4 files changed, 60 insertions, 1 deletions

diff --git a/drivers/infiniband/core/device.c b/drivers/infiniband/core/device.c
index c0f8b8cba7c0..1ca6a9b7ba1a 100644
--- a/drivers/infiniband/core/device.c
+++ b/drivers/infiniband/core/device.c
@@ -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
diff --git a/drivers/infiniband/core/rdma_core.c b/drivers/infiniband/core/rdma_core.c
index 90c177edf9b0..18918f463361 100644
--- a/drivers/infiniband/core/rdma_core.c
+++ b/drivers/infiniband/core/rdma_core.c
@@ -1019,3 +1019,32 @@ void uverbs_finalize_object(struct ib_uobject *uobj,
 		WARN_ON(true);
 	}
 }
+
+/**
+ * rdma_uattrs_has_raw_cap() - Returns whether a rdma device linked to the
+ *			       uverbs attributes file has CAP_NET_RAW
+ *			       capability or not.
+ *
+ * @attrs:       Pointer to uverbs attributes
+ *
+ * Returns true if a rdma device's owning user namespace has CAP_NET_RAW
+ * capability, otherwise false.
+ */
+bool rdma_uattrs_has_raw_cap(const struct uverbs_attr_bundle *attrs)
+{
+	struct ib_uverbs_file *ufile = attrs->ufile;
+	struct ib_ucontext *ucontext;
+	bool has_cap = false;
+	int srcu_key;
+
+	srcu_key = srcu_read_lock(&ufile->device->disassociate_srcu);
+	ucontext = ib_uverbs_get_ucontext_file(ufile);
+	if (IS_ERR(ucontext))
+		goto out;
+	has_cap = rdma_dev_has_raw_cap(ucontext->device);
+
+out:
+	srcu_read_unlock(&ufile->device->disassociate_srcu, srcu_key);
+	return has_cap;
+}
+EXPORT_SYMBOL(rdma_uattrs_has_raw_cap);
diff --git a/drivers/infiniband/core/uverbs_cmd.c b/drivers/infiniband/core/uverbs_cmd.c
index bc9fe3ceca4d..6700c2c66167 100644
--- a/drivers/infiniband/core/uverbs_cmd.c
+++ b/drivers/infiniband/core/uverbs_cmd.c
@@ -3225,7 +3225,7 @@ static int ib_uverbs_ex_create_flow(struct uverbs_attr_bundle *attrs)
 	if (cmd.comp_mask)
 		return -EINVAL;
 
-	if (!capable(CAP_NET_RAW))
+	if (!rdma_uattrs_has_raw_cap(attrs))
 		return -EPERM;
 
 	if (cmd.flow_attr.flags >= IB_FLOW_ATTR_FLAGS_RESERVED)
diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
index 7da27f01eeb6..010594dc755b 100644
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
@@ -4817,6 +4817,8 @@ static inline int uverbs_destroy_def_handler(struct uverbs_attr_bundle *attrs)
 }
 #endif
 
+bool rdma_uattrs_has_raw_cap(const struct uverbs_attr_bundle *attrs);
+
 struct net_device *rdma_alloc_netdev(struct ib_device *device, u32 port_num,
 				     enum rdma_netdev_t type, const char *name,
 				     unsigned char name_assign_type,
@@ -4871,6 +4873,7 @@ 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);
 static inline struct net *rdma_dev_net(struct ib_device *device)
 {
 	return read_pnet(&device->coredev.rdma_net);