fixes-v5.11

-----BEGIN PGP SIGNATURE-----
 
 iHUEABYKAB0WIQRAhzRXHqcMeLMyaSiRxhvAZXjcogUCX9daOgAKCRCRxhvAZXjc
 ohPkAQChXUB2BAjtIzXlCkZoDBbzHHblm5DZ37oy/4xYFmAcEwEA5sw6dQqyGHnF
 GEP9def51HvXLpBV2BzNUGggo1SoGgQ=
 =w/cO
 -----END PGP SIGNATURE-----

Merge tag 'fixes-v5.11' of git://git.kernel.org/pub/scm/linux/kernel/git/brauner/linux

Pull misc fixes from Christian Brauner:
 "This contains several fixes which felt worth being combined into a
  single branch:

   - Use put_nsproxy() instead of open-coding it switch_task_namespaces()

   - Kirill's work to unify lifecycle management for all namespaces. The
     lifetime counters are used identically for all namespaces types.
     Namespaces may of course have additional unrelated counters and
     these are not altered. This work allows us to unify the type of the
     counters and reduces maintenance cost by moving the counter in one
     place and indicating that basic lifetime management is identical
     for all namespaces.

   - Peilin's fix adding three byte padding to Dmitry's
     PTRACE_GET_SYSCALL_INFO uapi struct to prevent an info leak.

   - Two smal patches to convert from the /* fall through */ comment
     annotation to the fallthrough keyword annotation which I had taken
     into my branch and into -next before df561f6688 ("treewide: Use
     fallthrough pseudo-keyword") made it upstream which fixed this
     tree-wide.

     Since I didn't want to invalidate all testing for other commits I
     didn't rebase and kept them"

* tag 'fixes-v5.11' of git://git.kernel.org/pub/scm/linux/kernel/git/brauner/linux:
  nsproxy: use put_nsproxy() in switch_task_namespaces()
  sys: Convert to the new fallthrough notation
  signal: Convert to the new fallthrough notation
  time: Use generic ns_common::count
  cgroup: Use generic ns_common::count
  mnt: Use generic ns_common::count
  user: Use generic ns_common::count
  pid: Use generic ns_common::count
  ipc: Use generic ns_common::count
  uts: Use generic ns_common::count
  net: Use generic ns_common::count
  ns: Add a common refcount into ns_common
  ptrace: Prevent kernel-infoleak in ptrace_get_syscall_info()

fs/mount.h

@@ -6,7 +6,6 @@
 #include <linux/fs_pin.h>
 
 struct mnt_namespace {
-	atomic_t		count;
 	struct ns_common	ns;
 	struct mount *	root;
 	/*
@@ -120,7 +119,7 @@ static inline void detach_mounts(struct dentry *dentry)
 
 static inline void get_mnt_ns(struct mnt_namespace *ns)
 {
-	atomic_inc(&ns->count);
+	refcount_inc(&ns->ns.count);
 }
 
 extern seqlock_t mount_lock;

fs/namespace.c

@@ -3274,7 +3274,7 @@ static struct mnt_namespace *alloc_mnt_ns(struct user_namespace *user_ns, bool a
 	new_ns->ns.ops = &mntns_operations;
 	if (!anon)
 		new_ns->seq = atomic64_add_return(1, &mnt_ns_seq);
-	atomic_set(&new_ns->count, 1);
+	refcount_set(&new_ns->ns.count, 1);
 	INIT_LIST_HEAD(&new_ns->list);
 	init_waitqueue_head(&new_ns->poll);
 	spin_lock_init(&new_ns->ns_lock);
@@ -3848,7 +3848,7 @@ void __init mnt_init(void)
 
 void put_mnt_ns(struct mnt_namespace *ns)
 {
-	if (!atomic_dec_and_test(&ns->count))
+	if (!refcount_dec_and_test(&ns->ns.count))
 		return;
 	drop_collected_mounts(&ns->root->mnt);
 	free_mnt_ns(ns);

include/linux/cgroup.h

@@ -854,7 +854,6 @@ static inline void cgroup_sk_free(struct sock_cgroup_data *skcd) {}
 #endif	/* CONFIG_CGROUP_DATA */
 
 struct cgroup_namespace {
-	refcount_t		count;
 	struct ns_common	ns;
 	struct user_namespace	*user_ns;
 	struct ucounts		*ucounts;
@@ -889,12 +888,12 @@ copy_cgroup_ns(unsigned long flags, struct user_namespace *user_ns,
 static inline void get_cgroup_ns(struct cgroup_namespace *ns)
 {
 	if (ns)
-		refcount_inc(&ns->count);
+		refcount_inc(&ns->ns.count);
 }
 
 static inline void put_cgroup_ns(struct cgroup_namespace *ns)
 {
-	if (ns && refcount_dec_and_test(&ns->count))
+	if (ns && refcount_dec_and_test(&ns->ns.count))
 		free_cgroup_ns(ns);
 }
 

include/linux/ipc_namespace.h

@@ -27,7 +27,6 @@ struct ipc_ids {
 };
 
 struct ipc_namespace {
-	refcount_t	count;
 	struct ipc_ids	ids[3];
 
 	int		sem_ctls[4];
@@ -128,7 +127,7 @@ extern struct ipc_namespace *copy_ipcs(unsigned long flags,
 static inline struct ipc_namespace *get_ipc_ns(struct ipc_namespace *ns)
 {
 	if (ns)
-		refcount_inc(&ns->count);
+		refcount_inc(&ns->ns.count);
 	return ns;
 }
 

include/linux/ns_common.h

@@ -2,12 +2,15 @@
 #ifndef _LINUX_NS_COMMON_H
 #define _LINUX_NS_COMMON_H
 
+#include <linux/refcount.h>
+
 struct proc_ns_operations;
 
 struct ns_common {
 	atomic_long_t stashed;
 	const struct proc_ns_operations *ops;
 	unsigned int inum;
+	refcount_t count;
 };
 
 #endif

include/linux/pid_namespace.h

@@ -8,7 +8,6 @@
 #include <linux/workqueue.h>
 #include <linux/threads.h>
 #include <linux/nsproxy.h>
-#include <linux/kref.h>
 #include <linux/ns_common.h>
 #include <linux/idr.h>
 
@@ -18,7 +17,6 @@
 struct fs_pin;
 
 struct pid_namespace {
-	struct kref kref;
 	struct idr idr;
 	struct rcu_head rcu;
 	unsigned int pid_allocated;
@@ -43,7 +41,7 @@ extern struct pid_namespace init_pid_ns;
 static inline struct pid_namespace *get_pid_ns(struct pid_namespace *ns)
 {
 	if (ns != &init_pid_ns)
-		kref_get(&ns->kref);
+		refcount_inc(&ns->ns.count);
 	return ns;
 }
 

include/linux/time_namespace.h

@@ -4,7 +4,6 @@
 
 
 #include <linux/sched.h>
-#include <linux/kref.h>
 #include <linux/nsproxy.h>
 #include <linux/ns_common.h>
 #include <linux/err.h>
@@ -18,7 +17,6 @@ struct timens_offsets {
 };
 
 struct time_namespace {
-	struct kref		kref;
 	struct user_namespace	*user_ns;
 	struct ucounts		*ucounts;
 	struct ns_common	ns;
@@ -37,20 +35,21 @@ extern void timens_commit(struct task_struct *tsk, struct time_namespace *ns);
 
 static inline struct time_namespace *get_time_ns(struct time_namespace *ns)
 {
-	kref_get(&ns->kref);
+	refcount_inc(&ns->ns.count);
 	return ns;
 }
 
 struct time_namespace *copy_time_ns(unsigned long flags,
 				    struct user_namespace *user_ns,
 				    struct time_namespace *old_ns);
-void free_time_ns(struct kref *kref);
+void free_time_ns(struct time_namespace *ns);
 void timens_on_fork(struct nsproxy *nsproxy, struct task_struct *tsk);
 struct vdso_data *arch_get_vdso_data(void *vvar_page);
 
 static inline void put_time_ns(struct time_namespace *ns)
 {
-	kref_put(&ns->kref, free_time_ns);
+	if (refcount_dec_and_test(&ns->ns.count))
+		free_time_ns(ns);
 }
 
 void proc_timens_show_offsets(struct task_struct *p, struct seq_file *m);

include/linux/user_namespace.h

@@ -57,7 +57,6 @@ struct user_namespace {
 	struct uid_gid_map	uid_map;
 	struct uid_gid_map	gid_map;
 	struct uid_gid_map	projid_map;
-	atomic_t		count;
 	struct user_namespace	*parent;
 	int			level;
 	kuid_t			owner;
@@ -109,7 +108,7 @@ void dec_ucount(struct ucounts *ucounts, enum ucount_type type);
 static inline struct user_namespace *get_user_ns(struct user_namespace *ns)
 {
 	if (ns)
-		atomic_inc(&ns->count);
+		refcount_inc(&ns->ns.count);
 	return ns;
 }
 
@@ -119,7 +118,7 @@ extern void __put_user_ns(struct user_namespace *ns);
 
 static inline void put_user_ns(struct user_namespace *ns)
 {
-	if (ns && atomic_dec_and_test(&ns->count))
+	if (ns && refcount_dec_and_test(&ns->ns.count))
 		__put_user_ns(ns);
 }
 

include/linux/utsname.h

@@ -4,7 +4,6 @@
 
 
 #include <linux/sched.h>
-#include <linux/kref.h>
 #include <linux/nsproxy.h>
 #include <linux/ns_common.h>
 #include <linux/err.h>
@@ -22,7 +21,6 @@ struct user_namespace;
 extern struct user_namespace init_user_ns;
 
 struct uts_namespace {
-	struct kref kref;
 	struct new_utsname name;
 	struct user_namespace *user_ns;
 	struct ucounts *ucounts;
@@ -33,16 +31,17 @@ extern struct uts_namespace init_uts_ns;
 #ifdef CONFIG_UTS_NS
 static inline void get_uts_ns(struct uts_namespace *ns)
 {
-	kref_get(&ns->kref);
+	refcount_inc(&ns->ns.count);
 }
 
 extern struct uts_namespace *copy_utsname(unsigned long flags,
 	struct user_namespace *user_ns, struct uts_namespace *old_ns);
-extern void free_uts_ns(struct kref *kref);
+extern void free_uts_ns(struct uts_namespace *ns);
 
 static inline void put_uts_ns(struct uts_namespace *ns)
 {
-	kref_put(&ns->kref, free_uts_ns);
+	if (refcount_dec_and_test(&ns->ns.count))
+		free_uts_ns(ns);
 }
 
 void uts_ns_init(void);

include/net/net_namespace.h

@@ -60,9 +60,6 @@ struct net {
 	refcount_t		passive;	/* To decide when the network
 						 * namespace should be freed.
 						 */
-	refcount_t		count;		/* To decided when the network
-						 *  namespace should be shut down.
-						 */
 	spinlock_t		rules_mod_lock;
 
 	unsigned int		dev_unreg_count;
@@ -245,7 +242,7 @@ void __put_net(struct net *net);
 
 static inline struct net *get_net(struct net *net)
 {
-	refcount_inc(&net->count);
+	refcount_inc(&net->ns.count);
 	return net;
 }
 
@@ -256,14 +253,14 @@ static inline struct net *maybe_get_net(struct net *net)
 	 * exists.  If the reference count is zero this
 	 * function fails and returns NULL.
 	 */
-	if (!refcount_inc_not_zero(&net->count))
+	if (!refcount_inc_not_zero(&net->ns.count))
 		net = NULL;
 	return net;
 }
 
 static inline void put_net(struct net *net)
 {
-	if (refcount_dec_and_test(&net->count))
+	if (refcount_dec_and_test(&net->ns.count))
 		__put_net(net);
 }
 
@@ -275,7 +272,7 @@ int net_eq(const struct net *net1, const struct net *net2)
 
 static inline int check_net(const struct net *net)
 {
-	return refcount_read(&net->count) != 0;
+	return refcount_read(&net->ns.count) != 0;
 }
 
 void net_drop_ns(void *);

include/uapi/linux/ptrace.h

@@ -81,7 +81,8 @@ struct seccomp_metadata {
 
 struct ptrace_syscall_info {
 	__u8 op;	/* PTRACE_SYSCALL_INFO_* */
-	__u32 arch __attribute__((__aligned__(sizeof(__u32))));
+	__u8 pad[3];
+	__u32 arch;
 	__u64 instruction_pointer;
 	__u64 stack_pointer;
 	union {

init/version.c

@@ -25,7 +25,7 @@ int version_string(LINUX_VERSION_CODE);
 #endif
 
 struct uts_namespace init_uts_ns = {
-	.kref = KREF_INIT(2),
+	.ns.count = REFCOUNT_INIT(2),
 	.name = {
 		.sysname	= UTS_SYSNAME,
 		.nodename	= UTS_NODENAME,

ipc/msgutil.c

@@ -26,7 +26,7 @@ DEFINE_SPINLOCK(mq_lock);
  * and not CONFIG_IPC_NS.
  */
 struct ipc_namespace init_ipc_ns = {
-	.count		= REFCOUNT_INIT(1),
+	.ns.count = REFCOUNT_INIT(1),
 	.user_ns = &init_user_ns,
 	.ns.inum = PROC_IPC_INIT_INO,
 #ifdef CONFIG_IPC_NS

ipc/namespace.c

@@ -51,7 +51,7 @@ static struct ipc_namespace *create_ipc_ns(struct user_namespace *user_ns,
 		goto fail_free;
 	ns->ns.ops = &ipcns_operations;
 
-	refcount_set(&ns->count, 1);
+	refcount_set(&ns->ns.count, 1);
 	ns->user_ns = get_user_ns(user_ns);
 	ns->ucounts = ucounts;
 
@@ -164,7 +164,7 @@ static DECLARE_WORK(free_ipc_work, free_ipc);
  */
 void put_ipc_ns(struct ipc_namespace *ns)
 {
-	if (refcount_dec_and_lock(&ns->count, &mq_lock)) {
+	if (refcount_dec_and_lock(&ns->ns.count, &mq_lock)) {
 		mq_clear_sbinfo(ns);
 		spin_unlock(&mq_lock);
 

kernel/cgroup/cgroup.c

@@ -199,7 +199,7 @@ static u16 have_canfork_callback __read_mostly;
 
 /* cgroup namespace for init task */
 struct cgroup_namespace init_cgroup_ns = {
-	.count		= REFCOUNT_INIT(2),
+	.ns.count	= REFCOUNT_INIT(2),
 	.user_ns	= &init_user_ns,
 	.ns.ops		= &cgroupns_operations,
 	.ns.inum	= PROC_CGROUP_INIT_INO,

kernel/cgroup/namespace.c

@@ -32,7 +32,7 @@ static struct cgroup_namespace *alloc_cgroup_ns(void)
 		kfree(new_ns);
 		return ERR_PTR(ret);
 	}
-	refcount_set(&new_ns->count, 1);
+	refcount_set(&new_ns->ns.count, 1);
 	new_ns->ns.ops = &cgroupns_operations;
 	return new_ns;
 }

kernel/nsproxy.c

@@ -172,7 +172,7 @@ int copy_namespaces(unsigned long flags, struct task_struct *tsk)
 	 * it along with CLONE_NEWIPC.
 	 */
 	if ((flags & (CLONE_NEWIPC | CLONE_SYSVSEM)) ==
-		(CLONE_NEWIPC | CLONE_SYSVSEM)) 
+		(CLONE_NEWIPC | CLONE_SYSVSEM))
 		return -EINVAL;
 
 	new_ns = create_new_namespaces(flags, tsk, user_ns, tsk->fs);
@@ -245,8 +245,8 @@ void switch_task_namespaces(struct task_struct *p, struct nsproxy *new)
 	p->nsproxy = new;
 	task_unlock(p);
 
-	if (ns && atomic_dec_and_test(&ns->count))
-		free_nsproxy(ns);
+	if (ns)
+		put_nsproxy(ns);
 }
 
 void exit_task_namespaces(struct task_struct *p)

kernel/pid.c

@@ -73,7 +73,7 @@ int pid_max_max = PID_MAX_LIMIT;
  * the scheme scales to up to 4 million PIDs, runtime.
  */
 struct pid_namespace init_pid_ns = {
-	.kref = KREF_INIT(2),
+	.ns.count = REFCOUNT_INIT(2),
 	.idr = IDR_INIT(init_pid_ns.idr),
 	.pid_allocated = PIDNS_ADDING,
 	.level = 0,

kernel/pid_namespace.c

@@ -102,7 +102,7 @@ static struct pid_namespace *create_pid_namespace(struct user_namespace *user_ns
 		goto out_free_idr;
 	ns->ns.ops = &pidns_operations;
 
-	kref_init(&ns->kref);
+	refcount_set(&ns->ns.count, 1);
 	ns->level = level;
 	ns->parent = get_pid_ns(parent_pid_ns);
 	ns->user_ns = get_user_ns(user_ns);
@@ -148,22 +148,15 @@ struct pid_namespace *copy_pid_ns(unsigned long flags,
 	return create_pid_namespace(user_ns, old_ns);
 }
 
-static void free_pid_ns(struct kref *kref)
-{
-	struct pid_namespace *ns;
-
-	ns = container_of(kref, struct pid_namespace, kref);
-	destroy_pid_namespace(ns);
-}
-
 void put_pid_ns(struct pid_namespace *ns)
 {
 	struct pid_namespace *parent;
 
 	while (ns != &init_pid_ns) {
 		parent = ns->parent;
-		if (!kref_put(&ns->kref, free_pid_ns))
+		if (!refcount_dec_and_test(&ns->ns.count))
 			break;
+		destroy_pid_namespace(ns);
 		ns = parent;
 	}
 }

kernel/time/namespace.c

@@ -92,7 +92,7 @@ static struct time_namespace *clone_time_ns(struct user_namespace *user_ns,
 	if (!ns)
 		goto fail_dec;
 
-	kref_init(&ns->kref);
+	refcount_set(&ns->ns.count, 1);
 
 	ns->vvar_page = alloc_page(GFP_KERNEL | __GFP_ZERO);
 	if (!ns->vvar_page)
@@ -226,11 +226,8 @@ out:
 	mutex_unlock(&offset_lock);
 }
 
-void free_time_ns(struct kref *kref)
+void free_time_ns(struct time_namespace *ns)
 {
-	struct time_namespace *ns;
-
-	ns = container_of(kref, struct time_namespace, kref);
 	dec_time_namespaces(ns->ucounts);
 	put_user_ns(ns->user_ns);
 	ns_free_inum(&ns->ns);
@@ -462,7 +459,7 @@ const struct proc_ns_operations timens_for_children_operations = {
 };
 
 struct time_namespace init_time_ns = {
-	.kref		= KREF_INIT(3),
+	.ns.count	= REFCOUNT_INIT(3),
 	.user_ns	= &init_user_ns,
 	.ns.inum	= PROC_TIME_INIT_INO,
 	.ns.ops		= &timens_operations,

kernel/user.c

@@ -55,7 +55,7 @@ struct user_namespace init_user_ns = {
 			},
 		},
 	},
-	.count = ATOMIC_INIT(3),
+	.ns.count = REFCOUNT_INIT(3),
 	.owner = GLOBAL_ROOT_UID,
 	.group = GLOBAL_ROOT_GID,
 	.ns.inum = PROC_USER_INIT_INO,

kernel/user_namespace.c

@@ -111,7 +111,7 @@ int create_user_ns(struct cred *new)
 		goto fail_free;
 	ns->ns.ops = &userns_operations;
 
-	atomic_set(&ns->count, 1);
+	refcount_set(&ns->ns.count, 1);
 	/* Leave the new->user_ns reference with the new user namespace. */
 	ns->parent = parent_ns;
 	ns->level = parent_ns->level + 1;
@@ -197,7 +197,7 @@ static void free_user_ns(struct work_struct *work)
 		kmem_cache_free(user_ns_cachep, ns);
 		dec_user_namespaces(ucounts);
 		ns = parent;
-	} while (atomic_dec_and_test(&parent->count));
+	} while (refcount_dec_and_test(&parent->ns.count));
 }
 
 void __put_user_ns(struct user_namespace *ns)

kernel/utsname.c

@@ -33,7 +33,7 @@ static struct uts_namespace *create_uts_ns(void)
 
 	uts_ns = kmem_cache_alloc(uts_ns_cache, GFP_KERNEL);
 	if (uts_ns)
-		kref_init(&uts_ns->kref);
+		refcount_set(&uts_ns->ns.count, 1);
 	return uts_ns;
 }
 
@@ -103,11 +103,8 @@ struct uts_namespace *copy_utsname(unsigned long flags,
 	return new_ns;
 }
 
-void free_uts_ns(struct kref *kref)
+void free_uts_ns(struct uts_namespace *ns)
 {
-	struct uts_namespace *ns;
-
-	ns = container_of(kref, struct uts_namespace, kref);
 	dec_uts_namespaces(ns->ucounts);
 	put_user_ns(ns->user_ns);
 	ns_free_inum(&ns->ns);

net/core/net-sysfs.c

@@ -1027,7 +1027,7 @@ net_rx_queue_update_kobjects(struct net_device *dev, int old_num, int new_num)
 	while (--i >= new_num) {
 		struct kobject *kobj = &dev->_rx[i].kobj;
 
-		if (!refcount_read(&dev_net(dev)->count))
+		if (!refcount_read(&dev_net(dev)->ns.count))
 			kobj->uevent_suppress = 1;
 		if (dev->sysfs_rx_queue_group)
 			sysfs_remove_group(kobj, dev->sysfs_rx_queue_group);
@@ -1605,7 +1605,7 @@ netdev_queue_update_kobjects(struct net_device *dev, int old_num, int new_num)
 	while (--i >= new_num) {
 		struct netdev_queue *queue = dev->_tx + i;
 
-		if (!refcount_read(&dev_net(dev)->count))
+		if (!refcount_read(&dev_net(dev)->ns.count))
 			queue->kobj.uevent_suppress = 1;
 #ifdef CONFIG_BQL
 		sysfs_remove_group(&queue->kobj, &dql_group);
@@ -1852,7 +1852,7 @@ void netdev_unregister_kobject(struct net_device *ndev)
 {
 	struct device *dev = &ndev->dev;
 
-	if (!refcount_read(&dev_net(ndev)->count))
+	if (!refcount_read(&dev_net(ndev)->ns.count))
 		dev_set_uevent_suppress(dev, 1);
 
 	kobject_get(&dev->kobj);

net/core/net_namespace.c

@@ -45,7 +45,7 @@ static struct key_tag init_net_key_domain = { .usage = REFCOUNT_INIT(1) };
 #endif
 
 struct net init_net = {
-	.count		= REFCOUNT_INIT(1),
+	.ns.count	= REFCOUNT_INIT(1),
 	.dev_base_head	= LIST_HEAD_INIT(init_net.dev_base_head),
 #ifdef CONFIG_KEYS
 	.key_domain	= &init_net_key_domain,
@@ -249,7 +249,7 @@ int peernet2id_alloc(struct net *net, struct net *peer, gfp_t gfp)
 {
 	int id;
 
-	if (refcount_read(&net->count) == 0)
+	if (refcount_read(&net->ns.count) == 0)
 		return NETNSA_NSID_NOT_ASSIGNED;
 
 	spin_lock_bh(&net->nsid_lock);
@@ -329,7 +329,7 @@ static __net_init int setup_net(struct net *net, struct user_namespace *user_ns)
 	int error = 0;
 	LIST_HEAD(net_exit_list);
 
-	refcount_set(&net->count, 1);
+	refcount_set(&net->ns.count, 1);
 	refcount_set(&net->passive, 1);
 	get_random_bytes(&net->hash_mix, sizeof(u32));
 	net->dev_base_seq = 1;

net/ipv4/inet_timewait_sock.c

@@ -272,14 +272,14 @@ restart:
 				continue;
 			tw = inet_twsk(sk);
 			if ((tw->tw_family != family) ||
-				refcount_read(&twsk_net(tw)->count))
+				refcount_read(&twsk_net(tw)->ns.count))
 				continue;
 
 			if (unlikely(!refcount_inc_not_zero(&tw->tw_refcnt)))
 				continue;
 
 			if (unlikely((tw->tw_family != family) ||
-				     refcount_read(&twsk_net(tw)->count))) {
+				     refcount_read(&twsk_net(tw)->ns.count))) {
 				inet_twsk_put(tw);
 				goto restart;
 			}

net/ipv4/tcp_metrics.c

@@ -887,7 +887,7 @@ static void tcp_metrics_flush_all(struct net *net)
 		pp = &hb->chain;
 		for (tm = deref_locked(*pp); tm; tm = deref_locked(*pp)) {
 			match = net ? net_eq(tm_net(tm), net) :
-				!refcount_read(&tm_net(tm)->count);
+				!refcount_read(&tm_net(tm)->ns.count);
 			if (match) {
 				*pp = tm->tcpm_next;
 				kfree_rcu(tm, rcu_head);