lkml.org 
[lkml]   [2013]   [Jun]   [15]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
Patch in this message
/
Date
From
Subject[PATCH] vfree: don't schedule free_work() if llist_add() returns F
vfree() only needs schedule_work(&p->wq) if p->list was empty,
otherwise vfree_deferred->wq is already pending or it is running
and didn't do llist_del_all() yet.

Signed-off-by: Oleg Nesterov <oleg@redhat.com>
---
mm/vmalloc.c | 5 ++---
1 files changed, 2 insertions(+), 3 deletions(-)

diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index d365724..2b8f644 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -1524,7 +1524,6 @@ static void __vunmap(const void *addr, int deallocate_pages)
* conventions for vfree() arch-depenedent would be a really bad idea)
*
* NOTE: assumes that the object at *addr has a size >= sizeof(llist_node)
- *
*/
void vfree(const void *addr)
{
@@ -1536,8 +1535,8 @@ void vfree(const void *addr)
return;
if (unlikely(in_interrupt())) {
struct vfree_deferred *p = &__get_cpu_var(vfree_deferred);
- llist_add((struct llist_node *)addr, &p->list);
- schedule_work(&p->wq);
+ if (llist_add((struct llist_node *)addr, &p->list))
+ schedule_work(&p->wq);
} else
__vunmap(addr, 1);
}
--
1.5.5.1



\
 
 \ /
  Last update: 2013-06-15 21:01    [W:0.042 / U:0.880 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site