diff mbox series

[v10,10/25] nvme-tcp: Deal with netdevice DOWN events

Message ID 20230126162136.13003-11-aaptel@nvidia.com (mailing list archive)
State Superseded
Delegated to: Netdev Maintainers
Headers show
Series nvme-tcp receive offloads | expand


Context Check Description
netdev/tree_selection success Guessed tree name to be net-next, async
netdev/fixes_present success Fixes tag not required for -next series
netdev/subject_prefix success Link
netdev/cover_letter success Series has a cover letter
netdev/patch_count fail Series longer than 15 patches (and no cover letter)
netdev/header_inline success No static functions without inline keyword in header files
netdev/build_32bit success Errors and warnings before: 0 this patch: 0
netdev/cc_maintainers success CCed 5 of 5 maintainers
netdev/build_clang success Errors and warnings before: 0 this patch: 0
netdev/module_param success Was 0 now: 0
netdev/verify_signedoff success Signed-off-by tag matches author and committer
netdev/check_selftest success No net selftest shell script
netdev/verify_fixes success No Fixes tag
netdev/build_allmodconfig_warn success Errors and warnings before: 0 this patch: 0
netdev/checkpatch success total: 0 errors, 0 warnings, 0 checks, 71 lines checked
netdev/kdoc success Errors and warnings before: 0 this patch: 0
netdev/source_inline success Was 0 now: 0

Commit Message

Aurelien Aptel Jan. 26, 2023, 4:21 p.m. UTC
From: Or Gerlitz <ogerlitz@nvidia.com>

For ddp setup/teardown and resync, the offloading logic
uses HW resources at the NIC driver such as SQ and CQ.

These resources are destroyed when the netdevice does down
and hence we must stop using them before the NIC driver
destroys them.

Use netdevice notifier for that matter -- offloaded connections
are stopped before the stack continues to call the NIC driver
close ndo.

We use the existing recovery flow which has the advantage
of resuming the offload once the connection is re-set.

This also buys us proper handling for the UNREGISTER event
b/c our offloading starts in the UP state, and down is always
there between up to unregister.

Signed-off-by: Or Gerlitz <ogerlitz@nvidia.com>
Signed-off-by: Boris Pismenny <borisp@nvidia.com>
Signed-off-by: Ben Ben-Ishay <benishay@nvidia.com>
Signed-off-by: Yoray Zack <yorayz@nvidia.com>
Signed-off-by: Shai Malin <smalin@nvidia.com>
Signed-off-by: Aurelien Aptel <aaptel@nvidia.com>
Reviewed-by: Chaitanya Kulkarni <kch@nvidia.com>
 drivers/nvme/host/tcp.c | 40 ++++++++++++++++++++++++++++++++++++++++
 1 file changed, 40 insertions(+)
diff mbox series


diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c
index 7e3feb694e46..732f7636a6fc 100644
--- a/drivers/nvme/host/tcp.c
+++ b/drivers/nvme/host/tcp.c
@@ -204,6 +204,7 @@  struct nvme_tcp_ctrl {
 static LIST_HEAD(nvme_tcp_ctrl_list);
 static DEFINE_MUTEX(nvme_tcp_ctrl_mutex);
+static struct notifier_block nvme_tcp_netdevice_nb;
 static struct workqueue_struct *nvme_tcp_wq;
 static const struct blk_mq_ops nvme_tcp_mq_ops;
 static const struct blk_mq_ops nvme_tcp_admin_mq_ops;
@@ -3129,6 +3130,31 @@  static struct nvme_ctrl *nvme_tcp_create_ctrl(struct device *dev,
 	return ERR_PTR(ret);
+static int nvme_tcp_netdev_event(struct notifier_block *this,
+				 unsigned long event, void *ptr)
+	struct net_device *ndev = netdev_notifier_info_to_dev(ptr);
+	struct nvme_tcp_ctrl *ctrl;
+	switch (event) {
+		mutex_lock(&nvme_tcp_ctrl_mutex);
+		list_for_each_entry(ctrl, &nvme_tcp_ctrl_list, list) {
+			if (ndev != ctrl->offloading_netdev)
+				continue;
+			nvme_tcp_error_recovery(&ctrl->ctrl);
+		}
+		mutex_unlock(&nvme_tcp_ctrl_mutex);
+		flush_workqueue(nvme_reset_wq);
+		/*
+		 * The associated controllers teardown has completed,
+		 * ddp contexts were also torn down so we should be
+		 * safe to continue...
+		 */
+	}
+	return NOTIFY_DONE;
 static struct nvmf_transport_ops nvme_tcp_transport = {
 	.name		= "tcp",
 	.module		= THIS_MODULE,
@@ -3143,13 +3169,26 @@  static struct nvmf_transport_ops nvme_tcp_transport = {
 static int __init nvme_tcp_init_module(void)
+	int ret;
 	nvme_tcp_wq = alloc_workqueue("nvme_tcp_wq",
 	if (!nvme_tcp_wq)
 		return -ENOMEM;
+	nvme_tcp_netdevice_nb.notifier_call = nvme_tcp_netdev_event;
+	ret = register_netdevice_notifier(&nvme_tcp_netdevice_nb);
+	if (ret) {
+		pr_err("failed to register netdev notifier\n");
+		goto out_free_workqueue;
+	}
 	return 0;
+	destroy_workqueue(nvme_tcp_wq);
+	return ret;
 static void __exit nvme_tcp_cleanup_module(void)
@@ -3157,6 +3196,7 @@  static void __exit nvme_tcp_cleanup_module(void)
 	struct nvme_tcp_ctrl *ctrl;
+	unregister_netdevice_notifier(&nvme_tcp_netdevice_nb);
 	list_for_each_entry(ctrl, &nvme_tcp_ctrl_list, list)