From b2e0d98705e60e45bbb3c0032c48824ad7ae0704 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Thu, 26 Jul 2012 05:15:35 -0700 Subject: userns: Implement unshare of the user namespace - Add CLONE_THREAD to the unshare flags if CLONE_NEWUSER is selected As changing user namespaces is only valid if all there is only a single thread. - Restore the code to add CLONE_VM if CLONE_THREAD is selected and the code to addCLONE_SIGHAND if CLONE_VM is selected. Making the constraints in the code clear. Acked-by: Serge Hallyn Signed-off-by: "Eric W. Biederman" --- include/linux/user_namespace.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux/user_namespace.h') diff --git a/include/linux/user_namespace.h b/include/linux/user_namespace.h index 95142cae446a..17651f08d67f 100644 --- a/include/linux/user_namespace.h +++ b/include/linux/user_namespace.h @@ -39,6 +39,7 @@ 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 kref *kref); static inline void put_user_ns(struct user_namespace *ns) @@ -66,6 +67,14 @@ static inline int create_user_ns(struct cred *new) return -EINVAL; } +static inline int unshare_userns(unsigned long unshare_flags, + struct cred **new_cred) +{ + if (unshare_flags & CLONE_NEWUSER) + return -EINVAL; + return 0; +} + static inline void put_user_ns(struct user_namespace *ns) { } -- cgit v1.2.3 From 98f842e675f96ffac96e6c50315790912b2812be Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Wed, 15 Jun 2011 10:21:48 -0700 Subject: proc: Usable inode numbers for the namespace file descriptors. Assign a unique proc inode to each namespace, and use that inode number to ensure we only allocate at most one proc inode for every namespace in proc. A single proc inode per namespace allows userspace to test to see if two processes are in the same namespace. This has been a long requested feature and only blocked because a naive implementation would put the id in a global space and would ultimately require having a namespace for the names of namespaces, making migration and certain virtualization tricks impossible. We still don't have per superblock inode numbers for proc, which appears necessary for application unaware checkpoint/restart and migrations (if the application is using namespace file descriptors) but that is now allowd by the design if it becomes important. I have preallocated the ipc and uts initial proc inode numbers so their structures can be statically initialized. Signed-off-by: Eric W. Biederman --- include/linux/user_namespace.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux/user_namespace.h') diff --git a/include/linux/user_namespace.h b/include/linux/user_namespace.h index 17651f08d67f..b9bd2e6c73cc 100644 --- a/include/linux/user_namespace.h +++ b/include/linux/user_namespace.h @@ -25,6 +25,7 @@ struct user_namespace { struct user_namespace *parent; kuid_t owner; kgid_t group; + unsigned int proc_inum; }; extern struct user_namespace init_user_ns; -- cgit v1.2.3 From c61a2810a2161986353705b44d9503e6bb079f4f Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Fri, 28 Dec 2012 18:58:39 -0800 Subject: userns: Avoid recursion in put_user_ns When freeing a deeply nested user namespace free_user_ns calls put_user_ns on it's parent which may in turn call free_user_ns again. When -fno-optimize-sibling-calls is passed to gcc one stack frame per user namespace is left on the stack, potentially overflowing the kernel stack. CONFIG_FRAME_POINTER forces -fno-optimize-sibling-calls so we can't count on gcc to optimize this code. Remove struct kref and use a plain atomic_t. Making the code more flexible and easier to comprehend. Make the loop in free_user_ns explict to guarantee that the stack does not overflow with CONFIG_FRAME_POINTER enabled. I have tested this fix with a simple program that uses unshare to create a deeply nested user namespace structure and then calls exit. With 1000 nesteuser namespaces before this change running my test program causes the kernel to die a horrible death. With 10,000,000 nested user namespaces after this change my test program runs to completion and causes no harm. Acked-by: Serge Hallyn Pointed-out-by: Vasily Kulikov Signed-off-by: "Eric W. Biederman" --- include/linux/user_namespace.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux/user_namespace.h') diff --git a/include/linux/user_namespace.h b/include/linux/user_namespace.h index b9bd2e6c73cc..4ce009324933 100644 --- a/include/linux/user_namespace.h +++ b/include/linux/user_namespace.h @@ -21,7 +21,7 @@ struct user_namespace { struct uid_gid_map uid_map; struct uid_gid_map gid_map; struct uid_gid_map projid_map; - struct kref kref; + atomic_t count; struct user_namespace *parent; kuid_t owner; kgid_t group; @@ -35,18 +35,18 @@ extern struct user_namespace init_user_ns; static inline struct user_namespace *get_user_ns(struct user_namespace *ns) { if (ns) - kref_get(&ns->kref); + atomic_inc(&ns->count); return 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 kref *kref); +extern void free_user_ns(struct user_namespace *ns); static inline void put_user_ns(struct user_namespace *ns) { - if (ns) - kref_put(&ns->kref, free_user_ns); + if (ns && atomic_dec_and_test(&ns->count)) + free_user_ns(ns); } struct seq_operations; -- cgit v1.2.3