kernel_optimize_test/kernel/user.c
Eric W. Biederman 22d917d80e 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>
2012-04-26 02:01:39 -07:00

216 lines
5.0 KiB
C

/*
* 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 count is 1 for root user, 1 for init_uts_ns,
* and 1 for... ?
*/
struct user_namespace init_user_ns = {
.uid_map = {
.nr_extents = 1,
.extent[0] = {
.first = 0,
.lower_first = 0,
.count = 4294967295,
},
},
.gid_map = {
.nr_extents = 1,
.extent[0] = {
.first = 0,
.lower_first = 0,
.count = 4294967295,
},
},
.kref = {
.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.
*/
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);