From f1752eec6145c97163dbce62d17cf5d928e28a27 Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 14 Nov 2008 10:39:17 +1100 Subject: CRED: Detach the credentials from task_struct Detach the credentials from task_struct, duplicating them in copy_process() and releasing them in __put_task_struct(). Signed-off-by: David Howells Acked-by: James Morris Acked-by: Serge Hallyn Signed-off-by: James Morris --- kernel/cred.c | 96 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 96 insertions(+) create mode 100644 kernel/cred.c (limited to 'kernel/cred.c') diff --git a/kernel/cred.c b/kernel/cred.c new file mode 100644 index 00000000000..833244a7cb0 --- /dev/null +++ b/kernel/cred.c @@ -0,0 +1,96 @@ +/* Task credentials management + * + * Copyright (C) 2008 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public Licence + * as published by the Free Software Foundation; either version + * 2 of the Licence, or (at your option) any later version. + */ +#include +#include +#include +#include +#include +#include +#include + +/* + * The initial credentials for the initial task + */ +struct cred init_cred = { + .usage = ATOMIC_INIT(3), + .securebits = SECUREBITS_DEFAULT, + .cap_inheritable = CAP_INIT_INH_SET, + .cap_permitted = CAP_FULL_SET, + .cap_effective = CAP_INIT_EFF_SET, + .cap_bset = CAP_INIT_BSET, + .user = INIT_USER, + .group_info = &init_groups, +}; + +/* + * The RCU callback to actually dispose of a set of credentials + */ +static void put_cred_rcu(struct rcu_head *rcu) +{ + struct cred *cred = container_of(rcu, struct cred, rcu); + + BUG_ON(atomic_read(&cred->usage) != 0); + + key_put(cred->thread_keyring); + key_put(cred->request_key_auth); + put_group_info(cred->group_info); + free_uid(cred->user); + security_cred_free(cred); + kfree(cred); +} + +/** + * __put_cred - Destroy a set of credentials + * @sec: The record to release + * + * Destroy a set of credentials on which no references remain. + */ +void __put_cred(struct cred *cred) +{ + call_rcu(&cred->rcu, put_cred_rcu); +} +EXPORT_SYMBOL(__put_cred); + +/* + * Copy credentials for the new process created by fork() + */ +int copy_creds(struct task_struct *p, unsigned long clone_flags) +{ + struct cred *pcred; + int ret; + + pcred = kmemdup(p->cred, sizeof(*p->cred), GFP_KERNEL); + if (!pcred) + return -ENOMEM; + +#ifdef CONFIG_SECURITY + pcred->security = NULL; +#endif + + ret = security_cred_alloc(pcred); + if (ret < 0) { + kfree(pcred); + return ret; + } + + atomic_set(&pcred->usage, 1); + get_group_info(pcred->group_info); + get_uid(pcred->user); + key_get(pcred->thread_keyring); + key_get(pcred->request_key_auth); + + atomic_inc(&pcred->user->processes); + + /* RCU assignment is unneeded here as no-one can have accessed this + * pointer yet, barring us */ + p->cred = pcred; + return 0; +} -- cgit v1.2.3 From bb952bb98a7e479262c7eb25d5592545a3af147d Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 14 Nov 2008 10:39:20 +1100 Subject: CRED: Separate per-task-group keyrings from signal_struct Separate per-task-group keyrings from signal_struct and dangle their anchor from the cred struct rather than the signal_struct. Signed-off-by: David Howells Reviewed-by: James Morris Signed-off-by: James Morris --- kernel/cred.c | 63 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 63 insertions(+) (limited to 'kernel/cred.c') diff --git a/kernel/cred.c b/kernel/cred.c index 833244a7cb0..ac73e361768 100644 --- a/kernel/cred.c +++ b/kernel/cred.c @@ -16,6 +16,17 @@ #include #include +/* + * The common credentials for the initial task's thread group + */ +#ifdef CONFIG_KEYS +static struct thread_group_cred init_tgcred = { + .usage = ATOMIC_INIT(2), + .tgid = 0, + .lock = SPIN_LOCK_UNLOCKED, +}; +#endif + /* * The initial credentials for the initial task */ @@ -28,8 +39,41 @@ struct cred init_cred = { .cap_bset = CAP_INIT_BSET, .user = INIT_USER, .group_info = &init_groups, +#ifdef CONFIG_KEYS + .tgcred = &init_tgcred, +#endif }; +/* + * Dispose of the shared task group credentials + */ +#ifdef CONFIG_KEYS +static void release_tgcred_rcu(struct rcu_head *rcu) +{ + struct thread_group_cred *tgcred = + container_of(rcu, struct thread_group_cred, rcu); + + BUG_ON(atomic_read(&tgcred->usage) != 0); + + key_put(tgcred->session_keyring); + key_put(tgcred->process_keyring); + kfree(tgcred); +} +#endif + +/* + * Release a set of thread group credentials. + */ +static void release_tgcred(struct cred *cred) +{ +#ifdef CONFIG_KEYS + struct thread_group_cred *tgcred = cred->tgcred; + + if (atomic_dec_and_test(&tgcred->usage)) + call_rcu(&tgcred->rcu, release_tgcred_rcu); +#endif +} + /* * The RCU callback to actually dispose of a set of credentials */ @@ -41,6 +85,7 @@ static void put_cred_rcu(struct rcu_head *rcu) key_put(cred->thread_keyring); key_put(cred->request_key_auth); + release_tgcred(cred); put_group_info(cred->group_info); free_uid(cred->user); security_cred_free(cred); @@ -71,12 +116,30 @@ int copy_creds(struct task_struct *p, unsigned long clone_flags) if (!pcred) return -ENOMEM; +#ifdef CONFIG_KEYS + if (clone_flags & CLONE_THREAD) { + atomic_inc(&pcred->tgcred->usage); + } else { + pcred->tgcred = kmalloc(sizeof(struct cred), GFP_KERNEL); + if (!pcred->tgcred) { + kfree(pcred); + return -ENOMEM; + } + atomic_set(&pcred->tgcred->usage, 1); + spin_lock_init(&pcred->tgcred->lock); + pcred->tgcred->process_keyring = NULL; + pcred->tgcred->session_keyring = + key_get(p->cred->tgcred->session_keyring); + } +#endif + #ifdef CONFIG_SECURITY pcred->security = NULL; #endif ret = security_cred_alloc(pcred); if (ret < 0) { + release_tgcred(pcred); kfree(pcred); return ret; } -- cgit v1.2.3 From d84f4f992cbd76e8f39c488cf0c5d123843923b1 Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 14 Nov 2008 10:39:23 +1100 Subject: CRED: Inaugurate COW credentials Inaugurate copy-on-write credentials management. This uses RCU to manage the credentials pointer in the task_struct with respect to accesses by other tasks. A process may only modify its own credentials, and so does not need locking to access or modify its own credentials. A mutex (cred_replace_mutex) is added to the task_struct to control the effect of PTRACE_ATTACHED on credential calculations, particularly with respect to execve(). With this patch, the contents of an active credentials struct may not be changed directly; rather a new set of credentials must be prepared, modified and committed using something like the following sequence of events: struct cred *new = prepare_creds(); int ret = blah(new); if (ret < 0) { abort_creds(new); return ret; } return commit_creds(new); There are some exceptions to this rule: the keyrings pointed to by the active credentials may be instantiated - keyrings violate the COW rule as managing COW keyrings is tricky, given that it is possible for a task to directly alter the keys in a keyring in use by another task. To help enforce this, various pointers to sets of credentials, such as those in the task_struct, are declared const. The purpose of this is compile-time discouragement of altering credentials through those pointers. Once a set of credentials has been made public through one of these pointers, it may not be modified, except under special circumstances: (1) Its reference count may incremented and decremented. (2) The keyrings to which it points may be modified, but not replaced. The only safe way to modify anything else is to create a replacement and commit using the functions described in Documentation/credentials.txt (which will be added by a later patch). This patch and the preceding patches have been tested with the LTP SELinux testsuite. This patch makes several logical sets of alteration: (1) execve(). This now prepares and commits credentials in various places in the security code rather than altering the current creds directly. (2) Temporary credential overrides. do_coredump() and sys_faccessat() now prepare their own credentials and temporarily override the ones currently on the acting thread, whilst preventing interference from other threads by holding cred_replace_mutex on the thread being dumped. This will be replaced in a future patch by something that hands down the credentials directly to the functions being called, rather than altering the task's objective credentials. (3) LSM interface. A number of functions have been changed, added or removed: (*) security_capset_check(), ->capset_check() (*) security_capset_set(), ->capset_set() Removed in favour of security_capset(). (*) security_capset(), ->capset() New. This is passed a pointer to the new creds, a pointer to the old creds and the proposed capability sets. It should fill in the new creds or return an error. All pointers, barring the pointer to the new creds, are now const. (*) security_bprm_apply_creds(), ->bprm_apply_creds() Changed; now returns a value, which will cause the process to be killed if it's an error. (*) security_task_alloc(), ->task_alloc_security() Removed in favour of security_prepare_creds(). (*) security_cred_free(), ->cred_free() New. Free security data attached to cred->security. (*) security_prepare_creds(), ->cred_prepare() New. Duplicate any security data attached to cred->security. (*) security_commit_creds(), ->cred_commit() New. Apply any security effects for the upcoming installation of new security by commit_creds(). (*) security_task_post_setuid(), ->task_post_setuid() Removed in favour of security_task_fix_setuid(). (*) security_task_fix_setuid(), ->task_fix_setuid() Fix up the proposed new credentials for setuid(). This is used by cap_set_fix_setuid() to implicitly adjust capabilities in line with setuid() changes. Changes are made to the new credentials, rather than the task itself as in security_task_post_setuid(). (*) security_task_reparent_to_init(), ->task_reparent_to_init() Removed. Instead the task being reparented to init is referred directly to init's credentials. NOTE! This results in the loss of some state: SELinux's osid no longer records the sid of the thread that forked it. (*) security_key_alloc(), ->key_alloc() (*) security_key_permission(), ->key_permission() Changed. These now take cred pointers rather than task pointers to refer to the security context. (4) sys_capset(). This has been simplified and uses less locking. The LSM functions it calls have been merged. (5) reparent_to_kthreadd(). This gives the current thread the same credentials as init by simply using commit_thread() to point that way. (6) __sigqueue_alloc() and switch_uid() __sigqueue_alloc() can't stop the target task from changing its creds beneath it, so this function gets a reference to the currently applicable user_struct which it then passes into the sigqueue struct it returns if successful. switch_uid() is now called from commit_creds(), and possibly should be folded into that. commit_creds() should take care of protecting __sigqueue_alloc(). (7) [sg]et[ug]id() and co and [sg]et_current_groups. The set functions now all use prepare_creds(), commit_creds() and abort_creds() to build and check a new set of credentials before applying it. security_task_set[ug]id() is called inside the prepared section. This guarantees that nothing else will affect the creds until we've finished. The calling of set_dumpable() has been moved into commit_creds(). Much of the functionality of set_user() has been moved into commit_creds(). The get functions all simply access the data directly. (8) security_task_prctl() and cap_task_prctl(). security_task_prctl() has been modified to return -ENOSYS if it doesn't want to handle a function, or otherwise return the return value directly rather than through an argument. Additionally, cap_task_prctl() now prepares a new set of credentials, even if it doesn't end up using it. (9) Keyrings. A number of changes have been made to the keyrings code: (a) switch_uid_keyring(), copy_keys(), exit_keys() and suid_keys() have all been dropped and built in to the credentials functions directly. They may want separating out again later. (b) key_alloc() and search_process_keyrings() now take a cred pointer rather than a task pointer to specify the security context. (c) copy_creds() gives a new thread within the same thread group a new thread keyring if its parent had one, otherwise it discards the thread keyring. (d) The authorisation key now points directly to the credentials to extend the search into rather pointing to the task that carries them. (e) Installing thread, process or session keyrings causes a new set of credentials to be created, even though it's not strictly necessary for process or session keyrings (they're shared). (10) Usermode helper. The usermode helper code now carries a cred struct pointer in its subprocess_info struct instead of a new session keyring pointer. This set of credentials is derived from init_cred and installed on the new process after it has been cloned. call_usermodehelper_setup() allocates the new credentials and call_usermodehelper_freeinfo() discards them if they haven't been used. A special cred function (prepare_usermodeinfo_creds()) is provided specifically for call_usermodehelper_setup() to call. call_usermodehelper_setkeys() adjusts the credentials to sport the supplied keyring as the new session keyring. (11) SELinux. SELinux has a number of changes, in addition to those to support the LSM interface changes mentioned above: (a) selinux_setprocattr() no longer does its check for whether the current ptracer can access processes with the new SID inside the lock that covers getting the ptracer's SID. Whilst this lock ensures that the check is done with the ptracer pinned, the result is only valid until the lock is released, so there's no point doing it inside the lock. (12) is_single_threaded(). This function has been extracted from selinux_setprocattr() and put into a file of its own in the lib/ directory as join_session_keyring() now wants to use it too. The code in SELinux just checked to see whether a task shared mm_structs with other tasks (CLONE_VM), but that isn't good enough. We really want to know if they're part of the same thread group (CLONE_THREAD). (13) nfsd. The NFS server daemon now has to use the COW credentials to set the credentials it is going to use. It really needs to pass the credentials down to the functions it calls, but it can't do that until other patches in this series have been applied. Signed-off-by: David Howells Acked-by: James Morris Signed-off-by: James Morris --- kernel/cred.c | 321 +++++++++++++++++++++++++++++++++++++++++++++++++++------- 1 file changed, 284 insertions(+), 37 deletions(-) (limited to 'kernel/cred.c') diff --git a/kernel/cred.c b/kernel/cred.c index ac73e361768..cb6b5eda978 100644 --- a/kernel/cred.c +++ b/kernel/cred.c @@ -15,6 +15,10 @@ #include #include #include +#include +#include "cred-internals.h" + +static struct kmem_cache *cred_jar; /* * The common credentials for the initial task's thread group @@ -64,7 +68,7 @@ static void release_tgcred_rcu(struct rcu_head *rcu) /* * Release a set of thread group credentials. */ -static void release_tgcred(struct cred *cred) +void release_tgcred(struct cred *cred) { #ifdef CONFIG_KEYS struct thread_group_cred *tgcred = cred->tgcred; @@ -81,79 +85,322 @@ static void put_cred_rcu(struct rcu_head *rcu) { struct cred *cred = container_of(rcu, struct cred, rcu); - BUG_ON(atomic_read(&cred->usage) != 0); + if (atomic_read(&cred->usage) != 0) + panic("CRED: put_cred_rcu() sees %p with usage %d\n", + cred, atomic_read(&cred->usage)); + security_cred_free(cred); key_put(cred->thread_keyring); key_put(cred->request_key_auth); release_tgcred(cred); put_group_info(cred->group_info); free_uid(cred->user); - security_cred_free(cred); - kfree(cred); + kmem_cache_free(cred_jar, cred); } /** * __put_cred - Destroy a set of credentials - * @sec: The record to release + * @cred: The record to release * * Destroy a set of credentials on which no references remain. */ void __put_cred(struct cred *cred) { + BUG_ON(atomic_read(&cred->usage) != 0); + call_rcu(&cred->rcu, put_cred_rcu); } EXPORT_SYMBOL(__put_cred); +/** + * prepare_creds - Prepare a new set of credentials for modification + * + * Prepare a new set of task credentials for modification. A task's creds + * shouldn't generally be modified directly, therefore this function is used to + * prepare a new copy, which the caller then modifies and then commits by + * calling commit_creds(). + * + * Returns a pointer to the new creds-to-be if successful, NULL otherwise. + * + * Call commit_creds() or abort_creds() to clean up. + */ +struct cred *prepare_creds(void) +{ + struct task_struct *task = current; + const struct cred *old; + struct cred *new; + + BUG_ON(atomic_read(&task->cred->usage) < 1); + + new = kmem_cache_alloc(cred_jar, GFP_KERNEL); + if (!new) + return NULL; + + old = task->cred; + memcpy(new, old, sizeof(struct cred)); + + atomic_set(&new->usage, 1); + get_group_info(new->group_info); + get_uid(new->user); + +#ifdef CONFIG_KEYS + key_get(new->thread_keyring); + key_get(new->request_key_auth); + atomic_inc(&new->tgcred->usage); +#endif + +#ifdef CONFIG_SECURITY + new->security = NULL; +#endif + + if (security_prepare_creds(new, old, GFP_KERNEL) < 0) + goto error; + return new; + +error: + abort_creds(new); + return NULL; +} +EXPORT_SYMBOL(prepare_creds); + +/* + * prepare new credentials for the usermode helper dispatcher + */ +struct cred *prepare_usermodehelper_creds(void) +{ +#ifdef CONFIG_KEYS + struct thread_group_cred *tgcred = NULL; +#endif + struct cred *new; + +#ifdef CONFIG_KEYS + tgcred = kzalloc(sizeof(*new->tgcred), GFP_ATOMIC); + if (!tgcred) + return NULL; +#endif + + new = kmem_cache_alloc(cred_jar, GFP_ATOMIC); + if (!new) + return NULL; + + memcpy(new, &init_cred, sizeof(struct cred)); + + atomic_set(&new->usage, 1); + get_group_info(new->group_info); + get_uid(new->user); + +#ifdef CONFIG_KEYS + new->thread_keyring = NULL; + new->request_key_auth = NULL; + new->jit_keyring = KEY_REQKEY_DEFL_DEFAULT; + + atomic_set(&tgcred->usage, 1); + spin_lock_init(&tgcred->lock); + new->tgcred = tgcred; +#endif + +#ifdef CONFIG_SECURITY + new->security = NULL; +#endif + if (security_prepare_creds(new, &init_cred, GFP_ATOMIC) < 0) + goto error; + + BUG_ON(atomic_read(&new->usage) != 1); + return new; + +error: + put_cred(new); + return NULL; +} + /* * Copy credentials for the new process created by fork() + * + * We share if we can, but under some circumstances we have to generate a new + * set. */ int copy_creds(struct task_struct *p, unsigned long clone_flags) { - struct cred *pcred; - int ret; +#ifdef CONFIG_KEYS + struct thread_group_cred *tgcred; +#endif + struct cred *new; + + mutex_init(&p->cred_exec_mutex); - pcred = kmemdup(p->cred, sizeof(*p->cred), GFP_KERNEL); - if (!pcred) + if ( +#ifdef CONFIG_KEYS + !p->cred->thread_keyring && +#endif + clone_flags & CLONE_THREAD + ) { + get_cred(p->cred); + atomic_inc(&p->cred->user->processes); + return 0; + } + + new = prepare_creds(); + if (!new) return -ENOMEM; #ifdef CONFIG_KEYS - if (clone_flags & CLONE_THREAD) { - atomic_inc(&pcred->tgcred->usage); - } else { - pcred->tgcred = kmalloc(sizeof(struct cred), GFP_KERNEL); - if (!pcred->tgcred) { - kfree(pcred); + /* new threads get their own thread keyrings if their parent already + * had one */ + if (new->thread_keyring) { + key_put(new->thread_keyring); + new->thread_keyring = NULL; + if (clone_flags & CLONE_THREAD) + install_thread_keyring_to_cred(new); + } + + /* we share the process and session keyrings between all the threads in + * a process - this is slightly icky as we violate COW credentials a + * bit */ + if (!(clone_flags & CLONE_THREAD)) { + tgcred = kmalloc(sizeof(*tgcred), GFP_KERNEL); + if (!tgcred) { + put_cred(new); return -ENOMEM; } - atomic_set(&pcred->tgcred->usage, 1); - spin_lock_init(&pcred->tgcred->lock); - pcred->tgcred->process_keyring = NULL; - pcred->tgcred->session_keyring = - key_get(p->cred->tgcred->session_keyring); + atomic_set(&tgcred->usage, 1); + spin_lock_init(&tgcred->lock); + tgcred->process_keyring = NULL; + tgcred->session_keyring = key_get(new->tgcred->session_keyring); + + release_tgcred(new); + new->tgcred = tgcred; } #endif -#ifdef CONFIG_SECURITY - pcred->security = NULL; -#endif + atomic_inc(&new->user->processes); + p->cred = new; + return 0; +} - ret = security_cred_alloc(pcred); - if (ret < 0) { - release_tgcred(pcred); - kfree(pcred); - return ret; +/** + * commit_creds - Install new credentials upon the current task + * @new: The credentials to be assigned + * + * Install a new set of credentials to the current task, using RCU to replace + * the old set. + * + * This function eats the caller's reference to the new credentials. + * + * Always returns 0 thus allowing this function to be tail-called at the end + * of, say, sys_setgid(). + */ +int commit_creds(struct cred *new) +{ + struct task_struct *task = current; + const struct cred *old; + + BUG_ON(atomic_read(&new->usage) < 1); + BUG_ON(atomic_read(&task->cred->usage) < 1); + + old = task->cred; + security_commit_creds(new, old); + + /* dumpability changes */ + if (old->euid != new->euid || + old->egid != new->egid || + old->fsuid != new->fsuid || + old->fsgid != new->fsgid || + !cap_issubset(new->cap_permitted, old->cap_permitted)) { + set_dumpable(task->mm, suid_dumpable); + task->pdeath_signal = 0; + smp_wmb(); } - atomic_set(&pcred->usage, 1); - get_group_info(pcred->group_info); - get_uid(pcred->user); - key_get(pcred->thread_keyring); - key_get(pcred->request_key_auth); + /* alter the thread keyring */ + if (new->fsuid != old->fsuid) + key_fsuid_changed(task); + if (new->fsgid != old->fsgid) + key_fsgid_changed(task); + + /* do it + * - What if a process setreuid()'s and this brings the + * new uid over his NPROC rlimit? We can check this now + * cheaply with the new uid cache, so if it matters + * we should be checking for it. -DaveM + */ + if (new->user != old->user) + atomic_inc(&new->user->processes); + rcu_assign_pointer(task->cred, new); + if (new->user != old->user) + atomic_dec(&old->user->processes); + + sched_switch_user(task); + + /* send notifications */ + if (new->uid != old->uid || + new->euid != old->euid || + new->suid != old->suid || + new->fsuid != old->fsuid) + proc_id_connector(task, PROC_EVENT_UID); - atomic_inc(&pcred->user->processes); + if (new->gid != old->gid || + new->egid != old->egid || + new->sgid != old->sgid || + new->fsgid != old->fsgid) + proc_id_connector(task, PROC_EVENT_GID); - /* RCU assignment is unneeded here as no-one can have accessed this - * pointer yet, barring us */ - p->cred = pcred; + put_cred(old); return 0; } +EXPORT_SYMBOL(commit_creds); + +/** + * abort_creds - Discard a set of credentials and unlock the current task + * @new: The credentials that were going to be applied + * + * Discard a set of credentials that were under construction and unlock the + * current task. + */ +void abort_creds(struct cred *new) +{ + BUG_ON(atomic_read(&new->usage) < 1); + put_cred(new); +} +EXPORT_SYMBOL(abort_creds); + +/** + * override_creds - Temporarily override the current process's credentials + * @new: The credentials to be assigned + * + * Install a set of temporary override credentials on the current process, + * returning the old set for later reversion. + */ +const struct cred *override_creds(const struct cred *new) +{ + const struct cred *old = current->cred; + + rcu_assign_pointer(current->cred, get_cred(new)); + return old; +} +EXPORT_SYMBOL(override_creds); + +/** + * revert_creds - Revert a temporary credentials override + * @old: The credentials to be restored + * + * Revert a temporary set of override credentials to an old set, discarding the + * override set. + */ +void revert_creds(const struct cred *old) +{ + const struct cred *override = current->cred; + + rcu_assign_pointer(current->cred, old); + put_cred(override); +} +EXPORT_SYMBOL(revert_creds); + +/* + * initialise the credentials stuff + */ +void __init cred_init(void) +{ + /* allocate a slab in which we can store credentials */ + cred_jar = kmem_cache_create("cred_jar", sizeof(struct cred), + 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL); +} -- cgit v1.2.3 From a6f76f23d297f70e2a6b3ec607f7aeeea9e37e8d Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 14 Nov 2008 10:39:24 +1100 Subject: CRED: Make execve() take advantage of copy-on-write credentials Make execve() take advantage of copy-on-write credentials, allowing it to set up the credentials in advance, and then commit the whole lot after the point of no return. This patch and the preceding patches have been tested with the LTP SELinux testsuite. This patch makes several logical sets of alteration: (1) execve(). The credential bits from struct linux_binprm are, for the most part, replaced with a single credentials pointer (bprm->cred). This means that all the creds can be calculated in advance and then applied at the point of no return with no possibility of failure. I would like to replace bprm->cap_effective with: cap_isclear(bprm->cap_effective) but this seems impossible due to special behaviour for processes of pid 1 (they always retain their parent's capability masks where normally they'd be changed - see cap_bprm_set_creds()). The following sequence of events now happens: (a) At the start of do_execve, the current task's cred_exec_mutex is locked to prevent PTRACE_ATTACH from obsoleting the calculation of creds that we make. (a) prepare_exec_creds() is then called to make a copy of the current task's credentials and prepare it. This copy is then assigned to bprm->cred. This renders security_bprm_alloc() and security_bprm_free() unnecessary, and so they've been removed. (b) The determination of unsafe execution is now performed immediately after (a) rather than later on in the code. The result is stored in bprm->unsafe for future reference. (c) prepare_binprm() is called, possibly multiple times. (i) This applies the result of set[ug]id binaries to the new creds attached to bprm->cred. Personality bit clearance is recorded, but now deferred on the basis that the exec procedure may yet fail. (ii) This then calls the new security_bprm_set_creds(). This should calculate the new LSM and capability credentials into *bprm->cred. This folds together security_bprm_set() and parts of security_bprm_apply_creds() (these two have been removed). Anything that might fail must be done at this point. (iii) bprm->cred_prepared is set to 1. bprm->cred_prepared is 0 on the first pass of the security calculations, and 1 on all subsequent passes. This allows SELinux in (ii) to base its calculations only on the initial script and not on the interpreter. (d) flush_old_exec() is called to commit the task to execution. This performs the following steps with regard to credentials: (i) Clear pdeath_signal and set dumpable on certain circumstances that may not be covered by commit_creds(). (ii) Clear any bits in current->personality that were deferred from (c.i). (e) install_exec_creds() [compute_creds() as was] is called to install the new credentials. This performs the following steps with regard to credentials: (i) Calls security_bprm_committing_creds() to apply any security requirements, such as flushing unauthorised files in SELinux, that must be done before the credentials are changed. This is made up of bits of security_bprm_apply_creds() and security_bprm_post_apply_creds(), both of which have been removed. This function is not allowed to fail; anything that might fail must have been done in (c.ii). (ii) Calls commit_creds() to apply the new credentials in a single assignment (more or less). Possibly pdeath_signal and dumpable should be part of struct creds. (iii) Unlocks the task's cred_replace_mutex, thus allowing PTRACE_ATTACH to take place. (iv) Clears The bprm->cred pointer as the credentials it was holding are now immutable. (v) Calls security_bprm_committed_creds() to apply any security alterations that must be done after the creds have been changed. SELinux uses this to flush signals and signal handlers. (f) If an error occurs before (d.i), bprm_free() will call abort_creds() to destroy the proposed new credentials and will then unlock cred_replace_mutex. No changes to the credentials will have been made. (2) LSM interface. A number of functions have been changed, added or removed: (*) security_bprm_alloc(), ->bprm_alloc_security() (*) security_bprm_free(), ->bprm_free_security() Removed in favour of preparing new credentials and modifying those. (*) security_bprm_apply_creds(), ->bprm_apply_creds() (*) security_bprm_post_apply_creds(), ->bprm_post_apply_creds() Removed; split between security_bprm_set_creds(), security_bprm_committing_creds() and security_bprm_committed_creds(). (*) security_bprm_set(), ->bprm_set_security() Removed; folded into security_bprm_set_creds(). (*) security_bprm_set_creds(), ->bprm_set_creds() New. The new credentials in bprm->creds should be checked and set up as appropriate. bprm->cred_prepared is 0 on the first call, 1 on the second and subsequent calls. (*) security_bprm_committing_creds(), ->bprm_committing_creds() (*) security_bprm_committed_creds(), ->bprm_committed_creds() New. Apply the security effects of the new credentials. This includes closing unauthorised files in SELinux. This function may not fail. When the former is called, the creds haven't yet been applied to the process; when the latter is called, they have. The former may access bprm->cred, the latter may not. (3) SELinux. SELinux has a number of changes, in addition to those to support the LSM interface changes mentioned above: (a) The bprm_security_struct struct has been removed in favour of using the credentials-under-construction approach. (c) flush_unauthorized_files() now takes a cred pointer and passes it on to inode_has_perm(), file_has_perm() and dentry_open(). Signed-off-by: David Howells Acked-by: James Morris Acked-by: Serge Hallyn Signed-off-by: James Morris --- kernel/cred.c | 46 +++++++++++++++++++++++++++++++++++++++++++++- 1 file changed, 45 insertions(+), 1 deletion(-) (limited to 'kernel/cred.c') diff --git a/kernel/cred.c b/kernel/cred.c index cb6b5eda978..e6fcdd67b2e 100644 --- a/kernel/cred.c +++ b/kernel/cred.c @@ -68,7 +68,7 @@ static void release_tgcred_rcu(struct rcu_head *rcu) /* * Release a set of thread group credentials. */ -void release_tgcred(struct cred *cred) +static void release_tgcred(struct cred *cred) { #ifdef CONFIG_KEYS struct thread_group_cred *tgcred = cred->tgcred; @@ -163,6 +163,50 @@ error: } EXPORT_SYMBOL(prepare_creds); +/* + * Prepare credentials for current to perform an execve() + * - The caller must hold current->cred_exec_mutex + */ +struct cred *prepare_exec_creds(void) +{ + struct thread_group_cred *tgcred = NULL; + struct cred *new; + +#ifdef CONFIG_KEYS + tgcred = kmalloc(sizeof(*tgcred), GFP_KERNEL); + if (!tgcred) + return NULL; +#endif + + new = prepare_creds(); + if (!new) { + kfree(tgcred); + return new; + } + +#ifdef CONFIG_KEYS + /* newly exec'd tasks don't get a thread keyring */ + key_put(new->thread_keyring); + new->thread_keyring = NULL; + + /* create a new per-thread-group creds for all this set of threads to + * share */ + memcpy(tgcred, new->tgcred, sizeof(struct thread_group_cred)); + + atomic_set(&tgcred->usage, 1); + spin_lock_init(&tgcred->lock); + + /* inherit the session keyring; new process keyring */ + key_get(tgcred->session_keyring); + tgcred->process_keyring = NULL; + + release_tgcred(new); + new->tgcred = tgcred; +#endif + + return new; +} + /* * prepare new credentials for the usermode helper dispatcher */ -- cgit v1.2.3 From 98870ab0a5a3f1822aee681d2997017e1c87d026 Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 14 Nov 2008 10:39:26 +1100 Subject: CRED: Documentation Document credentials and the new credentials API. Signed-off-by: David Howells Signed-off-by: James Morris --- kernel/cred.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel/cred.c') diff --git a/kernel/cred.c b/kernel/cred.c index e6fcdd67b2e..b8bd2f99d8c 100644 --- a/kernel/cred.c +++ b/kernel/cred.c @@ -1,4 +1,4 @@ -/* Task credentials management +/* Task credentials management - see Documentation/credentials.txt * * Copyright (C) 2008 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) -- cgit v1.2.3 From 3b11a1decef07c19443d24ae926982bc8ec9f4c0 Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 14 Nov 2008 10:39:26 +1100 Subject: CRED: Differentiate objective and effective subjective credentials on a task Differentiate the objective and real subjective credentials from the effective subjective credentials on a task by introducing a second credentials pointer into the task_struct. task_struct::real_cred then refers to the objective and apparent real subjective credentials of a task, as perceived by the other tasks in the system. task_struct::cred then refers to the effective subjective credentials of a task, as used by that task when it's actually running. These are not visible to the other tasks in the system. __task_cred(task) then refers to the objective/real credentials of the task in question. current_cred() refers to the effective subjective credentials of the current task. prepare_creds() uses the objective creds as a base and commit_creds() changes both pointers in the task_struct (indeed commit_creds() requires them to be the same). override_creds() and revert_creds() change the subjective creds pointer only, and the former returns the old subjective creds. These are used by NFSD, faccessat() and do_coredump(), and will by used by CacheFiles. In SELinux, current_has_perm() is provided as an alternative to task_has_perm(). This uses the effective subjective context of current, whereas task_has_perm() uses the objective/real context of the subject. Signed-off-by: David Howells Signed-off-by: James Morris --- kernel/cred.c | 38 ++++++++++++++++++++++++++------------ 1 file changed, 26 insertions(+), 12 deletions(-) (limited to 'kernel/cred.c') diff --git a/kernel/cred.c b/kernel/cred.c index b8bd2f99d8c..f3ca1066061 100644 --- a/kernel/cred.c +++ b/kernel/cred.c @@ -35,7 +35,7 @@ static struct thread_group_cred init_tgcred = { * The initial credentials for the initial task */ struct cred init_cred = { - .usage = ATOMIC_INIT(3), + .usage = ATOMIC_INIT(4), .securebits = SECUREBITS_DEFAULT, .cap_inheritable = CAP_INIT_INH_SET, .cap_permitted = CAP_FULL_SET, @@ -120,6 +120,8 @@ EXPORT_SYMBOL(__put_cred); * prepare a new copy, which the caller then modifies and then commits by * calling commit_creds(). * + * Preparation involves making a copy of the objective creds for modification. + * * Returns a pointer to the new creds-to-be if successful, NULL otherwise. * * Call commit_creds() or abort_creds() to clean up. @@ -130,7 +132,7 @@ struct cred *prepare_creds(void) const struct cred *old; struct cred *new; - BUG_ON(atomic_read(&task->cred->usage) < 1); + BUG_ON(atomic_read(&task->real_cred->usage) < 1); new = kmem_cache_alloc(cred_jar, GFP_KERNEL); if (!new) @@ -262,6 +264,9 @@ error: * * We share if we can, but under some circumstances we have to generate a new * set. + * + * The new process gets the current process's subjective credentials as its + * objective and subjective credentials */ int copy_creds(struct task_struct *p, unsigned long clone_flags) { @@ -278,6 +283,7 @@ int copy_creds(struct task_struct *p, unsigned long clone_flags) #endif clone_flags & CLONE_THREAD ) { + p->real_cred = get_cred(p->cred); get_cred(p->cred); atomic_inc(&p->cred->user->processes); return 0; @@ -317,7 +323,7 @@ int copy_creds(struct task_struct *p, unsigned long clone_flags) #endif atomic_inc(&new->user->processes); - p->cred = new; + p->cred = p->real_cred = get_cred(new); return 0; } @@ -326,7 +332,9 @@ int copy_creds(struct task_struct *p, unsigned long clone_flags) * @new: The credentials to be assigned * * Install a new set of credentials to the current task, using RCU to replace - * the old set. + * the old set. Both the objective and the subjective credentials pointers are + * updated. This function may not be called if the subjective credentials are + * in an overridden state. * * This function eats the caller's reference to the new credentials. * @@ -338,12 +346,15 @@ int commit_creds(struct cred *new) struct task_struct *task = current; const struct cred *old; + BUG_ON(task->cred != task->real_cred); + BUG_ON(atomic_read(&task->real_cred->usage) < 2); BUG_ON(atomic_read(&new->usage) < 1); - BUG_ON(atomic_read(&task->cred->usage) < 1); - old = task->cred; + old = task->real_cred; security_commit_creds(new, old); + get_cred(new); /* we will require a ref for the subj creds too */ + /* dumpability changes */ if (old->euid != new->euid || old->egid != new->egid || @@ -369,6 +380,7 @@ int commit_creds(struct cred *new) */ if (new->user != old->user) atomic_inc(&new->user->processes); + rcu_assign_pointer(task->real_cred, new); rcu_assign_pointer(task->cred, new); if (new->user != old->user) atomic_dec(&old->user->processes); @@ -388,6 +400,8 @@ int commit_creds(struct cred *new) new->fsgid != old->fsgid) proc_id_connector(task, PROC_EVENT_GID); + /* release the old obj and subj refs both */ + put_cred(old); put_cred(old); return 0; } @@ -408,11 +422,11 @@ void abort_creds(struct cred *new) EXPORT_SYMBOL(abort_creds); /** - * override_creds - Temporarily override the current process's credentials + * override_creds - Override the current process's subjective credentials * @new: The credentials to be assigned * - * Install a set of temporary override credentials on the current process, - * returning the old set for later reversion. + * Install a set of temporary override subjective credentials on the current + * process, returning the old set for later reversion. */ const struct cred *override_creds(const struct cred *new) { @@ -424,11 +438,11 @@ const struct cred *override_creds(const struct cred *new) EXPORT_SYMBOL(override_creds); /** - * revert_creds - Revert a temporary credentials override + * revert_creds - Revert a temporary subjective credentials override * @old: The credentials to be restored * - * Revert a temporary set of override credentials to an old set, discarding the - * override set. + * Revert a temporary set of override subjective credentials to an old set, + * discarding the override set. */ void revert_creds(const struct cred *old) { -- cgit v1.2.3 From 3a3b7ce9336952ea7b9564d976d068a238976c9d Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 14 Nov 2008 10:39:28 +1100 Subject: CRED: Allow kernel services to override LSM settings for task actions Allow kernel services to override LSM settings appropriate to the actions performed by a task by duplicating a set of credentials, modifying it and then using task_struct::cred to point to it when performing operations on behalf of a task. This is used, for example, by CacheFiles which has to transparently access the cache on behalf of a process that thinks it is doing, say, NFS accesses with a potentially inappropriate (with respect to accessing the cache) set of credentials. This patch provides two LSM hooks for modifying a task security record: (*) security_kernel_act_as() which allows modification of the security datum with which a task acts on other objects (most notably files). (*) security_kernel_create_files_as() which allows modification of the security datum that is used to initialise the security data on a file that a task creates. The patch also provides four new credentials handling functions, which wrap the LSM functions: (1) prepare_kernel_cred() Prepare a set of credentials for a kernel service to use, based either on a daemon's credentials or on init_cred. All the keyrings are cleared. (2) set_security_override() Set the LSM security ID in a set of credentials to a specific security context, assuming permission from the LSM policy. (3) set_security_override_from_ctx() As (2), but takes the security context as a string. (4) set_create_files_as() Set the file creation LSM security ID in a set of credentials to be the same as that on a particular inode. Signed-off-by: Casey Schaufler [Smack changes] Signed-off-by: David Howells Signed-off-by: James Morris --- kernel/cred.c | 113 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 113 insertions(+) (limited to 'kernel/cred.c') diff --git a/kernel/cred.c b/kernel/cred.c index f3ca1066061..13697ca2bb3 100644 --- a/kernel/cred.c +++ b/kernel/cred.c @@ -462,3 +462,116 @@ void __init cred_init(void) cred_jar = kmem_cache_create("cred_jar", sizeof(struct cred), 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL); } + +/** + * prepare_kernel_cred - Prepare a set of credentials for a kernel service + * @daemon: A userspace daemon to be used as a reference + * + * Prepare a set of credentials for a kernel service. This can then be used to + * override a task's own credentials so that work can be done on behalf of that + * task that requires a different subjective context. + * + * @daemon is used to provide a base for the security record, but can be NULL. + * If @daemon is supplied, then the security data will be derived from that; + * otherwise they'll be set to 0 and no groups, full capabilities and no keys. + * + * The caller may change these controls afterwards if desired. + * + * Returns the new credentials or NULL if out of memory. + * + * Does not take, and does not return holding current->cred_replace_mutex. + */ +struct cred *prepare_kernel_cred(struct task_struct *daemon) +{ + const struct cred *old; + struct cred *new; + + new = kmem_cache_alloc(cred_jar, GFP_KERNEL); + if (!new) + return NULL; + + if (daemon) + old = get_task_cred(daemon); + else + old = get_cred(&init_cred); + + get_uid(new->user); + get_group_info(new->group_info); + +#ifdef CONFIG_KEYS + atomic_inc(&init_tgcred.usage); + new->tgcred = &init_tgcred; + new->request_key_auth = NULL; + new->thread_keyring = NULL; + new->jit_keyring = KEY_REQKEY_DEFL_THREAD_KEYRING; +#endif + +#ifdef CONFIG_SECURITY + new->security = NULL; +#endif + if (security_prepare_creds(new, old, GFP_KERNEL) < 0) + goto error; + + atomic_set(&new->usage, 1); + put_cred(old); + return new; + +error: + put_cred(new); + return NULL; +} +EXPORT_SYMBOL(prepare_kernel_cred); + +/** + * set_security_override - Set the security ID in a set of credentials + * @new: The credentials to alter + * @secid: The LSM security ID to set + * + * Set the LSM security ID in a set of credentials so that the subjective + * security is overridden when an alternative set of credentials is used. + */ +int set_security_override(struct cred *new, u32 secid) +{ + return security_kernel_act_as(new, secid); +} +EXPORT_SYMBOL(set_security_override); + +/** + * set_security_override_from_ctx - Set the security ID in a set of credentials + * @new: The credentials to alter + * @secctx: The LSM security context to generate the security ID from. + * + * Set the LSM security ID in a set of credentials so that the subjective + * security is overridden when an alternative set of credentials is used. The + * security ID is specified in string form as a security context to be + * interpreted by the LSM. + */ +int set_security_override_from_ctx(struct cred *new, const char *secctx) +{ + u32 secid; + int ret; + + ret = security_secctx_to_secid(secctx, strlen(secctx), &secid); + if (ret < 0) + return ret; + + return set_security_override(new, secid); +} +EXPORT_SYMBOL(set_security_override_from_ctx); + +/** + * set_create_files_as - Set the LSM file create context in a set of credentials + * @new: The credentials to alter + * @inode: The inode to take the context from + * + * Change the LSM file creation context in a set of credentials to be the same + * as the object context of the specified inode, so that the new inodes have + * the same MAC context as that inode. + */ +int set_create_files_as(struct cred *new, struct inode *inode) +{ + new->fsuid = inode->i_uid; + new->fsgid = inode->i_gid; + return security_kernel_create_files_as(new, inode); +} +EXPORT_SYMBOL(set_create_files_as); -- cgit v1.2.3 From 18b6e0414e42d95183f07d8177e3ff0241abd825 Mon Sep 17 00:00:00 2001 From: Serge Hallyn Date: Wed, 15 Oct 2008 16:38:45 -0500 Subject: 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 Changelog: Oct 20: integrate dhowells comments 1. leave thread_keyring alone 2. use current_user_ns() in set_user() Signed-off-by: Serge Hallyn --- kernel/cred.c | 15 +++++++++++++-- 1 file changed, 13 insertions(+), 2 deletions(-) (limited to 'kernel/cred.c') diff --git a/kernel/cred.c b/kernel/cred.c index 13697ca2bb3..ff7bc071991 100644 --- a/kernel/cred.c +++ b/kernel/cred.c @@ -274,6 +274,7 @@ int copy_creds(struct task_struct *p, unsigned long clone_flags) struct thread_group_cred *tgcred; #endif struct cred *new; + int ret; mutex_init(&p->cred_exec_mutex); @@ -293,6 +294,12 @@ int copy_creds(struct task_struct *p, unsigned long clone_flags) if (!new) return -ENOMEM; + if (clone_flags & CLONE_NEWUSER) { + ret = create_user_ns(new); + if (ret < 0) + goto error_put; + } + #ifdef CONFIG_KEYS /* new threads get their own thread keyrings if their parent already * had one */ @@ -309,8 +316,8 @@ int copy_creds(struct task_struct *p, unsigned long clone_flags) if (!(clone_flags & CLONE_THREAD)) { tgcred = kmalloc(sizeof(*tgcred), GFP_KERNEL); if (!tgcred) { - put_cred(new); - return -ENOMEM; + ret = -ENOMEM; + goto error_put; } atomic_set(&tgcred->usage, 1); spin_lock_init(&tgcred->lock); @@ -325,6 +332,10 @@ int copy_creds(struct task_struct *p, unsigned long clone_flags) atomic_inc(&new->user->processes); p->cred = p->real_cred = get_cred(new); return 0; + +error_put: + put_cred(new); + return ret; } /** -- cgit v1.2.3