QP can be created without internal WQs "packaged" inside it,
this QP can be configured to use "external" WQ object as its
receive/send queue.
WQ is a necessary component for RSS technology since RSS mechanism
is supposed to distribute the traffic between multiple
Receive Work Queues
Add receive Work Queue verbs, it includes:
creation, modification and destruction.
Signed-off-by: Yishai Hadas <yishaih@xxxxxxxxxxxx>
Signed-off-by: Eli Cohen <eli@xxxxxxxxxxxx>
---
drivers/infiniband/hw/mlx5/main.c | 9 ++
drivers/infiniband/hw/mlx5/mlx5_ib.h | 35 +++++
drivers/infiniband/hw/mlx5/qp.c | 263 ++++++++++++++++++++++++++++++++++
drivers/infiniband/hw/mlx5/user.h | 15 ++
4 files changed, 322 insertions(+), 0 deletions(-)
diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index 41d6911..1601f19 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -1505,6 +1505,15 @@ static void *mlx5_ib_add(struct mlx5_core_dev *mdev)
(1ull << IB_USER_VERBS_CMD_CLOSE_XRCD);
}
+ if (MLX5_CAP_GEN(mdev, port_type) == MLX5_CAP_PORT_TYPE_ETH) {
+ dev->ib_dev.create_wq = mlx5_ib_create_wq;
+ dev->ib_dev.modify_wq = mlx5_ib_modify_wq;
+ dev->ib_dev.destroy_wq = mlx5_ib_destroy_wq;
+ dev->ib_dev.uverbs_ex_cmd_mask |=
+ (1ull << IB_USER_VERBS_EX_CMD_CREATE_WQ) |
+ (1ull << IB_USER_VERBS_EX_CMD_MODIFY_WQ) |
+ (1ull << IB_USER_VERBS_EX_CMD_DESTROY_WQ);
+ }
err = init_node_data(dev);
if (err)
goto err_dealloc;
diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h
index bb8cda7..6c00aca 100644
--- a/drivers/infiniband/hw/mlx5/mlx5_ib.h
+++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h
@@ -143,12 +143,36 @@ struct mlx5_ib_wq {
void *qend;
};
+struct mlx5_ib_rwq {
+ struct ib_wq ibwq;
+ u32 rqn;
+ u32 rq_num_pas;
+ u32 log_rq_stride;
+ u32 log_rq_size;
+ u32 rq_page_offset;
+ u32 log_page_size;
+ struct ib_umem *umem;
+ size_t buf_size;
+ unsigned int page_shift;
+ int create_type;
+ struct mlx5_db db;
+ u32 user_index;
+ u32 wqe_count;
+ u32 wqe_shift;
+ int wq_sig;
+};
+
enum {
MLX5_QP_USER,
MLX5_QP_KERNEL,
MLX5_QP_EMPTY
};
+enum {
+ MLX5_WQ_USER,
+ MLX5_WQ_KERNEL
+};
+
/*
* Connect-IB can trigger up to four concurrent pagefaults
* per-QP.
@@ -493,6 +517,11 @@ static inline struct mlx5_ib_qp *to_mqp(struct ib_qp *ibqp)
return container_of(ibqp, struct mlx5_ib_qp, ibqp);
}
+static inline struct mlx5_ib_rwq *to_mrwq(struct ib_wq *ibwq)
+{
+ return container_of(ibwq, struct mlx5_ib_rwq, ibwq);
+}
+
static inline struct mlx5_ib_srq *to_mibsrq(struct mlx5_core_srq *msrq)
{
return container_of(msrq, struct mlx5_ib_srq, msrq);
@@ -630,6 +659,12 @@ int mlx5_mr_ib_cont_pages(struct ib_umem *umem, u64 addr, int *count, int *shift
void mlx5_umr_cq_handler(struct ib_cq *cq, void *cq_context);
int mlx5_ib_check_mr_status(struct ib_mr *ibmr, u32 check_mask,
struct ib_mr_status *mr_status);
+struct ib_wq *mlx5_ib_create_wq(struct ib_pd *pd,
+ struct ib_wq_init_attr *init_attr,
+ struct ib_udata *udata);
+int mlx5_ib_destroy_wq(struct ib_wq *wq);
+int mlx5_ib_modify_wq(struct ib_wq *wq, struct ib_wq_attr *wq_attr,
+ enum ib_wq_attr_mask attr_mask, struct ib_udata *udata);
#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
extern struct workqueue_struct *mlx5_ib_page_fault_wq;
diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c
index c745c6c..3763205 100644
--- a/drivers/infiniband/hw/mlx5/qp.c
+++ b/drivers/infiniband/hw/mlx5/qp.c
@@ -32,6 +32,7 @@
#include <linux/module.h>
#include <rdma/ib_umem.h>
+#include <linux/mlx5/transobj.h>
#include "mlx5_ib.h"
#include "user.h"
@@ -590,6 +591,71 @@ static int uuarn_to_uar_index(struct mlx5_uuar_info *uuari, int uuarn)
return uuari->uars[uuarn / MLX5_BF_REGS_PER_PAGE].index;
}
+static void destroy_user_rq(struct ib_pd *pd, struct mlx5_ib_rwq *rwq)
+{
+ struct mlx5_ib_ucontext *context;
+
+ context = to_mucontext(pd->uobject->context);
+ mlx5_ib_db_unmap_user(context, &rwq->db);
+ if (rwq->umem)
+ ib_umem_release(rwq->umem);
+}
+
+static int create_user_rq(struct mlx5_ib_dev *dev, struct ib_pd *pd,
+ struct mlx5_ib_rwq *rwq,
+ struct mlx5_ib_create_wq *ucmd)
+{
+ struct mlx5_ib_ucontext *context;
+ int page_shift = 0;
+ int npages;
+ u32 offset = 0;
+ int ncont = 0;
+ int err;
+
+ if (!ucmd->buf_addr)
+ return -EINVAL;
+
+ context = to_mucontext(pd->uobject->context);
+ rwq->umem = ib_umem_get(pd->uobject->context, ucmd->buf_addr,
+ rwq->buf_size, 0, 0);
+ if (IS_ERR(rwq->umem)) {
+ mlx5_ib_dbg(dev, "umem_get failed\n");
+ err = PTR_ERR(rwq->umem);
+ return err;
+ }
+
+ mlx5_ib_cont_pages(rwq->umem, ucmd->buf_addr, &npages, &page_shift,
+ &ncont, NULL);
+ err = mlx5_ib_get_buf_offset(ucmd->buf_addr, page_shift,
+ &rwq->rq_page_offset);
+ if (err) {
+ mlx5_ib_warn(dev, "bad offset\n");
+ goto err_umem;
+ }
+
+ rwq->rq_num_pas = ncont;
+ rwq->page_shift = page_shift;
+ rwq->log_page_size = page_shift - PAGE_SHIFT;
+ rwq->wq_sig = !!(ucmd->flags & MLX5_WQ_FLAG_SIGNATURE);
+
+ mlx5_ib_dbg(dev, "addr 0x%llx, size %zd, npages %d, page_shift %d, ncont %d, offset %d\n",
+ (unsigned long long)ucmd->buf_addr, rwq->buf_size,
+ npages, page_shift, ncont, offset);
+
+ err = mlx5_ib_db_map_user(context, ucmd->db_addr, &rwq->db);
+ if (err) {
+ mlx5_ib_dbg(dev, "map failed\n");
+ goto err_umem;
+ }
+
+ rwq->create_type = MLX5_WQ_USER;
+ return 0;
+
+err_umem:
+ ib_umem_release(rwq->umem);
+ return err;
+}
+
static int create_user_qp(struct mlx5_ib_dev *dev, struct ib_pd *pd,
struct mlx5_ib_qp *qp, struct ib_udata *udata,
struct mlx5_create_qp_mbox_in **in,
@@ -3160,3 +3226,200 @@ int mlx5_ib_dealloc_xrcd(struct ib_xrcd *xrcd)
return 0;
}
+
+static int create_rq(struct mlx5_ib_rwq *rwq, struct ib_pd *pd,
+ struct ib_wq_init_attr *init_attr)
+{
+ struct mlx5_ib_dev *dev;
+ __be64 *rq_pas0;
+ void *in;
+ void *rqc;
+ void *wq;
+ int inlen;
+ int err;
+
+ dev = to_mdev(pd->device);
+
+ inlen = MLX5_ST_SZ_BYTES(create_rq_in) + sizeof(u64) * rwq->rq_num_pas;
+ in = mlx5_vzalloc(inlen);
+ if (!in)
+ return -ENOMEM;
+
+ rqc = MLX5_ADDR_OF(create_rq_in, in, ctx);
+ MLX5_SET(rqc, rqc, mem_rq_type,
+ MLX5_RQC_MEM_RQ_TYPE_MEMORY_RQ_INLINE);
+ MLX5_SET(rqc, rqc, user_index, rwq->user_index);
+ MLX5_SET(rqc, rqc, cqn, to_mcq(init_attr->cq)->mcq.cqn);
+ MLX5_SET(rqc, rqc, state, MLX5_RQC_STATE_RST);
+ MLX5_SET(rqc, rqc, flush_in_error_en, 1);
+ wq = MLX5_ADDR_OF(rqc, rqc, wq);
+ MLX5_SET(wq, wq, wq_type, MLX5_WQ_TYPE_CYCLIC);
+ MLX5_SET(wq, wq, end_padding_mode, MLX5_WQ_END_PAD_MODE_ALIGN);
+ MLX5_SET(wq, wq, log_wq_stride, rwq->log_rq_stride);
+ MLX5_SET(wq, wq, log_wq_sz, rwq->log_rq_size);
+ MLX5_SET(wq, wq, pd, to_mpd(pd)->pdn);
+ MLX5_SET(wq, wq, page_offset, rwq->rq_page_offset);
+ MLX5_SET(wq, wq, log_wq_pg_sz, rwq->log_page_size);
+ MLX5_SET(wq, wq, wq_signature, rwq->wq_sig);
+ MLX5_SET64(wq, wq, dbr_addr, rwq->db.dma);
+ rq_pas0 = (__be64 *)MLX5_ADDR_OF(wq, wq, pas);
+ mlx5_ib_populate_pas(dev, rwq->umem, rwq->page_shift, rq_pas0, 0);
+ err = mlx5_core_create_rq(dev->mdev, in, inlen, &rwq->rqn);
+ kvfree(in);
+ return err;
+}
+
+static int set_user_rq_size(struct mlx5_ib_dev *dev,
+ struct ib_wq_init_attr *wq_init_attr,
+ struct mlx5_ib_create_wq *ucmd,
+ struct mlx5_ib_rwq *rwq)
+{
+ /* Sanity check RQ size before proceeding */
+ if (wq_init_attr->max_wr > (1 << MLX5_CAP_GEN(dev->mdev, log_max_wq_sz)))
+ return -EINVAL;
+
+ if (!ucmd->rq_wqe_count)
+ return -EINVAL;
+
+ rwq->wqe_count = ucmd->rq_wqe_count;
+ rwq->wqe_shift = ucmd->rq_wqe_shift;
+ rwq->buf_size = (rwq->wqe_count << rwq->wqe_shift);
+ rwq->log_rq_stride = rwq->wqe_shift;
+ rwq->log_rq_size = ilog2(rwq->wqe_count);
+ return 0;
+}
+
+static int prepare_user_rq(struct ib_pd *pd,
+ struct ib_wq_init_attr *init_attr,
+ struct ib_udata *udata,
+ struct mlx5_ib_rwq *rwq)
+{
+ struct mlx5_ib_dev *dev = to_mdev(pd->device);
+ struct mlx5_ib_create_wq ucmd;
+ int err;
+
+ if (udata->inlen < sizeof(ucmd)) {
+ mlx5_ib_dbg(dev, "invalid inlen\n");
+ return -EINVAL;
+ }
+
+ if (ib_copy_from_udata(&ucmd, udata, sizeof(ucmd))) {
+ mlx5_ib_dbg(dev, "copy failed\n");
+ return -EFAULT;
+ }
+
+ if (ucmd.reserved[0] || (ucmd.reserved[1])) {
+ mlx5_ib_dbg(dev, "invalid reserved\n");
+ return -EFAULT;
+ }
+
+ err = set_user_rq_size(dev, init_attr, &ucmd, rwq);
+ if (err) {
+ mlx5_ib_dbg(dev, "err %d\n", err);
+ return err;
+ }
+
+ err = create_user_rq(dev, pd, rwq, &ucmd);
+ if (err) {
+ mlx5_ib_dbg(dev, "err %d\n", err);
+ if (err)
+ return err;
+ }
+
+ rwq->user_index = ucmd.user_index;
+ return 0;
+}
+
+struct ib_wq *mlx5_ib_create_wq(struct ib_pd *pd,
+ struct ib_wq_init_attr *init_attr,
+ struct ib_udata *udata)
+{
+ struct mlx5_ib_dev *dev;
+ struct mlx5_ib_rwq *rwq;
+ int err;
+
+ if (!udata)
+ return ERR_PTR(-ENOSYS);
+
+ dev = to_mdev(pd->device);
+ switch (init_attr->wq_type) {
+ case IB_WQT_RQ:
+ rwq = kzalloc(sizeof(*rwq), GFP_KERNEL);
+ if (!rwq)
+ return ERR_PTR(-ENOMEM);
+ err = prepare_user_rq(pd, init_attr, udata, rwq);
+ if (err)
+ goto err;
+ err = create_rq(rwq, pd, init_attr);
+ if (err)
+ goto err_user_rq;
+ break;
+ default:
+ mlx5_ib_dbg(dev, "unsupported wq type %d\n",
+ init_attr->wq_type);
+ return ERR_PTR(-EINVAL);
+ }
+
+ rwq->ibwq.wq_num = rwq->rqn;
+ rwq->ibwq.state = IB_WQS_RESET;
+ return &rwq->ibwq;
+
+err_user_rq:
+ destroy_user_rq(pd, rwq);
+err:
+ kfree(rwq);
+ return ERR_PTR(err);
+}
+
+int mlx5_ib_destroy_wq(struct ib_wq *wq)
+{
+ struct mlx5_ib_dev *dev = to_mdev(wq->device);
+ struct mlx5_ib_rwq *rwq = to_mrwq(wq);
+
+ if (wq->wq_type != IB_WQT_RQ)
+ return -EINVAL;
+
+ mlx5_core_destroy_rq(dev->mdev, rwq->rqn);
+ destroy_user_rq(wq->pd, rwq);
+ kfree(rwq);
+
+ return 0;
+}
+
+int mlx5_ib_modify_wq(struct ib_wq *wq, struct ib_wq_attr *wq_attr,
+ enum ib_wq_attr_mask attr_mask, struct ib_udata *udata)
+{
+ struct mlx5_ib_dev *dev = to_mdev(wq->device);
+ struct mlx5_ib_rwq *rwq = to_mrwq(wq);
+ int curr_wq_state;
+ int wq_state;
+ int inlen;
+ int err;
+ void *rqc;
+ void *in;
+
+ inlen = MLX5_ST_SZ_BYTES(modify_rq_in);
+ in = mlx5_vzalloc(inlen);
+ if (!in)
+ return -ENOMEM;
+
+ rqc = MLX5_ADDR_OF(modify_rq_in, in, ctx);
+
+ curr_wq_state = (attr_mask & IB_WQ_CUR_STATE) ?
+ wq_attr->curr_wq_state : wq->state;
+ wq_state = (attr_mask & IB_WQ_STATE) ?
+ wq_attr->wq_state : curr_wq_state;
+ if (curr_wq_state == IB_WQS_ERR)
+ curr_wq_state = MLX5_RQC_STATE_ERR;
+ if (wq_state == IB_WQS_ERR)
+ wq_state = MLX5_RQC_STATE_ERR;
+ MLX5_SET(modify_rq_in, in, rq_state, curr_wq_state);
+ MLX5_SET(rqc, rqc, state, wq_state);
+
+ err = mlx5_core_modify_rq(dev->mdev, rwq->rqn, in, inlen);
+ kvfree(in);
+ if (!err)
+ rwq->ibwq.state = (wq_state == MLX5_RQC_STATE_ERR) ? IB_WQS_ERR : wq_state;
+
+ return err;
+}
diff --git a/drivers/infiniband/hw/mlx5/user.h b/drivers/infiniband/hw/mlx5/user.h
index 76fb7b9..270c699 100644
--- a/drivers/infiniband/hw/mlx5/user.h
+++ b/drivers/infiniband/hw/mlx5/user.h
@@ -44,6 +44,10 @@ enum {
MLX5_SRQ_FLAG_SIGNATURE = 1 << 0,
};
+enum {
+ MLX5_WQ_FLAG_SIGNATURE = 1 << 0,
+};
+
/* Increment this value if any changes that break userspace ABI
* compatibility are made.
@@ -130,4 +134,15 @@ struct mlx5_ib_create_qp {
struct mlx5_ib_create_qp_resp {
__u32 uuar_index;
};
+
+struct mlx5_ib_create_wq {
+ __u64 buf_addr;
+ __u64 db_addr;
+ __u32 rq_wqe_count;
+ __u32 rq_wqe_shift;
+ __u32 user_index;
+ __u32 flags;
+ __u64 reserved[2];
+};
+
#endif /* MLX5_IB_USER_H */
--
1.7.1
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
