From fbfb18718fa81633a0aabed9eaeff522295d7530 Mon Sep 17 00:00:00 2001 From: Israel Rukshin Date: Sun, 15 May 2022 18:04:40 +0300 Subject: [PATCH] nvme-rdma: remove timeout for getting RDMA-CM established event In case many controllers start error recovery at the same time (i.e., when port is down and up), they may never succeed to reconnect again. This is because the target can't handle all the connect requests at three seconds (the arbitrary value set today). Even if some of the connections are established, when a single queue fails to connect, all the controller's queues are destroyed as well. So, on the following reconnection attempts the number of connect requests may remain the same. To fix this, remove the timeout and wait for RDMA-CM event to abort/complete the connect request. RDMA-CM sends unreachable event when a timeout of ~90 seconds is expired. This approach is used at other RDMA-CM users like SRP and iSER at blocking mode. The commit also renames NVME_RDMA_CONNECT_TIMEOUT_MS to NVME_RDMA_CM_TIMEOUT_MS. Signed-off-by: Israel Rukshin Reviewed-by: Max Gurtovoy Acked-by: Sagi Grimberg Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- drivers/nvme/host/rdma.c | 13 +++++-------- 1 file changed, 5 insertions(+), 8 deletions(-) diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c index 7ecdeb58bd273..1a792e08b93ca 100644 --- a/drivers/nvme/host/rdma.c +++ b/drivers/nvme/host/rdma.c @@ -29,7 +29,7 @@ #include "fabrics.h" -#define NVME_RDMA_CONNECT_TIMEOUT_MS 3000 /* 3 second */ +#define NVME_RDMA_CM_TIMEOUT_MS 3000 /* 3 second */ #define NVME_RDMA_MAX_SEGMENTS 256 @@ -248,12 +248,9 @@ static int nvme_rdma_wait_for_cm(struct nvme_rdma_queue *queue) { int ret; - ret = wait_for_completion_interruptible_timeout(&queue->cm_done, - msecs_to_jiffies(NVME_RDMA_CONNECT_TIMEOUT_MS) + 1); - if (ret < 0) + ret = wait_for_completion_interruptible(&queue->cm_done); + if (ret) return ret; - if (ret == 0) - return -ETIMEDOUT; WARN_ON_ONCE(queue->cm_error > 0); return queue->cm_error; } @@ -612,7 +609,7 @@ static int nvme_rdma_alloc_queue(struct nvme_rdma_ctrl *ctrl, queue->cm_error = -ETIMEDOUT; ret = rdma_resolve_addr(queue->cm_id, src_addr, (struct sockaddr *)&ctrl->addr, - NVME_RDMA_CONNECT_TIMEOUT_MS); + NVME_RDMA_CM_TIMEOUT_MS); if (ret) { dev_info(ctrl->ctrl.device, "rdma_resolve_addr failed (%d).\n", ret); @@ -1895,7 +1892,7 @@ static int nvme_rdma_addr_resolved(struct nvme_rdma_queue *queue) if (ctrl->opts->tos >= 0) rdma_set_service_type(queue->cm_id, ctrl->opts->tos); - ret = rdma_resolve_route(queue->cm_id, NVME_RDMA_CONNECT_TIMEOUT_MS); + ret = rdma_resolve_route(queue->cm_id, NVME_RDMA_CM_TIMEOUT_MS); if (ret) { dev_err(ctrl->device, "rdma_resolve_route failed (%d).\n", queue->cm_error); -- 2.39.5