Merge patch series "ns: support file handles"

Christian Brauner <brauner@kernel.org> says:

For a while now we have supported file handles for pidfds. This has
proven to be very useful.

Extend the concept to cover namespaces as well. After this patchset it
is possible to encode and decode namespace file handles using the
commong name_to_handle_at() and open_by_handle_at() apis.

Namespaces file descriptors can already be derived from pidfds which
means they aren't subject to overmount protection bugs. IOW, it's
irrelevant if the caller would not have access to an appropriate
/proc/<pid>/ns/ directory as they could always just derive the namespace
based on a pidfd already.

It has the same advantage as pidfds. It's possible to reliably and for
the lifetime of the system refer to a namespace without pinning any
resources and to compare them.

Permission checking is kept simple. If the caller is located in the
namespace the file handle refers to they are able to open it otherwise
they must hold privilege over the owning namespace of the relevant
namespace.

Both the network namespace and the mount namespace already have an
associated cookie that isn't recycled and is fully exposed to userspace.
Move this into ns_common and use the same id space for all namespaces so
they can trivially and reliably be compared.

There's more coming based on the iterator infrastructure but the series
is large enough and focuses on file handles.

Extensive selftests included.

* patches from https://lore.kernel.org/20250912-work-namespace-v2-0-1a247645cef5@kernel.org: (33 commits)
  selftests/namespaces: add file handle selftests
  selftests/namespaces: add identifier selftests
  tools: update nsfs.h uapi header
  nsfs: add missing id retrieval support
  nsfs: support exhaustive file handles
  nsfs: support file handles
  nsfs: add current_in_namespace()
  ns: add to_<type>_ns() to respective headers
  uts: support ns lookup
  user: support ns lookup
  time: support ns lookup
  pid: support ns lookup
  net: support ns lookup
  ipc: support ns lookup
  cgroup: support ns lookup
  mnt: support ns lookup
  nstree: make iterator generic
  ns: remove ns_alloc_inum()
  uts: use ns_common_init()
  user: use ns_common_init()
  ...

Signed-off-by: Christian Brauner <brauner@kernel.org>

11 files changed, 92 insertions, 15 deletions

diff --git a/include/net/bluetooth/bluetooth.h b/include/net/bluetooth/bluetooth.h
index ada5b56a4413..e5751f3070b8 100644
--- a/include/net/bluetooth/bluetooth.h
+++ b/include/net/bluetooth/bluetooth.h
@@ -647,7 +647,7 @@ static inline void sco_exit(void)
 #if IS_ENABLED(CONFIG_BT_LE)
 int iso_init(void);
 int iso_exit(void);
-bool iso_enabled(void);
+bool iso_inited(void);
 #else
 static inline int iso_init(void)
 {
@@ -659,7 +659,7 @@ static inline int iso_exit(void)
 	return 0;
 }
 
-static inline bool iso_enabled(void)
+static inline bool iso_inited(void)
 {
 	return false;
 }
diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index 4dc11c66f7b8..6906af7a8f24 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -129,7 +129,9 @@ struct hci_conn_hash {
 	struct list_head list;
 	unsigned int     acl_num;
 	unsigned int     sco_num;
-	unsigned int     iso_num;
+	unsigned int     cis_num;
+	unsigned int     bis_num;
+	unsigned int     pa_num;
 	unsigned int     le_num;
 	unsigned int     le_num_peripheral;
 };
@@ -1014,9 +1016,13 @@ static inline void hci_conn_hash_add(struct hci_dev *hdev, struct hci_conn *c)
 		h->sco_num++;
 		break;
 	case CIS_LINK:
+		h->cis_num++;
+		break;
 	case BIS_LINK:
+		h->bis_num++;
+		break;
 	case PA_LINK:
-		h->iso_num++;
+		h->pa_num++;
 		break;
 	}
 }
@@ -1042,9 +1048,13 @@ static inline void hci_conn_hash_del(struct hci_dev *hdev, struct hci_conn *c)
 		h->sco_num--;
 		break;
 	case CIS_LINK:
+		h->cis_num--;
+		break;
 	case BIS_LINK:
+		h->bis_num--;
+		break;
 	case PA_LINK:
-		h->iso_num--;
+		h->pa_num--;
 		break;
 	}
 }
@@ -1061,9 +1071,11 @@ static inline unsigned int hci_conn_num(struct hci_dev *hdev, __u8 type)
 	case ESCO_LINK:
 		return h->sco_num;
 	case CIS_LINK:
+		return h->cis_num;
 	case BIS_LINK:
+		return h->bis_num;
 	case PA_LINK:
-		return h->iso_num;
+		return h->pa_num;
 	default:
 		return 0;
 	}
@@ -1073,7 +1085,15 @@ static inline unsigned int hci_conn_count(struct hci_dev *hdev)
 {
 	struct hci_conn_hash *c = &hdev->conn_hash;
 
-	return c->acl_num + c->sco_num + c->le_num + c->iso_num;
+	return c->acl_num + c->sco_num + c->le_num + c->cis_num + c->bis_num +
+		c->pa_num;
+}
+
+static inline unsigned int hci_iso_count(struct hci_dev *hdev)
+{
+	struct hci_conn_hash *c = &hdev->conn_hash;
+
+	return c->cis_num + c->bis_num;
 }
 
 static inline bool hci_conn_valid(struct hci_dev *hdev, struct hci_conn *conn)
@@ -1915,6 +1935,8 @@ void hci_conn_del_sysfs(struct hci_conn *conn);
 				!hci_dev_test_flag(dev, HCI_RPA_EXPIRED))
 #define adv_rpa_valid(adv)     (bacmp(&adv->random_addr, BDADDR_ANY) && \
 				!adv->rpa_expired)
+#define le_enabled(dev)        (lmp_le_capable(dev) && \
+				hci_dev_test_flag(dev, HCI_LE_ENABLED))
 
 #define scan_1m(dev) (((dev)->le_tx_def_phys & HCI_LE_SET_PHY_1M) || \
 		      ((dev)->le_rx_def_phys & HCI_LE_SET_PHY_1M))
@@ -1932,6 +1954,7 @@ void hci_conn_del_sysfs(struct hci_conn *conn);
 			 ((dev)->le_rx_def_phys & HCI_LE_SET_PHY_CODED))
 
 #define ll_privacy_capable(dev) ((dev)->le_features[0] & HCI_LE_LL_PRIVACY)
+#define ll_privacy_enabled(dev) (le_enabled(dev) && ll_privacy_capable(dev))
 
 #define privacy_mode_capable(dev) (ll_privacy_capable(dev) && \
 				   ((dev)->commands[39] & 0x04))
@@ -1981,14 +2004,23 @@ void hci_conn_del_sysfs(struct hci_conn *conn);
 
 /* CIS Master/Slave and BIS support */
 #define iso_capable(dev) (cis_capable(dev) || bis_capable(dev))
+#define iso_enabled(dev) (le_enabled(dev) && iso_capable(dev))
 #define cis_capable(dev) \
 	(cis_central_capable(dev) || cis_peripheral_capable(dev))
+#define cis_enabled(dev) (le_enabled(dev) && cis_capable(dev))
 #define cis_central_capable(dev) \
 	((dev)->le_features[3] & HCI_LE_CIS_CENTRAL)
+#define cis_central_enabled(dev) \
+	(le_enabled(dev) && cis_central_capable(dev))
 #define cis_peripheral_capable(dev) \
 	((dev)->le_features[3] & HCI_LE_CIS_PERIPHERAL)
+#define cis_peripheral_enabled(dev) \
+	(le_enabled(dev) && cis_peripheral_capable(dev))
 #define bis_capable(dev) ((dev)->le_features[3] & HCI_LE_ISO_BROADCASTER)
-#define sync_recv_capable(dev) ((dev)->le_features[3] & HCI_LE_ISO_SYNC_RECEIVER)
+#define bis_enabled(dev) (le_enabled(dev) && bis_capable(dev))
+#define sync_recv_capable(dev) \
+	((dev)->le_features[3] & HCI_LE_ISO_SYNC_RECEIVER)
+#define sync_recv_enabled(dev) (le_enabled(dev) && sync_recv_capable(dev))
 
 #define mws_transport_config_capable(dev) (((dev)->commands[30] & 0x08) && \
 	(!hci_test_quirk((dev), HCI_QUIRK_BROKEN_MWS_TRANSPORT_CONFIG)))
diff --git a/include/net/bluetooth/hci_sync.h b/include/net/bluetooth/hci_sync.h
index 5224f57f6af2..e352a4e0ef8d 100644
--- a/include/net/bluetooth/hci_sync.h
+++ b/include/net/bluetooth/hci_sync.h
@@ -93,7 +93,7 @@ int hci_update_class_sync(struct hci_dev *hdev);
 
 int hci_update_eir_sync(struct hci_dev *hdev);
 int hci_update_class_sync(struct hci_dev *hdev);
-int hci_update_name_sync(struct hci_dev *hdev);
+int hci_update_name_sync(struct hci_dev *hdev, const u8 *name);
 int hci_write_ssp_mode_sync(struct hci_dev *hdev, u8 mode);
 
 int hci_get_random_address(struct hci_dev *hdev, bool require_privacy,
diff --git a/include/net/bond_3ad.h b/include/net/bond_3ad.h
index 2053cd8e788a..dba369a2cf27 100644
--- a/include/net/bond_3ad.h
+++ b/include/net/bond_3ad.h
@@ -307,6 +307,7 @@ int bond_3ad_lacpdu_recv(const struct sk_buff *skb, struct bonding *bond,
 			 struct slave *slave);
 int bond_3ad_set_carrier(struct bonding *bond);
 void bond_3ad_update_lacp_rate(struct bonding *bond);
+void bond_3ad_update_lacp_active(struct bonding *bond);
 void bond_3ad_update_ad_actor_settings(struct bonding *bond);
 int bond_3ad_stats_fill(struct sk_buff *skb, struct bond_3ad_stats *stats);
 size_t bond_3ad_stats_size(void);
diff --git a/include/net/devlink.h b/include/net/devlink.h
index 93640a29427c..b32c9ceeb81d 100644
--- a/include/net/devlink.h
+++ b/include/net/devlink.h
@@ -78,6 +78,9 @@ struct devlink_port_pci_sf_attrs {
  * @flavour: flavour of the port
  * @split: indicates if this is split port
  * @splittable: indicates if the port can be split.
+ * @no_phys_port_name: skip automatic phys_port_name generation; for
+ *		       compatibility only, newly added driver/port instance
+ *		       should never set this.
  * @lanes: maximum number of lanes the port supports. 0 value is not passed to netlink.
  * @switch_id: if the port is part of switch, this is buffer with ID, otherwise this is NULL
  * @phys: physical port attributes
@@ -87,7 +90,8 @@ struct devlink_port_pci_sf_attrs {
  */
 struct devlink_port_attrs {
 	u8 split:1,
-	   splittable:1;
+	   splittable:1,
+	   no_phys_port_name:1;
 	u32 lanes;
 	enum devlink_port_flavour flavour;
 	struct netdev_phys_item_id switch_id;
diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index ff406ef4fd4a..29a36709e7f3 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -1163,6 +1163,14 @@ static inline const struct cpumask *sysctl_est_cpulist(struct netns_ipvs *ipvs)
 		return housekeeping_cpumask(HK_TYPE_KTHREAD);
 }
 
+static inline const struct cpumask *sysctl_est_preferred_cpulist(struct netns_ipvs *ipvs)
+{
+	if (ipvs->est_cpulist_valid)
+		return ipvs->sysctl_est_cpulist;
+	else
+		return NULL;
+}
+
 static inline int sysctl_est_nice(struct netns_ipvs *ipvs)
 {
 	return ipvs->sysctl_est_nice;
@@ -1270,6 +1278,11 @@ static inline const struct cpumask *sysctl_est_cpulist(struct netns_ipvs *ipvs)
 	return housekeeping_cpumask(HK_TYPE_KTHREAD);
 }
 
+static inline const struct cpumask *sysctl_est_preferred_cpulist(struct netns_ipvs *ipvs)
+{
+	return NULL;
+}
+
 static inline int sysctl_est_nice(struct netns_ipvs *ipvs)
 {
 	return IPVS_EST_NICE;
diff --git a/include/net/kcm.h b/include/net/kcm.h
index 441e993be634..d9c35e71ecea 100644
--- a/include/net/kcm.h
+++ b/include/net/kcm.h
@@ -71,7 +71,6 @@ struct kcm_sock {
 	struct list_head wait_psock_list;
 	struct sk_buff *seq_skb;
 	struct mutex tx_mutex;
-	u32 tx_stopped : 1;
 
 	/* Don't use bit fields here, these are set under different locks */
 	bool tx_wait;
diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h
index 025a7574b275..fd090ceb80bf 100644
--- a/include/net/net_namespace.h
+++ b/include/net/net_namespace.h
@@ -262,6 +262,11 @@ void ipx_unregister_sysctl(void);
 #ifdef CONFIG_NET_NS
 void __put_net(struct net *net);
 
+static inline struct net *to_net_ns(struct ns_common *ns)
+{
+	return container_of(ns, struct net, ns);
+}
+
 /* Try using get_net_track() instead */
 static inline struct net *get_net(struct net *net)
 {
diff --git a/include/net/page_pool/types.h b/include/net/page_pool/types.h
index 431b593de709..1509a536cb85 100644
--- a/include/net/page_pool/types.h
+++ b/include/net/page_pool/types.h
@@ -265,6 +265,8 @@ struct page_pool *page_pool_create_percpu(const struct page_pool_params *params,
 struct xdp_mem_info;
 
 #ifdef CONFIG_PAGE_POOL
+void page_pool_enable_direct_recycling(struct page_pool *pool,
+				       struct napi_struct *napi);
 void page_pool_disable_direct_recycling(struct page_pool *pool);
 void page_pool_destroy(struct page_pool *pool);
 void page_pool_use_xdp_mem(struct page_pool *pool, void (*disconnect)(void *),
diff --git a/include/net/rose.h b/include/net/rose.h
index 23267b4efcfa..2b5491bbf39a 100644
--- a/include/net/rose.h
+++ b/include/net/rose.h
@@ -8,6 +8,7 @@
 #ifndef _ROSE_H
 #define _ROSE_H 
 
+#include <linux/refcount.h>
 #include <linux/rose.h>
 #include <net/ax25.h>
 #include <net/sock.h>
@@ -96,7 +97,7 @@ struct rose_neigh {
 	ax25_cb			*ax25;
 	struct net_device		*dev;
 	unsigned short		count;
-	unsigned short		use;
+	refcount_t		use;
 	unsigned int		number;
 	char			restarted;
 	char			dce_mode;
@@ -151,6 +152,21 @@ struct rose_sock {
 
 #define rose_sk(sk) ((struct rose_sock *)(sk))
 
+static inline void rose_neigh_hold(struct rose_neigh *rose_neigh)
+{
+	refcount_inc(&rose_neigh->use);
+}
+
+static inline void rose_neigh_put(struct rose_neigh *rose_neigh)
+{
+	if (refcount_dec_and_test(&rose_neigh->use)) {
+		if (rose_neigh->ax25)
+			ax25_cb_put(rose_neigh->ax25);
+		kfree(rose_neigh->digipeat);
+		kfree(rose_neigh);
+	}
+}
+
 /* af_rose.c */
 extern ax25_address rose_callsign;
 extern int  sysctl_rose_restart_request_timeout;
diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index 638948be4c50..738cd5b13c62 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -1038,12 +1038,17 @@ static inline struct sk_buff *qdisc_dequeue_internal(struct Qdisc *sch, bool dir
 	skb = __skb_dequeue(&sch->gso_skb);
 	if (skb) {
 		sch->q.qlen--;
+		qdisc_qstats_backlog_dec(sch, skb);
 		return skb;
 	}
-	if (direct)
-		return __qdisc_dequeue_head(&sch->q);
-	else
+	if (direct) {
+		skb = __qdisc_dequeue_head(&sch->q);
+		if (skb)
+			qdisc_qstats_backlog_dec(sch, skb);
+		return skb;
+	} else {
 		return sch->dequeue(sch);
+	}
 }
 
 static inline struct sk_buff *qdisc_dequeue_head(struct Qdisc *sch)