IB/mlx4: Fix max_wqe capacity reported from query device

1. Limit the max number of WQEs per QP reported when querying the
   device, so that ib_create_qp() will not fail for a QP size that the
   device claimed to support due to additional headroom WQEs being
   allocated.

2. Limit qp resources accepted for ib_create_qp() to the limits
   reported in ib_query_device().  In kernel space, make sure that the
   limits returned to the caller following qp creation also lie within
   the reported device limits. For userspace, report as before, and do
   adjustment in libmlx4 (so as not to break ABI).

Signed-off-by: Jack Morgenstein <jackm@dev.mellanox.co.il>
Signed-off-by: Sagi Grimberg <sagig@mellanox.co.il>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Roland Dreier <roland@purestorage.com>

drivers/infiniband/hw/mlx4/main.c

@@ -140,7 +140,7 @@ static int mlx4_ib_query_device(struct ib_device *ibdev,
 	props->max_mr_size	   = ~0ull;
 	props->page_size_cap	   = dev->dev->caps.page_size_cap;
 	props->max_qp		   = dev->dev->caps.num_qps - dev->dev->caps.reserved_qps;
-	props->max_qp_wr	   = dev->dev->caps.max_wqes;
+	props->max_qp_wr	   = dev->dev->caps.max_wqes - MLX4_IB_SQ_MAX_SPARE;
 	props->max_sge		   = min(dev->dev->caps.max_sq_sg,
 					 dev->dev->caps.max_rq_sg);
 	props->max_cq		   = dev->dev->caps.num_cqs - dev->dev->caps.reserved_cqs;

drivers/infiniband/hw/mlx4/mlx4_ib.h

@@ -44,6 +44,14 @@
 #include <linux/mlx4/device.h>
 #include <linux/mlx4/doorbell.h>
 
+enum {
+	MLX4_IB_SQ_MIN_WQE_SHIFT = 6,
+	MLX4_IB_MAX_HEADROOM	 = 2048
+};
+
+#define MLX4_IB_SQ_HEADROOM(shift)	((MLX4_IB_MAX_HEADROOM >> (shift)) + 1)
+#define MLX4_IB_SQ_MAX_SPARE		(MLX4_IB_SQ_HEADROOM(MLX4_IB_SQ_MIN_WQE_SHIFT))
+
 struct mlx4_ib_ucontext {
 	struct ib_ucontext	ibucontext;
 	struct mlx4_uar		uar;

drivers/infiniband/hw/mlx4/qp.c

@@ -310,8 +310,8 @@ static int set_rq_size(struct mlx4_ib_dev *dev, struct ib_qp_cap *cap,
 		       int is_user, int has_rq, struct mlx4_ib_qp *qp)
 {
 	/* Sanity check RQ size before proceeding */
-	if (cap->max_recv_wr  > dev->dev->caps.max_wqes  ||
+	if (cap->max_recv_wr > dev->dev->caps.max_wqes - MLX4_IB_SQ_MAX_SPARE ||
-	    cap->max_recv_sge > dev->dev->caps.max_rq_sg)
+	    cap->max_recv_sge > min(dev->dev->caps.max_sq_sg, dev->dev->caps.max_rq_sg))
 		return -EINVAL;
 
 	if (!has_rq) {
@@ -329,8 +329,17 @@ static int set_rq_size(struct mlx4_ib_dev *dev, struct ib_qp_cap *cap,
 		qp->rq.wqe_shift = ilog2(qp->rq.max_gs * sizeof (struct mlx4_wqe_data_seg));
 	}
 
-	cap->max_recv_wr  = qp->rq.max_post = qp->rq.wqe_cnt;
+	/* leave userspace return values as they were, so as not to break ABI */
-	cap->max_recv_sge = qp->rq.max_gs;
+	if (is_user) {
+		cap->max_recv_wr  = qp->rq.max_post = qp->rq.wqe_cnt;
+		cap->max_recv_sge = qp->rq.max_gs;
+	} else {
+		cap->max_recv_wr  = qp->rq.max_post =
+			min(dev->dev->caps.max_wqes - MLX4_IB_SQ_MAX_SPARE, qp->rq.wqe_cnt);
+		cap->max_recv_sge = min(qp->rq.max_gs,
+					min(dev->dev->caps.max_sq_sg,
+					    dev->dev->caps.max_rq_sg));
+	}
 
 	return 0;
 }
@@ -341,8 +350,8 @@ static int set_kernel_sq_size(struct mlx4_ib_dev *dev, struct ib_qp_cap *cap,
 	int s;
 
 	/* Sanity check SQ size before proceeding */
-	if (cap->max_send_wr	 > dev->dev->caps.max_wqes  ||
+	if (cap->max_send_wr  > (dev->dev->caps.max_wqes - MLX4_IB_SQ_MAX_SPARE) ||
-	    cap->max_send_sge	 > dev->dev->caps.max_sq_sg ||
+	    cap->max_send_sge > min(dev->dev->caps.max_sq_sg, dev->dev->caps.max_rq_sg) ||
 	    cap->max_inline_data + send_wqe_overhead(type, qp->flags) +
 	    sizeof (struct mlx4_wqe_inline_seg) > dev->dev->caps.max_sq_desc_sz)
 		return -EINVAL;