IB/core: Enforce PKey security on QPs

Add new LSM hooks to allocate and free security contexts and check for
permission to access a PKey.

Allocate and free a security context when creating and destroying a QP.
This context is used for controlling access to PKeys.

When a request is made to modify a QP that changes the port, PKey index,
or alternate path, check that the QP has permission for the PKey in the
PKey table index on the subnet prefix of the port. If the QP is shared
make sure all handles to the QP also have access.

Store which port and PKey index a QP is using. After the reset to init
transition the user can modify the port, PKey index and alternate path
independently. So port and PKey settings changes can be a merge of the
previous settings and the new ones.

In order to maintain access control if there are PKey table or subnet
prefix change keep a list of all QPs are using each PKey index on
each port. If a change occurs all QPs using that device and port must
have access enforced for the new cache settings.

These changes add a transaction to the QP modify process. Association
with the old port and PKey index must be maintained if the modify fails,
and must be removed if it succeeds. Association with the new port and
PKey index must be established prior to the modify and removed if the
modify fails.

1. When a QP is modified to a particular Port, PKey index or alternate
   path insert that QP into the appropriate lists.

2. Check permission to access the new settings.

3. If step 2 grants access attempt to modify the QP.

4a. If steps 2 and 3 succeed remove any prior associations.

4b. If ether fails remove the new setting associations.

If a PKey table or subnet prefix changes walk the list of QPs and
check that they have permission. If not send the QP to the error state
and raise a fatal error event. If it's a shared QP make sure all the
QPs that share the real_qp have permission as well. If the QP that
owns a security structure is denied access the security structure is
marked as such and the QP is added to an error_list. Once the moving
the QP to error is complete the security structure mark is cleared.

Maintaining the lists correctly turns QP destroy into a transaction.
The hardware driver for the device frees the ib_qp structure, so while
the destroy is in progress the ib_qp pointer in the ib_qp_security
struct is undefined. When the destroy process begins the ib_qp_security
structure is marked as destroying. This prevents any action from being
taken on the QP pointer. After the QP is destroyed successfully it
could still listed on an error_list wait for it to be processed by that
flow before cleaning up the structure.

If the destroy fails the QPs port and PKey settings are reinserted into
the appropriate lists, the destroying flag is cleared, and access control
is enforced, in case there were any cache changes during the destroy
flow.

To keep the security changes isolated a new file is used to hold security
related functionality.

Signed-off-by: Daniel Jurgens <[email protected]>
Acked-by: Doug Ledford <[email protected]>
[PM: merge fixup in ib_verbs.h and uverbs_cmd.c]
Signed-off-by: Paul Moore <[email protected]>

Author: Daniel Jurgens

drivers/infiniband/core/Makefile

@@ -10,7 +10,8 @@ obj-$(CONFIG_INFINIBAND_USER_ACCESS) +=	ib_uverbs.o ib_ucm.o \
 ib_core-y :=			packer.o ud_header.o verbs.o cq.o rw.o sysfs.o \
 				device.o fmr_pool.o cache.o netlink.o \
 				roce_gid_mgmt.o mr_pool.o addr.o sa_query.o \
-				multicast.o mad.o smi.o agent.o mad_rmpp.o
+				multicast.o mad.o smi.o agent.o mad_rmpp.o \
+				security.o
 ib_core-$(CONFIG_INFINIBAND_USER_MEM) += umem.o
 ib_core-$(CONFIG_INFINIBAND_ON_DEMAND_PAGING) += umem_odp.o umem_rbtree.o
 ib_core-$(CONFIG_CGROUP_RDMA) += cgroup.o

drivers/infiniband/core/cache.c

@@ -53,6 +53,7 @@ struct ib_update_work {
 	struct work_struct work;
 	struct ib_device  *device;
 	u8                 port_num;
+	bool		   enforce_security;
 };
 
 union ib_gid zgid;
@@ -1042,7 +1043,8 @@ int ib_get_cached_port_state(struct ib_device   *device,
 EXPORT_SYMBOL(ib_get_cached_port_state);
 
 static void ib_cache_update(struct ib_device *device,
-			    u8                port)
+			    u8                port,
+			    bool	      enforce_security)
 {
 	struct ib_port_attr       *tprops = NULL;
 	struct ib_pkey_cache      *pkey_cache = NULL, *old_pkey_cache;
@@ -1132,6 +1134,11 @@ static void ib_cache_update(struct ib_device *device,
 							tprops->subnet_prefix;
 	write_unlock_irq(&device->cache.lock);
 
+	if (enforce_security)
+		ib_security_cache_change(device,
+					 port,
+					 tprops->subnet_prefix);
+
 	kfree(gid_cache);
 	kfree(old_pkey_cache);
 	kfree(tprops);
@@ -1148,7 +1155,9 @@ static void ib_cache_task(struct work_struct *_work)
 	struct ib_update_work *work =
 		container_of(_work, struct ib_update_work, work);
 
-	ib_cache_update(work->device, work->port_num);
+	ib_cache_update(work->device,
+			work->port_num,
+			work->enforce_security);
 	kfree(work);
 }
 
@@ -1169,6 +1178,12 @@ static void ib_cache_event(struct ib_event_handler *handler,
 			INIT_WORK(&work->work, ib_cache_task);
 			work->device   = event->device;
 			work->port_num = event->element.port_num;
+			if (event->event == IB_EVENT_PKEY_CHANGE ||
+			    event->event == IB_EVENT_GID_CHANGE)
+				work->enforce_security = true;
+			else
+				work->enforce_security = false;
+
 			queue_work(ib_wq, &work->work);
 		}
 	}
@@ -1194,7 +1209,7 @@ int ib_cache_setup_one(struct ib_device *device)
 		goto out;
 
 	for (p = 0; p <= rdma_end_port(device) - rdma_start_port(device); ++p)
-		ib_cache_update(device, p + rdma_start_port(device));
+		ib_cache_update(device, p + rdma_start_port(device), true);
 
 	INIT_IB_EVENT_HANDLER(&device->cache.event_handler,
 			      device, ib_cache_event);

drivers/infiniband/core/core_priv.h

@@ -39,6 +39,14 @@
 
 #include <rdma/ib_verbs.h>
 
+struct pkey_index_qp_list {
+	struct list_head    pkey_index_list;
+	u16                 pkey_index;
+	/* Lock to hold while iterating the qp_list. */
+	spinlock_t          qp_list_lock;
+	struct list_head    qp_list;
+};
+
 #if IS_ENABLED(CONFIG_INFINIBAND_ADDR_TRANS_CONFIGFS)
 int cma_configfs_init(void);
 void cma_configfs_exit(void);
@@ -179,4 +187,73 @@ int ib_nl_handle_ip_res_resp(struct sk_buff *skb,
 int ib_get_cached_subnet_prefix(struct ib_device *device,
 				u8                port_num,
 				u64              *sn_pfx);
+
+#ifdef CONFIG_SECURITY_INFINIBAND
+void ib_security_destroy_port_pkey_list(struct ib_device *device);
+
+void ib_security_cache_change(struct ib_device *device,
+			      u8 port_num,
+			      u64 subnet_prefix);
+
+int ib_security_modify_qp(struct ib_qp *qp,
+			  struct ib_qp_attr *qp_attr,
+			  int qp_attr_mask,
+			  struct ib_udata *udata);
+
+int ib_create_qp_security(struct ib_qp *qp, struct ib_device *dev);
+void ib_destroy_qp_security_begin(struct ib_qp_security *sec);
+void ib_destroy_qp_security_abort(struct ib_qp_security *sec);
+void ib_destroy_qp_security_end(struct ib_qp_security *sec);
+int ib_open_shared_qp_security(struct ib_qp *qp, struct ib_device *dev);
+void ib_close_shared_qp_security(struct ib_qp_security *sec);
+#else
+static inline void ib_security_destroy_port_pkey_list(struct ib_device *device)
+{
+}
+
+static inline void ib_security_cache_change(struct ib_device *device,
+					    u8 port_num,
+					    u64 subnet_prefix)
+{
+}
+
+static inline int ib_security_modify_qp(struct ib_qp *qp,
+					struct ib_qp_attr *qp_attr,
+					int qp_attr_mask,
+					struct ib_udata *udata)
+{
+	return qp->device->modify_qp(qp->real_qp,
+				     qp_attr,
+				     qp_attr_mask,
+				     udata);
+}
+
+static inline int ib_create_qp_security(struct ib_qp *qp,
+					struct ib_device *dev)
+{
+	return 0;
+}
+
+static inline void ib_destroy_qp_security_begin(struct ib_qp_security *sec)
+{
+}
+
+static inline void ib_destroy_qp_security_abort(struct ib_qp_security *sec)
+{
+}
+
+static inline void ib_destroy_qp_security_end(struct ib_qp_security *sec)
+{
+}
+
+static inline int ib_open_shared_qp_security(struct ib_qp *qp,
+					     struct ib_device *dev)
+{
+	return 0;
+}
+
+static inline void ib_close_shared_qp_security(struct ib_qp_security *sec)
+{
+}
+#endif
 #endif /* _CORE_PRIV_H */

drivers/infiniband/core/device.c

@@ -325,6 +325,30 @@ void ib_get_device_fw_str(struct ib_device *dev, char *str, size_t str_len)
 }
 EXPORT_SYMBOL(ib_get_device_fw_str);
 
+static int setup_port_pkey_list(struct ib_device *device)
+{
+	int i;
+
+	/**
+	 * device->port_pkey_list is indexed directly by the port number,
+	 * Therefore it is declared as a 1 based array with potential empty
+	 * slots at the beginning.
+	 */
+	device->port_pkey_list = kcalloc(rdma_end_port(device) + 1,
+					 sizeof(*device->port_pkey_list),
+					 GFP_KERNEL);
+
+	if (!device->port_pkey_list)
+		return -ENOMEM;
+
+	for (i = 0; i < (rdma_end_port(device) + 1); i++) {
+		spin_lock_init(&device->port_pkey_list[i].list_lock);
+		INIT_LIST_HEAD(&device->port_pkey_list[i].pkey_list);
+	}
+
+	return 0;
+}
+
 /**
  * ib_register_device - Register an IB device with IB core
  * @device:Device to register
@@ -385,6 +409,12 @@ int ib_register_device(struct ib_device *device,
 		goto out;
 	}
 
+	ret = setup_port_pkey_list(device);
+	if (ret) {
+		pr_warn("Couldn't create per port_pkey_list\n");
+		goto out;
+	}
+
 	ret = ib_cache_setup_one(device);
 	if (ret) {
 		pr_warn("Couldn't set up InfiniBand P_Key/GID cache\n");
@@ -468,6 +498,9 @@ void ib_unregister_device(struct ib_device *device)
 	ib_device_unregister_sysfs(device);
 	ib_cache_cleanup_one(device);
 
+	ib_security_destroy_port_pkey_list(device);
+	kfree(device->port_pkey_list);
+
 	down_write(&lists_rwsem);
 	spin_lock_irqsave(&device->client_data_lock, flags);
 	list_for_each_entry_safe(context, tmp, &device->client_data_list, list)