mm: introduce get_mm_hiwater_xxx(), fix taskstats->hiwater_xxx accounting

xacct_add_tsk() relies on do_exit()->update_hiwater_xxx() and uses
mm->hiwater_xxx directly, this leads to 2 problems:

- taskstats_user_cmd() can call fill_pid()->xacct_add_tsk() at any
  moment before the task exits, so we should check the current values of
  rss/vm anyway.

- do_exit()->update_hiwater_xxx() calls are racy.  An exiting thread can
  be preempted right before mm->hiwater_xxx = new_val, and another thread
  can use A_LOT of memory and exit in between.  When the first thread
  resumes it can be the last thread in the thread group, in that case we
  report the wrong hiwater_xxx values which do not take A_LOT into
  account.

Introduce get_mm_hiwater_rss() and get_mm_hiwater_vm() helpers and change
xacct_add_tsk() to use them.  The first helper will also be used by
rusage->ru_maxrss accounting.

Kill do_exit()->update_hiwater_xxx() calls.  Unless we are going to
decrease rss/vm there is no point to update mm->hiwater_xxx, and nobody
can look at this mm_struct when exit_mmap() actually unmaps the memory.
Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Acked-by: Hugh Dickins <hugh@veritas.com>
Reviewed-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Acked-by: Balbir Singh <balbir@linux.vnet.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

include/linux/sched.h

@@ -386,6 +386,9 @@ extern void arch_unmap_area_topdown(struct mm_struct *, unsigned long);
 		(mm)->hiwater_vm = (mm)->total_vm;	\
 } while (0)
 
+#define get_mm_hiwater_rss(mm)	max((mm)->hiwater_rss, get_mm_rss(mm))
+#define get_mm_hiwater_vm(mm)	max((mm)->hiwater_vm, (mm)->total_vm)
+
 extern void set_dumpable(struct mm_struct *mm, int value);
 extern int get_dumpable(struct mm_struct *mm);
 

kernel/exit.c

@@ -1051,10 +1051,7 @@ NORET_TYPE void do_exit(long code)
 				preempt_count());
 
 	acct_update_integrals(tsk);
-	if (tsk->mm) {
-		update_hiwater_rss(tsk->mm);
-		update_hiwater_vm(tsk->mm);
-	}
+
 	group_dead = atomic_dec_and_test(&tsk->signal->live);
 	if (group_dead) {
 		hrtimer_cancel(&tsk->signal->real_timer);

kernel/tsacct.c

@@ -92,8 +92,8 @@ void xacct_add_tsk(struct taskstats *stats, struct task_struct *p)
 	mm = get_task_mm(p);
 	if (mm) {
 		/* adjust to KB unit */
-		stats->hiwater_rss   = mm->hiwater_rss * PAGE_SIZE / KB;
-		stats->hiwater_vm    = mm->hiwater_vm * PAGE_SIZE / KB;
+		stats->hiwater_rss   = get_mm_hiwater_rss(mm) * PAGE_SIZE / KB;
+		stats->hiwater_vm    = get_mm_hiwater_vm(mm)  * PAGE_SIZE / KB;
 		mmput(mm);
 	}
 	stats->read_char	= p->ioac.rchar;

mm/mmap.c

@@ -2102,7 +2102,7 @@ void exit_mmap(struct mm_struct *mm)
 	lru_add_drain();
 	flush_cache_mm(mm);
 	tlb = tlb_gather_mmu(mm, 1);
-	/* Don't update_hiwater_rss(mm) here, do_exit already did */
+	/* update_hiwater_rss(mm) here? but nobody should be looking */
 	/* Use -1 here to ensure all VMAs in the mm are unmapped */
 	end = unmap_vmas(&tlb, vma, 0, -1, &nr_accounted, NULL);
 	vm_unacct_memory(nr_accounted);