coredump: only SIGKILL should interrupt the coredumping task

There are 2 well known and ancient problems with coredump/signals, and a
lot of related bug reports:

- do_coredump() clears TIF_SIGPENDING but of course this can't help
  if, say, SIGCHLD comes after that.

  In this case the coredump can fail unexpectedly. See for example
  wait_for_dump_helper()->signal_pending() check but there are other
  reasons.

- At the same time, dumping a huge core on the slow media can take a
  lot of time/resources and there is no way to kill the coredumping
  task reliably. In particular this is not oom_kill-friendly.

This patch tries to fix the 1st problem, and makes the preparation for the
next changes.

We add the new SIGNAL_GROUP_COREDUMP flag set by zap_threads() to indicate
that this process dumps the core.  prepare_signal() checks this flag and
nacks any signal except SIGKILL.

Note that this check tries to be conservative, in the long term we should
probably treat the SIGNAL_GROUP_EXIT case equally but this needs more
discussion.  See marc.info/?l=linux-kernel&m=120508897917439

Notes:
	- recalc_sigpending() doesn't check SIGNAL_GROUP_COREDUMP.
	  The patch assumes that dump_write/etc paths should never
	  call it, but we can change it as well.

	- There is another source of TIF_SIGPENDING, freezer. This
	  will be addressed separately.

Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Tested-by: Mandeep Singh Baines <msb@chromium.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Neil Horman <nhorman@redhat.com>
Cc: "Rafael J. Wysocki" <rjw@sisk.pl>
Cc: Roland McGrath <roland@hack.frob.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/fs/coredump.c b/fs/coredump.c
index d52f6bd5ad8e39ec67f8dda1922e47acaa679697..f91cfd8cd5f2ec83284dac73eacd5b71d8449fd1 100644 (file)
--- a/fs/coredump.c
+++ b/fs/coredump.c
@@ -280,8 +280,8 @@ static int zap_process(struct task_struct *start, int exit_code)
        return nr;
 }
 
-static inline int zap_threads(struct task_struct *tsk, struct mm_struct *mm,
-                               struct core_state *core_state, int exit_code)
+static int zap_threads(struct task_struct *tsk, struct mm_struct *mm,
+                       struct core_state *core_state, int exit_code)
 {
        struct task_struct *g, *p;
        unsigned long flags;
@@ -291,6 +291,9 @@ static inline 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);
+               /* ignore all signals except SIGKILL, see prepare_signal() */
+               tsk->signal->flags |= SIGNAL_GROUP_COREDUMP;
+               clear_tsk_thread_flag(tsk, TIF_SIGPENDING);
        }
        spin_unlock_irq(&tsk->sighand->siglock);
        if (unlikely(nr < 0))
@@ -514,12 +517,6 @@ void do_coredump(siginfo_t *siginfo)
 
        old_cred = override_creds(cred);
 
-       /*
-        * Clear any false indication of pending signals that might
-        * be seen by the filesystem code called to write the core file.
-        */
-       clear_thread_flag(TIF_SIGPENDING);
-
        ispipe = format_corename(&cn, &cprm);
 
        if (ispipe) {

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 54ddcb82cddfd025073f98f923490a60c9c72aaa..a22baf83c20c17bbeedf9597379da02e44c9ccb3 100644 (file)
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -626,6 +626,7 @@ struct signal_struct {
 #define SIGNAL_STOP_STOPPED    0x00000001 /* job control stop in effect */
 #define SIGNAL_STOP_CONTINUED  0x00000002 /* SIGCONT since WCONTINUED reap */
 #define SIGNAL_GROUP_EXIT      0x00000004 /* group exit in progress */
+#define SIGNAL_GROUP_COREDUMP  0x00000008 /* coredump in progress */
 /*
  * Pending notifications to parent.
  */

diff --git a/kernel/signal.c b/kernel/signal.c
index 27ece019bd0a6d4e3dddb275cab0662447766daf..cede58910f9c6629304cdddce66e0edf42a40148 100644 (file)
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -854,12 +854,14 @@ static void ptrace_trap_notify(struct task_struct *t)
  * Returns true if the signal should be actually delivered, otherwise
  * it should be dropped.
  */
-static int prepare_signal(int sig, struct task_struct *p, bool force)
+static bool prepare_signal(int sig, struct task_struct *p, bool force)
 {
        struct signal_struct *signal = p->signal;
        struct task_struct *t;
 
-       if (unlikely(signal->flags & SIGNAL_GROUP_EXIT)) {
+       if (signal->flags & (SIGNAL_GROUP_EXIT | SIGNAL_GROUP_COREDUMP)) {
+               if (signal->flags & SIGNAL_GROUP_COREDUMP)
+                       return sig == SIGKILL;
                /*
                 * The process is in the middle of dying, nothing to do.
                 */