blob: 4ed72a2a786c259cf1cd932a57a5e27841571f18 [file] [log] [blame]
From 4939519be5763d83b856a0a7cbcddf688f53a2cc Mon Sep 17 00:00:00 2001
From: Sasha Levin <>
Date: Thu, 24 Mar 2022 13:05:11 -0600
Subject: nvme-multipath: fix hang when disk goes live over reconnect
From: Anton Eidelman <>
[ Upstream commit a4a6f3c8f61c3cfbda4998ad94596059ad7e4332 ]
nvme_mpath_init_identify() invoked from nvme_init_identify() fetches a
fresh ANA log from the ctrl. This is essential to have an up to date
path states for both existing namespaces and for those scan_work may
discover once the ctrl is up.
This happens in the following cases:
1) A new ctrl is being connected.
2) An existing ctrl is successfully reconnected.
3) An existing ctrl is being reset.
While in (1) ctrl->namespaces is empty, (2 & 3) may have namespaces, and
nvme_read_ana_log() may call nvme_update_ns_ana_state().
This result in a hang when the ANA state of an existing namespace changes
and makes the disk live: nvme_mpath_set_live() issues IO to the namespace
through the ctrl, which does NOT have IO queues yet.
See sample hang below.
- nvme_update_ns_ana_state() to call set_live only if ctrl is live
- nvme_read_ana_log() call from nvme_mpath_init_identify()
therefore only fetches and parses the ANA log;
any erros in this process will fail the ctrl setup as appropriate;
- a separate function nvme_mpath_update()
is called in nvme_start_ctrl();
this parses the ANA log without fetching it.
At this point the ctrl is live,
therefore, disks can be set live normally.
Sample failure:
nvme nvme0: starting error recovery
nvme nvme0: Reconnecting in 10 seconds...
block nvme0n6: no usable path - requeuing I/O
INFO: task kworker/u8:3:312 blocked for more than 122 seconds.
Tainted: G E 5.14.5-1.el7.elrepo.x86_64 #1
Workqueue: nvme-wq nvme_tcp_reconnect_ctrl_work [nvme_tcp]
Call Trace:
nvme_mpath_set_live+0x138/0x1b0 [nvme_core]
nvme_update_ns_ana_state+0x2b/0x30 [nvme_core]
nvme_update_ana_state+0xca/0xe0 [nvme_core]
nvme_parse_ana_log+0xac/0x170 [nvme_core]
nvme_read_ana_log+0x7d/0xe0 [nvme_core]
nvme_mpath_init_identify+0x105/0x150 [nvme_core]
nvme_init_identify+0x2df/0x4d0 [nvme_core]
nvme_init_ctrl_finish+0x8d/0x3b0 [nvme_core]
nvme_tcp_setup_ctrl+0x337/0x390 [nvme_tcp]
nvme_tcp_reconnect_ctrl_work+0x24/0x40 [nvme_tcp]
Signed-off-by: Anton Eidelman <>
Reviewed-by: Sagi Grimberg <>
Signed-off-by: Christoph Hellwig <>
Signed-off-by: Sasha Levin <>
drivers/nvme/host/core.c | 1 +
drivers/nvme/host/multipath.c | 25 +++++++++++++++++++++++--
drivers/nvme/host/nvme.h | 4 ++++
3 files changed, 28 insertions(+), 2 deletions(-)
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index ad4f1cfbad2e..e73a5c62a858 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -4420,6 +4420,7 @@ void nvme_start_ctrl(struct nvme_ctrl *ctrl)
if (ctrl->queue_count > 1) {
+ nvme_mpath_update(ctrl);
diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c
index 18a756444d5a..a9e15c8f907b 100644
--- a/drivers/nvme/host/multipath.c
+++ b/drivers/nvme/host/multipath.c
@@ -484,8 +484,17 @@ static void nvme_update_ns_ana_state(struct nvme_ana_group_desc *desc,
ns->ana_grpid = le32_to_cpu(desc->grpid);
ns->ana_state = desc->state;
clear_bit(NVME_NS_ANA_PENDING, &ns->flags);
- if (nvme_state_is_live(ns->ana_state))
+ /*
+ * nvme_mpath_set_live() will trigger I/O to the multipath path device
+ * and in turn to this path device. However we cannot accept this I/O
+ * if the controller is not live. This may deadlock if called from
+ * nvme_mpath_init_identify() and the ctrl will never complete
+ * initialization, preventing I/O from completing. For this case we
+ * will reprocess the ANA log page in nvme_mpath_update() once the
+ * controller is ready.
+ */
+ if (nvme_state_is_live(ns->ana_state) &&
+ ns->ctrl->state == NVME_CTRL_LIVE)
@@ -572,6 +581,18 @@ static void nvme_ana_work(struct work_struct *work)
+void nvme_mpath_update(struct nvme_ctrl *ctrl)
+ u32 nr_change_groups = 0;
+ if (!ctrl->ana_log_buf)
+ return;
+ mutex_lock(&ctrl->ana_lock);
+ nvme_parse_ana_log(ctrl, &nr_change_groups, nvme_update_ana_state);
+ mutex_unlock(&ctrl->ana_lock);
static void nvme_anatt_timeout(struct timer_list *t)
struct nvme_ctrl *ctrl = from_timer(ctrl, t, anatt_timer);
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index 10e5ae3a8c0d..95b9657cabaf 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -712,6 +712,7 @@ void nvme_mpath_add_disk(struct nvme_ns *ns, struct nvme_id_ns *id);
void nvme_mpath_remove_disk(struct nvme_ns_head *head);
int nvme_mpath_init_identify(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id);
void nvme_mpath_init_ctrl(struct nvme_ctrl *ctrl);
+void nvme_mpath_update(struct nvme_ctrl *ctrl);
void nvme_mpath_uninit(struct nvme_ctrl *ctrl);
void nvme_mpath_stop(struct nvme_ctrl *ctrl);
bool nvme_mpath_clear_current_path(struct nvme_ns *ns);
@@ -798,6 +799,9 @@ static inline int nvme_mpath_init_identify(struct nvme_ctrl *ctrl,
"Please enable CONFIG_NVME_MULTIPATH for full support of multi-port devices.\n");
return 0;
+static inline void nvme_mpath_update(struct nvme_ctrl *ctrl)
static inline void nvme_mpath_uninit(struct nvme_ctrl *ctrl)