From a8f072c1d624a627b67f2ace2f0c25d856ef4e54 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 2 Jun 2011 11:13:59 +0200 Subject: job control: rename signal->group_stop and flags to jobctl and update them signal->group_stop currently hosts mostly group stop related flags; however, it's gonna be used for wider purposes and the GROUP_STOP_ flag prefix becomes confusing. Rename signal->group_stop to signal->jobctl and rename all GROUP_STOP_* flags to JOBCTL_*. Bit position macros JOBCTL_*_BIT are defined and JOBCTL_* flags are defined in terms of them to allow using bitops later. While at it, reassign JOBCTL_TRAPPING to bit 22 to better accomodate future additions. This doesn't cause any functional change. -v2: JOBCTL_*_BIT macros added as suggested by Linus. Signed-off-by: Tejun Heo Cc: Linus Torvalds Signed-off-by: Oleg Nesterov --- fs/exec.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'fs') diff --git a/fs/exec.c b/fs/exec.c index ea5f748906a..8986bb0f9dc 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -1772,7 +1772,7 @@ static int zap_process(struct task_struct *start, int exit_code) t = start; do { - task_clear_group_stop_pending(t); + task_clear_jobctl_stop_pending(t); if (t != current && t->mm) { sigaddset(&t->pending.signal, SIGKILL); signal_wake_up(t, 1); -- cgit v1.2.3-18-g5258 From 3759a0d94c18764247b66511d1038f2b93aa95de Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 2 Jun 2011 11:14:00 +0200 Subject: job control: introduce JOBCTL_PENDING_MASK and task_clear_jobctl_pending() This patch introduces JOBCTL_PENDING_MASK and replaces task_clear_jobctl_stop_pending() with task_clear_jobctl_pending() which takes an extra @mask argument. JOBCTL_PENDING_MASK is currently equal to JOBCTL_STOP_PENDING but future patches will add more bits. recalc_sigpending_tsk() is updated to use JOBCTL_PENDING_MASK instead. task_clear_jobctl_pending() takes @mask which in subset of JOBCTL_PENDING_MASK and clears the relevant jobctl bits. If JOBCTL_STOP_PENDING is set, other STOP bits are cleared together. All task_clear_jobctl_stop_pending() users are updated to call task_clear_jobctl_pending() with JOBCTL_STOP_PENDING which is functionally identical to task_clear_jobctl_stop_pending(). This patch doesn't cause any functional change. Signed-off-by: Tejun Heo Signed-off-by: Oleg Nesterov --- fs/exec.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'fs') diff --git a/fs/exec.c b/fs/exec.c index 8986bb0f9dc..4402105287c 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -1772,7 +1772,7 @@ static int zap_process(struct task_struct *start, int exit_code) t = start; do { - task_clear_jobctl_stop_pending(t); + task_clear_jobctl_pending(t, JOBCTL_STOP_PENDING); if (t != current && t->mm) { sigaddset(&t->pending.signal, SIGKILL); signal_wake_up(t, 1); -- cgit v1.2.3-18-g5258 From 6dfca32984237a8a011b5bf367e53341a265b2a4 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 2 Jun 2011 11:14:00 +0200 Subject: job control: make task_clear_jobctl_pending() clear TRAPPING automatically JOBCTL_TRAPPING indicates that ptracer is waiting for tracee to (re)transit into TRACED. task_clear_jobctl_pending() must be called when either tracee enters TRACED or the transition is cancelled for some reason. The former is achieved by explicitly calling task_clear_jobctl_pending() in ptrace_stop() and the latter by calling it at the end of do_signal_stop(). Calling task_clear_jobctl_trapping() at the end of do_signal_stop() limits the scope TRAPPING can be used and is fragile in that seemingly unrelated changes to tracee's control flow can lead to stuck TRAPPING. We already have task_clear_jobctl_pending() calls on those cancelling events to clear JOBCTL_STOP_PENDING. Cancellations can be handled by making those call sites use JOBCTL_PENDING_MASK instead and updating task_clear_jobctl_pending() such that task_clear_jobctl_trapping() is called automatically if no stop/trap is pending. This patch makes the above changes and removes the fallback task_clear_jobctl_trapping() call from do_signal_stop(). Signed-off-by: Tejun Heo Signed-off-by: Oleg Nesterov --- fs/exec.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'fs') diff --git a/fs/exec.c b/fs/exec.c index 4402105287c..a9f2b3631bd 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -1772,7 +1772,7 @@ static int zap_process(struct task_struct *start, int exit_code) t = start; do { - task_clear_jobctl_pending(t, JOBCTL_STOP_PENDING); + task_clear_jobctl_pending(t, JOBCTL_PENDING_MASK); if (t != current && t->mm) { sigaddset(&t->pending.signal, SIGKILL); signal_wake_up(t, 1); -- cgit v1.2.3-18-g5258 From a288eecce5253cc1565d400a52b9b476a157e040 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Fri, 17 Jun 2011 16:50:37 +0200 Subject: ptrace: kill trivial tracehooks At this point, tracehooks aren't useful to mainline kernel and mostly just add an extra layer of obfuscation. Although they have comments, without actual in-kernel users, it is difficult to tell what are their assumptions and they're actually trying to achieve. To mainline kernel, they just aren't worth keeping around. This patch kills the following trivial tracehooks. * Ones testing whether task is ptraced. Replace with ->ptrace test. tracehook_expect_breakpoints() tracehook_consider_ignored_signal() tracehook_consider_fatal_signal() * ptrace_event() wrappers. Call directly. tracehook_report_exec() tracehook_report_exit() tracehook_report_vfork_done() * ptrace_release_task() wrapper. Call directly. tracehook_finish_release_task() * noop tracehook_prepare_release_task() tracehook_report_death() This doesn't introduce any behavior change. Signed-off-by: Tejun Heo Cc: Christoph Hellwig Cc: Martin Schwidefsky Signed-off-by: Oleg Nesterov --- fs/exec.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'fs') diff --git a/fs/exec.c b/fs/exec.c index a9f2b3631bd..b37030d0a50 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -1384,7 +1384,7 @@ int search_binary_handler(struct linux_binprm *bprm,struct pt_regs *regs) bprm->recursion_depth = depth; if (retval >= 0) { if (depth == 0) - tracehook_report_exec(fmt, bprm, regs); + ptrace_event(PTRACE_EVENT_EXEC, 0); put_binfmt(fmt); allow_write_access(bprm->file); if (bprm->file) -- cgit v1.2.3-18-g5258 From 4b9d33e6d83cc05a8005a8f9a8b9677fa0f53626 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Fri, 17 Jun 2011 16:50:38 +0200 Subject: ptrace: kill clone/exec tracehooks At this point, tracehooks aren't useful to mainline kernel and mostly just add an extra layer of obfuscation. Although they have comments, without actual in-kernel users, it is difficult to tell what are their assumptions and they're actually trying to achieve. To mainline kernel, they just aren't worth keeping around. This patch kills the following clone and exec related tracehooks. tracehook_prepare_clone() tracehook_finish_clone() tracehook_report_clone() tracehook_report_clone_complete() tracehook_unsafe_exec() The changes are mostly trivial - logic is moved to the caller and comments are merged and adjusted appropriately. The only exception is in check_unsafe_exec() where LSM_UNSAFE_PTRACE* are OR'd to bprm->unsafe instead of setting it, which produces the same result as the field is always zero on entry. It also tests p->ptrace instead of (p->ptrace & PT_PTRACED) for consistency, which also gives the same result. This doesn't introduce any behavior change. Signed-off-by: Tejun Heo Cc: Christoph Hellwig Signed-off-by: Oleg Nesterov --- fs/exec.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'fs') diff --git a/fs/exec.c b/fs/exec.c index b37030d0a50..8dca45b0dae 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -1224,7 +1224,12 @@ int check_unsafe_exec(struct linux_binprm *bprm) unsigned n_fs; int res = 0; - bprm->unsafe = tracehook_unsafe_exec(p); + if (p->ptrace) { + if (p->ptrace & PT_PTRACE_CAP) + bprm->unsafe |= LSM_UNSAFE_PTRACE_CAP; + else + bprm->unsafe |= LSM_UNSAFE_PTRACE; + } n_fs = 1; spin_lock(&p->fs->lock); -- cgit v1.2.3-18-g5258 From 06d984737bac0545fe20bb5447ee488b95adb531 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Fri, 17 Jun 2011 16:50:40 +0200 Subject: ptrace: s/tracehook_tracer_task()/ptrace_parent()/ tracehook.h is on the way out. Rename tracehook_tracer_task() to ptrace_parent() and move it from tracehook.h to ptrace.h. Signed-off-by: Tejun Heo Cc: Christoph Hellwig Cc: John Johansen Cc: Stephen Smalley Signed-off-by: Oleg Nesterov --- fs/proc/array.c | 2 +- fs/proc/base.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'fs') diff --git a/fs/proc/array.c b/fs/proc/array.c index 9b45ee84fbc..3a1dafd228d 100644 --- a/fs/proc/array.c +++ b/fs/proc/array.c @@ -172,7 +172,7 @@ static inline void task_state(struct seq_file *m, struct pid_namespace *ns, task_tgid_nr_ns(rcu_dereference(p->real_parent), ns) : 0; tpid = 0; if (pid_alive(p)) { - struct task_struct *tracer = tracehook_tracer_task(p); + struct task_struct *tracer = ptrace_parent(p); if (tracer) tpid = task_pid_nr_ns(tracer, ns); } diff --git a/fs/proc/base.c b/fs/proc/base.c index 14def991d9d..c883dad74b9 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -216,7 +216,7 @@ static struct mm_struct *__check_mem_permission(struct task_struct *task) if (task_is_stopped_or_traced(task)) { int match; rcu_read_lock(); - match = (tracehook_tracer_task(task) == current); + match = (ptrace_parent(task) == current); rcu_read_unlock(); if (match && ptrace_may_access(task, PTRACE_MODE_ATTACH)) return mm; -- cgit v1.2.3-18-g5258 From 087806b1281563e4ae7a5bce3155f894af5f4118 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Wed, 22 Jun 2011 23:10:26 +0200 Subject: redefine thread_group_leader() as exit_signal >= 0 Change de_thread() to set old_leader->exit_signal = -1. This is good for the consistency, it is no longer the leader and all sub-threads have exit_signal = -1 set by copy_process(CLONE_THREAD). And this allows us to micro-optimize thread_group_leader(), it can simply check exit_signal >= 0. This also makes sense because we should move ->group_leader from task_struct to signal_struct. Signed-off-by: Oleg Nesterov Reviewed-by: Tejun Heo --- fs/exec.c | 1 + 1 file changed, 1 insertion(+) (limited to 'fs') diff --git a/fs/exec.c b/fs/exec.c index 8dca45b0dae..c3d517bfdd2 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -963,6 +963,7 @@ static int de_thread(struct task_struct *tsk) leader->group_leader = tsk; tsk->exit_signal = SIGCHLD; + leader->exit_signal = -1; BUG_ON(leader->exit_state != EXIT_ZOMBIE); leader->exit_state = EXIT_DEAD; -- cgit v1.2.3-18-g5258 From bb188d7e64deb0e9cf13a99f44ae0065de5352d6 Mon Sep 17 00:00:00 2001 From: Denys Vlasenko Date: Wed, 29 Jun 2011 04:13:39 +0200 Subject: ptrace: make former thread ID available via PTRACE_GETEVENTMSG after PTRACE_EVENT_EXEC stop When multithreaded program execs under ptrace, all traced threads report WIFEXITED status, except for thread group leader and the thread which execs. Unless tracer tracks thread group relationship between tracees, which is a nontrivial task, it will not detect that execed thread no longer exists. This patch allows tracer to figure out which thread performed this exec, by requesting PTRACE_GETEVENTMSG in PTRACE_EVENT_EXEC stop. Another, samller problem which is solved by this patch is that tracer now can figure out which of the several concurrent execs in multithreaded program succeeded. Signed-off-by: Denys Vlasenko Signed-off-by: Oleg Nesterov --- fs/exec.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) (limited to 'fs') diff --git a/fs/exec.c b/fs/exec.c index c3d517bfdd2..b08367abf30 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -1358,6 +1358,7 @@ int search_binary_handler(struct linux_binprm *bprm,struct pt_regs *regs) unsigned int depth = bprm->recursion_depth; int try,retval; struct linux_binfmt *fmt; + pid_t old_pid; retval = security_bprm_check(bprm); if (retval) @@ -1371,6 +1372,11 @@ int search_binary_handler(struct linux_binprm *bprm,struct pt_regs *regs) if (retval) return retval; + /* Need to fetch pid before load_binary changes it */ + rcu_read_lock(); + old_pid = task_pid_nr_ns(current, task_active_pid_ns(current->parent)); + rcu_read_unlock(); + retval = -ENOENT; for (try=0; try<2; try++) { read_lock(&binfmt_lock); @@ -1390,7 +1396,8 @@ int search_binary_handler(struct linux_binprm *bprm,struct pt_regs *regs) bprm->recursion_depth = depth; if (retval >= 0) { if (depth == 0) - ptrace_event(PTRACE_EVENT_EXEC, 0); + ptrace_event(PTRACE_EVENT_EXEC, + old_pid); put_binfmt(fmt); allow_write_access(bprm->file); if (bprm->file) -- cgit v1.2.3-18-g5258 From eac1b5e57d7abc836e78fd3fbcf77dbeed01edc9 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Thu, 21 Jul 2011 20:00:43 +0200 Subject: ptrace: do_wait(traced_leader_killed_by_mt_exec) can block forever Test-case: void *tfunc(void *arg) { execvp("true", NULL); return NULL; } int main(void) { int pid; if (fork()) { pthread_t t; kill(getpid(), SIGSTOP); pthread_create(&t, NULL, tfunc, NULL); for (;;) pause(); } pid = getppid(); assert(ptrace(PTRACE_ATTACH, pid, 0,0) == 0); while (wait(NULL) > 0) ptrace(PTRACE_CONT, pid, 0,0); return 0; } It is racy, exit_notify() does __wake_up_parent() too. But in the likely case it triggers the problem: de_thread() does release_task() and the old leader goes away without the notification, the tracer sleeps in do_wait() without children/tracees. Change de_thread() to do __wake_up_parent(traced_leader->parent). Since it is already EXIT_DEAD we can do this without ptrace_unlink(), EXIT_DEAD threads do not exist from do_wait's pov. Signed-off-by: Oleg Nesterov Acked-by: Tejun Heo --- fs/exec.c | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'fs') diff --git a/fs/exec.c b/fs/exec.c index b08367abf30..d219541db06 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -967,6 +967,14 @@ static int de_thread(struct task_struct *tsk) BUG_ON(leader->exit_state != EXIT_ZOMBIE); leader->exit_state = EXIT_DEAD; + + /* + * We are going to release_task()->ptrace_unlink() silently, + * the tracer can sleep in do_wait(). EXIT_DEAD guarantees + * the tracer wont't block again waiting for this thread. + */ + if (unlikely(leader->ptrace)) + __wake_up_parent(leader, leader->parent); write_unlock_irq(&tasklist_lock); release_task(leader); -- cgit v1.2.3-18-g5258