IB/mlx5: Support the new memory registration API
Support the new memory registration API by allocating a
private page list array in mlx5_ib_mr and populate it when
mlx5_ib_map_mr_sg is invoked. Also, support IB_WR_REG_MR
by setting the exact WQE as IB_WR_FAST_REG_MR, just take the
needed information from different places:
- page_size, iova, length, access flags (ib_mr)
- page array (mlx5_ib_mr)
- key (ib_reg_wr)
The IB_WR_FAST_REG_MR handlers will be removed later when
all the ULPs will be converted.
Signed-off-by: Sagi Grimberg <sagig@mellanox.com>
Acked-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Doug Ledford <dledford@redhat.com>
diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c
index 9bad688..da2b46c 100644
--- a/drivers/infiniband/hw/mlx5/qp.c
+++ b/drivers/infiniband/hw/mlx5/qp.c
@@ -65,6 +65,7 @@
[IB_WR_SEND_WITH_INV] = MLX5_OPCODE_SEND_INVAL,
[IB_WR_LOCAL_INV] = MLX5_OPCODE_UMR,
[IB_WR_FAST_REG_MR] = MLX5_OPCODE_UMR,
+ [IB_WR_REG_MR] = MLX5_OPCODE_UMR,
[IB_WR_MASKED_ATOMIC_CMP_AND_SWP] = MLX5_OPCODE_ATOMIC_MASKED_CS,
[IB_WR_MASKED_ATOMIC_FETCH_AND_ADD] = MLX5_OPCODE_ATOMIC_MASKED_FA,
[MLX5_IB_WR_UMR] = MLX5_OPCODE_UMR,
@@ -1896,6 +1897,17 @@
return cpu_to_be64(result);
}
+static void set_reg_umr_seg(struct mlx5_wqe_umr_ctrl_seg *umr,
+ struct mlx5_ib_mr *mr)
+{
+ int ndescs = mr->ndescs;
+
+ memset(umr, 0, sizeof(*umr));
+ umr->flags = MLX5_UMR_CHECK_NOT_FREE;
+ umr->klm_octowords = get_klm_octo(ndescs);
+ umr->mkey_mask = frwr_mkey_mask();
+}
+
static void set_frwr_umr_segment(struct mlx5_wqe_umr_ctrl_seg *umr,
struct ib_send_wr *wr, int li)
{
@@ -1987,6 +1999,22 @@
MLX5_PERM_LOCAL_READ | MLX5_PERM_UMR_EN;
}
+static void set_reg_mkey_seg(struct mlx5_mkey_seg *seg,
+ struct mlx5_ib_mr *mr,
+ u32 key, int access)
+{
+ int ndescs = ALIGN(mr->ndescs, 8) >> 1;
+
+ memset(seg, 0, sizeof(*seg));
+ seg->flags = get_umr_flags(access) | MLX5_ACCESS_MODE_MTT;
+ seg->qpn_mkey7_0 = cpu_to_be32((key & 0xff) | 0xffffff00);
+ seg->flags_pd = cpu_to_be32(MLX5_MKEY_REMOTE_INVAL);
+ seg->start_addr = cpu_to_be64(mr->ibmr.iova);
+ seg->len = cpu_to_be64(mr->ibmr.length);
+ seg->xlt_oct_size = cpu_to_be32(ndescs);
+ seg->log2_page_size = ilog2(mr->ibmr.page_size);
+}
+
static void set_mkey_segment(struct mlx5_mkey_seg *seg, struct ib_send_wr *wr,
int li, int *writ)
{
@@ -2028,6 +2056,17 @@
mlx5_mkey_variant(umrwr->mkey));
}
+static void set_reg_data_seg(struct mlx5_wqe_data_seg *dseg,
+ struct mlx5_ib_mr *mr,
+ struct mlx5_ib_pd *pd)
+{
+ int bcount = mr->desc_size * mr->ndescs;
+
+ dseg->addr = cpu_to_be64(mr->desc_map);
+ dseg->byte_count = cpu_to_be32(ALIGN(bcount, 64));
+ dseg->lkey = cpu_to_be32(pd->ibpd.local_dma_lkey);
+}
+
static void set_frwr_pages(struct mlx5_wqe_data_seg *dseg,
struct ib_send_wr *wr,
struct mlx5_core_dev *mdev,
@@ -2433,6 +2472,38 @@
return 0;
}
+static int set_reg_wr(struct mlx5_ib_qp *qp,
+ struct ib_reg_wr *wr,
+ void **seg, int *size)
+{
+ struct mlx5_ib_mr *mr = to_mmr(wr->mr);
+ struct mlx5_ib_pd *pd = to_mpd(qp->ibqp.pd);
+
+ if (unlikely(wr->wr.send_flags & IB_SEND_INLINE)) {
+ mlx5_ib_warn(to_mdev(qp->ibqp.device),
+ "Invalid IB_SEND_INLINE send flag\n");
+ return -EINVAL;
+ }
+
+ set_reg_umr_seg(*seg, mr);
+ *seg += sizeof(struct mlx5_wqe_umr_ctrl_seg);
+ *size += sizeof(struct mlx5_wqe_umr_ctrl_seg) / 16;
+ if (unlikely((*seg == qp->sq.qend)))
+ *seg = mlx5_get_send_wqe(qp, 0);
+
+ set_reg_mkey_seg(*seg, mr, wr->key, wr->access);
+ *seg += sizeof(struct mlx5_mkey_seg);
+ *size += sizeof(struct mlx5_mkey_seg) / 16;
+ 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);
+
+ return 0;
+}
+
static int set_frwr_li_wr(void **seg, struct ib_send_wr *wr, int *size,
struct mlx5_core_dev *mdev, struct mlx5_ib_pd *pd, struct mlx5_ib_qp *qp)
{
@@ -2675,6 +2746,18 @@
num_sge = 0;
break;
+ case IB_WR_REG_MR:
+ next_fence = MLX5_FENCE_MODE_INITIATOR_SMALL;
+ qp->sq.wr_data[idx] = IB_WR_REG_MR;
+ ctrl->imm = cpu_to_be32(reg_wr(wr)->key);
+ err = set_reg_wr(qp, reg_wr(wr), &seg, &size);
+ if (err) {
+ *bad_wr = wr;
+ goto out;
+ }
+ num_sge = 0;
+ break;
+
case IB_WR_REG_SIG_MR:
qp->sq.wr_data[idx] = IB_WR_REG_SIG_MR;
mr = to_mmr(sig_handover_wr(wr)->sig_mr);