Revert "mm: correctly synchronize rss-counters at exit/exec"

This reverts commit 40af1bbdca47e5c8a2044039bb78ca8fd8b20f94.

It's horribly and utterly broken for at least the following reasons:

 - calling sync_mm_rss() from mmput() is fundamentally wrong, because
   there's absolutely no reason to believe that the task that does the
   mmput() always does it on its own VM.  Example: fork, ptrace, /proc -
   you name it.

 - calling it *after* having done mmdrop() on it is doubly insane, since
   the mm struct may well be gone now.

 - testing mm against NULL before you call it is insane too, since a
NULL mm there would have caused oopses long before.

.. and those are just the three bugs I found before I decided to give up
looking for me and revert it asap.  I should have caught it before I
even took it, but I trusted Andrew too much.

Cc: Konstantin Khlebnikov <khlebnikov@openvz.org>
Cc: Markus Trippelsdorf <markus@trippelsdorf.de>
Cc: Hugh Dickins <hughd@google.com>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/fs/exec.c b/fs/exec.c
index b926ed19301e270c6717b3156118b5fcee87c22c..a79786a8d2c88d5b6c580859ef12496f43b4b0f4 100644 (file)
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -819,6 +819,7 @@ static int exec_mmap(struct mm_struct *mm)
        /* Notify parent that we're no longer interested in the old VM */
        tsk = current;
        old_mm = current->mm;
+       sync_mm_rss(old_mm);
        mm_release(tsk, old_mm);
 
        if (old_mm) {

diff --git a/kernel/exit.c b/kernel/exit.c
index 804fb6bb81616db531f7786f050bd86c71c63cfb..34867cc5b42a77f325c204bb2fd09e1fabe38955 100644 (file)
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -423,7 +423,6 @@ void daemonize(const char *name, ...)
         * user space pages.  We don't need them, and if we didn't close them
         * they would be locked into memory.
         */
-       mm_release(current, current->mm);
        exit_mm(current);
        /*
         * We don't want to get frozen, in case system-wide hibernation
@@ -641,6 +640,7 @@ 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)
                return;
        /*
@@ -960,13 +960,9 @@ void do_exit(long code)
                                preempt_count());
 
        acct_update_integrals(tsk);
-
-       /* Set exit_code before complete_vfork_done() in mm_release() */
-       tsk->exit_code = code;
-
-       /* Release mm and sync mm's RSS info before statistics gathering */
-       mm_release(tsk, tsk->mm);
-
+       /* sync mm's RSS info before statistics gathering */
+       if (tsk->mm)
+               sync_mm_rss(tsk->mm);
        group_dead = atomic_dec_and_test(&tsk->signal->live);
        if (group_dead) {
                hrtimer_cancel(&tsk->signal->real_timer);
@@ -979,6 +975,7 @@ void do_exit(long code)
                tty_audit_exit();
        audit_free(tsk);
 
+       tsk->exit_code = code;
        taskstats_exit(tsk, group_dead);
 
        exit_mm(tsk);

diff --git a/kernel/fork.c b/kernel/fork.c
index 0560781c69048991c4e90d561a07b371247d271b..ab5211b9e622cf94d07b7bfb4ccfd9bac85e7b79 100644 (file)
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -619,14 +619,6 @@ void mmput(struct mm_struct *mm)
                        module_put(mm->binfmt->module);
                mmdrop(mm);
        }
-
-       /*
-        * Final rss-counter synchronization. After this point there must be
-        * no pagefaults into this mm from the current context.  Otherwise
-        * mm->rss_stat will be inconsistent.
-        */
-       if (mm)
-               sync_mm_rss(mm);
 }
 EXPORT_SYMBOL_GPL(mmput);