[PATCH] nvme-rdma: remove race conditions from IB signalling

[Marta Rybczynska]

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@xxxxxxxxx>
---
 drivers/nvme/host/rdma.c | 31 +++++++++++++++++++++----------
 1 file changed, 21 insertions(+), 10 deletions(-)

diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c
index 28bd255..80682f7 100644
--- a/drivers/nvme/host/rdma.c
+++ b/drivers/nvme/host/rdma.c
@@ -88,7 +88,7 @@ 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;
@@ -554,6 +554,8 @@ static int nvme_rdma_init_queue(struct nvme_rdma_ctrl *ctrl,
 
        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);
        if (IS_ERR(queue->cm_id)) {
@@ -1038,17 +1040,26 @@ 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)
+static inline int nvme_rdma_init_sig_count(int queue_size)
 {
-       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.
+       /* 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).
         */
-       sig_limit = max(queue->queue_size / 2, 1);
-       return (++queue->sig_count % sig_limit) == 0;
+       return 1 << ilog2((queue_size + 1) / 2);
+}
+
+static inline bool nvme_rdma_queue_sig_limit(struct nvme_rdma_queue *queue)
+{
+       int count, limit;
+
+       limit = nvme_rdma_init_sig_count(queue->queue_size);
+       count = atomic_inc_return(&queue->sig_count);
+
+       /* Signal if count is a multiple of limit */
+       if ((count & (limit - 1)) == 0)
+               return true;
+       return false;
 }
 
 static int nvme_rdma_post_send(struct nvme_rdma_queue *queue,
-- 
1.8.3.1