From ae057808924227e244492444b8f6e6ea6fc9544d Mon Sep 17 00:00:00 2001 From: Marta Rybczynska Date: Mon, 10 Apr 2017 17:12:34 +0200 Subject: nvme-rdma: support devices with queue size < 32 commit 0544f5494a03b8846db74e02be5685d1f32b06c9 upstream. In the case of small NVMe-oF queue size (<32) we may enter a deadlock caused by the fact that the IB completions aren't sent waiting for 32 and the send queue will fill up. The error is seen as (using mlx5): [ 2048.693355] mlx5_0:mlx5_ib_post_send:3765:(pid 7273): [ 2048.693360] nvme nvme1: nvme_rdma_post_send failed with error code -12 This patch changes the way the signaling is done so that it depends on the queue depth now. The magic define has been removed completely. Signed-off-by: Marta Rybczynska Signed-off-by: Samuel Jones Acked-by: Sagi Grimberg Signed-off-by: Christoph Hellwig Signed-off-by: Greg Kroah-Hartman diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c index 3d25add..3222f3e 100644 --- a/drivers/nvme/host/rdma.c +++ b/drivers/nvme/host/rdma.c @@ -1011,6 +1011,19 @@ static void nvme_rdma_send_done(struct ib_cq *cq, struct ib_wc *wc) nvme_rdma_wr_error(cq, wc, "SEND"); } +static inline int nvme_rdma_queue_sig_limit(struct nvme_rdma_queue *queue) +{ + int sig_limit; + + /* + * We signal completion every queue depth/2 and also handle the + * degenerated case of a device with queue_depth=1, where we + * would need to signal every message. + */ + sig_limit = max(queue->queue_size / 2, 1); + return (++queue->sig_count % sig_limit) == 0; +} + static int nvme_rdma_post_send(struct nvme_rdma_queue *queue, struct nvme_rdma_qe *qe, struct ib_sge *sge, u32 num_sge, struct ib_send_wr *first, bool flush) @@ -1038,9 +1051,6 @@ static int nvme_rdma_post_send(struct nvme_rdma_queue *queue, * Would have been way to obvious to handle this in hardware or * at least the RDMA stack.. * - * This messy and racy code sniplet is copy and pasted from the iSER - * initiator, and the magic '32' comes from there as well. - * * Always signal the flushes. The magic request used for the flush * sequencer is not allocated in our driver's tagset and it's * triggered to be freed by blk_cleanup_queue(). So we need to @@ -1048,7 +1058,7 @@ static int nvme_rdma_post_send(struct nvme_rdma_queue *queue, * embeded in request's payload, is not freed when __ib_process_cq() * calls wr_cqe->done(). */ - if ((++queue->sig_count % 32) == 0 || flush) + if (nvme_rdma_queue_sig_limit(queue) || flush) wr.send_flags |= IB_SEND_SIGNALED; if (first) -- cgit v0.10.2