nvme: add keep-alive support
Periodic keep-alive is a mandatory feature in NVMe over Fabrics, and
optional in NVMe 1.2.1 for PCIe. This patch adds periodic keep-alive
sent from the host to verify that the controller is still responsive
and vice-versa. The keep-alive timeout is user-defined (with
keep_alive_tmo connection parameter) and defaults to 5 seconds.
In order to avoid a race condition where the host sends a keep-alive
competing with the target side keep-alive timeout expiration, the host
adds a grace period of 10 seconds when publishing the keep-alive timeout
to the target.
In case a keep-alive failed (or timed out), a transport specific error
recovery kicks in.
For now only NVMe over Fabrics is wired up to support keep alive, but
we can add PCIe support easily once controllers actually supporting it
become available.
Signed-off-by: Sagi Grimberg <sagi@grimberg.me>
Reviewed-by: Steve Wise <swise@chelsio.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Keith Busch <keith.busch@intel.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index e5c1d75..c01687d 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -30,6 +30,7 @@
#include <asm/unaligned.h>
#include "nvme.h"
+#include "fabrics.h"
#define NVME_MINORS (1U << MINORBITS)
@@ -463,6 +464,74 @@
result, timeout);
}
+static void nvme_keep_alive_end_io(struct request *rq, int error)
+{
+ struct nvme_ctrl *ctrl = rq->end_io_data;
+
+ blk_mq_free_request(rq);
+
+ if (error) {
+ dev_err(ctrl->device,
+ "failed nvme_keep_alive_end_io error=%d\n", error);
+ return;
+ }
+
+ schedule_delayed_work(&ctrl->ka_work, ctrl->kato * HZ);
+}
+
+static int nvme_keep_alive(struct nvme_ctrl *ctrl)
+{
+ struct nvme_command c;
+ struct request *rq;
+
+ memset(&c, 0, sizeof(c));
+ c.common.opcode = nvme_admin_keep_alive;
+
+ rq = nvme_alloc_request(ctrl->admin_q, &c, BLK_MQ_REQ_RESERVED,
+ NVME_QID_ANY);
+ if (IS_ERR(rq))
+ return PTR_ERR(rq);
+
+ rq->timeout = ctrl->kato * HZ;
+ rq->end_io_data = ctrl;
+
+ blk_execute_rq_nowait(rq->q, NULL, rq, 0, nvme_keep_alive_end_io);
+
+ return 0;
+}
+
+static void nvme_keep_alive_work(struct work_struct *work)
+{
+ struct nvme_ctrl *ctrl = container_of(to_delayed_work(work),
+ struct nvme_ctrl, ka_work);
+
+ if (nvme_keep_alive(ctrl)) {
+ /* allocation failure, reset the controller */
+ dev_err(ctrl->device, "keep-alive failed\n");
+ ctrl->ops->reset_ctrl(ctrl);
+ return;
+ }
+}
+
+void nvme_start_keep_alive(struct nvme_ctrl *ctrl)
+{
+ if (unlikely(ctrl->kato == 0))
+ return;
+
+ INIT_DELAYED_WORK(&ctrl->ka_work, nvme_keep_alive_work);
+ schedule_delayed_work(&ctrl->ka_work, ctrl->kato * HZ);
+}
+EXPORT_SYMBOL_GPL(nvme_start_keep_alive);
+
+void nvme_stop_keep_alive(struct nvme_ctrl *ctrl)
+{
+ if (unlikely(ctrl->kato == 0))
+ return;
+
+ cancel_delayed_work_sync(&ctrl->ka_work);
+}
+EXPORT_SYMBOL_GPL(nvme_stop_keep_alive);
+
int nvme_identify_ctrl(struct nvme_ctrl *dev, struct nvme_id_ctrl **id)
{
struct nvme_command c = { };
@@ -1179,6 +1248,7 @@
nvme_set_queue_limits(ctrl, ctrl->admin_q);
ctrl->sgls = le32_to_cpu(id->sgls);
+ ctrl->kas = le16_to_cpu(id->kas);
if (ctrl->ops->is_fabrics) {
ctrl->icdoff = le16_to_cpu(id->icdoff);
@@ -1192,6 +1262,12 @@
*/
if (ctrl->cntlid != le16_to_cpu(id->cntlid))
ret = -EINVAL;
+
+ if (!ctrl->opts->discovery_nqn && !ctrl->kas) {
+ dev_err(ctrl->dev,
+ "keep-alive support is mandatory for fabrics\n");
+ ret = -EINVAL;
+ }
} else {
ctrl->cntlid = le16_to_cpu(id->cntlid);
}