IB/mlx5: Add function to read WQE from user-space

Add a helper function mlx5_ib_read_user_wqe to read information from
user-space owned work queues.  The function will be used in a later
patch by the page-fault handling code in mlx5_ib.

Signed-off-by: Haggai Eran <haggaie@mellanox.com>

[ Add stub for ib_umem_copy_from() for CONFIG_INFINIBAND_USER_MEM=n
  - Roland ]

Signed-off-by: Roland Dreier <roland@purestorage.com>

4 files changed, 80 insertions, 1 deletions

diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h
index 53d19e6e69a4..14a0311eaa1c 100644
--- a/drivers/infiniband/hw/mlx5/mlx5_ib.h
+++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h
@@ -503,6 +503,8 @@ int mlx5_ib_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr,
 int mlx5_ib_post_recv(struct ib_qp *ibqp, struct ib_recv_wr *wr,
                       struct ib_recv_wr **bad_wr);
 void *mlx5_get_send_wqe(struct mlx5_ib_qp *qp, int n);
+int mlx5_ib_read_user_wqe(struct mlx5_ib_qp *qp, int send, int wqe_index,
+                          void *buffer, u32 length);
 struct ib_cq *mlx5_ib_create_cq(struct ib_device *ibdev, int entries,
                                 int vector, struct ib_ucontext *context,
                                 struct ib_udata *udata);
diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c
index 36e2cfe1c2fe..9783c3342dbf 100644
--- a/drivers/infiniband/hw/mlx5/qp.c
+++ b/drivers/infiniband/hw/mlx5/qp.c
@@ -101,6 +101,77 @@ void *mlx5_get_send_wqe(struct mlx5_ib_qp *qp, int n)
         return get_wqe(qp, qp->sq.offset + (n << MLX5_IB_SQ_STRIDE));
 }
 
+/**
+ * mlx5_ib_read_user_wqe() - Copy a user-space WQE to kernel space.
+ *
+ * @qp: QP to copy from.
+ * @send: copy from the send queue when non-zero, use the receive queue
+ *        otherwise.
+ * @wqe_index:  index to start copying from. For send work queues, the
+ *              wqe_index is in units of MLX5_SEND_WQE_BB.
+ *              For receive work queue, it is the number of work queue
+ *              element in the queue.
+ * @buffer: destination buffer.
+ * @length: maximum number of bytes to copy.
+ *
+ * Copies at least a single WQE, but may copy more data.
+ *
+ * Return: the number of bytes copied, or an error code.
+ */
+int mlx5_ib_read_user_wqe(struct mlx5_ib_qp *qp, int send, int wqe_index,
+                          void *buffer, u32 length)
+{
+        struct ib_device *ibdev = qp->ibqp.device;
+        struct mlx5_ib_dev *dev = to_mdev(ibdev);
+        struct mlx5_ib_wq *wq = send ? &qp->sq : &qp->rq;
+        size_t offset;
+        size_t wq_end;
+        struct ib_umem *umem = qp->umem;
+        u32 first_copy_length;
+        int wqe_length;
+        int ret;
+
+        if (wq->wqe_cnt == 0) {
+                mlx5_ib_dbg(dev, "mlx5_ib_read_user_wqe for a QP with wqe_cnt == 0. qp_type: 0x%x\n",
+                            qp->ibqp.qp_type);
+                return -EINVAL;
+        }
+
+        offset = wq->offset + ((wqe_index % wq->wqe_cnt) << wq->wqe_shift);
+        wq_end = wq->offset + (wq->wqe_cnt << wq->wqe_shift);
+
+        if (send && length < sizeof(struct mlx5_wqe_ctrl_seg))
+                return -EINVAL;
+
+        if (offset > umem->length ||
+            (send && offset + sizeof(struct mlx5_wqe_ctrl_seg) > umem->length))
+                return -EINVAL;
+
+        first_copy_length = min_t(u32, offset + length, wq_end) - offset;
+        ret = ib_umem_copy_from(buffer, umem, offset, first_copy_length);
+        if (ret)
+                return ret;
+
+        if (send) {
+                struct mlx5_wqe_ctrl_seg *ctrl = buffer;
+                int ds = be32_to_cpu(ctrl->qpn_ds) & MLX5_WQE_CTRL_DS_MASK;
+
+                wqe_length = ds * MLX5_WQE_DS_UNITS;
+        } else {
+                wqe_length = 1 << wq->wqe_shift;
+        }
+
+        if (wqe_length <= first_copy_length)
+                return first_copy_length;
+
+        ret = ib_umem_copy_from(buffer + first_copy_length, umem, wq->offset,
+                                wqe_length - first_copy_length);
+        if (ret)
+                return ret;
+
+        return wqe_length;
+}
+
 static void mlx5_ib_qp_event(struct mlx5_core_qp *qp, int type)
 {
         struct ib_qp *ibqp = &to_mibqp(qp)->ibqp;
diff --git a/include/linux/mlx5/qp.h b/include/linux/mlx5/qp.h
index 3fa075daeb1d..67f4b9660b06 100644
--- a/include/linux/mlx5/qp.h
+++ b/include/linux/mlx5/qp.h
@@ -189,6 +189,9 @@ struct mlx5_wqe_ctrl_seg {
         __be32                  imm;
 };
 
+#define MLX5_WQE_CTRL_DS_MASK 0x3f
+#define MLX5_WQE_DS_UNITS 16
+
 struct mlx5_wqe_xrc_seg {
         __be32                  xrc_srqn;
         u8                      rsvd[12];
diff --git a/include/rdma/ib_umem.h b/include/rdma/ib_umem.h
index 45bb04bc88cd..a51f4091489a 100644
--- a/include/rdma/ib_umem.h
+++ b/include/rdma/ib_umem.h
@@ -98,7 +98,10 @@ static inline struct ib_umem *ib_umem_get(struct ib_ucontext *context,
 }
 static inline void ib_umem_release(struct ib_umem *umem) { }
 static inline int ib_umem_page_count(struct ib_umem *umem) { return 0; }
-
+static inline int ib_umem_copy_from(void *dst, struct ib_umem *umem, size_t offset,
+                                    size_t length) {
+        return -EINVAL;
+}
 #endif /* CONFIG_INFINIBAND_USER_MEM */
 
 #endif /* IB_UMEM_H */