nvme-rdma: remove race conditions from IB signalling

This patch improves the way the RDMA IB signalling is done by using atomic
operations for the signalling variable. This avoids race conditions on
sig_count.

The signalling interval changes slightly and is now the largest power of
two not larger than queue depth / 2.

ilog() usage idea by Bart Van Assche.

Signed-off-by: Marta Rybczynska <marta.rybczynska@kalray.eu>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Cc: stable@vger.kernel.org

diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c
index cfb22531fc161beb2dbcb439279695fb5bb17a49..0ab163e6e640eb3617e22c5f5bbf300ab969a8f1 100644 (file)
--- a/drivers/nvme/host/rdma.c
+++ b/drivers/nvme/host/rdma.c
@@ -86,7 +86,7 @@ enum nvme_rdma_queue_flags {
 
 struct nvme_rdma_queue {
        struct nvme_rdma_qe     *rsp_ring;
-       u8                      sig_count;
+       atomic_t                sig_count;
        int                     queue_size;
        size_t                  cmnd_capsule_len;
        struct nvme_rdma_ctrl   *ctrl;
@@ -523,6 +523,7 @@ static int nvme_rdma_init_queue(struct nvme_rdma_ctrl *ctrl,
                queue->cmnd_capsule_len = sizeof(struct nvme_command);
 
        queue->queue_size = queue_size;
+       atomic_set(&queue->sig_count, 0);
 
        queue->cm_id = rdma_create_id(&init_net, nvme_rdma_cm_handler, queue,
                        RDMA_PS_TCP, IB_QPT_RC);
@@ -1009,17 +1010,16 @@ 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)
+/*
+ * We want to signal completion at least every queue depth/2.  This returns the
+ * largest power of two that is not above half of (queue size + 1) to optimize
+ * (avoid divisions).
+ */
+static inline bool nvme_rdma_queue_sig_limit(struct nvme_rdma_queue *queue)
 {
-       int sig_limit;
+       int limit = 1 << ilog2((queue->queue_size + 1) / 2);
 
-       /*
-        * 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;
+       return (atomic_inc_return(&queue->sig_count) & (limit - 1)) == 0;
 }
 
 static int nvme_rdma_post_send(struct nvme_rdma_queue *queue,