Check CAP_NET_RAW in right namespace
Subsystems (2)
cover Check CAP_NET_RAW in right namespace
The following series from Parav clears the mud where against which namespace the CAP_NET_RAW should be checked.
It is followup of this discussion:
https://lore.kernel.org/all/[email protected]
Thanks
Parav Pandit (7):
RDMA/uverbs: Check CAP_NET_RAW in user namespace for flow create RDMA/uverbs: Check CAP_NET_RAW in user namespace for QP create RDMA/mlx5: Check CAP_NET_RAW in user namespace for flow create RDMA/mlx5: Check CAP_NET_RAW in user namespace for anchor create RDMA/mlx5: Check CAP_NET_RAW in user namespace for devx create RDMA/counter: Check CAP_NET_RAW check in user namespace for RDMA
counters
RDMA/nldev: Check CAP_NET_RAW in user namespace for QP modify
drivers/infiniband/core/core_priv.h | 2 +- drivers/infiniband/core/counters.c | 2 +- drivers/infiniband/core/device.c | 27 +++++++++++++++++++ drivers/infiniband/core/nldev.c | 4 +-- drivers/infiniband/core/uverbs_cmd.c | 21 +++++++++------ drivers/infiniband/core/uverbs_std_types_qp.c | 2 +- drivers/infiniband/hw/mlx5/devx.c | 2 +- drivers/infiniband/hw/mlx5/fs.c | 7 +++-- include/rdma/ib_verbs.h | 2 ++ 9 files changed, 51 insertions(+), 18 deletions(-)
Signature · 1 line
2.49.0
PATCH 1/7 RDMA/uverbs: Check CAP_NET_RAW in user namespace for flow create
From: Parav Pandit <[email protected]>
Currently, the capability check is done in the default init_user_ns user namespace. When a process runs in a non default user namespace, such check fails. Due to this when a process is running using podman, it fails to create the flow resource.
Since the RDMA device is a resource within a network namespace, use the network namespace associated with the RDMA device to determine its owning user namespace.
--- drivers/infiniband/core/device.c | 27 +++++++++++++++++++++++++++ drivers/infiniband/core/uverbs_cmd.c | 8 +++++--- include/rdma/ib_verbs.h | 2 ++ 3 files changed, 34 insertions(+), 3 deletions(-)
drivers/infiniband/core/device.c +27 -0
@@ -145,6 +145,33 @@ bool rdma_dev_access_netns(const struct ib_device *dev, const struct net *net) }EXPORT_SYMBOL (rdma_dev_access_netns); +/** +* rdma_dev_has_raw_cap() - Returns whether a specified rdma device has +* CAP_NET_RAW capability or not. +* +* @dev: Pointer to rdma device whose capability to be checked +* +* Returns true if a rdma device's owning user namespace has CAP_NET_RAW +* capability, otherwise false. When rdma subsystem is in legacy shared network, +* namespace mode, the default net namespace is considered. +*/ +bool rdma_dev_has_raw_cap (const struct ib_device *dev) +{ +const struct net *net; + +/* Network namespace is the resource whose user namespace +* to be considered. When in shared mode, there is no reliable +* network namespace resource, so consider the default net namespace. +*/ +if (ib_devices_shared_netns) + net = &init_net; +else + net =read_pnet (&dev->coredev.rdma_net); + +return ns_capable (net->user_ns,CAP_NET_RAW ); +} +EXPORT_SYMBOL (rdma_dev_has_raw_cap); +/* * xarray has this behavior where it won't iterate over NULL values stored in * allocated arrays. So we need our own iterator to see all values stored in
drivers/infiniband/core/uverbs_cmd.c +5 -3
@@ -3225,9 +3225,6 @@ static int ib_uverbs_ex_create_flow(struct uverbs_attr_bundle *attrs)if (cmd.comp_mask)return -EINVAL ; -if (!capable (CAP_NET_RAW )) -return -EPERM ; -if (cmd.flow_attr.flags >=IB_FLOW_ATTR_FLAGS_RESERVED )return -EINVAL ;
@@ -3272,6 +3269,11 @@ static int ib_uverbs_ex_create_flow(struct uverbs_attr_bundle *attrs) goto err_free_attr; } +if (!rdma_dev_has_raw_cap (uobj->context->device)) { + err = -EPERM ; + goto err_uobj; + } +if (!rdma_is_port_valid (uobj->context->device, cmd.flow_attr.port)) { err = -EINVAL ; goto err_uobj;
include/rdma/ib_verbs.h +2 -0
@@ -4864,6 +4864,8 @@ static inline int ibdev_to_node(struct ib_device *ibdev)bool rdma_dev_access_netns (const struct ib_device *device,const struct net *net); +bool rdma_dev_has_raw_cap (const struct ib_device *dev); +#define IB_ROCE_UDP_ENCAP_VALID_PORT_MIN (0xC000)#define IB_ROCE_UDP_ENCAP_VALID_PORT_MAX (0xFFFF)#define IB_GRH_FLOWLABEL_MASK (0x000FFFFF)
Signature · 1 line
2.49.0
PATCH 2/7 RDMA/uverbs: Check CAP_NET_RAW in user namespace for QP create
In reply to Leon RomanovskyFrom: Parav Pandit <[email protected]>
Currently, the capability check is done in the default init_user_ns user namespace. When a process runs in a non default user namespace, such check fails. Due to this when a process is running using podman, it fails to create the QP.
Since the RDMA device is a resource within a network namespace, use the network namespace associated with the RDMA device to determine its owning user namespace.
--- drivers/infiniband/core/uverbs_cmd.c | 11 +++++++---- drivers/infiniband/core/uverbs_std_types_qp.c | 2 +- 2 files changed, 8 insertions(+), 5 deletions(-)
drivers/infiniband/core/uverbs_cmd.c +7 -4
@@ -1312,9 +1312,6 @@ static int create_qp(struct uverbs_attr_bundle *attrs,switch (cmd->qp_type) {case IB_QPT_RAW_PACKET : -if (!capable (CAP_NET_RAW )) -return -EPERM ; -break ;case IB_QPT_RC :case IB_QPT_UC :case IB_QPT_UD :
@@ -1330,6 +1327,12 @@ static int create_qp(struct uverbs_attr_bundle *attrs, &ib_dev);if (IS_ERR (obj))return PTR_ERR (obj); + +if (cmd->qp_type ==IB_QPT_RAW_PACKET ) { +if (!rdma_dev_has_raw_cap (ib_dev)) +return -EPERM ; + } + obj->uxrcd =NULL ; obj->uevent.uobject.user_handle = cmd->user_handle;mutex_init (&obj->mcast_lock);
@@ -1451,7 +1454,7 @@ static int create_qp(struct uverbs_attr_bundle *attrs, }if (attr.create_flags &IB_QP_CREATE_SOURCE_QPN ) { -if (!capable (CAP_NET_RAW )) { +if (!rdma_dev_has_raw_cap (device)) { ret = -EPERM ; goto err_put; }
drivers/infiniband/core/uverbs_std_types_qp.c +1 -1
@@ -133,7 +133,7 @@ static int UVERBS_HANDLER(UVERBS_METHOD_QP_CREATE)( device = xrcd->device;break ;case IB_UVERBS_QPT_RAW_PACKET : -if (!capable (CAP_NET_RAW )) +if (!rdma_dev_has_raw_cap (attrs->context->device))return -EPERM ; fallthrough;case IB_UVERBS_QPT_RC :
Signature · 1 line
2.49.0
Jason Gunthorpe
maintainerRe: [PATCH rdma-next 2/7] RDMA/uverbs: Check CAP_NET_RAW in user namespace for QP create
Quoted 26 lines · Leon Romanovsky
From: Parav Pandit <[email protected]>
Currently, the capability check is done in the default
init_user_nsuser namespace. When a process runs in a non default user namespace, such check fails. Due to this when a process is running using podman, it fails to create the QP.Since the RDMA device is a resource within a network namespace, use the network namespace associated with the RDMA device to determine its owning user namespace.
Fixes 2dee0e545894 ("IB/uverbs: Enable QP creation with a given source QP number")Fixes 6d1e7ba241e9 ("IB/uverbs: Introduce create/destroy QP commands over ioctl")Signed-off-by Parav Pandit <[email protected]>Signed-off-by Leon Romanovsky <[email protected]>--- drivers/infiniband/core/uverbs_cmd.c | 11 +++++++---- drivers/infiniband/core/uverbs_std_types_qp.c | 2 +- 2 files changed, 8 insertions(+), 5 deletions(-)drivers/infiniband/core/uverbs_cmd.c +0
-0
drivers/infiniband/core/uverbs_cmd.c static int create_qp(struct uverbs_attr_bundle *attrs, · line 1317
Quoted 6 lines
drivers/infiniband/core/uverbs_cmd.c +0
-3@@ -1312,9 +1312,6 @@ static int create_qp(struct uverbs_attr_bundle *attrs,switch (cmd->qp_type) {case IB_QPT_RAW_PACKET : -if (!capable (CAP_NET_RAW )) -return -EPERM ; -break ;
I don't think we should do these code movements, I'm not sure we won't create a security problem by actually creating the object and then immediately destroying it.
Add a rdma_uattrs_has_raw_cap() and call ib_uverbs_get_ucontext_file() to get the ->ib_device
Jason
RE: [PATCH rdma-next 2/7] RDMA/uverbs: Check CAP_NET_RAW in user namespace for QP create
Quoted 45 lines
From: Jason Gunthorpe <[email protected]>
Sent: 17 June 2025 23:23Quoted 28 lines · Leon Romanovsky
From: Parav Pandit <[email protected]>
Currently, the capability check is done in the default
init_user_nsuser namespace. When a process runs in a non default user namespace, such check fails. Due to this when a process is running using podman, it fails to create the QP.Since the RDMA device is a resource within a network namespace, use the network namespace associated with the RDMA device to determine its owning user namespace.
Fixes 2dee0e545894 ("IB/uverbs: Enable QP creation with a givensource QP number")
Fixes 6d1e7ba241e9 ("IB/uverbs: Introduce create/destroy QP commandsover ioctl")
Signed-off-by Parav Pandit <[email protected]>Signed-off-by Leon Romanovsky <[email protected]>--- drivers/infiniband/core/uverbs_cmd.c | 11 +++++++---- drivers/infiniband/core/uverbs_std_types_qp.c | 2 +- 2 files changed, 8 insertions(+), 5 deletions(-)drivers/infiniband/core/uverbs_cmd.c +0
-0drivers/infiniband/core/uverbs_cmd.c static int create_qp(struct uverbs_attr_bundle · line 1318
Quoted 7 lines
drivers/infiniband/core/uverbs_cmd.c +0
-3@@ -1312,9 +1312,6 @@ static int create_qp(struct uverbs_attr_bundle *attrs, switch (cmd->qp_type) {case IB_QPT_RAW_PACKET : -if (!capable (CAP_NET_RAW )) -return -EPERM ; -break ;I don't think we should do these code movements, I'm not sure we won't create a security problem by actually creating the object and then immediately destroying it.
Quoted 3 lines
Add a
rdma_uattrs_has_raw_cap()and callib_uverbs_get_ucontext_file()to get the ->ib_device
Ok. Sending v1 with the suggested change.
Quoted 1 line
Jason
PATCH 3/7 RDMA/mlx5: Check CAP_NET_RAW in user namespace for flow create
In reply to Leon RomanovskyFrom: Parav Pandit <[email protected]>
Currently, the capability check is done in the default init_user_ns user namespace. When a process runs in a non default user namespace, such check fails. Due to this when a process is running using podman, it fails to create the flow.
Since the RDMA device is a resource within a network namespace, use the network namespace associated with the RDMA device to determine its owning user namespace.
--- drivers/infiniband/hw/mlx5/fs.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-)
drivers/infiniband/hw/mlx5/fs.c +2 -3
@@ -2459,13 +2459,12 @@ static int UVERBS_HANDLER(MLX5_IB_METHOD_CREATE_FLOW)(struct mlx5_ib_dev *dev;u32 flags; -if (!capable (CAP_NET_RAW )) -return -EPERM ; - fs_matcher =uverbs_attr_get_obj (attrs,MLX5_IB_ATTR_CREATE_FLOW_MATCHER ); uobj =uverbs_attr_get_uobject (attrs,MLX5_IB_ATTR_CREATE_FLOW_HANDLE ); dev =mlx5_udata_to_mdev (&attrs->driver_udata); +if (!rdma_dev_has_raw_cap (&dev->ib_dev)) +return -EPERM ;if (get_dests (attrs, fs_matcher, &dest_id, &dest_type, &qp, &flags))return -EINVAL ;
Signature · 1 line
2.49.0
PATCH 4/7 RDMA/mlx5: Check CAP_NET_RAW in user namespace for anchor create
In reply to Leon RomanovskyFrom: Parav Pandit <[email protected]>
Currently, the capability check is done in the default init_user_ns user namespace. When a process runs in a non default user namespace, such check fails. Due to this when a process is running using podman, it fails to create the anchor.
Since the RDMA device is a resource within a network namespace, use the network namespace associated with the RDMA device to determine its owning user namespace.
--- drivers/infiniband/hw/mlx5/fs.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/infiniband/hw/mlx5/fs.c +1 -1
@@ -2989,7 +2989,7 @@ static int UVERBS_HANDLER(MLX5_IB_METHOD_STEERING_ANCHOR_CREATE)(u32 ft_id;int err; -if (!capable (CAP_NET_RAW )) +if (!rdma_dev_has_raw_cap (&dev->ib_dev))return -EPERM ; err = uverbs_get_const(&ib_uapi_ft_type, attrs,
Signature · 1 line
2.49.0
PATCH 5/7 RDMA/mlx5: Check CAP_NET_RAW in user namespace for devx create
In reply to Leon RomanovskyFrom: Parav Pandit <[email protected]>
Currently, the capability check is done in the default init_user_ns user namespace. When a process runs in a non default user namespace, such check fails. Due to this when a process is running using podman, it fails to create the devx object.
Since the RDMA device is a resource within a network namespace, use the network namespace associated with the RDMA device to determine its owning user namespace.
--- drivers/infiniband/hw/mlx5/devx.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/infiniband/hw/mlx5/devx.c +1 -1
@@ -159,7 +159,7 @@ int mlx5_ib_devx_create(struct mlx5_ib_dev *dev, bool is_user, u64 req_ucaps) uctx =MLX5_ADDR_OF (create_uctx_in, in, uctx);if (is_user && (MLX5_CAP_GEN (dev->mdev, uctx_cap) &MLX5_UCTX_CAP_RAW_TX ) && -capable (CAP_NET_RAW )) +rdma_dev_has_raw_cap (&dev->ib_dev)) cap |=MLX5_UCTX_CAP_RAW_TX ; if (is_user && (MLX5_CAP_GEN(dev->mdev, uctx_cap) &
Signature · 1 line
2.49.0
PATCH 6/7 RDMA/counter: Check CAP_NET_RAW check in user namespace for RDMA counters
In reply to Leon RomanovskyFrom: Parav Pandit <[email protected]>
Currently, the capability check is done in the default init_user_ns user namespace. When a process runs in a non default user namespace, such check fails.
Since the RDMA device is a resource within a network namespace, use the network namespace associated with the RDMA device to determine its owning user namespace.
--- drivers/infiniband/core/counters.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/infiniband/core/counters.c +1 -1
@@ -461,7 +461,7 @@ static struct ib_qp *rdma_counter_get_qp(struct ib_device *dev, u32 qp_num)return NULL ; qp = container_of(res, struct ib_qp, res); -if (qp->qp_type ==IB_QPT_RAW_PACKET && !capable (CAP_NET_RAW )) +if (qp->qp_type ==IB_QPT_RAW_PACKET && !rdma_dev_has_raw_cap (dev)) goto err;return qp;
Signature · 1 line
2.49.0
PATCH 7/7 RDMA/nldev: Check CAP_NET_RAW in user namespace for QP modify
In reply to Leon RomanovskyFrom: Parav Pandit <[email protected]>
Currently, the capability check is done in the default init_user_ns user namespace. When a process runs in a non default user namespace, such check fails. Due to this when a process is running using Podman, it fails to modify the QP.
Since the RDMA device is a resource within a network namespace, use the network namespace associated with the RDMA device to determine its owning user namespace.
--- drivers/infiniband/core/core_priv.h | 2 +- drivers/infiniband/core/nldev.c | 4 ++-- drivers/infiniband/core/uverbs_cmd.c | 2 +- 3 files changed, 4 insertions(+), 4 deletions(-)
drivers/infiniband/core/core_priv.h +1 -1
@@ -370,5 +370,5 @@ void rdma_umap_priv_init(struct rdma_umap_priv *priv,void ib_cq_pool_cleanup (struct ib_device *dev); -bool rdma_nl_get_privileged_qkey (void ); +bool rdma_nl_get_privileged_qkey (const struct ib_device *device);#endif /* _CORE_PRIV_H */
drivers/infiniband/core/nldev.c +2 -2
@@ -253,9 +253,9 @@ int rdma_nl_put_driver_u64_hex(struct sk_buff *msg, const char *name, u64 value) }EXPORT_SYMBOL (rdma_nl_put_driver_u64_hex); -bool rdma_nl_get_privileged_qkey (void ) +bool rdma_nl_get_privileged_qkey (const struct ib_device *device) { -return privileged_qkey ||capable (CAP_NET_RAW ); +return privileged_qkey ||rdma_dev_has_raw_cap (device); }EXPORT_SYMBOL (rdma_nl_get_privileged_qkey);
drivers/infiniband/core/uverbs_cmd.c +1 -1
@@ -1880,7 +1880,7 @@ static int modify_qp(struct uverbs_attr_bundle *attrs, attr->path_mig_state = cmd->base.path_mig_state;if (cmd->base.attr_mask &IB_QP_QKEY ) {if (cmd->base.qkey &IB_QP_SET_QKEY && - !rdma_nl_get_privileged_qkey ()) { + !rdma_nl_get_privileged_qkey (qp->device)) { ret = -EPERM ; goto release_qp; }
Signature · 1 line
2.49.0