coredump: Limit coredumps to a single thread group

Today when a signal is delivered with a handler of SIG_DFL whose
default behavior is to generate a core dump not only that process but
every process that shares the mm is killed.

In the case of vfork this looks like a real world problem.  Consider
the following well defined sequence.

	if (vfork() == 0) {
		execve(...);
		_exit(EXIT_FAILURE);
	}

If a signal that generates a core dump is received after vfork but
before the execve changes the mm the process that called vfork will
also be killed (as the mm is shared).

Similarly if the execve fails after the point of no return the kernel
delivers SIGSEGV which will kill both the exec'ing process and because
the mm is shared the process that called vfork as well.

As far as I can tell this behavior is a violation of people's
reasonable expectations, POSIX, and is unnecessarily fragile when the
system is low on memory.

Solve this by making a userspace visible change to only kill a single
process/thread group.  This is possible because Jann Horn recently
modified[1] the coredump code so that the mm can safely be modified
while the coredump is happening.  With LinuxThreads long gone I don't
expect anyone to have a notice this behavior change in practice.

To accomplish this move the core_state pointer from mm_struct to
signal_struct, which allows different thread groups to coredump
simultatenously.

In zap_threads remove the work to kill anything except for the current
thread group.

v2: Remove core_state from the VM_BUG_ON_MM print to fix
    compile failure when CONFIG_DEBUG_VM is enabled.
    Reported-by: Stephen Rothwell <sfr@canb.auug.org.au>

[1] a07279c9a8cd ("binfmt_elf, binfmt_elf_fdpic: use a VMA list snapshot")
Fixes: d89f3847def4 ("[PATCH] thread-aware coredumps, 2.5.43-C3")
History-tree: git://git.kernel.org/pub/scm/linux/kernel/git/tglx/history.git
Link: https://lkml.kernel.org/r/87y27mvnke.fsf@disp2133
Link: https://lkml.kernel.org/r/20211007144701.67592574@canb.auug.org.au
Reviewed-by: Kees Cook <keescook@chromium.org>
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>

2 files changed, 13 insertions, 13 deletions

diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 7f8ee09c711f..1039f6ae922c 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -387,17 +387,6 @@ struct vm_area_struct {
 	struct vm_userfaultfd_ctx vm_userfaultfd_ctx;
 } __randomize_layout;
 
-struct core_thread {
-	struct task_struct *task;
-	struct core_thread *next;
-};
-
-struct core_state {
-	atomic_t nr_threads;
-	struct core_thread dumper;
-	struct completion startup;
-};
-
 struct kioctx_table;
 struct mm_struct {
 	struct {
@@ -518,8 +507,6 @@ struct mm_struct {
 
 		unsigned long flags; /* Must use atomic bitops to access */
 
-		struct core_state *core_state; /* coredumping support */
-
 #ifdef CONFIG_AIO
 		spinlock_t			ioctx_lock;
 		struct kioctx_table __rcu	*ioctx_table;
diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h
index e5f4ce622ee6..a8fe2a593a3a 100644
--- a/include/linux/sched/signal.h
+++ b/include/linux/sched/signal.h
@@ -72,6 +72,17 @@ struct multiprocess_signals {
 	struct hlist_node node;
 };
 
+struct core_thread {
+	struct task_struct *task;
+	struct core_thread *next;
+};
+
+struct core_state {
+	atomic_t nr_threads;
+	struct core_thread dumper;
+	struct completion startup;
+};
+
 /*
  * NOTE! "signal_struct" does not have its own
  * locking, because a shared signal_struct always
@@ -110,6 +121,8 @@ struct signal_struct {
 	int			group_stop_count;
 	unsigned int		flags; /* see SIGNAL_* flags below */
 
+	struct core_state *core_state; /* coredumping support */
+
 	/*
 	 * PR_SET_CHILD_SUBREAPER marks a process, like a service
 	 * manager, to re-parent orphan (double-forking) child processes