sagi Grimberg
2021-09-29 15:44 ` Ming Lei
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=20210929041559.701102-5-ming.lei@redhat.com \
--to=ming.lei@redhat.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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox