From a70b81bd4d9d2d6c05cfe6ef2a10bccc2e04357a Mon Sep 17 00:00:00 2001 From: Hannes Reinecke Date: Fri, 16 Apr 2021 13:46:20 +0200 Subject: nvme: sanitize KATO setting 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 Signed-off-by: Christoph Hellwig --- 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(-) (limited to 'drivers/nvme/host') diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 40f08e6325ef..0cb097cd6a8e 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -1109,6 +1109,17 @@ void nvme_execute_passthru_rq(struct request *rq) } EXPORT_SYMBOL_NS_GPL(nvme_execute_passthru_rq, NVME_TARGET_PASSTHRU); +/* + * 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; @@ -1131,7 +1142,7 @@ static void nvme_keep_alive_end_io(struct request *rq, blk_status_t status) 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 int nvme_keep_alive(struct nvme_ctrl *ctrl) @@ -1161,7 +1172,7 @@ static void nvme_keep_alive_work(struct work_struct *work) 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; } @@ -1178,7 +1189,7 @@ static void nvme_start_keep_alive(struct nvme_ctrl *ctrl) 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) diff --git a/drivers/nvme/host/fabrics.c b/drivers/nvme/host/fabrics.c index 604ab0e5a2ad..13c2747e3d00 100644 --- a/drivers/nvme/host/fabrics.c +++ b/drivers/nvme/host/fabrics.c @@ -379,10 +379,8 @@ int nvmf_connect_admin_queue(struct nvme_ctrl *ctrl) /* * 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; diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h index c6102ce83bb4..49276186d5bd 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 -- cgit v1.2.3