From 0663c6f8fa37d777ede74ff991a0cba3a42fcbd7 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Sun, 7 Mar 2010 17:48:52 -0800 Subject: ns: Introduce the setns syscall With the networking stack today there is demand to handle multiple network stacks at a time. Not in the context of containers but in the context of people doing interesting things with routing. There is also demand in the context of containers to have an efficient way to execute some code in the container itself. If nothing else it is very useful ad a debugging technique. Both problems can be solved by starting some form of login daemon in the namespaces people want access to, or you can play games by ptracing a process and getting the traced process to do things you want it to do. However it turns out that a login daemon or a ptrace puppet controller are more code, they are more prone to failure, and generally they are less efficient than simply changing the namespace of a process to a specified one. Pieces of this puzzle can also be solved by instead of coming up with a general purpose system call coming up with targed system calls perhaps socketat that solve a subset of the larger problem. Overall that appears to be more work for less reward. int setns(int fd, int nstype); The fd argument is a file descriptor referring to a proc file of the namespace you want to switch the process to. In the setns system call the nstype is 0 or specifies an clone flag of the namespace you intend to change to prevent changing a namespace unintentionally. v2: Most of the architecture support added by Daniel Lezcano v3: ported to v2.6.36-rc4 by: Eric W. Biederman v4: Moved wiring up of the system call to another patch v5: Cleaned up the system call arguments - Changed the order. - Modified nstype to take the standard clone flags. v6: Added missing error handling as pointed out by Matt Helsley Acked-by: Daniel Lezcano Signed-off-by: Eric W. Biederman --- kernel/nsproxy.c | 42 ++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 42 insertions(+) (limited to 'kernel') diff --git a/kernel/nsproxy.c b/kernel/nsproxy.c index a05d191ffdd..5424e37673e 100644 --- a/kernel/nsproxy.c +++ b/kernel/nsproxy.c @@ -22,6 +22,9 @@ #include #include #include +#include +#include +#include static struct kmem_cache *nsproxy_cachep; @@ -233,6 +236,45 @@ void exit_task_namespaces(struct task_struct *p) switch_task_namespaces(p, NULL); } +SYSCALL_DEFINE2(setns, int, fd, int, nstype) +{ + const struct proc_ns_operations *ops; + struct task_struct *tsk = current; + struct nsproxy *new_nsproxy; + struct proc_inode *ei; + struct file *file; + int err; + + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + + file = proc_ns_fget(fd); + if (IS_ERR(file)) + return PTR_ERR(file); + + err = -EINVAL; + ei = PROC_I(file->f_dentry->d_inode); + ops = ei->ns_ops; + if (nstype && (ops->type != nstype)) + goto out; + + new_nsproxy = create_new_namespaces(0, tsk, tsk->fs); + if (IS_ERR(new_nsproxy)) { + err = PTR_ERR(new_nsproxy); + goto out; + } + + err = ops->install(new_nsproxy, ei->ns); + if (err) { + free_nsproxy(new_nsproxy); + goto out; + } + switch_task_namespaces(tsk, new_nsproxy); +out: + fput(file); + return err; +} + static int __init nsproxy_cache_init(void) { nsproxy_cachep = KMEM_CACHE(nsproxy, SLAB_PANIC); -- cgit v1.2.3-70-g09d2 From 34482e89a5218f0f9317abf1cfba3bb38b5c29dd Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Sun, 7 Mar 2010 18:43:27 -0800 Subject: ns proc: Add support for the uts namespace Acked-by: Daniel Lezcano Signed-off-by: Eric W. Biederman --- fs/proc/namespaces.c | 3 +++ include/linux/proc_fs.h | 1 + kernel/utsname.c | 39 +++++++++++++++++++++++++++++++++++++++ 3 files changed, 43 insertions(+) (limited to 'kernel') diff --git a/fs/proc/namespaces.c b/fs/proc/namespaces.c index dcbd483e991..b017181f127 100644 --- a/fs/proc/namespaces.c +++ b/fs/proc/namespaces.c @@ -19,6 +19,9 @@ static const struct proc_ns_operations *ns_entries[] = { #ifdef CONFIG_NET_NS &netns_operations, #endif +#ifdef CONFIG_UTS_NS + &utsns_operations, +#endif }; static const struct file_operations ns_file_operations = { diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h index 62126ec6ede..52aa89df8a6 100644 --- a/include/linux/proc_fs.h +++ b/include/linux/proc_fs.h @@ -266,6 +266,7 @@ struct proc_ns_operations { int (*install)(struct nsproxy *nsproxy, void *ns); }; extern const struct proc_ns_operations netns_operations; +extern const struct proc_ns_operations utsns_operations; union proc_op { int (*proc_get_link)(struct inode *, struct path *); diff --git a/kernel/utsname.c b/kernel/utsname.c index 44646179eab..bff131b9510 100644 --- a/kernel/utsname.c +++ b/kernel/utsname.c @@ -15,6 +15,7 @@ #include #include #include +#include static struct uts_namespace *create_uts_ns(void) { @@ -79,3 +80,41 @@ void free_uts_ns(struct kref *kref) put_user_ns(ns->user_ns); kfree(ns); } + +static void *utsns_get(struct task_struct *task) +{ + struct uts_namespace *ns = NULL; + struct nsproxy *nsproxy; + + rcu_read_lock(); + nsproxy = task_nsproxy(task); + if (nsproxy) { + ns = nsproxy->uts_ns; + get_uts_ns(ns); + } + rcu_read_unlock(); + + return ns; +} + +static void utsns_put(void *ns) +{ + put_uts_ns(ns); +} + +static int utsns_install(struct nsproxy *nsproxy, void *ns) +{ + get_uts_ns(ns); + put_uts_ns(nsproxy->uts_ns); + nsproxy->uts_ns = ns; + return 0; +} + +const struct proc_ns_operations utsns_operations = { + .name = "uts", + .type = CLONE_NEWUTS, + .get = utsns_get, + .put = utsns_put, + .install = utsns_install, +}; + -- cgit v1.2.3-70-g09d2