linux/kernel/ptrace.c

943 lines
23 KiB
C
Raw Normal View History

/*
* linux/kernel/ptrace.c
*
* (C) Copyright 1999 Linus Torvalds
*
* Common interfaces for "ptrace()" which we do not want
* to continually duplicate across every architecture.
*/
#include <linux/capability.h>
#include <linux/module.h>
#include <linux/sched.h>
#include <linux/errno.h>
#include <linux/mm.h>
#include <linux/highmem.h>
#include <linux/pagemap.h>
#include <linux/ptrace.h>
#include <linux/security.h>
#include <linux/signal.h>
#include <linux/audit.h>
#include <linux/pid_namespace.h>
#include <linux/syscalls.h>
#include <linux/uaccess.h>
#include <linux/regset.h>
#include <linux/hw_breakpoint.h>
/*
* ptrace a task: make the debugger its new parent and
* move it to the ptrace list.
*
* Must be called with the tasklist lock write-held.
*/
void __ptrace_link(struct task_struct *child, struct task_struct *new_parent)
{
BUG_ON(!list_empty(&child->ptrace_entry));
list_add(&child->ptrace_entry, &new_parent->ptraced);
child->parent = new_parent;
}
/**
* __ptrace_unlink - unlink ptracee and restore its execution state
* @child: ptracee to be unlinked
*
ptrace: Always put ptracee into appropriate execution state Currently, __ptrace_unlink() wakes up the tracee iff it's in TASK_TRACED. For unlinking from PTRACE_DETACH, this is correct as the tracee is guaranteed to be in TASK_TRACED or dead; however, unlinking also happens when the ptracer exits and in this case the ptracee can be in any state and ptrace might be left running even if the group it belongs to is stopped. This patch updates __ptrace_unlink() such that GROUP_STOP_PENDING is reinstated regardless of the ptracee's current state as long as it's alive and makes sure that signal_wake_up() is called if execution state transition is necessary. Test case follows. #include <unistd.h> #include <time.h> #include <sys/types.h> #include <sys/ptrace.h> #include <sys/wait.h> static const struct timespec ts1s = { .tv_sec = 1 }; int main(void) { pid_t tracee; siginfo_t si; tracee = fork(); if (tracee == 0) { while (1) { nanosleep(&ts1s, NULL); write(1, ".", 1); } } ptrace(PTRACE_ATTACH, tracee, NULL, NULL); waitid(P_PID, tracee, &si, WSTOPPED); ptrace(PTRACE_CONT, tracee, NULL, (void *)(long)si.si_status); waitid(P_PID, tracee, &si, WSTOPPED); ptrace(PTRACE_CONT, tracee, NULL, (void *)(long)si.si_status); write(1, "exiting", 7); return 0; } Before the patch, after the parent process exits, the child is left running and prints out "." every second. exiting..... (continues) After the patch, the group stop initiated by the implied SIGSTOP from PTRACE_ATTACH is re-established when the parent exits. exiting Signed-off-by: Tejun Heo <tj@kernel.org> Reported-by: Oleg Nesterov <oleg@redhat.com> Acked-by: Oleg Nesterov <oleg@redhat.com>
2011-03-23 17:37:01 +08:00
* Remove @child from the ptrace list, move it back to the original parent,
* and restore the execution state so that it conforms to the group stop
* state.
*
* Unlinking can happen via two paths - explicit PTRACE_DETACH or ptracer
* exiting. For PTRACE_DETACH, unless the ptracee has been killed between
* ptrace_check_attach() and here, it's guaranteed to be in TASK_TRACED.
* If the ptracer is exiting, the ptracee can be in any state.
*
* After detach, the ptracee should be in a state which conforms to the
* group stop. If the group is stopped or in the process of stopping, the
* ptracee should be put into TASK_STOPPED; otherwise, it should be woken
* up from TASK_TRACED.
*
* If the ptracee is in TASK_TRACED and needs to be moved to TASK_STOPPED,
* it goes through TRACED -> RUNNING -> STOPPED transition which is similar
* to but in the opposite direction of what happens while attaching to a
* stopped task. However, in this direction, the intermediate RUNNING
* state is not hidden even from the current ptracer and if it immediately
* re-attaches and performs a WNOHANG wait(2), it may fail.
*
* CONTEXT:
* write_lock_irq(tasklist_lock)
*/
void __ptrace_unlink(struct task_struct *child)
{
BUG_ON(!child->ptrace);
child->ptrace = 0;
child->parent = child->real_parent;
list_del_init(&child->ptrace_entry);
spin_lock(&child->sighand->siglock);
ptrace: Always put ptracee into appropriate execution state Currently, __ptrace_unlink() wakes up the tracee iff it's in TASK_TRACED. For unlinking from PTRACE_DETACH, this is correct as the tracee is guaranteed to be in TASK_TRACED or dead; however, unlinking also happens when the ptracer exits and in this case the ptracee can be in any state and ptrace might be left running even if the group it belongs to is stopped. This patch updates __ptrace_unlink() such that GROUP_STOP_PENDING is reinstated regardless of the ptracee's current state as long as it's alive and makes sure that signal_wake_up() is called if execution state transition is necessary. Test case follows. #include <unistd.h> #include <time.h> #include <sys/types.h> #include <sys/ptrace.h> #include <sys/wait.h> static const struct timespec ts1s = { .tv_sec = 1 }; int main(void) { pid_t tracee; siginfo_t si; tracee = fork(); if (tracee == 0) { while (1) { nanosleep(&ts1s, NULL); write(1, ".", 1); } } ptrace(PTRACE_ATTACH, tracee, NULL, NULL); waitid(P_PID, tracee, &si, WSTOPPED); ptrace(PTRACE_CONT, tracee, NULL, (void *)(long)si.si_status); waitid(P_PID, tracee, &si, WSTOPPED); ptrace(PTRACE_CONT, tracee, NULL, (void *)(long)si.si_status); write(1, "exiting", 7); return 0; } Before the patch, after the parent process exits, the child is left running and prints out "." every second. exiting..... (continues) After the patch, the group stop initiated by the implied SIGSTOP from PTRACE_ATTACH is re-established when the parent exits. exiting Signed-off-by: Tejun Heo <tj@kernel.org> Reported-by: Oleg Nesterov <oleg@redhat.com> Acked-by: Oleg Nesterov <oleg@redhat.com>
2011-03-23 17:37:01 +08:00
/*
* Reinstate GROUP_STOP_PENDING if group stop is in effect and
* @child isn't dead.
*/
if (!(child->flags & PF_EXITING) &&
(child->signal->flags & SIGNAL_STOP_STOPPED ||
child->signal->group_stop_count))
child->group_stop |= GROUP_STOP_PENDING;
/*
* If transition to TASK_STOPPED is pending or in TASK_TRACED, kick
* @child in the butt. Note that @resume should be used iff @child
* is in TASK_TRACED; otherwise, we might unduly disrupt
* TASK_KILLABLE sleeps.
*/
if (child->group_stop & GROUP_STOP_PENDING || task_is_traced(child))
signal_wake_up(child, task_is_traced(child));
spin_unlock(&child->sighand->siglock);
}
/*
* Check that we have indeed attached to the thing..
*/
int ptrace_check_attach(struct task_struct *child, int kill)
{
int ret = -ESRCH;
/*
* We take the read lock around doing both checks to close a
* possible race where someone else was tracing our child and
* detached between these two checks. After this locked check,
* we are sure that this is our traced child and that can only
* be changed by us so it's not changing right after this.
*/
read_lock(&tasklist_lock);
if ((child->ptrace & PT_PTRACED) && child->parent == current) {
/*
* child->sighand can't be NULL, release_task()
* does ptrace_unlink() before __exit_signal().
*/
spin_lock_irq(&child->sighand->siglock);
WARN_ON_ONCE(task_is_stopped(child));
if (task_is_traced(child) || kill)
ret = 0;
spin_unlock_irq(&child->sighand->siglock);
}
read_unlock(&tasklist_lock);
if (!ret && !kill)
ret = wait_task_inactive(child, TASK_TRACED) ? 0 : -ESRCH;
/* All systems go.. */
return ret;
}
Security: split proc ptrace checking into read vs. attach Enable security modules to distinguish reading of process state via proc from full ptrace access by renaming ptrace_may_attach to ptrace_may_access and adding a mode argument indicating whether only read access or full attach access is requested. This allows security modules to permit access to reading process state without granting full ptrace access. The base DAC/capability checking remains unchanged. Read access to /proc/pid/mem continues to apply a full ptrace attach check since check_mem_permission() already requires the current task to already be ptracing the target. The other ptrace checks within proc for elements like environ, maps, and fds are changed to pass the read mode instead of attach. In the SELinux case, we model such reading of process state as a reading of a proc file labeled with the target process' label. This enables SELinux policy to permit such reading of process state without permitting control or manipulation of the target process, as there are a number of cases where programs probe for such information via proc but do not need to be able to control the target (e.g. procps, lsof, PolicyKit, ConsoleKit). At present we have to choose between allowing full ptrace in policy (more permissive than required/desired) or breaking functionality (or in some cases just silencing the denials via dontaudit rules but this can hide genuine attacks). This version of the patch incorporates comments from Casey Schaufler (change/replace existing ptrace_may_attach interface, pass access mode), and Chris Wright (provide greater consistency in the checking). Note that like their predecessors __ptrace_may_attach and ptrace_may_attach, the __ptrace_may_access and ptrace_may_access interfaces use different return value conventions from each other (0 or -errno vs. 1 or 0). I retained this difference to avoid any changes to the caller logic but made the difference clearer by changing the latter interface to return a bool rather than an int and by adding a comment about it to ptrace.h for any future callers. Signed-off-by: Stephen Smalley <sds@tycho.nsa.gov> Acked-by: Chris Wright <chrisw@sous-sol.org> Signed-off-by: James Morris <jmorris@namei.org>
2008-05-19 20:32:49 +08:00
int __ptrace_may_access(struct task_struct *task, unsigned int mode)
{
const struct cred *cred = current_cred(), *tcred;
/* May we inspect the given task?
* This check is used both for attaching with ptrace
* and for allowing access to sensitive information in /proc.
*
* ptrace_attach denies several cases that /proc allows
* because setting up the necessary parent/child relationship
* or halting the specified task is impossible.
*/
int dumpable = 0;
/* Don't let security modules deny introspection */
if (task == current)
return 0;
rcu_read_lock();
tcred = __task_cred(task);
if (cred->user->user_ns == tcred->user->user_ns &&
(cred->uid == tcred->euid &&
cred->uid == tcred->suid &&
cred->uid == tcred->uid &&
cred->gid == tcred->egid &&
cred->gid == tcred->sgid &&
cred->gid == tcred->gid))
goto ok;
if (ns_capable(tcred->user->user_ns, CAP_SYS_PTRACE))
goto ok;
rcu_read_unlock();
return -EPERM;
ok:
rcu_read_unlock();
smp_rmb();
if (task->mm)
dumpable = get_dumpable(task->mm);
if (!dumpable && !task_ns_capable(task, CAP_SYS_PTRACE))
return -EPERM;
return security_ptrace_access_check(task, mode);
}
Security: split proc ptrace checking into read vs. attach Enable security modules to distinguish reading of process state via proc from full ptrace access by renaming ptrace_may_attach to ptrace_may_access and adding a mode argument indicating whether only read access or full attach access is requested. This allows security modules to permit access to reading process state without granting full ptrace access. The base DAC/capability checking remains unchanged. Read access to /proc/pid/mem continues to apply a full ptrace attach check since check_mem_permission() already requires the current task to already be ptracing the target. The other ptrace checks within proc for elements like environ, maps, and fds are changed to pass the read mode instead of attach. In the SELinux case, we model such reading of process state as a reading of a proc file labeled with the target process' label. This enables SELinux policy to permit such reading of process state without permitting control or manipulation of the target process, as there are a number of cases where programs probe for such information via proc but do not need to be able to control the target (e.g. procps, lsof, PolicyKit, ConsoleKit). At present we have to choose between allowing full ptrace in policy (more permissive than required/desired) or breaking functionality (or in some cases just silencing the denials via dontaudit rules but this can hide genuine attacks). This version of the patch incorporates comments from Casey Schaufler (change/replace existing ptrace_may_attach interface, pass access mode), and Chris Wright (provide greater consistency in the checking). Note that like their predecessors __ptrace_may_attach and ptrace_may_attach, the __ptrace_may_access and ptrace_may_access interfaces use different return value conventions from each other (0 or -errno vs. 1 or 0). I retained this difference to avoid any changes to the caller logic but made the difference clearer by changing the latter interface to return a bool rather than an int and by adding a comment about it to ptrace.h for any future callers. Signed-off-by: Stephen Smalley <sds@tycho.nsa.gov> Acked-by: Chris Wright <chrisw@sous-sol.org> Signed-off-by: James Morris <jmorris@namei.org>
2008-05-19 20:32:49 +08:00
bool ptrace_may_access(struct task_struct *task, unsigned int mode)
{
int err;
task_lock(task);
Security: split proc ptrace checking into read vs. attach Enable security modules to distinguish reading of process state via proc from full ptrace access by renaming ptrace_may_attach to ptrace_may_access and adding a mode argument indicating whether only read access or full attach access is requested. This allows security modules to permit access to reading process state without granting full ptrace access. The base DAC/capability checking remains unchanged. Read access to /proc/pid/mem continues to apply a full ptrace attach check since check_mem_permission() already requires the current task to already be ptracing the target. The other ptrace checks within proc for elements like environ, maps, and fds are changed to pass the read mode instead of attach. In the SELinux case, we model such reading of process state as a reading of a proc file labeled with the target process' label. This enables SELinux policy to permit such reading of process state without permitting control or manipulation of the target process, as there are a number of cases where programs probe for such information via proc but do not need to be able to control the target (e.g. procps, lsof, PolicyKit, ConsoleKit). At present we have to choose between allowing full ptrace in policy (more permissive than required/desired) or breaking functionality (or in some cases just silencing the denials via dontaudit rules but this can hide genuine attacks). This version of the patch incorporates comments from Casey Schaufler (change/replace existing ptrace_may_attach interface, pass access mode), and Chris Wright (provide greater consistency in the checking). Note that like their predecessors __ptrace_may_attach and ptrace_may_attach, the __ptrace_may_access and ptrace_may_access interfaces use different return value conventions from each other (0 or -errno vs. 1 or 0). I retained this difference to avoid any changes to the caller logic but made the difference clearer by changing the latter interface to return a bool rather than an int and by adding a comment about it to ptrace.h for any future callers. Signed-off-by: Stephen Smalley <sds@tycho.nsa.gov> Acked-by: Chris Wright <chrisw@sous-sol.org> Signed-off-by: James Morris <jmorris@namei.org>
2008-05-19 20:32:49 +08:00
err = __ptrace_may_access(task, mode);
task_unlock(task);
return !err;
}
static int ptrace_attach(struct task_struct *task)
{
ptrace: Clean transitions between TASK_STOPPED and TRACED Currently, if the task is STOPPED on ptrace attach, it's left alone and the state is silently changed to TRACED on the next ptrace call. The behavior breaks the assumption that arch_ptrace_stop() is called before any task is poked by ptrace and is ugly in that a task manipulates the state of another task directly. With GROUP_STOP_PENDING, the transitions between TASK_STOPPED and TRACED can be made clean. The tracer can use the flag to tell the tracee to retry stop on attach and detach. On retry, the tracee will enter the desired state in the correct way. The lower 16bits of task->group_stop is used to remember the signal number which caused the last group stop. This is used while retrying for ptrace attach as the original group_exit_code could have been consumed with wait(2) by then. As the real parent may wait(2) and consume the group_exit_code anytime, the group_exit_code needs to be saved separately so that it can be used when switching from regular sleep to ptrace_stop(). This is recorded in the lower 16bits of task->group_stop. If a task is already stopped and there's no intervening SIGCONT, a ptrace request immediately following a successful PTRACE_ATTACH should always succeed even if the tracer doesn't wait(2) for attach completion; however, with this change, the tracee might still be TASK_RUNNING trying to enter TASK_TRACED which would cause the following request to fail with -ESRCH. This intermediate state is hidden from the ptracer by setting GROUP_STOP_TRAPPING on attach and making ptrace_check_attach() wait for it to clear on its signal->wait_chldexit. Completing the transition or getting killed clears TRAPPING and wakes up the tracer. Note that the STOPPED -> RUNNING -> TRACED transition is still visible to other threads which are in the same group as the ptracer and the reverse transition is visible to all. Please read the comments for details. Oleg: * Spotted a race condition where a task may retry group stop without proper bookkeeping. Fixed by redoing bookkeeping on retry. * Spotted that the transition is visible to userland in several different ways. Most are fixed with GROUP_STOP_TRAPPING. Unhandled corner case is documented. * Pointed out not setting GROUP_STOP_SIGMASK on an already stopped task would result in more consistent behavior. * Pointed out that calling ptrace_stop() from do_signal_stop() in TASK_STOPPED can race with group stop start logic and then confuse the TRAPPING wait in ptrace_check_attach(). ptrace_stop() is now called with TASK_RUNNING. * Suggested using signal->wait_chldexit instead of bit wait. * Spotted a race condition between TRACED transition and clearing of TRAPPING. Signed-off-by: Tejun Heo <tj@kernel.org> Acked-by: Oleg Nesterov <oleg@redhat.com> Cc: Roland McGrath <roland@redhat.com> Cc: Jan Kratochvil <jan.kratochvil@redhat.com>
2011-03-23 17:37:00 +08:00
bool wait_trap = false;
int retval;
audit_ptrace(task);
retval = -EPERM;
if (unlikely(task->flags & PF_KTHREAD))
goto out;
if (same_thread_group(task, current))
goto out;
/*
* Protect exec's credential calculations against our interference;
* interference; SUID, SGID and LSM creds get determined differently
* under ptrace.
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 <dhowells@redhat.com> Acked-by: James Morris <jmorris@namei.org> Signed-off-by: James Morris <jmorris@namei.org>
2008-11-14 07:39:23 +08:00
*/
retval = -ERESTARTNOINTR;
if (mutex_lock_interruptible(&task->signal->cred_guard_mutex))
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 <dhowells@redhat.com> Acked-by: James Morris <jmorris@namei.org> Signed-off-by: James Morris <jmorris@namei.org>
2008-11-14 07:39:23 +08:00
goto out;
task_lock(task);
Security: split proc ptrace checking into read vs. attach Enable security modules to distinguish reading of process state via proc from full ptrace access by renaming ptrace_may_attach to ptrace_may_access and adding a mode argument indicating whether only read access or full attach access is requested. This allows security modules to permit access to reading process state without granting full ptrace access. The base DAC/capability checking remains unchanged. Read access to /proc/pid/mem continues to apply a full ptrace attach check since check_mem_permission() already requires the current task to already be ptracing the target. The other ptrace checks within proc for elements like environ, maps, and fds are changed to pass the read mode instead of attach. In the SELinux case, we model such reading of process state as a reading of a proc file labeled with the target process' label. This enables SELinux policy to permit such reading of process state without permitting control or manipulation of the target process, as there are a number of cases where programs probe for such information via proc but do not need to be able to control the target (e.g. procps, lsof, PolicyKit, ConsoleKit). At present we have to choose between allowing full ptrace in policy (more permissive than required/desired) or breaking functionality (or in some cases just silencing the denials via dontaudit rules but this can hide genuine attacks). This version of the patch incorporates comments from Casey Schaufler (change/replace existing ptrace_may_attach interface, pass access mode), and Chris Wright (provide greater consistency in the checking). Note that like their predecessors __ptrace_may_attach and ptrace_may_attach, the __ptrace_may_access and ptrace_may_access interfaces use different return value conventions from each other (0 or -errno vs. 1 or 0). I retained this difference to avoid any changes to the caller logic but made the difference clearer by changing the latter interface to return a bool rather than an int and by adding a comment about it to ptrace.h for any future callers. Signed-off-by: Stephen Smalley <sds@tycho.nsa.gov> Acked-by: Chris Wright <chrisw@sous-sol.org> Signed-off-by: James Morris <jmorris@namei.org>
2008-05-19 20:32:49 +08:00
retval = __ptrace_may_access(task, PTRACE_MODE_ATTACH);
task_unlock(task);
if (retval)
goto unlock_creds;
write_lock_irq(&tasklist_lock);
retval = -EPERM;
if (unlikely(task->exit_state))
goto unlock_tasklist;
if (task->ptrace)
goto unlock_tasklist;
task->ptrace = PT_PTRACED;
if (task_ns_capable(task, CAP_SYS_PTRACE))
task->ptrace |= PT_PTRACE_CAP;
__ptrace_link(task, current);
send_sig_info(SIGSTOP, SEND_SIG_FORCED, task);
ptrace: Clean transitions between TASK_STOPPED and TRACED Currently, if the task is STOPPED on ptrace attach, it's left alone and the state is silently changed to TRACED on the next ptrace call. The behavior breaks the assumption that arch_ptrace_stop() is called before any task is poked by ptrace and is ugly in that a task manipulates the state of another task directly. With GROUP_STOP_PENDING, the transitions between TASK_STOPPED and TRACED can be made clean. The tracer can use the flag to tell the tracee to retry stop on attach and detach. On retry, the tracee will enter the desired state in the correct way. The lower 16bits of task->group_stop is used to remember the signal number which caused the last group stop. This is used while retrying for ptrace attach as the original group_exit_code could have been consumed with wait(2) by then. As the real parent may wait(2) and consume the group_exit_code anytime, the group_exit_code needs to be saved separately so that it can be used when switching from regular sleep to ptrace_stop(). This is recorded in the lower 16bits of task->group_stop. If a task is already stopped and there's no intervening SIGCONT, a ptrace request immediately following a successful PTRACE_ATTACH should always succeed even if the tracer doesn't wait(2) for attach completion; however, with this change, the tracee might still be TASK_RUNNING trying to enter TASK_TRACED which would cause the following request to fail with -ESRCH. This intermediate state is hidden from the ptracer by setting GROUP_STOP_TRAPPING on attach and making ptrace_check_attach() wait for it to clear on its signal->wait_chldexit. Completing the transition or getting killed clears TRAPPING and wakes up the tracer. Note that the STOPPED -> RUNNING -> TRACED transition is still visible to other threads which are in the same group as the ptracer and the reverse transition is visible to all. Please read the comments for details. Oleg: * Spotted a race condition where a task may retry group stop without proper bookkeeping. Fixed by redoing bookkeeping on retry. * Spotted that the transition is visible to userland in several different ways. Most are fixed with GROUP_STOP_TRAPPING. Unhandled corner case is documented. * Pointed out not setting GROUP_STOP_SIGMASK on an already stopped task would result in more consistent behavior. * Pointed out that calling ptrace_stop() from do_signal_stop() in TASK_STOPPED can race with group stop start logic and then confuse the TRAPPING wait in ptrace_check_attach(). ptrace_stop() is now called with TASK_RUNNING. * Suggested using signal->wait_chldexit instead of bit wait. * Spotted a race condition between TRACED transition and clearing of TRAPPING. Signed-off-by: Tejun Heo <tj@kernel.org> Acked-by: Oleg Nesterov <oleg@redhat.com> Cc: Roland McGrath <roland@redhat.com> Cc: Jan Kratochvil <jan.kratochvil@redhat.com>
2011-03-23 17:37:00 +08:00
spin_lock(&task->sighand->siglock);
/*
* If the task is already STOPPED, set GROUP_STOP_PENDING and
* TRAPPING, and kick it so that it transits to TRACED. TRAPPING
* will be cleared if the child completes the transition or any
* event which clears the group stop states happens. We'll wait
* for the transition to complete before returning from this
* function.
*
* This hides STOPPED -> RUNNING -> TRACED transition from the
* attaching thread but a different thread in the same group can
* still observe the transient RUNNING state. IOW, if another
* thread's WNOHANG wait(2) on the stopped tracee races against
* ATTACH, the wait(2) may fail due to the transient RUNNING.
*
* The following task_is_stopped() test is safe as both transitions
* in and out of STOPPED are protected by siglock.
*/
if (task_is_stopped(task)) {
task->group_stop |= GROUP_STOP_PENDING | GROUP_STOP_TRAPPING;
signal_wake_up(task, 1);
wait_trap = true;
}
spin_unlock(&task->sighand->siglock);
retval = 0;
unlock_tasklist:
write_unlock_irq(&tasklist_lock);
unlock_creds:
mutex_unlock(&task->signal->cred_guard_mutex);
out:
ptrace: Clean transitions between TASK_STOPPED and TRACED Currently, if the task is STOPPED on ptrace attach, it's left alone and the state is silently changed to TRACED on the next ptrace call. The behavior breaks the assumption that arch_ptrace_stop() is called before any task is poked by ptrace and is ugly in that a task manipulates the state of another task directly. With GROUP_STOP_PENDING, the transitions between TASK_STOPPED and TRACED can be made clean. The tracer can use the flag to tell the tracee to retry stop on attach and detach. On retry, the tracee will enter the desired state in the correct way. The lower 16bits of task->group_stop is used to remember the signal number which caused the last group stop. This is used while retrying for ptrace attach as the original group_exit_code could have been consumed with wait(2) by then. As the real parent may wait(2) and consume the group_exit_code anytime, the group_exit_code needs to be saved separately so that it can be used when switching from regular sleep to ptrace_stop(). This is recorded in the lower 16bits of task->group_stop. If a task is already stopped and there's no intervening SIGCONT, a ptrace request immediately following a successful PTRACE_ATTACH should always succeed even if the tracer doesn't wait(2) for attach completion; however, with this change, the tracee might still be TASK_RUNNING trying to enter TASK_TRACED which would cause the following request to fail with -ESRCH. This intermediate state is hidden from the ptracer by setting GROUP_STOP_TRAPPING on attach and making ptrace_check_attach() wait for it to clear on its signal->wait_chldexit. Completing the transition or getting killed clears TRAPPING and wakes up the tracer. Note that the STOPPED -> RUNNING -> TRACED transition is still visible to other threads which are in the same group as the ptracer and the reverse transition is visible to all. Please read the comments for details. Oleg: * Spotted a race condition where a task may retry group stop without proper bookkeeping. Fixed by redoing bookkeeping on retry. * Spotted that the transition is visible to userland in several different ways. Most are fixed with GROUP_STOP_TRAPPING. Unhandled corner case is documented. * Pointed out not setting GROUP_STOP_SIGMASK on an already stopped task would result in more consistent behavior. * Pointed out that calling ptrace_stop() from do_signal_stop() in TASK_STOPPED can race with group stop start logic and then confuse the TRAPPING wait in ptrace_check_attach(). ptrace_stop() is now called with TASK_RUNNING. * Suggested using signal->wait_chldexit instead of bit wait. * Spotted a race condition between TRACED transition and clearing of TRAPPING. Signed-off-by: Tejun Heo <tj@kernel.org> Acked-by: Oleg Nesterov <oleg@redhat.com> Cc: Roland McGrath <roland@redhat.com> Cc: Jan Kratochvil <jan.kratochvil@redhat.com>
2011-03-23 17:37:00 +08:00
if (wait_trap)
wait_event(current->signal->wait_chldexit,
!(task->group_stop & GROUP_STOP_TRAPPING));
return retval;
}
/**
* ptrace_traceme -- helper for PTRACE_TRACEME
*
* Performs checks and sets PT_PTRACED.
* Should be used by all ptrace implementations for PTRACE_TRACEME.
*/
static int ptrace_traceme(void)
{
int ret = -EPERM;
write_lock_irq(&tasklist_lock);
/* Are we already being traced? */
if (!current->ptrace) {
ret = security_ptrace_traceme(current->parent);
/*
* Check PF_EXITING to ensure ->real_parent has not passed
* exit_ptrace(). Otherwise we don't report the error but
* pretend ->real_parent untraces us right after return.
*/
if (!ret && !(current->real_parent->flags & PF_EXITING)) {
current->ptrace = PT_PTRACED;
__ptrace_link(current, current->real_parent);
}
}
write_unlock_irq(&tasklist_lock);
return ret;
}
/*
* Called with irqs disabled, returns true if childs should reap themselves.
*/
static int ignoring_children(struct sighand_struct *sigh)
{
int ret;
spin_lock(&sigh->siglock);
ret = (sigh->action[SIGCHLD-1].sa.sa_handler == SIG_IGN) ||
(sigh->action[SIGCHLD-1].sa.sa_flags & SA_NOCLDWAIT);
spin_unlock(&sigh->siglock);
return ret;
}
/*
* Called with tasklist_lock held for writing.
* Unlink a traced task, and clean it up if it was a traced zombie.
* Return true if it needs to be reaped with release_task().
* (We can't call release_task() here because we already hold tasklist_lock.)
*
* If it's a zombie, our attachedness prevented normal parent notification
* or self-reaping. Do notification now if it would have happened earlier.
* If it should reap itself, return true.
*
* If it's our own child, there is no notification to do. But if our normal
* children self-reap, then this child was prevented by ptrace and we must
* reap it now, in that case we must also wake up sub-threads sleeping in
* do_wait().
*/
static bool __ptrace_detach(struct task_struct *tracer, struct task_struct *p)
{
__ptrace_unlink(p);
if (p->exit_state == EXIT_ZOMBIE) {
if (!task_detached(p) && thread_group_empty(p)) {
if (!same_thread_group(p->real_parent, tracer))
do_notify_parent(p, p->exit_signal);
else if (ignoring_children(tracer->sighand)) {
__wake_up_parent(p, tracer);
p->exit_signal = -1;
}
}
if (task_detached(p)) {
/* Mark it as in the process of being reaped. */
p->exit_state = EXIT_DEAD;
return true;
}
}
return false;
}
static int ptrace_detach(struct task_struct *child, unsigned int data)
{
bool dead = false;
if (!valid_signal(data))
return -EIO;
/* Architecture-specific hardware disable .. */
ptrace_disable(child);
clear_tsk_thread_flag(child, TIF_SYSCALL_TRACE);
write_lock_irq(&tasklist_lock);
/*
* This child can be already killed. Make sure de_thread() or
* our sub-thread doing do_wait() didn't do release_task() yet.
*/
if (child->ptrace) {
child->exit_code = data;
dead = __ptrace_detach(current, child);
}
write_unlock_irq(&tasklist_lock);
if (unlikely(dead))
release_task(child);
return 0;
}
/*
* Detach all tasks we were using ptrace on. Called with tasklist held
* for writing, and returns with it held too. But note it can release
* and reacquire the lock.
*/
void exit_ptrace(struct task_struct *tracer)
__releases(&tasklist_lock)
__acquires(&tasklist_lock)
{
struct task_struct *p, *n;
LIST_HEAD(ptrace_dead);
if (likely(list_empty(&tracer->ptraced)))
return;
list_for_each_entry_safe(p, n, &tracer->ptraced, ptrace_entry) {
if (__ptrace_detach(tracer, p))
list_add(&p->ptrace_entry, &ptrace_dead);
}
write_unlock_irq(&tasklist_lock);
BUG_ON(!list_empty(&tracer->ptraced));
list_for_each_entry_safe(p, n, &ptrace_dead, ptrace_entry) {
list_del_init(&p->ptrace_entry);
release_task(p);
}
write_lock_irq(&tasklist_lock);
}
int ptrace_readdata(struct task_struct *tsk, unsigned long src, char __user *dst, int len)
{
int copied = 0;
while (len > 0) {
char buf[128];
int this_len, retval;
this_len = (len > sizeof(buf)) ? sizeof(buf) : len;
retval = access_process_vm(tsk, src, buf, this_len, 0);
if (!retval) {
if (copied)
break;
return -EIO;
}
if (copy_to_user(dst, buf, retval))
return -EFAULT;
copied += retval;
src += retval;
dst += retval;
len -= retval;
}
return copied;
}
int ptrace_writedata(struct task_struct *tsk, char __user *src, unsigned long dst, int len)
{
int copied = 0;
while (len > 0) {
char buf[128];
int this_len, retval;
this_len = (len > sizeof(buf)) ? sizeof(buf) : len;
if (copy_from_user(buf, src, this_len))
return -EFAULT;
retval = access_process_vm(tsk, dst, buf, this_len, 1);
if (!retval) {
if (copied)
break;
return -EIO;
}
copied += retval;
src += retval;
dst += retval;
len -= retval;
}
return copied;
}
static int ptrace_setoptions(struct task_struct *child, unsigned long data)
{
child->ptrace &= ~PT_TRACE_MASK;
if (data & PTRACE_O_TRACESYSGOOD)
child->ptrace |= PT_TRACESYSGOOD;
if (data & PTRACE_O_TRACEFORK)
child->ptrace |= PT_TRACE_FORK;
if (data & PTRACE_O_TRACEVFORK)
child->ptrace |= PT_TRACE_VFORK;
if (data & PTRACE_O_TRACECLONE)
child->ptrace |= PT_TRACE_CLONE;
if (data & PTRACE_O_TRACEEXEC)
child->ptrace |= PT_TRACE_EXEC;
if (data & PTRACE_O_TRACEVFORKDONE)
child->ptrace |= PT_TRACE_VFORK_DONE;
if (data & PTRACE_O_TRACEEXIT)
child->ptrace |= PT_TRACE_EXIT;
return (data & ~PTRACE_O_MASK) ? -EINVAL : 0;
}
static int ptrace_getsiginfo(struct task_struct *child, siginfo_t *info)
{
unsigned long flags;
int error = -ESRCH;
if (lock_task_sighand(child, &flags)) {
error = -EINVAL;
if (likely(child->last_siginfo != NULL)) {
*info = *child->last_siginfo;
error = 0;
}
unlock_task_sighand(child, &flags);
}
return error;
}
static int ptrace_setsiginfo(struct task_struct *child, const siginfo_t *info)
{
unsigned long flags;
int error = -ESRCH;
if (lock_task_sighand(child, &flags)) {
error = -EINVAL;
if (likely(child->last_siginfo != NULL)) {
*child->last_siginfo = *info;
error = 0;
}
unlock_task_sighand(child, &flags);
}
return error;
}
#ifdef PTRACE_SINGLESTEP
#define is_singlestep(request) ((request) == PTRACE_SINGLESTEP)
#else
#define is_singlestep(request) 0
#endif
#ifdef PTRACE_SINGLEBLOCK
#define is_singleblock(request) ((request) == PTRACE_SINGLEBLOCK)
#else
#define is_singleblock(request) 0
#endif
#ifdef PTRACE_SYSEMU
#define is_sysemu_singlestep(request) ((request) == PTRACE_SYSEMU_SINGLESTEP)
#else
#define is_sysemu_singlestep(request) 0
#endif
static int ptrace_resume(struct task_struct *child, long request,
unsigned long data)
{
if (!valid_signal(data))
return -EIO;
if (request == PTRACE_SYSCALL)
set_tsk_thread_flag(child, TIF_SYSCALL_TRACE);
else
clear_tsk_thread_flag(child, TIF_SYSCALL_TRACE);
#ifdef TIF_SYSCALL_EMU
if (request == PTRACE_SYSEMU || request == PTRACE_SYSEMU_SINGLESTEP)
set_tsk_thread_flag(child, TIF_SYSCALL_EMU);
else
clear_tsk_thread_flag(child, TIF_SYSCALL_EMU);
#endif
if (is_singleblock(request)) {
if (unlikely(!arch_has_block_step()))
return -EIO;
user_enable_block_step(child);
} else if (is_singlestep(request) || is_sysemu_singlestep(request)) {
if (unlikely(!arch_has_single_step()))
return -EIO;
user_enable_single_step(child);
} else {
user_disable_single_step(child);
}
child->exit_code = data;
ptrace: ptrace_resume() shouldn't wake up !TASK_TRACED thread It is not clear why ptrace_resume() does wake_up_process(). Unless the caller is PTRACE_KILL the tracee should be TASK_TRACED so we can use wake_up_state(__TASK_TRACED). If sys_ptrace() races with SIGKILL we do not need the extra and potentionally spurious wakeup. If the caller is PTRACE_KILL, wake_up_process() is even more wrong. The tracee can sleep in any state in any place, and if we have a buggy code which doesn't handle a spurious wakeup correctly PTRACE_KILL can be used to exploit it. For example: int main(void) { int child, status; child = fork(); if (!child) { int ret; assert(ptrace(PTRACE_TRACEME, 0,0,0) == 0); ret = pause(); printf("pause: %d %m\n", ret); return 0x23; } sleep(1); assert(ptrace(PTRACE_KILL, child, 0,0) == 0); assert(child == wait(&status)); printf("wait: %x\n", status); return 0; } prints "pause: -1 Unknown error 514", -ERESTARTNOHAND leaks to the userland. In this case sys_pause() is buggy as well and should be fixed. I do not know what was the original rationality behind PTRACE_KILL. The man page is simply wrong and afaics it was always wrong. Imho it should be deprecated, or may be it should do send_sig(SIGKILL) as Denys suggests, but in any case I do not think that the current behaviour was intentional. Note: there is another problem, ptrace_resume() changes ->exit_code and this can race with SIGKILL too. Eventually we should change ptrace to not use ->exit_code. Signed-off-by: Oleg Nesterov <oleg@redhat.com>
2011-05-26 01:20:21 +08:00
wake_up_state(child, __TASK_TRACED);
return 0;
}
#ifdef CONFIG_HAVE_ARCH_TRACEHOOK
static const struct user_regset *
find_regset(const struct user_regset_view *view, unsigned int type)
{
const struct user_regset *regset;
int n;
for (n = 0; n < view->n; ++n) {
regset = view->regsets + n;
if (regset->core_note_type == type)
return regset;
}
return NULL;
}
static int ptrace_regset(struct task_struct *task, int req, unsigned int type,
struct iovec *kiov)
{
const struct user_regset_view *view = task_user_regset_view(task);
const struct user_regset *regset = find_regset(view, type);
int regset_no;
if (!regset || (kiov->iov_len % regset->size) != 0)
return -EINVAL;
regset_no = regset - view->regsets;
kiov->iov_len = min(kiov->iov_len,
(__kernel_size_t) (regset->n * regset->size));
if (req == PTRACE_GETREGSET)
return copy_regset_to_user(task, view, regset_no, 0,
kiov->iov_len, kiov->iov_base);
else
return copy_regset_from_user(task, view, regset_no, 0,
kiov->iov_len, kiov->iov_base);
}
#endif
int ptrace_request(struct task_struct *child, long request,
unsigned long addr, unsigned long data)
{
int ret = -EIO;
siginfo_t siginfo;
void __user *datavp = (void __user *) data;
unsigned long __user *datalp = datavp;
switch (request) {
case PTRACE_PEEKTEXT:
case PTRACE_PEEKDATA:
return generic_ptrace_peekdata(child, addr, data);
case PTRACE_POKETEXT:
case PTRACE_POKEDATA:
return generic_ptrace_pokedata(child, addr, data);
#ifdef PTRACE_OLDSETOPTIONS
case PTRACE_OLDSETOPTIONS:
#endif
case PTRACE_SETOPTIONS:
ret = ptrace_setoptions(child, data);
break;
case PTRACE_GETEVENTMSG:
ret = put_user(child->ptrace_message, datalp);
break;
case PTRACE_GETSIGINFO:
ret = ptrace_getsiginfo(child, &siginfo);
if (!ret)
ret = copy_siginfo_to_user(datavp, &siginfo);
break;
case PTRACE_SETSIGINFO:
if (copy_from_user(&siginfo, datavp, sizeof siginfo))
ret = -EFAULT;
else
ret = ptrace_setsiginfo(child, &siginfo);
break;
case PTRACE_DETACH: /* detach a process that was attached. */
ret = ptrace_detach(child, data);
break;
#ifdef CONFIG_BINFMT_ELF_FDPIC
case PTRACE_GETFDPIC: {
struct mm_struct *mm = get_task_mm(child);
unsigned long tmp = 0;
ret = -ESRCH;
if (!mm)
break;
switch (addr) {
case PTRACE_GETFDPIC_EXEC:
tmp = mm->context.exec_fdpic_loadmap;
break;
case PTRACE_GETFDPIC_INTERP:
tmp = mm->context.interp_fdpic_loadmap;
break;
default:
break;
}
mmput(mm);
ret = put_user(tmp, datalp);
break;
}
#endif
#ifdef PTRACE_SINGLESTEP
case PTRACE_SINGLESTEP:
#endif
#ifdef PTRACE_SINGLEBLOCK
case PTRACE_SINGLEBLOCK:
#endif
#ifdef PTRACE_SYSEMU
case PTRACE_SYSEMU:
case PTRACE_SYSEMU_SINGLESTEP:
#endif
case PTRACE_SYSCALL:
case PTRACE_CONT:
return ptrace_resume(child, request, data);
case PTRACE_KILL:
if (child->exit_state) /* already dead */
return 0;
return ptrace_resume(child, request, SIGKILL);
#ifdef CONFIG_HAVE_ARCH_TRACEHOOK
case PTRACE_GETREGSET:
case PTRACE_SETREGSET:
{
struct iovec kiov;
struct iovec __user *uiov = datavp;
if (!access_ok(VERIFY_WRITE, uiov, sizeof(*uiov)))
return -EFAULT;
if (__get_user(kiov.iov_base, &uiov->iov_base) ||
__get_user(kiov.iov_len, &uiov->iov_len))
return -EFAULT;
ret = ptrace_regset(child, request, addr, &kiov);
if (!ret)
ret = __put_user(kiov.iov_len, &uiov->iov_len);
break;
}
#endif
default:
break;
}
return ret;
}
static struct task_struct *ptrace_get_task_struct(pid_t pid)
{
struct task_struct *child;
rcu_read_lock();
child = find_task_by_vpid(pid);
if (child)
get_task_struct(child);
rcu_read_unlock();
if (!child)
return ERR_PTR(-ESRCH);
return child;
}
#ifndef arch_ptrace_attach
#define arch_ptrace_attach(child) do { } while (0)
#endif
SYSCALL_DEFINE4(ptrace, long, request, long, pid, unsigned long, addr,
unsigned long, data)
{
struct task_struct *child;
long ret;
if (request == PTRACE_TRACEME) {
ret = ptrace_traceme();
if (!ret)
arch_ptrace_attach(current);
goto out;
}
child = ptrace_get_task_struct(pid);
if (IS_ERR(child)) {
ret = PTR_ERR(child);
goto out;
}
if (request == PTRACE_ATTACH) {
ret = ptrace_attach(child);
/*
* Some architectures need to do book-keeping after
* a ptrace attach.
*/
if (!ret)
arch_ptrace_attach(child);
goto out_put_task_struct;
}
ret = ptrace_check_attach(child, request == PTRACE_KILL);
if (ret < 0)
goto out_put_task_struct;
ret = arch_ptrace(child, request, addr, data);
out_put_task_struct:
put_task_struct(child);
out:
return ret;
}
int generic_ptrace_peekdata(struct task_struct *tsk, unsigned long addr,
unsigned long data)
{
unsigned long tmp;
int copied;
copied = access_process_vm(tsk, addr, &tmp, sizeof(tmp), 0);
if (copied != sizeof(tmp))
return -EIO;
return put_user(tmp, (unsigned long __user *)data);
}
int generic_ptrace_pokedata(struct task_struct *tsk, unsigned long addr,
unsigned long data)
{
int copied;
copied = access_process_vm(tsk, addr, &data, sizeof(data), 1);
return (copied == sizeof(data)) ? 0 : -EIO;
}
#if defined CONFIG_COMPAT
#include <linux/compat.h>
int compat_ptrace_request(struct task_struct *child, compat_long_t request,
compat_ulong_t addr, compat_ulong_t data)
{
compat_ulong_t __user *datap = compat_ptr(data);
compat_ulong_t word;
siginfo_t siginfo;
int ret;
switch (request) {
case PTRACE_PEEKTEXT:
case PTRACE_PEEKDATA:
ret = access_process_vm(child, addr, &word, sizeof(word), 0);
if (ret != sizeof(word))
ret = -EIO;
else
ret = put_user(word, datap);
break;
case PTRACE_POKETEXT:
case PTRACE_POKEDATA:
ret = access_process_vm(child, addr, &data, sizeof(data), 1);
ret = (ret != sizeof(data) ? -EIO : 0);
break;
case PTRACE_GETEVENTMSG:
ret = put_user((compat_ulong_t) child->ptrace_message, datap);
break;
case PTRACE_GETSIGINFO:
ret = ptrace_getsiginfo(child, &siginfo);
if (!ret)
ret = copy_siginfo_to_user32(
(struct compat_siginfo __user *) datap,
&siginfo);
break;
case PTRACE_SETSIGINFO:
memset(&siginfo, 0, sizeof siginfo);
if (copy_siginfo_from_user32(
&siginfo, (struct compat_siginfo __user *) datap))
ret = -EFAULT;
else
ret = ptrace_setsiginfo(child, &siginfo);
break;
#ifdef CONFIG_HAVE_ARCH_TRACEHOOK
case PTRACE_GETREGSET:
case PTRACE_SETREGSET:
{
struct iovec kiov;
struct compat_iovec __user *uiov =
(struct compat_iovec __user *) datap;
compat_uptr_t ptr;
compat_size_t len;
if (!access_ok(VERIFY_WRITE, uiov, sizeof(*uiov)))
return -EFAULT;
if (__get_user(ptr, &uiov->iov_base) ||
__get_user(len, &uiov->iov_len))
return -EFAULT;
kiov.iov_base = compat_ptr(ptr);
kiov.iov_len = len;
ret = ptrace_regset(child, request, addr, &kiov);
if (!ret)
ret = __put_user(kiov.iov_len, &uiov->iov_len);
break;
}
#endif
default:
ret = ptrace_request(child, request, addr, data);
}
return ret;
}
asmlinkage long compat_sys_ptrace(compat_long_t request, compat_long_t pid,
compat_long_t addr, compat_long_t data)
{
struct task_struct *child;
long ret;
if (request == PTRACE_TRACEME) {
ret = ptrace_traceme();
goto out;
}
child = ptrace_get_task_struct(pid);
if (IS_ERR(child)) {
ret = PTR_ERR(child);
goto out;
}
if (request == PTRACE_ATTACH) {
ret = ptrace_attach(child);
/*
* Some architectures need to do book-keeping after
* a ptrace attach.
*/
if (!ret)
arch_ptrace_attach(child);
goto out_put_task_struct;
}
ret = ptrace_check_attach(child, request == PTRACE_KILL);
if (!ret)
ret = compat_arch_ptrace(child, request, addr, data);
out_put_task_struct:
put_task_struct(child);
out:
return ret;
}
#endif /* CONFIG_COMPAT */
#ifdef CONFIG_HAVE_HW_BREAKPOINT
int ptrace_get_breakpoints(struct task_struct *tsk)
{
if (atomic_inc_not_zero(&tsk->ptrace_bp_refcnt))
return 0;
return -1;
}
void ptrace_put_breakpoints(struct task_struct *tsk)
{
if (atomic_dec_and_test(&tsk->ptrace_bp_refcnt))
flush_ptrace_hw_breakpoint(tsk);
}
#endif /* CONFIG_HAVE_HW_BREAKPOINT */