From 6cd8f0acae3420afce37bf51a9ff8c2c20342af5 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Tue, 30 Apr 2013 15:28:12 -0700 Subject: coredump: ensure that SIGKILL always kills the dumping thread prepare_signal() blesses SIGKILL sent to the dumping process but this signal can be "lost" anyway. The problems is, complete_signal() sees SIGNAL_GROUP_EXIT and skips the "kill them all" logic. And even if the dumping process is single-threaded (so the target is always "correct"), the group-wide SIGKILL is not recorded in task->pending and thus __fatal_signal_pending() won't be true. A multi-threaded case has even more problems. And even ignoring all technical details, SIGNAL_GROUP_EXIT doesn't look right to me. This coredumping process is not exiting yet, it can do a lot of work dumping the core. With this patch the dumping process doesn't have SIGNAL_GROUP_EXIT, we set signal->group_exit_task instead. This makes signal_group_exit() true and thus this should equally close the races with exit/exec/stop but allows to kill the dumping thread reliably. Notes: - It is not clear what should we do with ->group_exit_code if the dumper was killed, see the next change. - we need more (hopefully straightforward) changes to ensure that SIGKILL actually interrupts the coredump. Basically we need to check __fatal_signal_pending() in dump_write() and dump_seek(). Signed-off-by: Oleg Nesterov Tested-by: Mandeep Singh Baines Cc: Ingo Molnar Cc: Neil Horman Cc: "Rafael J. Wysocki" Cc: Roland McGrath Cc: Tejun Heo Cc: Al Viro Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds diff --git a/fs/coredump.c b/fs/coredump.c index f91cfd8..6fea590 100644 --- a/fs/coredump.c +++ b/fs/coredump.c @@ -263,7 +263,6 @@ static int zap_process(struct task_struct *start, int exit_code) struct task_struct *t; int nr = 0; - start->signal->flags = SIGNAL_GROUP_EXIT; start->signal->group_exit_code = exit_code; start->signal->group_stop_count = 0; @@ -291,8 +290,9 @@ static int zap_threads(struct task_struct *tsk, struct mm_struct *mm, if (!signal_group_exit(tsk->signal)) { mm->core_state = core_state; nr = zap_process(tsk, exit_code); + tsk->signal->group_exit_task = tsk; /* ignore all signals except SIGKILL, see prepare_signal() */ - tsk->signal->flags |= SIGNAL_GROUP_COREDUMP; + tsk->signal->flags = SIGNAL_GROUP_COREDUMP; clear_tsk_thread_flag(tsk, TIF_SIGPENDING); } spin_unlock_irq(&tsk->sighand->siglock); @@ -343,6 +343,7 @@ static int zap_threads(struct task_struct *tsk, struct mm_struct *mm, if (unlikely(p->mm == mm)) { lock_task_sighand(p, &flags); nr += zap_process(p, exit_code); + p->signal->flags = SIGNAL_GROUP_EXIT; unlock_task_sighand(p, &flags); } break; @@ -394,6 +395,11 @@ static void coredump_finish(struct mm_struct *mm) struct core_thread *curr, *next; struct task_struct *task; + spin_lock_irq(¤t->sighand->siglock); + current->signal->group_exit_task = NULL; + current->signal->flags = SIGNAL_GROUP_EXIT; + spin_unlock_irq(¤t->sighand->siglock); + next = mm->core_state->dumper.next; while ((curr = next) != NULL) { next = curr->next; -- cgit v0.10.2