OpenCloudOS-Kernel/kernel/user.c

224 lines
5.2 KiB
C
Raw Normal View History

/*
* The "user cache".
*
* (C) Copyright 1991-2000 Linus Torvalds
*
* We have a per-user structure to keep track of how many
* processes, files etc the user has claimed, in order to be
* able to have per-user limits for system resources.
*/
#include <linux/init.h>
#include <linux/sched.h>
#include <linux/slab.h>
#include <linux/bitops.h>
#include <linux/key.h>
#include <linux/interrupt.h>
#include <linux/export.h>
#include <linux/user_namespace.h>
userns: add a user_namespace as creator/owner of uts_namespace The expected course of development for user namespaces targeted capabilities is laid out at https://wiki.ubuntu.com/UserNamespace. Goals: - Make it safe for an unprivileged user to unshare namespaces. They will be privileged with respect to the new namespace, but this should only include resources which the unprivileged user already owns. - Provide separate limits and accounting for userids in different namespaces. Status: Currently (as of 2.6.38) you can clone with the CLONE_NEWUSER flag to get a new user namespace if you have the CAP_SYS_ADMIN, CAP_SETUID, and CAP_SETGID capabilities. What this gets you is a whole new set of userids, meaning that user 500 will have a different 'struct user' in your namespace than in other namespaces. So any accounting information stored in struct user will be unique to your namespace. However, throughout the kernel there are checks which - simply check for a capability. Since root in a child namespace has all capabilities, this means that a child namespace is not constrained. - simply compare uid1 == uid2. Since these are the integer uids, uid 500 in namespace 1 will be said to be equal to uid 500 in namespace 2. As a result, the lxc implementation at lxc.sf.net does not use user namespaces. This is actually helpful because it leaves us free to develop user namespaces in such a way that, for some time, user namespaces may be unuseful. Bugs aside, this patchset is supposed to not at all affect systems which are not actively using user namespaces, and only restrict what tasks in child user namespace can do. They begin to limit privilege to a user namespace, so that root in a container cannot kill or ptrace tasks in the parent user namespace, and can only get world access rights to files. Since all files currently belong to the initila user namespace, that means that child user namespaces can only get world access rights to *all* files. While this temporarily makes user namespaces bad for system containers, it starts to get useful for some sandboxing. I've run the 'runltplite.sh' with and without this patchset and found no difference. This patch: copy_process() handles CLONE_NEWUSER before the rest of the namespaces. So in the case of clone(CLONE_NEWUSER|CLONE_NEWUTS) the new uts namespace will have the new user namespace as its owner. That is what we want, since we want root in that new userns to be able to have privilege over it. Changelog: Feb 15: don't set uts_ns->user_ns if we didn't create a new uts_ns. Feb 23: Move extern init_user_ns declaration from init/version.c to utsname.h. Signed-off-by: Serge E. Hallyn <serge.hallyn@canonical.com> Acked-by: "Eric W. Biederman" <ebiederm@xmission.com> Acked-by: Daniel Lezcano <daniel.lezcano@free.fr> Acked-by: David Howells <dhowells@redhat.com> Cc: James Morris <jmorris@namei.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-03-24 07:43:16 +08:00
/*
* userns count is 1 for root user, 1 for init_uts_ns,
* and 1 for... ?
*/
struct user_namespace init_user_ns = {
userns: Rework the user_namespace adding uid/gid mapping support - Convert the old uid mapping functions into compatibility wrappers - Add a uid/gid mapping layer from user space uid and gids to kernel internal uids and gids that is extent based for simplicty and speed. * Working with number space after mapping uids/gids into their kernel internal version adds only mapping complexity over what we have today, leaving the kernel code easy to understand and test. - Add proc files /proc/self/uid_map /proc/self/gid_map These files display the mapping and allow a mapping to be added if a mapping does not exist. - Allow entering the user namespace without a uid or gid mapping. Since we are starting with an existing user our uids and gids still have global mappings so are still valid and useful they just don't have local mappings. The requirement for things to work are global uid and gid so it is odd but perfectly fine not to have a local uid and gid mapping. Not requiring global uid and gid mappings greatly simplifies the logic of setting up the uid and gid mappings by allowing the mappings to be set after the namespace is created which makes the slight weirdness worth it. - Make the mappings in the initial user namespace to the global uid/gid space explicit. Today it is an identity mapping but in the future we may want to twist this for debugging, similar to what we do with jiffies. - Document the memory ordering requirements of setting the uid and gid mappings. We only allow the mappings to be set once and there are no pointers involved so the requirments are trivial but a little atypical. Performance: In this scheme for the permission checks the performance is expected to stay the same as the actuall machine instructions should remain the same. The worst case I could think of is ls -l on a large directory where all of the stat results need to be translated with from kuids and kgids to uids and gids. So I benchmarked that case on my laptop with a dual core hyperthread Intel i5-2520M cpu with 3M of cpu cache. My benchmark consisted of going to single user mode where nothing else was running. On an ext4 filesystem opening 1,000,000 files and looping through all of the files 1000 times and calling fstat on the individuals files. This was to ensure I was benchmarking stat times where the inodes were in the kernels cache, but the inode values were not in the processors cache. My results: v3.4-rc1: ~= 156ns (unmodified v3.4-rc1 with user namespace support disabled) v3.4-rc1-userns-: ~= 155ns (v3.4-rc1 with my user namespace patches and user namespace support disabled) v3.4-rc1-userns+: ~= 164ns (v3.4-rc1 with my user namespace patches and user namespace support enabled) All of the configurations ran in roughly 120ns when I performed tests that ran in the cpu cache. So in summary the performance impact is: 1ns improvement in the worst case with user namespace support compiled out. 8ns aka 5% slowdown in the worst case with user namespace support compiled in. Acked-by: Serge Hallyn <serge.hallyn@canonical.com> Signed-off-by: Eric W. Biederman <ebiederm@xmission.com>
2011-11-17 16:11:58 +08:00
.uid_map = {
.nr_extents = 1,
.extent[0] = {
.first = 0,
.lower_first = 0,
.count = 4294967295U,
userns: Rework the user_namespace adding uid/gid mapping support - Convert the old uid mapping functions into compatibility wrappers - Add a uid/gid mapping layer from user space uid and gids to kernel internal uids and gids that is extent based for simplicty and speed. * Working with number space after mapping uids/gids into their kernel internal version adds only mapping complexity over what we have today, leaving the kernel code easy to understand and test. - Add proc files /proc/self/uid_map /proc/self/gid_map These files display the mapping and allow a mapping to be added if a mapping does not exist. - Allow entering the user namespace without a uid or gid mapping. Since we are starting with an existing user our uids and gids still have global mappings so are still valid and useful they just don't have local mappings. The requirement for things to work are global uid and gid so it is odd but perfectly fine not to have a local uid and gid mapping. Not requiring global uid and gid mappings greatly simplifies the logic of setting up the uid and gid mappings by allowing the mappings to be set after the namespace is created which makes the slight weirdness worth it. - Make the mappings in the initial user namespace to the global uid/gid space explicit. Today it is an identity mapping but in the future we may want to twist this for debugging, similar to what we do with jiffies. - Document the memory ordering requirements of setting the uid and gid mappings. We only allow the mappings to be set once and there are no pointers involved so the requirments are trivial but a little atypical. Performance: In this scheme for the permission checks the performance is expected to stay the same as the actuall machine instructions should remain the same. The worst case I could think of is ls -l on a large directory where all of the stat results need to be translated with from kuids and kgids to uids and gids. So I benchmarked that case on my laptop with a dual core hyperthread Intel i5-2520M cpu with 3M of cpu cache. My benchmark consisted of going to single user mode where nothing else was running. On an ext4 filesystem opening 1,000,000 files and looping through all of the files 1000 times and calling fstat on the individuals files. This was to ensure I was benchmarking stat times where the inodes were in the kernels cache, but the inode values were not in the processors cache. My results: v3.4-rc1: ~= 156ns (unmodified v3.4-rc1 with user namespace support disabled) v3.4-rc1-userns-: ~= 155ns (v3.4-rc1 with my user namespace patches and user namespace support disabled) v3.4-rc1-userns+: ~= 164ns (v3.4-rc1 with my user namespace patches and user namespace support enabled) All of the configurations ran in roughly 120ns when I performed tests that ran in the cpu cache. So in summary the performance impact is: 1ns improvement in the worst case with user namespace support compiled out. 8ns aka 5% slowdown in the worst case with user namespace support compiled in. Acked-by: Serge Hallyn <serge.hallyn@canonical.com> Signed-off-by: Eric W. Biederman <ebiederm@xmission.com>
2011-11-17 16:11:58 +08:00
},
},
.gid_map = {
.nr_extents = 1,
.extent[0] = {
.first = 0,
.lower_first = 0,
.count = 4294967295U,
userns: Rework the user_namespace adding uid/gid mapping support - Convert the old uid mapping functions into compatibility wrappers - Add a uid/gid mapping layer from user space uid and gids to kernel internal uids and gids that is extent based for simplicty and speed. * Working with number space after mapping uids/gids into their kernel internal version adds only mapping complexity over what we have today, leaving the kernel code easy to understand and test. - Add proc files /proc/self/uid_map /proc/self/gid_map These files display the mapping and allow a mapping to be added if a mapping does not exist. - Allow entering the user namespace without a uid or gid mapping. Since we are starting with an existing user our uids and gids still have global mappings so are still valid and useful they just don't have local mappings. The requirement for things to work are global uid and gid so it is odd but perfectly fine not to have a local uid and gid mapping. Not requiring global uid and gid mappings greatly simplifies the logic of setting up the uid and gid mappings by allowing the mappings to be set after the namespace is created which makes the slight weirdness worth it. - Make the mappings in the initial user namespace to the global uid/gid space explicit. Today it is an identity mapping but in the future we may want to twist this for debugging, similar to what we do with jiffies. - Document the memory ordering requirements of setting the uid and gid mappings. We only allow the mappings to be set once and there are no pointers involved so the requirments are trivial but a little atypical. Performance: In this scheme for the permission checks the performance is expected to stay the same as the actuall machine instructions should remain the same. The worst case I could think of is ls -l on a large directory where all of the stat results need to be translated with from kuids and kgids to uids and gids. So I benchmarked that case on my laptop with a dual core hyperthread Intel i5-2520M cpu with 3M of cpu cache. My benchmark consisted of going to single user mode where nothing else was running. On an ext4 filesystem opening 1,000,000 files and looping through all of the files 1000 times and calling fstat on the individuals files. This was to ensure I was benchmarking stat times where the inodes were in the kernels cache, but the inode values were not in the processors cache. My results: v3.4-rc1: ~= 156ns (unmodified v3.4-rc1 with user namespace support disabled) v3.4-rc1-userns-: ~= 155ns (v3.4-rc1 with my user namespace patches and user namespace support disabled) v3.4-rc1-userns+: ~= 164ns (v3.4-rc1 with my user namespace patches and user namespace support enabled) All of the configurations ran in roughly 120ns when I performed tests that ran in the cpu cache. So in summary the performance impact is: 1ns improvement in the worst case with user namespace support compiled out. 8ns aka 5% slowdown in the worst case with user namespace support compiled in. Acked-by: Serge Hallyn <serge.hallyn@canonical.com> Signed-off-by: Eric W. Biederman <ebiederm@xmission.com>
2011-11-17 16:11:58 +08:00
},
},
.projid_map = {
.nr_extents = 1,
.extent[0] = {
.first = 0,
.lower_first = 0,
.count = 4294967295U,
},
},
.kref = {
userns: add a user_namespace as creator/owner of uts_namespace The expected course of development for user namespaces targeted capabilities is laid out at https://wiki.ubuntu.com/UserNamespace. Goals: - Make it safe for an unprivileged user to unshare namespaces. They will be privileged with respect to the new namespace, but this should only include resources which the unprivileged user already owns. - Provide separate limits and accounting for userids in different namespaces. Status: Currently (as of 2.6.38) you can clone with the CLONE_NEWUSER flag to get a new user namespace if you have the CAP_SYS_ADMIN, CAP_SETUID, and CAP_SETGID capabilities. What this gets you is a whole new set of userids, meaning that user 500 will have a different 'struct user' in your namespace than in other namespaces. So any accounting information stored in struct user will be unique to your namespace. However, throughout the kernel there are checks which - simply check for a capability. Since root in a child namespace has all capabilities, this means that a child namespace is not constrained. - simply compare uid1 == uid2. Since these are the integer uids, uid 500 in namespace 1 will be said to be equal to uid 500 in namespace 2. As a result, the lxc implementation at lxc.sf.net does not use user namespaces. This is actually helpful because it leaves us free to develop user namespaces in such a way that, for some time, user namespaces may be unuseful. Bugs aside, this patchset is supposed to not at all affect systems which are not actively using user namespaces, and only restrict what tasks in child user namespace can do. They begin to limit privilege to a user namespace, so that root in a container cannot kill or ptrace tasks in the parent user namespace, and can only get world access rights to files. Since all files currently belong to the initila user namespace, that means that child user namespaces can only get world access rights to *all* files. While this temporarily makes user namespaces bad for system containers, it starts to get useful for some sandboxing. I've run the 'runltplite.sh' with and without this patchset and found no difference. This patch: copy_process() handles CLONE_NEWUSER before the rest of the namespaces. So in the case of clone(CLONE_NEWUSER|CLONE_NEWUTS) the new uts namespace will have the new user namespace as its owner. That is what we want, since we want root in that new userns to be able to have privilege over it. Changelog: Feb 15: don't set uts_ns->user_ns if we didn't create a new uts_ns. Feb 23: Move extern init_user_ns declaration from init/version.c to utsname.h. Signed-off-by: Serge E. Hallyn <serge.hallyn@canonical.com> Acked-by: "Eric W. Biederman" <ebiederm@xmission.com> Acked-by: Daniel Lezcano <daniel.lezcano@free.fr> Acked-by: David Howells <dhowells@redhat.com> Cc: James Morris <jmorris@namei.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-03-24 07:43:16 +08:00
.refcount = ATOMIC_INIT(3),
},
.owner = GLOBAL_ROOT_UID,
.group = GLOBAL_ROOT_GID,
};
EXPORT_SYMBOL_GPL(init_user_ns);
/*
* UID task count cache, to get fast user lookup in "alloc_uid"
* when changing user ID's (ie setuid() and friends).
*/
#define UIDHASH_BITS (CONFIG_BASE_SMALL ? 3 : 7)
#define UIDHASH_SZ (1 << UIDHASH_BITS)
#define UIDHASH_MASK (UIDHASH_SZ - 1)
#define __uidhashfn(uid) (((uid >> UIDHASH_BITS) + uid) & UIDHASH_MASK)
#define uidhashentry(uid) (uidhash_table + __uidhashfn((__kuid_val(uid))))
static struct kmem_cache *uid_cachep;
struct hlist_head uidhash_table[UIDHASH_SZ];
/*
* The uidhash_lock is mostly taken from process context, but it is
* occasionally also taken from softirq/tasklet context, when
* task-structs get RCU-freed. Hence all locking must be softirq-safe.
* But free_uid() is also called with local interrupts disabled, and running
* local_bh_enable() with local interrupts disabled is an error - we'll run
* softirq callbacks, and they can unconditionally enable interrupts, and
* the caller of free_uid() didn't expect that..
*/
static DEFINE_SPINLOCK(uidhash_lock);
/* root_user.__count is 1, for init task cred */
struct user_struct root_user = {
.__count = ATOMIC_INIT(1),
.processes = ATOMIC_INIT(1),
.files = ATOMIC_INIT(0),
.sigpending = ATOMIC_INIT(0),
.locked_shm = 0,
.uid = GLOBAL_ROOT_UID,
};
/*
* These routines must be called with the uidhash spinlock held!
*/
static void uid_hash_insert(struct user_struct *up, struct hlist_head *hashent)
{
hlist_add_head(&up->uidhash_node, hashent);
}
static void uid_hash_remove(struct user_struct *up)
{
hlist_del_init(&up->uidhash_node);
}
static struct user_struct *uid_hash_find(kuid_t uid, struct hlist_head *hashent)
{
struct user_struct *user;
struct hlist_node *h;
hlist_for_each_entry(user, h, hashent, uidhash_node) {
if (uid_eq(user->uid, uid)) {
atomic_inc(&user->__count);
return user;
}
}
return NULL;
}
/* IRQs are disabled and uidhash_lock is held upon function entry.
* IRQ state (as stored in flags) is restored and uidhash_lock released
* upon function exit.
*/
User namespaces: set of cleanups (v2) The user_ns is moved from nsproxy to user_struct, so that a struct cred by itself is sufficient to determine access (which it otherwise would not be). Corresponding ecryptfs fixes (by David Howells) are here as well. Fix refcounting. The following rules now apply: 1. The task pins the user struct. 2. The user struct pins its user namespace. 3. The user namespace pins the struct user which created it. User namespaces are cloned during copy_creds(). Unsharing a new user_ns is no longer possible. (We could re-add that, but it'll cause code duplication and doesn't seem useful if PAM doesn't need to clone user namespaces). When a user namespace is created, its first user (uid 0) gets empty keyrings and a clean group_info. This incorporates a previous patch by David Howells. Here is his original patch description: >I suggest adding the attached incremental patch. It makes the following >changes: > > (1) Provides a current_user_ns() macro to wrap accesses to current's user > namespace. > > (2) Fixes eCryptFS. > > (3) Renames create_new_userns() to create_user_ns() to be more consistent > with the other associated functions and because the 'new' in the name is > superfluous. > > (4) Moves the argument and permission checks made for CLONE_NEWUSER to the > beginning of do_fork() so that they're done prior to making any attempts > at allocation. > > (5) Calls create_user_ns() after prepare_creds(), and gives it the new creds > to fill in rather than have it return the new root user. I don't imagine > the new root user being used for anything other than filling in a cred > struct. > > This also permits me to get rid of a get_uid() and a free_uid(), as the > reference the creds were holding on the old user_struct can just be > transferred to the new namespace's creator pointer. > > (6) Makes create_user_ns() reset the UIDs and GIDs of the creds under > preparation rather than doing it in copy_creds(). > >David >Signed-off-by: David Howells <dhowells@redhat.com> Changelog: Oct 20: integrate dhowells comments 1. leave thread_keyring alone 2. use current_user_ns() in set_user() Signed-off-by: Serge Hallyn <serue@us.ibm.com>
2008-10-16 05:38:45 +08:00
static void free_user(struct user_struct *up, unsigned long flags)
__releases(&uidhash_lock)
{
uid_hash_remove(up);
spin_unlock_irqrestore(&uidhash_lock, flags);
key_put(up->uid_keyring);
key_put(up->session_keyring);
kmem_cache_free(uid_cachep, up);
}
/*
* Locate the user_struct for the passed UID. If found, take a ref on it. The
* caller must undo that ref with free_uid().
*
* If the user_struct could not be found, return NULL.
*/
struct user_struct *find_user(kuid_t uid)
{
struct user_struct *ret;
unsigned long flags;
spin_lock_irqsave(&uidhash_lock, flags);
ret = uid_hash_find(uid, uidhashentry(uid));
spin_unlock_irqrestore(&uidhash_lock, flags);
return ret;
}
void free_uid(struct user_struct *up)
{
unsigned long flags;
if (!up)
return;
local_irq_save(flags);
if (atomic_dec_and_lock(&up->__count, &uidhash_lock))
free_user(up, flags);
else
local_irq_restore(flags);
}
struct user_struct *alloc_uid(kuid_t uid)
{
struct hlist_head *hashent = uidhashentry(uid);
struct user_struct *up, *new;
spin_lock_irq(&uidhash_lock);
up = uid_hash_find(uid, hashent);
spin_unlock_irq(&uidhash_lock);
if (!up) {
new = kmem_cache_zalloc(uid_cachep, GFP_KERNEL);
if (!new)
goto out_unlock;
new->uid = uid;
atomic_set(&new->__count, 1);
/*
* Before adding this, check whether we raced
* on adding the same user already..
*/
spin_lock_irq(&uidhash_lock);
up = uid_hash_find(uid, hashent);
if (up) {
key_put(new->uid_keyring);
key_put(new->session_keyring);
kmem_cache_free(uid_cachep, new);
} else {
uid_hash_insert(new, hashent);
up = new;
}
spin_unlock_irq(&uidhash_lock);
}
return up;
out_unlock:
return NULL;
}
static int __init uid_cache_init(void)
{
int n;
uid_cachep = kmem_cache_create("uid_cache", sizeof(struct user_struct),
0, SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL);
for(n = 0; n < UIDHASH_SZ; ++n)
INIT_HLIST_HEAD(uidhash_table + n);
/* Insert the root user immediately (init already runs as root) */
spin_lock_irq(&uidhash_lock);
uid_hash_insert(&root_user, uidhashentry(GLOBAL_ROOT_UID));
spin_unlock_irq(&uidhash_lock);
return 0;
}
module_init(uid_cache_init);