On 6/9/2015 1:55 AM, Hefty, Sean wrote:
--- a/drivers/infiniband/hw/mlx5/mr.c +++ b/drivers/infiniband/hw/mlx5/mr.c @@ -1174,6 +1174,18 @@ static int clean_mr(struct mlx5_ib_mr *mr) int umred = mr->umred; int err; + if (mr->sig) { + if (mlx5_core_destroy_psv(dev->mdev, + mr->sig->psv_memory.psv_idx)) + mlx5_ib_warn(dev, "failed to destroy mem psv %d\n", + mr->sig->psv_memory.psv_idx); + if (mlx5_core_destroy_psv(dev->mdev, + mr->sig->psv_wire.psv_idx)) + mlx5_ib_warn(dev, "failed to destroy wire psv %d\n", + mr->sig->psv_wire.psv_idx); + kfree(mr->sig); + } + if (!umred) { err = destroy_mkey(dev, mr); if (err) {This patch doesn't introduce this problem, but the err check suggests that deregistration can fail for some reason. If so, should mr->sig be cleared above, so that a second call to dereg doesn't attempt to free the memory twice?
Hi Sean, clean_mr() failure is not propagated back at the moment, but you are correct, it's not a good idea to rely on that. I'll clear mr->sig in v2. Thanks! -- To unsubscribe from this list: send the line "unsubscribe linux-rdma" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
