From: Hannes Reinecke <hare@suse.de>
Date: Fri, 16 Apr 2021 13:46:20 +0200
Subject: nvme: sanitize KATO setting
Patch-mainline: v5.13-rc1
Git-commit: a70b81bd4d9d2d6c05cfe6ef2a10bccc2e04357a
References: bsc#1179825
According to the NVMe base spec the KATO commands should be sent
at half of the KATO interval, to properly account for round-trip
times.
As we now will only ever send one KATO command per connection we
can easily use the recommended values.
This also fixes a potential issue where the request timeout for
the KATO command does not match the value in the connect command,
which might be causing spurious connection drops from the target.
Signed-off-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Daniel Wagner <dwagner@suse.de>
---
drivers/nvme/host/core.c | 17 ++++++++++++++---
drivers/nvme/host/fabrics.c | 4 +---
drivers/nvme/host/nvme.h | 1 -
3 files changed, 15 insertions(+), 7 deletions(-)
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -985,6 +985,17 @@ static int nvme_submit_user_cmd(struct r
return ret;
}
+/*
+ * Recommended frequency for KATO commands per NVMe 1.4 section 7.12.1:
+ *
+ * The host should send Keep Alive commands at half of the Keep Alive Timeout
+ * accounting for transport roundtrip times [..].
+ */
+static void nvme_queue_keep_alive_work(struct nvme_ctrl *ctrl)
+{
+ queue_delayed_work(nvme_wq, &ctrl->ka_work, ctrl->kato * HZ / 2);
+}
+
static void nvme_keep_alive_end_io(struct request *rq, blk_status_t status)
{
struct nvme_ctrl *ctrl = rq->end_io_data;
@@ -1007,7 +1018,7 @@ static void nvme_keep_alive_end_io(struc
startka = true;
spin_unlock_irqrestore(&ctrl->lock, flags);
if (startka)
- queue_delayed_work(nvme_wq, &ctrl->ka_work, ctrl->kato * HZ);
+ nvme_queue_keep_alive_work(ctrl);
}
static void nvme_keep_alive_work(struct work_struct *work)
@@ -1021,7 +1032,7 @@ static void nvme_keep_alive_work(struct
dev_dbg(ctrl->device,
"reschedule traffic based keep-alive timer\n");
ctrl->comp_seen = false;
- queue_delayed_work(nvme_wq, &ctrl->ka_work, ctrl->kato * HZ);
+ nvme_queue_keep_alive_work(ctrl);
return;
}
@@ -1045,7 +1056,7 @@ static void nvme_start_keep_alive(struct
if (unlikely(ctrl->kato == 0))
return;
- queue_delayed_work(nvme_wq, &ctrl->ka_work, ctrl->kato * HZ);
+ nvme_queue_keep_alive_work(ctrl);
}
void nvme_stop_keep_alive(struct nvme_ctrl *ctrl)
--- a/drivers/nvme/host/fabrics.c
+++ b/drivers/nvme/host/fabrics.c
@@ -379,10 +379,8 @@ int nvmf_connect_admin_queue(struct nvme
/*
* Set keep-alive timeout in seconds granularity (ms * 1000)
- * and add a grace period for controller kato enforcement
*/
- cmd.connect.kato = ctrl->kato ?
- cpu_to_le32((ctrl->kato + NVME_KATO_GRACE) * 1000) : 0;
+ cmd.connect.kato = cpu_to_le32(ctrl->kato * 1000);
if (ctrl->opts->disable_sqflow)
cmd.connect.cattr |= NVME_CONNECT_DISABLE_SQFLOW;
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -26,7 +26,6 @@ extern unsigned int admin_timeout;
#define ADMIN_TIMEOUT (admin_timeout * HZ)
#define NVME_DEFAULT_KATO 5
-#define NVME_KATO_GRACE 10
#ifdef CONFIG_ARCH_NO_SG_CHAIN
#define NVME_INLINE_SG_CNT 0