From: Max Gurtovoy <mgurtovoy@nvidia.com>
To: <linux-nvme@lists.infradead.org>, <hch@lst.de>,
<kbusch@kernel.org>, <sagi@grimberg.me>
Cc: <chaitanyak@nvidia.com>, <israelr@nvidia.com>, <oren@nvidia.com>,
<hare@suse.de>, <jsmart2021@gmail.com>,
Max Gurtovoy <mgurtovoy@nvidia.com>
Subject: [PATCH 05/10] nvme/nvme-fabrics: introduce nvmf_error_recovery_work API
Date: Wed, 20 Oct 2021 13:38:39 +0300 [thread overview]
Message-ID: <20211020103844.7533-6-mgurtovoy@nvidia.com> (raw)
In-Reply-To: <20211020103844.7533-1-mgurtovoy@nvidia.com>
Error recovery work is duplicated in RDMA and TCP transports. Move this
logic to common code. For that, introduce 2 new ctrl ops to teardown IO
and admin queue.
Also update the RDMA/TCP transport drivers to use this API and remove
the duplicated code.
Reviewed-by: Israel Rukshin <israelr@nvidia.com>
Reviewed-by: Chaitanya Kulkarni <kch@nvidia.com>
Signed-off-by: Max Gurtovoy <mgurtovoy@nvidia.com>
---
drivers/nvme/host/fabrics.c | 23 +++++++++++
drivers/nvme/host/fabrics.h | 1 +
drivers/nvme/host/nvme.h | 4 ++
drivers/nvme/host/rdma.c | 78 +++++++++++++++----------------------
drivers/nvme/host/tcp.c | 46 +++++++---------------
5 files changed, 73 insertions(+), 79 deletions(-)
diff --git a/drivers/nvme/host/fabrics.c b/drivers/nvme/host/fabrics.c
index 2edd086fa922..5a770196eb60 100644
--- a/drivers/nvme/host/fabrics.c
+++ b/drivers/nvme/host/fabrics.c
@@ -493,6 +493,29 @@ void nvmf_reconnect_or_remove(struct nvme_ctrl *ctrl)
}
EXPORT_SYMBOL_GPL(nvmf_reconnect_or_remove);
+void nvmf_error_recovery_work(struct work_struct *work)
+{
+ struct nvme_ctrl *ctrl = container_of(work,
+ struct nvme_ctrl, err_work);
+
+ nvme_stop_keep_alive(ctrl);
+ ctrl->ops->teardown_ctrl_io_queues(ctrl, false);
+ /* unquiesce to fail fast pending requests */
+ nvme_start_queues(ctrl);
+ ctrl->ops->teardown_ctrl_admin_queue(ctrl, false);
+ blk_mq_unquiesce_queue(ctrl->admin_q);
+
+ if (!nvme_change_ctrl_state(ctrl, NVME_CTRL_CONNECTING)) {
+ /* state change failure is ok if we started ctrl delete */
+ WARN_ON_ONCE(ctrl->state != NVME_CTRL_DELETING &&
+ ctrl->state != NVME_CTRL_DELETING_NOIO);
+ return;
+ }
+
+ nvmf_reconnect_or_remove(ctrl);
+}
+EXPORT_SYMBOL_GPL(nvmf_error_recovery_work);
+
void nvmf_error_recovery(struct nvme_ctrl *ctrl)
{
if (!nvme_change_ctrl_state(ctrl, NVME_CTRL_RESETTING))
diff --git a/drivers/nvme/host/fabrics.h b/drivers/nvme/host/fabrics.h
index 3d8ec7133fc8..8655eff74ed0 100644
--- a/drivers/nvme/host/fabrics.h
+++ b/drivers/nvme/host/fabrics.h
@@ -190,6 +190,7 @@ int nvmf_get_address(struct nvme_ctrl *ctrl, char *buf, int size);
bool nvmf_should_reconnect(struct nvme_ctrl *ctrl);
void nvmf_reconnect_or_remove(struct nvme_ctrl *ctrl);
void nvmf_error_recovery(struct nvme_ctrl *ctrl);
+void nvmf_error_recovery_work(struct work_struct *work);
bool nvmf_ip_options_match(struct nvme_ctrl *ctrl,
struct nvmf_ctrl_options *opts);
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index f9e1ce93d61d..5cdf2ec45e9a 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -493,6 +493,10 @@ struct nvme_ctrl_ops {
void (*submit_async_event)(struct nvme_ctrl *ctrl);
void (*delete_ctrl)(struct nvme_ctrl *ctrl);
int (*get_address)(struct nvme_ctrl *ctrl, char *buf, int size);
+
+ /* Fabrics only */
+ void (*teardown_ctrl_io_queues)(struct nvme_ctrl *ctrl, bool remove);
+ void (*teardown_ctrl_admin_queue)(struct nvme_ctrl *ctrl, bool remove);
};
/*
diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c
index 1c57e371af61..4e42f1956181 100644
--- a/drivers/nvme/host/rdma.c
+++ b/drivers/nvme/host/rdma.c
@@ -1019,29 +1019,33 @@ static int nvme_rdma_configure_io_queues(struct nvme_rdma_ctrl *ctrl, bool new)
return ret;
}
-static void nvme_rdma_teardown_admin_queue(struct nvme_rdma_ctrl *ctrl,
+static void nvme_rdma_teardown_admin_queue(struct nvme_ctrl *nctrl,
bool remove)
{
- blk_mq_quiesce_queue(ctrl->ctrl.admin_q);
- blk_sync_queue(ctrl->ctrl.admin_q);
+ struct nvme_rdma_ctrl *ctrl = to_rdma_ctrl(nctrl);
+
+ blk_mq_quiesce_queue(nctrl->admin_q);
+ blk_sync_queue(nctrl->admin_q);
nvme_rdma_stop_queue(&ctrl->queues[0]);
- nvme_cancel_admin_tagset(&ctrl->ctrl);
+ nvme_cancel_admin_tagset(nctrl);
if (remove)
- blk_mq_unquiesce_queue(ctrl->ctrl.admin_q);
+ blk_mq_unquiesce_queue(nctrl->admin_q);
nvme_rdma_destroy_admin_queue(ctrl, remove);
}
-static void nvme_rdma_teardown_io_queues(struct nvme_rdma_ctrl *ctrl,
+static void nvme_rdma_teardown_io_queues(struct nvme_ctrl *nctrl,
bool remove)
{
- if (ctrl->ctrl.queue_count > 1) {
- nvme_start_freeze(&ctrl->ctrl);
- nvme_stop_queues(&ctrl->ctrl);
- nvme_sync_io_queues(&ctrl->ctrl);
+ struct nvme_rdma_ctrl *ctrl = to_rdma_ctrl(nctrl);
+
+ if (nctrl->queue_count > 1) {
+ nvme_start_freeze(nctrl);
+ nvme_stop_queues(nctrl);
+ nvme_sync_io_queues(nctrl);
nvme_rdma_stop_io_queues(ctrl);
- nvme_cancel_tagset(&ctrl->ctrl);
+ nvme_cancel_tagset(nctrl);
if (remove)
- nvme_start_queues(&ctrl->ctrl);
+ nvme_start_queues(nctrl);
nvme_rdma_destroy_io_queues(ctrl, remove);
}
}
@@ -1164,27 +1168,6 @@ static void nvme_rdma_reconnect_ctrl_work(struct work_struct *work)
nvmf_reconnect_or_remove(&ctrl->ctrl);
}
-static void nvme_rdma_error_recovery_work(struct work_struct *work)
-{
- struct nvme_rdma_ctrl *ctrl = container_of(work,
- struct nvme_rdma_ctrl, ctrl.err_work);
-
- nvme_stop_keep_alive(&ctrl->ctrl);
- nvme_rdma_teardown_io_queues(ctrl, false);
- nvme_start_queues(&ctrl->ctrl);
- nvme_rdma_teardown_admin_queue(ctrl, false);
- blk_mq_unquiesce_queue(ctrl->ctrl.admin_q);
-
- if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_CONNECTING)) {
- /* state change failure is ok if we started ctrl delete */
- WARN_ON_ONCE(ctrl->ctrl.state != NVME_CTRL_DELETING &&
- ctrl->ctrl.state != NVME_CTRL_DELETING_NOIO);
- return;
- }
-
- nvmf_reconnect_or_remove(&ctrl->ctrl);
-}
-
static void nvme_rdma_end_request(struct nvme_rdma_request *req)
{
struct request *rq = blk_mq_rq_from_pdu(req);
@@ -2201,13 +2184,13 @@ static void nvme_rdma_shutdown_ctrl(struct nvme_rdma_ctrl *ctrl, bool shutdown)
cancel_work_sync(&ctrl->ctrl.err_work);
cancel_delayed_work_sync(&ctrl->ctrl.connect_work);
- nvme_rdma_teardown_io_queues(ctrl, shutdown);
+ nvme_rdma_teardown_io_queues(&ctrl->ctrl, shutdown);
blk_mq_quiesce_queue(ctrl->ctrl.admin_q);
if (shutdown)
nvme_shutdown_ctrl(&ctrl->ctrl);
else
nvme_disable_ctrl(&ctrl->ctrl);
- nvme_rdma_teardown_admin_queue(ctrl, shutdown);
+ nvme_rdma_teardown_admin_queue(&ctrl->ctrl, shutdown);
}
static void nvme_rdma_delete_ctrl(struct nvme_ctrl *ctrl)
@@ -2240,16 +2223,19 @@ static void nvme_rdma_reset_ctrl_work(struct work_struct *work)
}
static const struct nvme_ctrl_ops nvme_rdma_ctrl_ops = {
- .name = "rdma",
- .module = THIS_MODULE,
- .flags = NVME_F_FABRICS | NVME_F_METADATA_SUPPORTED,
- .reg_read32 = nvmf_reg_read32,
- .reg_read64 = nvmf_reg_read64,
- .reg_write32 = nvmf_reg_write32,
- .free_ctrl = nvme_rdma_free_ctrl,
- .submit_async_event = nvme_rdma_submit_async_event,
- .delete_ctrl = nvme_rdma_delete_ctrl,
- .get_address = nvmf_get_address,
+ .name = "rdma",
+ .module = THIS_MODULE,
+ .flags = NVME_F_FABRICS |
+ NVME_F_METADATA_SUPPORTED,
+ .reg_read32 = nvmf_reg_read32,
+ .reg_read64 = nvmf_reg_read64,
+ .reg_write32 = nvmf_reg_write32,
+ .free_ctrl = nvme_rdma_free_ctrl,
+ .submit_async_event = nvme_rdma_submit_async_event,
+ .delete_ctrl = nvme_rdma_delete_ctrl,
+ .get_address = nvmf_get_address,
+ .teardown_ctrl_io_queues = nvme_rdma_teardown_io_queues,
+ .teardown_ctrl_admin_queue = nvme_rdma_teardown_admin_queue,
};
/*
@@ -2329,7 +2315,7 @@ static struct nvme_ctrl *nvme_rdma_create_ctrl(struct device *dev,
INIT_DELAYED_WORK(&ctrl->ctrl.connect_work,
nvme_rdma_reconnect_ctrl_work);
- INIT_WORK(&ctrl->ctrl.err_work, nvme_rdma_error_recovery_work);
+ INIT_WORK(&ctrl->ctrl.err_work, nvmf_error_recovery_work);
INIT_WORK(&ctrl->ctrl.reset_work, nvme_rdma_reset_ctrl_work);
ctrl->ctrl.queue_count = opts->nr_io_queues + opts->nr_write_queues +
diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c
index fe1f2fec457b..679eb3c2b8fd 100644
--- a/drivers/nvme/host/tcp.c
+++ b/drivers/nvme/host/tcp.c
@@ -2056,28 +2056,6 @@ static void nvme_tcp_reconnect_ctrl_work(struct work_struct *work)
nvmf_reconnect_or_remove(ctrl);
}
-static void nvme_tcp_error_recovery_work(struct work_struct *work)
-{
- struct nvme_ctrl *ctrl = container_of(work,
- struct nvme_ctrl, err_work);
-
- nvme_stop_keep_alive(ctrl);
- nvme_tcp_teardown_io_queues(ctrl, false);
- /* unquiesce to fail fast pending requests */
- nvme_start_queues(ctrl);
- nvme_tcp_teardown_admin_queue(ctrl, false);
- blk_mq_unquiesce_queue(ctrl->admin_q);
-
- if (!nvme_change_ctrl_state(ctrl, NVME_CTRL_CONNECTING)) {
- /* state change failure is ok if we started ctrl delete */
- WARN_ON_ONCE(ctrl->state != NVME_CTRL_DELETING &&
- ctrl->state != NVME_CTRL_DELETING_NOIO);
- return;
- }
-
- nvmf_reconnect_or_remove(ctrl);
-}
-
static void nvme_tcp_teardown_ctrl(struct nvme_ctrl *ctrl, bool shutdown)
{
cancel_work_sync(&ctrl->err_work);
@@ -2435,16 +2413,18 @@ static const struct blk_mq_ops nvme_tcp_admin_mq_ops = {
};
static const struct nvme_ctrl_ops nvme_tcp_ctrl_ops = {
- .name = "tcp",
- .module = THIS_MODULE,
- .flags = NVME_F_FABRICS,
- .reg_read32 = nvmf_reg_read32,
- .reg_read64 = nvmf_reg_read64,
- .reg_write32 = nvmf_reg_write32,
- .free_ctrl = nvme_tcp_free_ctrl,
- .submit_async_event = nvme_tcp_submit_async_event,
- .delete_ctrl = nvme_tcp_delete_ctrl,
- .get_address = nvmf_get_address,
+ .name = "tcp",
+ .module = THIS_MODULE,
+ .flags = NVME_F_FABRICS,
+ .reg_read32 = nvmf_reg_read32,
+ .reg_read64 = nvmf_reg_read64,
+ .reg_write32 = nvmf_reg_write32,
+ .free_ctrl = nvme_tcp_free_ctrl,
+ .submit_async_event = nvme_tcp_submit_async_event,
+ .delete_ctrl = nvme_tcp_delete_ctrl,
+ .get_address = nvmf_get_address,
+ .teardown_ctrl_io_queues = nvme_tcp_teardown_io_queues,
+ .teardown_ctrl_admin_queue = nvme_tcp_teardown_admin_queue,
};
static bool
@@ -2483,7 +2463,7 @@ static struct nvme_ctrl *nvme_tcp_create_ctrl(struct device *dev,
INIT_DELAYED_WORK(&ctrl->ctrl.connect_work,
nvme_tcp_reconnect_ctrl_work);
- INIT_WORK(&ctrl->ctrl.err_work, nvme_tcp_error_recovery_work);
+ INIT_WORK(&ctrl->ctrl.err_work, nvmf_error_recovery_work);
INIT_WORK(&ctrl->ctrl.reset_work, nvme_reset_ctrl_work);
if (!(opts->mask & NVMF_OPT_TRSVCID)) {
--
2.18.1
next prev parent reply other threads:[~2021-10-20 10:40 UTC|newest]
Thread overview: 21+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-10-20 10:38 [PATCH v2 0/10] Centrelize common fabrics code to core drivers Max Gurtovoy
2021-10-20 10:38 ` [PATCH 01/10] nvme: add connect_work attribute to nvme ctrl Max Gurtovoy
2021-11-02 22:59 ` James Smart
2021-10-20 10:38 ` [PATCH 02/10] nvme-fabrics: introduce nvmf_reconnect_or_remove API Max Gurtovoy
2021-11-02 23:38 ` James Smart
2021-10-20 10:38 ` [PATCH 03/10] nvme: add err_work attribute to nvme ctrl Max Gurtovoy
2021-10-20 11:05 ` Hannes Reinecke
2021-11-02 23:53 ` James Smart
2021-10-20 10:38 ` [PATCH 04/10] nvme-fabrics: introduce nvmf_error_recovery API Max Gurtovoy
2021-11-02 23:59 ` James Smart
2021-10-20 10:38 ` Max Gurtovoy [this message]
2021-11-03 0:04 ` [PATCH 05/10] nvme/nvme-fabrics: introduce nvmf_error_recovery_work API James Smart
2021-10-20 10:38 ` [PATCH 06/10] nvme/nvme-fabrics: introduce nvmf_reconnect_ctrl_work API Max Gurtovoy
2021-11-03 0:15 ` James Smart
2021-10-20 10:38 ` [PATCH 07/10] nvme-fabrics: add nvmf_init_ctrl/nvmf_uninit_ctrl API Max Gurtovoy
2021-11-03 0:19 ` James Smart
2021-10-20 10:38 ` [PATCH 08/10] nvme-rdma: update WARN_ON condition during reset Max Gurtovoy
2021-10-20 10:38 ` [PATCH 09/10] nvme/nvme-fabrics: move reset ctrl flow to common code Max Gurtovoy
2021-11-03 0:27 ` James Smart
2021-10-20 10:38 ` [PATCH 10/10] nvme-fabrics: set common attributes during nvmf_init_ctrl Max Gurtovoy
2021-11-03 0:30 ` James Smart
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=20211020103844.7533-6-mgurtovoy@nvidia.com \
--to=mgurtovoy@nvidia.com \
--cc=chaitanyak@nvidia.com \
--cc=hare@suse.de \
--cc=hch@lst.de \
--cc=israelr@nvidia.com \
--cc=jsmart2021@gmail.com \
--cc=kbusch@kernel.org \
--cc=linux-nvme@lists.infradead.org \
--cc=oren@nvidia.com \
--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