Merge branch 'mlx5-dump-fill-mkey' into rdma.git for-next

For dependencies, branch based on 'mellanox/mlx5-next' of
git://git.kernel.org/pub/scm/linux/kernel/git/mellanox/linux.git

Pull Dump and fill MKEY from Leon Romanovsky:

====================
MLX5 IB HCA offers the memory key, dump_fill_mkey to increase performance,
when used in a send or receive operations.

It is used to force local HCA operations to skip the PCI bus access, while
keeping track of the processed length in the ibv_sge handling.

In this three patch series, we expose various bits in our HW spec
file (mlx5_ifc.h), move unneeded for mlx5_core FW command and export such
memory key to user space thought our mlx5-abi header file.
====================

Botched auto-merge in mlx5_ib_alloc_ucontext() resolved by hand.

* branch 'mlx5-dump-fill-mkey':
  IB/mlx5: Expose dump and fill memory key
  net/mlx5: Add hardware definitions for dump_fill_mkey
  net/mlx5: Limit scope of dump_fill_mkey function
  net/mlx5: Rate limit errors in command interface

Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>

drivers/infiniband/hw/mlx5/cmd.c

@@ -32,6 +32,21 @@
 
 #include "cmd.h"
 
+int mlx5_cmd_dump_fill_mkey(struct mlx5_core_dev *dev, u32 *mkey)
+{
+	u32 out[MLX5_ST_SZ_DW(query_special_contexts_out)] = {0};
+	u32 in[MLX5_ST_SZ_DW(query_special_contexts_in)]   = {0};
+	int err;
+
+	MLX5_SET(query_special_contexts_in, in, opcode,
+		 MLX5_CMD_OP_QUERY_SPECIAL_CONTEXTS);
+	err = mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
+	if (!err)
+		*mkey = MLX5_GET(query_special_contexts_out, out,
+				 dump_fill_mkey);
+	return err;
+}
+
 int mlx5_cmd_null_mkey(struct mlx5_core_dev *dev, u32 *null_mkey)
 {
 	u32 out[MLX5_ST_SZ_DW(query_special_contexts_out)] = {};

drivers/infiniband/hw/mlx5/cmd.h

@@ -37,6 +37,7 @@
 #include <linux/kernel.h>
 #include <linux/mlx5/driver.h>
 
+int mlx5_cmd_dump_fill_mkey(struct mlx5_core_dev *dev, u32 *mkey);
 int mlx5_cmd_null_mkey(struct mlx5_core_dev *dev, u32 *null_mkey);
 int mlx5_cmd_query_cong_params(struct mlx5_core_dev *dev, int cong_point,
 			       void *out, int out_size);

drivers/infiniband/hw/mlx5/main.c

@@ -1632,6 +1632,7 @@ static struct ib_ucontext *mlx5_ib_alloc_ucontext(struct ib_device *ibdev,
 	int err;
 	size_t min_req_v2 = offsetof(struct mlx5_ib_alloc_ucontext_req_v2,
 				     max_cqe_version);
+	u32 dump_fill_mkey;
 	bool lib_uar_4k;
 
 	if (!dev->ib_active)
@@ -1743,6 +1744,12 @@ static struct ib_ucontext *mlx5_ib_alloc_ucontext(struct ib_device *ibdev,
 			goto out_td;
 	}
 
+	if (MLX5_CAP_GEN(dev->mdev, dump_fill_mkey)) {
+		err = mlx5_cmd_dump_fill_mkey(dev->mdev, &dump_fill_mkey);
+		if (err)
+			goto out_mdev;
+	}
+
 	INIT_LIST_HEAD(&context->vma_private_list);
 	mutex_init(&context->vma_private_list_mutex);
 	INIT_LIST_HEAD(&context->db_page_list);
@@ -1801,6 +1808,15 @@ static struct ib_ucontext *mlx5_ib_alloc_ucontext(struct ib_device *ibdev,
 		resp.response_length += sizeof(resp.num_dyn_bfregs);
 	}
 
+	if (field_avail(typeof(resp), dump_fill_mkey, udata->outlen)) {
+		if (MLX5_CAP_GEN(dev->mdev, dump_fill_mkey)) {
+			resp.dump_fill_mkey = dump_fill_mkey;
+			resp.comp_mask |=
+				MLX5_IB_ALLOC_UCONTEXT_RESP_MASK_DUMP_FILL_MKEY;
+		}
+		resp.response_length += sizeof(resp.dump_fill_mkey);
+	}
+
 	err = ib_copy_to_udata(udata, &resp, resp.response_length);
 	if (err)
 		goto out_mdev;