[PATCH 2/2] nvme: sanitize KATO setting

[Hannes Reinecke]

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 at suse.de>
---
 drivers/nvme/host/core.c    | 14 ++++++++++----
 drivers/nvme/host/fabrics.c |  2 +-
 drivers/nvme/host/nvme.h    |  1 -
 3 files changed, 11 insertions(+), 6 deletions(-)

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 9b8596eb4047..eedbee80b7b9 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -1226,8 +1226,11 @@ static void nvme_keep_alive_end_io(struct request *rq, blk_status_t status)
 	    ctrl->state == NVME_CTRL_CONNECTING)
 		startka = true;
 	spin_unlock_irqrestore(&ctrl->lock, flags);
-	if (startka)
-		queue_delayed_work(nvme_wq, &ctrl->ka_work, ctrl->kato * HZ);
+	if (startka) {
+		unsigned long kato_delay = ctrl->kato >> 1;
+
+		queue_delayed_work(nvme_wq, &ctrl->ka_work, kato_delay * HZ);
+	}
 }
 
 static int nvme_keep_alive(struct nvme_ctrl *ctrl)
@@ -1259,10 +1262,12 @@ static void nvme_keep_alive_work(struct work_struct *work)
 	bool comp_seen = ctrl->comp_seen;
 
 	if ((ctrl->ctratt & NVME_CTRL_ATTR_TBKAS) && comp_seen) {
+		unsigned long kato_delay = ctrl->kato >> 1;
+
 		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);
+		queue_delayed_work(nvme_wq, &ctrl->ka_work, kato_delay * HZ);
 		return;
 	}
 
@@ -1276,10 +1281,11 @@ static void nvme_keep_alive_work(struct work_struct *work)
 
 static void nvme_start_keep_alive(struct nvme_ctrl *ctrl)
 {
+	unsigned long kato_delay = ctrl->kato >> 1;
 	if (unlikely(ctrl->kato == 0))
 		return;
 
-	queue_delayed_work(nvme_wq, &ctrl->ka_work, ctrl->kato * HZ);
+	queue_delayed_work(nvme_wq, &ctrl->ka_work, kato_delay * HZ);
 }
 
 void nvme_stop_keep_alive(struct nvme_ctrl *ctrl)
diff --git a/drivers/nvme/host/fabrics.c b/drivers/nvme/host/fabrics.c
index 5dfd806fc2d2..dba32e39afbf 100644
--- a/drivers/nvme/host/fabrics.c
+++ b/drivers/nvme/host/fabrics.c
@@ -382,7 +382,7 @@ int nvmf_connect_admin_queue(struct nvme_ctrl *ctrl)
 	 * and add a grace period for controller kato enforcement
 	 */
 	cmd.connect.kato = ctrl->kato ?
-		cpu_to_le32((ctrl->kato + NVME_KATO_GRACE) * 1000) : 0;
+		cpu_to_le32(ctrl->kato * 1000) : 0;
 
 	if (ctrl->opts->disable_sqflow)
 		cmd.connect.cattr |= NVME_CONNECT_DISABLE_SQFLOW;
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index e00e3400c8b6..de0b270f95fc 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -27,7 +27,6 @@ extern unsigned int admin_timeout;
 #define NVME_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
-- 
2.29.2