From: Yishai Hadas <yishaih@xxxxxxxxxxxx>
Introduce DEVX to enable direct device commands in downstream patches
from this series.
In that mode of work the firmware manages the isolation between
processes' resources and as such a DEVX user id is created and assigned
to the given user context upon allocation request.
A capability check is done to make sure that this feature is really
supported by the firmware prior to creating the DEVX user id.
Signed-off-by: Yishai Hadas <yishaih@xxxxxxxxxxxx>
Signed-off-by: Leon Romanovsky <leonro@xxxxxxxxxxxx>
---
drivers/infiniband/hw/mlx5/Makefile | 1 +
drivers/infiniband/hw/mlx5/devx.c | 58 +++++++++++++++++++++++++++
drivers/infiniband/hw/mlx5/main.c | 24 +++++++++--
drivers/infiniband/hw/mlx5/mlx5_ib.h | 13 ++++++
drivers/net/ethernet/mellanox/mlx5/core/cmd.c | 4 ++
include/linux/mlx5/device.h | 3 ++
include/linux/mlx5/mlx5_ifc.h | 15 ++++++-
include/uapi/rdma/mlx5-abi.h | 3 ++
8 files changed, 117 insertions(+), 4 deletions(-)
create mode 100644 drivers/infiniband/hw/mlx5/devx.c
diff --git a/drivers/infiniband/hw/mlx5/Makefile b/drivers/infiniband/hw/mlx5/Makefile
index d42b922bede8..577e4c418bae 100644
--- a/drivers/infiniband/hw/mlx5/Makefile
+++ b/drivers/infiniband/hw/mlx5/Makefile
@@ -3,3 +3,4 @@ obj-$(CONFIG_MLX5_INFINIBAND) += mlx5_ib.o
mlx5_ib-y := main.o cq.o doorbell.o qp.o mem.o srq.o mr.o ah.o mad.o gsi.o ib_virt.o cmd.o cong.o
mlx5_ib-$(CONFIG_INFINIBAND_ON_DEMAND_PAGING) += odp.o
mlx5_ib-$(CONFIG_MLX5_ESWITCH) += ib_rep.o
+mlx5_ib-$(CONFIG_INFINIBAND_USER_ACCESS) += devx.o
diff --git a/drivers/infiniband/hw/mlx5/devx.c b/drivers/infiniband/hw/mlx5/devx.c
new file mode 100644
index 000000000000..775448910ad1
--- /dev/null
+++ b/drivers/infiniband/hw/mlx5/devx.c
@@ -0,0 +1,58 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/*
+ * Copyright (c) 2018, Mellanox Technologies inc. All rights reserved.
+ */
+
+#include <rdma/ib_user_verbs.h>
+#include <rdma/ib_verbs.h>
+#include <rdma/uverbs_types.h>
+#include <rdma/uverbs_ioctl.h>
+#include <rdma/mlx5_user_ioctl_cmds.h>
+#include <rdma/ib_umem.h>
+#include <linux/mlx5/driver.h>
+#include <linux/mlx5/fs.h>
+#include "mlx5_ib.h"
+
+int mlx5_ib_devx_create(struct mlx5_ib_dev *dev, struct mlx5_ib_ucontext *context)
+{
+ u32 in[MLX5_ST_SZ_DW(create_uctx_in)] = {0};
+ u32 out[MLX5_ST_SZ_DW(general_obj_out_cmd_hdr)] = {0};
+ u64 general_obj_types;
+ void *uctx;
+ void *hdr;
+ int err;
+
+ uctx = MLX5_ADDR_OF(create_uctx_in, in, uctx);
+ hdr = MLX5_ADDR_OF(create_uctx_in, in, hdr);
+
+ general_obj_types = MLX5_CAP_GEN_64(dev->mdev, general_obj_types);
+ if (!(general_obj_types & MLX5_GENERAL_OBJ_TYPES_CAP_UCTX) ||
+ !(general_obj_types & MLX5_GENERAL_OBJ_TYPES_CAP_UMEM))
+ return -EINVAL;
+
+ if (!capable(CAP_NET_RAW))
+ return -EPERM;
+
+ MLX5_SET(general_obj_in_cmd_hdr, hdr, opcode, MLX5_CMD_OP_CREATE_GENERAL_OBJECT);
+ MLX5_SET(general_obj_in_cmd_hdr, hdr, obj_type, MLX5_OBJ_TYPE_UCTX);
+
+ err = mlx5_cmd_exec(dev->mdev, in, sizeof(in), out, sizeof(out));
+ if (err)
+ return err;
+
+ context->devx_uid = MLX5_GET(general_obj_out_cmd_hdr, out, obj_id);
+ return 0;
+}
+
+void mlx5_ib_devx_destroy(struct mlx5_ib_dev *dev,
+ struct mlx5_ib_ucontext *context)
+{
+ u32 in[MLX5_ST_SZ_DW(general_obj_in_cmd_hdr)] = {0};
+ u32 out[MLX5_ST_SZ_DW(general_obj_out_cmd_hdr)] = {0};
+
+ MLX5_SET(general_obj_in_cmd_hdr, in, opcode, MLX5_CMD_OP_DESTROY_GENERAL_OBJECT);
+ MLX5_SET(general_obj_in_cmd_hdr, in, obj_type, MLX5_OBJ_TYPE_UCTX);
+ MLX5_SET(general_obj_in_cmd_hdr, in, obj_id, context->devx_uid);
+
+ mlx5_cmd_exec(dev->mdev, in, sizeof(in), out, sizeof(out));
+}
diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index e52dd21519b4..430a9e36d392 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -1676,8 +1676,8 @@ static struct ib_ucontext *mlx5_ib_alloc_ucontext(struct ib_device *ibdev,
if (err)
return ERR_PTR(err);
- if (req.flags)
- return ERR_PTR(-EINVAL);
+ if (req.flags & ~MLX5_IB_ALLOC_UCTX_DEVX)
+ return ERR_PTR(-EOPNOTSUPP);
if (req.comp_mask || req.reserved0 || req.reserved1 || req.reserved2)
return ERR_PTR(-EOPNOTSUPP);
@@ -1761,6 +1761,18 @@ static struct ib_ucontext *mlx5_ib_alloc_ucontext(struct ib_device *ibdev,
goto out_uars;
}
+ if (req.flags & MLX5_IB_ALLOC_UCTX_DEVX) {
+ /* Block DEVX on Infiniband as of SELinux */
+ if (mlx5_ib_port_link_layer(ibdev, 1) != IB_LINK_LAYER_ETHERNET) {
+ err = -EPERM;
+ goto out_td;
+ }
+
+ err = mlx5_ib_devx_create(dev, context);
+ if (err)
+ goto out_td;
+ }
+
INIT_LIST_HEAD(&context->vma_private_list);
mutex_init(&context->vma_private_list_mutex);
INIT_LIST_HEAD(&context->db_page_list);
@@ -1821,7 +1833,7 @@ static struct ib_ucontext *mlx5_ib_alloc_ucontext(struct ib_device *ibdev,
err = ib_copy_to_udata(udata, &resp, resp.response_length);
if (err)
- goto out_td;
+ goto out_mdev;
bfregi->ver = ver;
bfregi->num_low_latency_bfregs = req.num_low_latency_bfregs;
@@ -1831,6 +1843,9 @@ static struct ib_ucontext *mlx5_ib_alloc_ucontext(struct ib_device *ibdev,
return &context->ibucontext;
+out_mdev:
+ if (req.flags & MLX5_IB_ALLOC_UCTX_DEVX)
+ mlx5_ib_devx_destroy(dev, context);
out_td:
if (MLX5_CAP_GEN(dev->mdev, log_max_transport_domain))
mlx5_ib_dealloc_transport_domain(dev, context->tdn);
@@ -1856,6 +1871,9 @@ static int mlx5_ib_dealloc_ucontext(struct ib_ucontext *ibcontext)
struct mlx5_ib_dev *dev = to_mdev(ibcontext->device);
struct mlx5_bfreg_info *bfregi;
+ if (context->devx_uid)
+ mlx5_ib_devx_destroy(dev, context);
+
bfregi = &context->bfregi;
if (MLX5_CAP_GEN(dev->mdev, log_max_transport_domain))
mlx5_ib_dealloc_transport_domain(dev, context->tdn);
diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h
index d89c8fe626f6..5e8abd8bcd71 100644
--- a/drivers/infiniband/hw/mlx5/mlx5_ib.h
+++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h
@@ -143,6 +143,7 @@ struct mlx5_ib_ucontext {
u64 lib_caps;
DECLARE_BITMAP(dm_pages, MLX5_MAX_MEMIC_PAGES);
+ u16 devx_uid;
};
static inline struct mlx5_ib_ucontext *to_mucontext(struct ib_ucontext *ibucontext)
@@ -1217,6 +1218,18 @@ struct mlx5_core_dev *mlx5_ib_get_native_port_mdev(struct mlx5_ib_dev *dev,
void mlx5_ib_put_native_port_mdev(struct mlx5_ib_dev *dev,
u8 port_num);
+#if IS_ENABLED(CONFIG_INFINIBAND_USER_ACCESS)
+int mlx5_ib_devx_create(struct mlx5_ib_dev *dev,
+ struct mlx5_ib_ucontext *context);
+void mlx5_ib_devx_destroy(struct mlx5_ib_dev *dev,
+ struct mlx5_ib_ucontext *context);
+#else
+static inline int
+mlx5_ib_devx_create(struct mlx5_ib_dev *dev,
+ struct mlx5_ib_ucontext *context) { return -EOPNOTSUPP; };
+static inline void mlx5_ib_devx_destroy(struct mlx5_ib_dev *dev,
+ struct mlx5_ib_ucontext *context) {}
+#endif
static inline void init_query_mad(struct ib_smp *mad)
{
mad->base_version = 1;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
index b99d6df3905b..d07f24de8fa3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
@@ -310,6 +310,7 @@ static int mlx5_internal_err_ret_value(struct mlx5_core_dev *dev, u16 op,
case MLX5_CMD_OP_DEALLOC_ENCAP_HEADER:
case MLX5_CMD_OP_DEALLOC_MODIFY_HEADER_CONTEXT:
case MLX5_CMD_OP_FPGA_DESTROY_QP:
+ case MLX5_CMD_OP_DESTROY_GENERAL_OBJECT:
return MLX5_CMD_STAT_OK;
case MLX5_CMD_OP_QUERY_HCA_CAP:
@@ -427,6 +428,7 @@ static int mlx5_internal_err_ret_value(struct mlx5_core_dev *dev, u16 op,
case MLX5_CMD_OP_FPGA_MODIFY_QP:
case MLX5_CMD_OP_FPGA_QUERY_QP:
case MLX5_CMD_OP_FPGA_QUERY_QP_COUNTERS:
+ case MLX5_CMD_OP_CREATE_GENERAL_OBJECT:
*status = MLX5_DRIVER_STATUS_ABORTED;
*synd = MLX5_DRIVER_SYND;
return -EIO;
@@ -599,6 +601,8 @@ const char *mlx5_command_str(int command)
MLX5_COMMAND_STR_CASE(FPGA_QUERY_QP);
MLX5_COMMAND_STR_CASE(FPGA_QUERY_QP_COUNTERS);
MLX5_COMMAND_STR_CASE(FPGA_DESTROY_QP);
+ MLX5_COMMAND_STR_CASE(CREATE_GENERAL_OBJECT);
+ MLX5_COMMAND_STR_CASE(DESTROY_GENERAL_OBJECT);
default: return "unknown command opcode";
}
}
diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h
index 02f72ebf31a7..f8671c0a43aa 100644
--- a/include/linux/mlx5/device.h
+++ b/include/linux/mlx5/device.h
@@ -1071,6 +1071,9 @@ enum mlx5_qcam_feature_groups {
#define MLX5_CAP_GEN(mdev, cap) \
MLX5_GET(cmd_hca_cap, mdev->caps.hca_cur[MLX5_CAP_GENERAL], cap)
+#define MLX5_CAP_GEN_64(mdev, cap) \
+ MLX5_GET64(cmd_hca_cap, mdev->caps.hca_cur[MLX5_CAP_GENERAL], cap)
+
#define MLX5_CAP_GEN_MAX(mdev, cap) \
MLX5_GET(cmd_hca_cap, mdev->caps.hca_max[MLX5_CAP_GENERAL], cap)
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 78d4993a2920..f810772e80c0 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -75,6 +75,15 @@ enum {
MLX5_SET_HCA_CAP_OP_MOD_ATOMIC = 0x3,
};
+enum {
+ MLX5_GENERAL_OBJ_TYPES_CAP_UCTX = (1ULL << 4),
+ MLX5_GENERAL_OBJ_TYPES_CAP_UMEM = (1ULL << 5),
+};
+
+enum {
+ MLX5_OBJ_TYPE_UCTX = 0x0004,
+};
+
enum {
MLX5_CMD_OP_QUERY_HCA_CAP = 0x100,
MLX5_CMD_OP_QUERY_ADAPTER = 0x101,
@@ -242,6 +251,8 @@ enum {
MLX5_CMD_OP_FPGA_QUERY_QP = 0x962,
MLX5_CMD_OP_FPGA_DESTROY_QP = 0x963,
MLX5_CMD_OP_FPGA_QUERY_QP_COUNTERS = 0x964,
+ MLX5_CMD_OP_CREATE_GENERAL_OBJECT = 0xa00,
+ MLX5_CMD_OP_DESTROY_GENERAL_OBJECT = 0xa03,
MLX5_CMD_OP_MAX
};
@@ -1113,7 +1124,9 @@ struct mlx5_ifc_cmd_hca_cap_bits {
u8 reserved_at_3f8[0x3];
u8 log_max_current_uc_list[0x5];
- u8 reserved_at_400[0x80];
+ u8 general_obj_types[0x40];
+
+ u8 reserved_at_440[0x40];
u8 reserved_at_480[0x3];
u8 log_max_l2_table[0x5];
diff --git a/include/uapi/rdma/mlx5-abi.h b/include/uapi/rdma/mlx5-abi.h
index 8daec1fa49cf..5d591ff28139 100644
--- a/include/uapi/rdma/mlx5-abi.h
+++ b/include/uapi/rdma/mlx5-abi.h
@@ -76,6 +76,9 @@ enum mlx5_lib_caps {
MLX5_LIB_CAP_4K_UAR = (__u64)1 << 0,
};
+enum mlx5_ib_alloc_uctx_v2_flags {
+ MLX5_IB_ALLOC_UCTX_DEVX = 1 << 0,
+};
struct mlx5_ib_alloc_ucontext_req_v2 {
__u32 total_num_bfregs;
__u32 num_low_latency_bfregs;
--
2.14.4
--
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
