diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2016-10-06 16:52:23 (GMT) |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2016-10-06 16:52:23 (GMT) |
commit | 14986a34e1289424811443a524cdd9e1688c7913 (patch) | |
tree | 5ec26b7b16802755eff052016ea47958098dc14b /include | |
parent | 8d370595811e13378243832006f8c52bbc9cca5e (diff) | |
parent | 069d5ac9ae0d271903cc4607890616418118379a (diff) | |
download | linux-14986a34e1289424811443a524cdd9e1688c7913.tar.xz |
Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/ebiederm/user-namespace
Pull namespace updates from Eric Biederman:
"This set of changes is a number of smaller things that have been
overlooked in other development cycles focused on more fundamental
change. The devpts changes are small things that were a distraction
until we managed to kill off DEVPTS_MULTPLE_INSTANCES. There is an
trivial regression fix to autofs for the unprivileged mount changes
that went in last cycle. A pair of ioctls has been added by Andrey
Vagin making it is possible to discover the relationships between
namespaces when referring to them through file descriptors.
The big user visible change is starting to add simple resource limits
to catch programs that misbehave. With namespaces in general and user
namespaces in particular allowing users to use more kinds of
resources, it has become important to have something to limit errant
programs. Because the purpose of these limits is to catch errant
programs the code needs to be inexpensive to use as it always on, and
the default limits need to be high enough that well behaved programs
on well behaved systems don't encounter them.
To this end, after some review I have implemented per user per user
namespace limits, and use them to limit the number of namespaces. The
limits being per user mean that one user can not exhause the limits of
another user. The limits being per user namespace allow contexts where
the limit is 0 and security conscious folks can remove from their
threat anlysis the code used to manage namespaces (as they have
historically done as it root only). At the same time the limits being
per user namespace allow other parts of the system to use namespaces.
Namespaces are increasingly being used in application sand boxing
scenarios so an all or nothing disable for the entire system for the
security conscious folks makes increasing use of these sandboxes
impossible.
There is also added a limit on the maximum number of mounts present in
a single mount namespace. It is nontrivial to guess what a reasonable
system wide limit on the number of mount structure in the kernel would
be, especially as it various based on how a system is using
containers. A limit on the number of mounts in a mount namespace
however is much easier to understand and set. In most cases in
practice only about 1000 mounts are used. Given that some autofs
scenarious have the potential to be 30,000 to 50,000 mounts I have set
the default limit for the number of mounts at 100,000 which is well
above every known set of users but low enough that the mount hash
tables don't degrade unreaonsably.
These limits are a start. I expect this estabilishes a pattern that
other limits for resources that namespaces use will follow. There has
been interest in making inotify event limits per user per user
namespace as well as interest expressed in making details about what
is going on in the kernel more visible"
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/ebiederm/user-namespace: (28 commits)
autofs: Fix automounts by using current_real_cred()->uid
mnt: Add a per mount namespace limit on the number of mounts
netns: move {inc,dec}_net_namespaces into #ifdef
nsfs: Simplify __ns_get_path
tools/testing: add a test to check nsfs ioctl-s
nsfs: add ioctl to get a parent namespace
nsfs: add ioctl to get an owning user namespace for ns file descriptor
kernel: add a helper to get an owning user namespace for a namespace
devpts: Change the owner of /dev/pts/ptmx to the mounter of /dev/pts
devpts: Remove sync_filesystems
devpts: Make devpts_kill_sb safe if fsi is NULL
devpts: Simplify devpts_mount by using mount_nodev
devpts: Move the creation of /dev/pts/ptmx into fill_super
devpts: Move parse_mount_options into fill_super
userns: When the per user per user namespace limit is reached return ENOSPC
userns; Document per user per user namespace limits.
mntns: Add a limit on the number of mount namespaces.
netns: Add a limit on the number of net namespaces
cgroupns: Add a limit on the number of cgroup namespaces
ipcns: Add a limit on the number of ipc namespaces
...
Diffstat (limited to 'include')
-rw-r--r-- | include/linux/cgroup.h | 1 | ||||
-rw-r--r-- | include/linux/ipc_namespace.h | 1 | ||||
-rw-r--r-- | include/linux/mount.h | 2 | ||||
-rw-r--r-- | include/linux/pid_namespace.h | 1 | ||||
-rw-r--r-- | include/linux/proc_ns.h | 2 | ||||
-rw-r--r-- | include/linux/sysctl.h | 3 | ||||
-rw-r--r-- | include/linux/user_namespace.h | 44 | ||||
-rw-r--r-- | include/linux/utsname.h | 1 | ||||
-rw-r--r-- | include/net/net_namespace.h | 1 | ||||
-rw-r--r-- | include/uapi/linux/nsfs.h | 13 |
10 files changed, 65 insertions, 4 deletions
diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index a4414a1..440a721 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -644,6 +644,7 @@ struct cgroup_namespace { atomic_t count; struct ns_common ns; struct user_namespace *user_ns; + struct ucounts *ucounts; struct css_set *root_cset; }; diff --git a/include/linux/ipc_namespace.h b/include/linux/ipc_namespace.h index d10e54f..848e579 100644 --- a/include/linux/ipc_namespace.h +++ b/include/linux/ipc_namespace.h @@ -58,6 +58,7 @@ struct ipc_namespace { /* user_ns which owns the ipc ns */ struct user_namespace *user_ns; + struct ucounts *ucounts; struct ns_common ns; }; diff --git a/include/linux/mount.h b/include/linux/mount.h index 54a594d..1172cce 100644 --- a/include/linux/mount.h +++ b/include/linux/mount.h @@ -96,4 +96,6 @@ extern void mark_mounts_for_expiry(struct list_head *mounts); extern dev_t name_to_dev_t(const char *name); +extern unsigned int sysctl_mount_max; + #endif /* _LINUX_MOUNT_H */ diff --git a/include/linux/pid_namespace.h b/include/linux/pid_namespace.h index 918b117..34cce96 100644 --- a/include/linux/pid_namespace.h +++ b/include/linux/pid_namespace.h @@ -40,6 +40,7 @@ struct pid_namespace { struct fs_pin *bacct; #endif struct user_namespace *user_ns; + struct ucounts *ucounts; struct work_struct proc_work; kgid_t pid_gid; int hide_pid; diff --git a/include/linux/proc_ns.h b/include/linux/proc_ns.h index de0e771..12cb8bd 100644 --- a/include/linux/proc_ns.h +++ b/include/linux/proc_ns.h @@ -18,6 +18,8 @@ struct proc_ns_operations { struct ns_common *(*get)(struct task_struct *task); void (*put)(struct ns_common *ns); int (*install)(struct nsproxy *nsproxy, struct ns_common *ns); + struct user_namespace *(*owner)(struct ns_common *ns); + struct ns_common *(*get_parent)(struct ns_common *ns); }; extern const struct proc_ns_operations netns_operations; diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h index ecc3e07..adf4e51 100644 --- a/include/linux/sysctl.h +++ b/include/linux/sysctl.h @@ -158,8 +158,7 @@ struct ctl_table_set { struct ctl_table_root { struct ctl_table_set default_set; - struct ctl_table_set *(*lookup)(struct ctl_table_root *root, - struct nsproxy *namespaces); + struct ctl_table_set *(*lookup)(struct ctl_table_root *root); void (*set_ownership)(struct ctl_table_header *head, struct ctl_table *table, kuid_t *uid, kgid_t *gid); diff --git a/include/linux/user_namespace.h b/include/linux/user_namespace.h index 9217169..eb209d4 100644 --- a/include/linux/user_namespace.h +++ b/include/linux/user_namespace.h @@ -22,6 +22,19 @@ struct uid_gid_map { /* 64 bytes -- 1 cache line */ #define USERNS_INIT_FLAGS USERNS_SETGROUPS_ALLOWED +struct ucounts; + +enum ucount_type { + UCOUNT_USER_NAMESPACES, + UCOUNT_PID_NAMESPACES, + UCOUNT_UTS_NAMESPACES, + UCOUNT_IPC_NAMESPACES, + UCOUNT_NET_NAMESPACES, + UCOUNT_MNT_NAMESPACES, + UCOUNT_CGROUP_NAMESPACES, + UCOUNT_COUNTS, +}; + struct user_namespace { struct uid_gid_map uid_map; struct uid_gid_map gid_map; @@ -39,10 +52,30 @@ struct user_namespace { struct key *persistent_keyring_register; struct rw_semaphore persistent_keyring_register_sem; #endif + struct work_struct work; +#ifdef CONFIG_SYSCTL + struct ctl_table_set set; + struct ctl_table_header *sysctls; +#endif + struct ucounts *ucounts; + int ucount_max[UCOUNT_COUNTS]; +}; + +struct ucounts { + struct hlist_node node; + struct user_namespace *ns; + kuid_t uid; + atomic_t count; + atomic_t ucount[UCOUNT_COUNTS]; }; extern struct user_namespace init_user_ns; +bool setup_userns_sysctls(struct user_namespace *ns); +void retire_userns_sysctls(struct user_namespace *ns); +struct ucounts *inc_ucount(struct user_namespace *ns, kuid_t uid, enum ucount_type type); +void dec_ucount(struct ucounts *ucounts, enum ucount_type type); + #ifdef CONFIG_USER_NS static inline struct user_namespace *get_user_ns(struct user_namespace *ns) @@ -54,12 +87,12 @@ static inline struct user_namespace *get_user_ns(struct user_namespace *ns) extern int create_user_ns(struct cred *new); extern int unshare_userns(unsigned long unshare_flags, struct cred **new_cred); -extern void free_user_ns(struct user_namespace *ns); +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)) - free_user_ns(ns); + __put_user_ns(ns); } struct seq_operations; @@ -73,6 +106,8 @@ extern ssize_t proc_setgroups_write(struct file *, const char __user *, size_t, extern int proc_setgroups_show(struct seq_file *m, void *v); extern bool userns_may_setgroups(const struct user_namespace *ns); extern bool current_in_userns(const struct user_namespace *target_ns); + +struct ns_common *ns_get_owner(struct ns_common *ns); #else static inline struct user_namespace *get_user_ns(struct user_namespace *ns) @@ -106,6 +141,11 @@ static inline bool current_in_userns(const struct user_namespace *target_ns) { return true; } + +static inline struct ns_common *ns_get_owner(struct ns_common *ns) +{ + return ERR_PTR(-EPERM); +} #endif #endif /* _LINUX_USER_H */ diff --git a/include/linux/utsname.h b/include/linux/utsname.h index 5093f58..60f0bb8 100644 --- a/include/linux/utsname.h +++ b/include/linux/utsname.h @@ -24,6 +24,7 @@ struct uts_namespace { struct kref kref; struct new_utsname name; struct user_namespace *user_ns; + struct ucounts *ucounts; struct ns_common ns; }; extern struct uts_namespace init_uts_ns; diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h index 0933c74..fc4f757 100644 --- a/include/net/net_namespace.h +++ b/include/net/net_namespace.h @@ -60,6 +60,7 @@ struct net { struct list_head exit_list; /* Use only net_mutex */ struct user_namespace *user_ns; /* Owning user namespace */ + struct ucounts *ucounts; spinlock_t nsid_lock; struct idr netns_ids; diff --git a/include/uapi/linux/nsfs.h b/include/uapi/linux/nsfs.h new file mode 100644 index 0000000..3af6172 --- /dev/null +++ b/include/uapi/linux/nsfs.h @@ -0,0 +1,13 @@ +#ifndef __LINUX_NSFS_H +#define __LINUX_NSFS_H + +#include <linux/ioctl.h> + +#define NSIO 0xb7 + +/* Returns a file descriptor that refers to an owning user namespace */ +#define NS_GET_USERNS _IO(NSIO, 0x1) +/* Returns a file descriptor that refers to a parent namespace */ +#define NS_GET_PARENT _IO(NSIO, 0x2) + +#endif /* __LINUX_NSFS_H */ |