[IB] uverbs: have kernel return QP capabilities

Move the computation of QP capabilities (max scatter/gather entries,
max inline data, etc) into the kernel, and have the uverbs module
return the values as part of the create QP response.  This keeps
precise knowledge of device limits in the low-level kernel driver.

This requires an ABI bump, so while we're making changes, get rid of
the max_sge parameter for the modify SRQ command -- it's not used and
shouldn't be there.

Signed-off-by: Jack Morgenstein <jackm@mellanox.co.il>
Signed-off-by: Michael S. Tsirkin <mst@mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>

1 files changed, 78 insertions, 8 deletions

diff --git a/drivers/infiniband/hw/mthca/mthca_qp.c b/drivers/infiniband/hw/mthca/mthca_qp.c
index 8852ea477c2..7f39af44b27 100644
--- a/drivers/infiniband/hw/mthca/mthca_qp.c
+++ b/drivers/infiniband/hw/mthca/mthca_qp.c
@@ -885,6 +885,48 @@ int mthca_modify_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr, int attr_mask)
 	return err;
 }
 
+static void mthca_adjust_qp_caps(struct mthca_dev *dev,
+				 struct mthca_pd *pd,
+				 struct mthca_qp *qp)
+{
+	int max_data_size;
+
+	/*
+	 * Calculate the maximum size of WQE s/g segments, excluding
+	 * the next segment and other non-data segments.
+	 */
+	max_data_size = min(dev->limits.max_desc_sz, 1 << qp->sq.wqe_shift) -
+		sizeof (struct mthca_next_seg);
+
+	switch (qp->transport) {
+	case MLX:
+		max_data_size -= 2 * sizeof (struct mthca_data_seg);
+		break;
+
+	case UD:
+		if (mthca_is_memfree(dev))
+			max_data_size -= sizeof (struct mthca_arbel_ud_seg);
+		else
+			max_data_size -= sizeof (struct mthca_tavor_ud_seg);
+		break;
+
+	default:
+		max_data_size -= sizeof (struct mthca_raddr_seg);
+		break;
+	}
+
+	/* We don't support inline data for kernel QPs (yet). */
+	if (!pd->ibpd.uobject)
+		qp->max_inline_data = 0;
+        else
+		qp->max_inline_data = max_data_size - MTHCA_INLINE_HEADER_SIZE;
+
+	qp->sq.max_gs = max_data_size / sizeof (struct mthca_data_seg);
+	qp->rq.max_gs = (min(dev->limits.max_desc_sz, 1 << qp->rq.wqe_shift) -
+			sizeof (struct mthca_next_seg)) /
+			sizeof (struct mthca_data_seg);
+}
+
 /*
  * Allocate and register buffer for WQEs.  qp->rq.max, sq.max,
  * rq.max_gs and sq.max_gs must all be assigned.
@@ -902,27 +944,53 @@ static int mthca_alloc_wqe_buf(struct mthca_dev *dev,
 	size = sizeof (struct mthca_next_seg) +
 		qp->rq.max_gs * sizeof (struct mthca_data_seg);
 
+	if (size > dev->limits.max_desc_sz)
+		return -EINVAL;
+
 	for (qp->rq.wqe_shift = 6; 1 << qp->rq.wqe_shift < size;
 	     qp->rq.wqe_shift++)
 		; /* nothing */
 
-	size = sizeof (struct mthca_next_seg) +
-		qp->sq.max_gs * sizeof (struct mthca_data_seg);
+	size = qp->sq.max_gs * sizeof (struct mthca_data_seg);
 	switch (qp->transport) {
 	case MLX:
 		size += 2 * sizeof (struct mthca_data_seg);
 		break;
+
 	case UD:
-		if (mthca_is_memfree(dev))
-			size += sizeof (struct mthca_arbel_ud_seg);
-		else
-			size += sizeof (struct mthca_tavor_ud_seg);
+		size += mthca_is_memfree(dev) ?
+			sizeof (struct mthca_arbel_ud_seg) :
+			sizeof (struct mthca_tavor_ud_seg);
 		break;
+
+	case UC:
+		size += sizeof (struct mthca_raddr_seg);
+		break;
+
+	case RC:
+		size += sizeof (struct mthca_raddr_seg);
+		/*
+		 * An atomic op will require an atomic segment, a
+		 * remote address segment and one scatter entry.
+		 */
+		size = max_t(int, size,
+			     sizeof (struct mthca_atomic_seg) +
+			     sizeof (struct mthca_raddr_seg) +
+			     sizeof (struct mthca_data_seg));
+		break;
+
 	default:
-		/* bind seg is as big as atomic + raddr segs */
-		size += sizeof (struct mthca_bind_seg);
+		break;
 	}
 
+	/* Make sure that we have enough space for a bind request */
+	size = max_t(int, size, sizeof (struct mthca_bind_seg));
+
+	size += sizeof (struct mthca_next_seg);
+
+	if (size > dev->limits.max_desc_sz)
+		return -EINVAL;
+
 	for (qp->sq.wqe_shift = 6; 1 << qp->sq.wqe_shift < size;
 	     qp->sq.wqe_shift++)
 		; /* nothing */
@@ -1066,6 +1134,8 @@ static int mthca_alloc_qp_common(struct mthca_dev *dev,
 		return ret;
 	}
 
+	mthca_adjust_qp_caps(dev, pd, qp);
+
 	/*
 	 * If this is a userspace QP, we're done now.  The doorbells
 	 * will be allocated and buffers will be initialized in