coredump: construct the list of coredumping threads at startup time

binfmt->core_dump() has to iterate over the all threads in system in order
to find the coredumping threads and construct the list using the
GFP_ATOMIC allocations.

With this patch each thread allocates the list node on exit_mm()'s stack and
adds itself to the list.

This allows us to do further changes:

	- simplify ->core_dump()

	- change exit_mm() to clear ->mm first, then wait for ->core_done.
	  this makes the coredumping process visible to oom_kill

	- kill mm->core_done

Signed-off-by: Oleg Nesterov <oleg@tv-sign.ru>
Acked-by: Roland McGrath <roland@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

3 files changed, 20 insertions, 3 deletions

diff --git a/fs/exec.c b/fs/exec.c
index b8ee842d93cd..fe2873b8037f 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -1604,6 +1604,8 @@ static int coredump_wait(int exit_code, struct core_state *core_state)
 
         init_completion(&mm->core_done);
         init_completion(&core_state->startup);
+        core_state->dumper.task = tsk;
+        core_state->dumper.next = NULL;
         core_waiters = zap_threads(tsk, mm, core_state, exit_code);
         up_write(&mm->mmap_sem);
 
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index ae99a28ba6ae..4d0d0abc79fe 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -159,8 +159,14 @@ struct vm_area_struct {
 #endif
 };
 
+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;
 };
 
diff --git a/kernel/exit.c b/kernel/exit.c
index 63d82957baae..b66f0d55c791 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -664,6 +664,7 @@ assign_new_owner:
 static void exit_mm(struct task_struct * tsk)
 {
         struct mm_struct *mm = tsk->mm;
+        struct core_state *core_state;
 
         mm_release(tsk, mm);
         if (!mm)
@@ -676,11 +677,19 @@ static void exit_mm(struct task_struct * tsk)
          * group with ->mm != NULL.
          */
         down_read(&mm->mmap_sem);
-        if (mm->core_state) {
+        core_state = mm->core_state;
+        if (core_state) {
+                struct core_thread self;
                 up_read(&mm->mmap_sem);
 
-                if (atomic_dec_and_test(&mm->core_state->nr_threads))
-                        complete(&mm->core_state->startup);
+                self.task = tsk;
+                self.next = xchg(&core_state->dumper.next, &self);
+                /*
+                 * Implies mb(), the result of xchg() must be visible
+                 * to core_state->dumper.
+                 */
+                if (atomic_dec_and_test(&core_state->nr_threads))
+                        complete(&core_state->startup);
 
                 wait_for_completion(&mm->core_done);
                 down_read(&mm->mmap_sem);