1 files changed, 47 insertions, 14 deletions

diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c
index 87b7c1be2a11..a4f1f638509f 100644
--- a/drivers/infiniband/hw/mlx5/qp.c
+++ b/drivers/infiniband/hw/mlx5/qp.c
@@ -54,6 +54,7 @@ enum {
 
 enum {
 	MLX5_IB_SQ_STRIDE	= 6,
+	MLX5_IB_SQ_UMR_INLINE_THRESHOLD = 64,
 };
 
 static const u32 mlx5_ib_opcode[] = {
@@ -302,7 +303,9 @@ static int sq_overhead(struct ib_qp_init_attr *attr)
 			max(sizeof(struct mlx5_wqe_atomic_seg) +
 			    sizeof(struct mlx5_wqe_raddr_seg),
 			    sizeof(struct mlx5_wqe_umr_ctrl_seg) +
-			    sizeof(struct mlx5_mkey_seg));
+			    sizeof(struct mlx5_mkey_seg) +
+			    MLX5_IB_SQ_UMR_INLINE_THRESHOLD /
+			    MLX5_IB_UMR_OCTOWORD);
 		break;
 
 	case IB_QPT_XRC_TGT:
@@ -484,11 +487,6 @@ static int qp_has_rq(struct ib_qp_init_attr *attr)
 	return 1;
 }
 
-static int first_med_bfreg(void)
-{
-	return 1;
-}
-
 enum {
 	/* this is the first blue flame register in the array of bfregs assigned
 	 * to a processes. Since we do not use it for blue flame but rather
@@ -514,6 +512,12 @@ static int num_med_bfreg(struct mlx5_ib_dev *dev,
 	return n >= 0 ? n : 0;
 }
 
+static int first_med_bfreg(struct mlx5_ib_dev *dev,
+			   struct mlx5_bfreg_info *bfregi)
+{
+	return num_med_bfreg(dev, bfregi) ? 1 : -ENOMEM;
+}
+
 static int first_hi_bfreg(struct mlx5_ib_dev *dev,
 			  struct mlx5_bfreg_info *bfregi)
 {
@@ -541,10 +545,13 @@ static int alloc_high_class_bfreg(struct mlx5_ib_dev *dev,
 static int alloc_med_class_bfreg(struct mlx5_ib_dev *dev,
 				 struct mlx5_bfreg_info *bfregi)
 {
-	int minidx = first_med_bfreg();
+	int minidx = first_med_bfreg(dev, bfregi);
 	int i;
 
-	for (i = first_med_bfreg(); i < first_hi_bfreg(dev, bfregi); i++) {
+	if (minidx < 0)
+		return minidx;
+
+	for (i = minidx; i < first_hi_bfreg(dev, bfregi); i++) {
 		if (bfregi->count[i] < bfregi->count[minidx])
 			minidx = i;
 		if (!bfregi->count[minidx])
@@ -3637,13 +3644,15 @@ static __be64 sig_mkey_mask(void)
 }
 
 static void set_reg_umr_seg(struct mlx5_wqe_umr_ctrl_seg *umr,
-			    struct mlx5_ib_mr *mr)
+			    struct mlx5_ib_mr *mr, bool umr_inline)
 {
 	int size = mr->ndescs * mr->desc_size;
 
 	memset(umr, 0, sizeof(*umr));
 
 	umr->flags = MLX5_UMR_CHECK_NOT_FREE;
+	if (umr_inline)
+		umr->flags |= MLX5_UMR_INLINE;
 	umr->xlt_octowords = cpu_to_be16(get_xlt_octo(size));
 	umr->mkey_mask = frwr_mkey_mask();
 }
@@ -3827,6 +3836,24 @@ static void set_reg_data_seg(struct mlx5_wqe_data_seg *dseg,
 	dseg->lkey = cpu_to_be32(pd->ibpd.local_dma_lkey);
 }
 
+static void set_reg_umr_inline_seg(void *seg, struct mlx5_ib_qp *qp,
+				   struct mlx5_ib_mr *mr, int mr_list_size)
+{
+	void *qend = qp->sq.qend;
+	void *addr = mr->descs;
+	int copy;
+
+	if (unlikely(seg + mr_list_size > qend)) {
+		copy = qend - seg;
+		memcpy(seg, addr, copy);
+		addr += copy;
+		mr_list_size -= copy;
+		seg = mlx5_get_send_wqe(qp, 0);
+	}
+	memcpy(seg, addr, mr_list_size);
+	seg += mr_list_size;
+}
+
 static __be32 send_ieth(struct ib_send_wr *wr)
 {
 	switch (wr->opcode) {
@@ -4221,6 +4248,8 @@ static int set_reg_wr(struct mlx5_ib_qp *qp,
 {
 	struct mlx5_ib_mr *mr = to_mmr(wr->mr);
 	struct mlx5_ib_pd *pd = to_mpd(qp->ibqp.pd);
+	int mr_list_size = mr->ndescs * mr->desc_size;
+	bool umr_inline = mr_list_size <= MLX5_IB_SQ_UMR_INLINE_THRESHOLD;
 
 	if (unlikely(wr->wr.send_flags & IB_SEND_INLINE)) {
 		mlx5_ib_warn(to_mdev(qp->ibqp.device),
@@ -4228,7 +4257,7 @@ static int set_reg_wr(struct mlx5_ib_qp *qp,
 		return -EINVAL;
 	}
 
-	set_reg_umr_seg(*seg, mr);
+	set_reg_umr_seg(*seg, mr, umr_inline);
 	*seg += sizeof(struct mlx5_wqe_umr_ctrl_seg);
 	*size += sizeof(struct mlx5_wqe_umr_ctrl_seg) / 16;
 	if (unlikely((*seg == qp->sq.qend)))
@@ -4240,10 +4269,14 @@ static int set_reg_wr(struct mlx5_ib_qp *qp,
 	if (unlikely((*seg == qp->sq.qend)))
 		*seg = mlx5_get_send_wqe(qp, 0);
 
-	set_reg_data_seg(*seg, mr, pd);
-	*seg += sizeof(struct mlx5_wqe_data_seg);
-	*size += (sizeof(struct mlx5_wqe_data_seg) / 16);
-
+	if (umr_inline) {
+		set_reg_umr_inline_seg(*seg, qp, mr, mr_list_size);
+		*size += get_xlt_octo(mr_list_size);
+	} else {
+		set_reg_data_seg(*seg, mr, pd);
+		*seg += sizeof(struct mlx5_wqe_data_seg);
+		*size += (sizeof(struct mlx5_wqe_data_seg) / 16);
+	}
 	return 0;
 }