From d3e8b1858734bf46cda495be4165787b9a3981a6 Mon Sep 17 00:00:00 2001
From: Keith Busch <kbusch@kernel.org>
Date: Mon, 18 Dec 2023 08:19:39 -0800
Subject: [PATCH 1/2] Revert "nvme-fc: fix race between error recovery and
creating association"
The commit was identified to might sleep in invalid context and is
blocking regression testing.
This reverts commit ee6fdc5055e916b1dd497f11260d4901c4c1e55e.
Link: https://lore.kernel.org/linux-nvme/hkhl56n665uvc6t5d6h3wtx7utkcorw4xlwi7d2t2bnonavhe6@xaan6pu43ap6/
Link: https://lists.infradead.org/pipermail/linux-nvme/2023-December/043756.html
Reported-by: Daniel Wagner <dwagner@suse.de>
Reported-by: Maurizio Lombardi <mlombard@redhat.com>
Cc: Michael Liang <mliang@purestorage.com>
Tested-by: Daniel Wagner <dwagner@suse.de>
Reviewed-by: Daniel Wagner <dwagner@suse.de>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
drivers/nvme/host/fc.c | 21 +++++----------------
1 file changed, 5 insertions(+), 16 deletions(-)
diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c
index fb22976a36a8..1d51925ea67f 100644
--- a/drivers/nvme/host/fc.c
+++ b/drivers/nvme/host/fc.c
@@ -2548,24 +2548,17 @@ nvme_fc_error_recovery(struct nvme_fc_ctrl *ctrl, char *errmsg)
* the controller. Abort any ios on the association and let the
* create_association error path resolve things.
*/
- enum nvme_ctrl_state state;
- unsigned long flags;
-
- spin_lock_irqsave(&ctrl->lock, flags);
- state = ctrl->ctrl.state;
- if (state == NVME_CTRL_CONNECTING) {
- set_bit(ASSOC_FAILED, &ctrl->flags);
- spin_unlock_irqrestore(&ctrl->lock, flags);
+ if (ctrl->ctrl.state == NVME_CTRL_CONNECTING) {
__nvme_fc_abort_outstanding_ios(ctrl, true);
+ set_bit(ASSOC_FAILED, &ctrl->flags);
dev_warn(ctrl->ctrl.device,
"NVME-FC{%d}: transport error during (re)connect\n",
ctrl->cnum);
return;
}
- spin_unlock_irqrestore(&ctrl->lock, flags);
/* Otherwise, only proceed if in LIVE state - e.g. on first error */
- if (state != NVME_CTRL_LIVE)
+ if (ctrl->ctrl.state != NVME_CTRL_LIVE)
return;
dev_warn(ctrl->ctrl.device,
@@ -3180,16 +3173,12 @@ nvme_fc_create_association(struct nvme_fc_ctrl *ctrl)
else
ret = nvme_fc_recreate_io_queues(ctrl);
}
-
- spin_lock_irqsave(&ctrl->lock, flags);
if (!ret && test_bit(ASSOC_FAILED, &ctrl->flags))
ret = -EIO;
- if (ret) {
- spin_unlock_irqrestore(&ctrl->lock, flags);
+ if (ret)
goto out_term_aen_ops;
- }
+
changed = nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_LIVE);
- spin_unlock_irqrestore(&ctrl->lock, flags);
ctrl->ctrl.nr_reconnects = 0;
From f6fe0b2d35457c10ec37acc209d19726bdc16dbd Mon Sep 17 00:00:00 2001
From: Maurizio Lombardi <mlombard@redhat.com>
Date: Tue, 19 Dec 2023 17:48:23 +0100
Subject: [PATCH 2/2] nvme-pci: fix sleeping function called from interrupt
context
the nvme_handle_cqe() interrupt handler calls nvme_complete_async_event()
but the latter may call nvme_auth_stop() which is a blocking function.
Sleeping functions can't be called in interrupt context
BUG: sleeping function called from invalid context
in_atomic(): 1, irqs_disabled(): 1, non_block: 0, pid: 0, name: swapper/15
Call Trace:
<IRQ>
__cancel_work_timer+0x31e/0x460
? nvme_change_ctrl_state+0xcf/0x3c0 [nvme_core]
? nvme_change_ctrl_state+0xcf/0x3c0 [nvme_core]
nvme_complete_async_event+0x365/0x480 [nvme_core]
nvme_poll_cq+0x262/0xe50 [nvme]
Fix the bug by moving nvme_auth_stop() to fw_act_work
(executed by the nvme_wq workqueue)
Fixes: f50fff73d620 ("nvme: implement In-Band authentication")
Signed-off-by: Maurizio Lombardi <mlombard@redhat.com>
Reviewed-by: Jens Axboe <axboe@kernel.dk>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
drivers/nvme/host/core.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 8ebdfd623e0f..60f14019f981 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -4137,6 +4137,8 @@ static void nvme_fw_act_work(struct work_struct *work)
struct nvme_ctrl, fw_act_work);
unsigned long fw_act_timeout;
+ nvme_auth_stop(ctrl);
+
if (ctrl->mtfa)
fw_act_timeout = jiffies +
msecs_to_jiffies(ctrl->mtfa * 100);
@@ -4192,7 +4194,6 @@ static bool nvme_handle_aen_notice(struct nvme_ctrl *ctrl, u32 result)
* firmware activation.
*/
if (nvme_change_ctrl_state(ctrl, NVME_CTRL_RESETTING)) {
- nvme_auth_stop(ctrl);
requeue = false;
queue_work(nvme_wq, &ctrl->fw_act_work);
}