[PATCH 6/4] ipc/mqueue: don't use kmalloc(KMALLOC_MAX_SIZE)

[KOSAKI Motohiro]

KMALLOC_MAX_SIZE is no good threshold. It is extream high and
problematic. Unfortunately, some silly drivers depend on and
we can't change it. but any new code don't use such extream
ugly high order allocations. It bring us awful fragmentation
issue and system slowdown.

Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@xxxxxxxxx>
Cc: Doug Ledford <dledford@xxxxxxxxxx>
Cc: Amerigo Wang <amwang@xxxxxxxxxx>
Cc: Serge E. Hallyn <serue@xxxxxxxxxx>
Cc: Jiri Slaby <jslaby@xxxxxxx>
Cc: Joe Korty <joe.korty@xxxxxxxx>
---
 ipc/mqueue.c |    4 ++--
 1 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/ipc/mqueue.c b/ipc/mqueue.c
index 229a5fb..91ca145 100644
--- a/ipc/mqueue.c
+++ b/ipc/mqueue.c
@@ -151,7 +151,7 @@ static struct inode *mqueue_get_inode(struct super_block *sb,
 			info->attr.mq_msgsize = attr->mq_msgsize;
 		}
 		mq_msg_tblsz = info->attr.mq_maxmsg * sizeof(struct msg_msg *);
-		if (mq_msg_tblsz > KMALLOC_MAX_SIZE)
+		if (mq_msg_tblsz > PAGE_SIZE)
 			info->messages = vmalloc(mq_msg_tblsz);
 		else
 			info->messages = kmalloc(mq_msg_tblsz, GFP_KERNEL);
@@ -275,7 +275,7 @@ static void mqueue_evict_inode(struct inode *inode)
 	spin_lock(&info->lock);
 	for (i = 0; i < info->attr.mq_curmsgs; i++)
 		free_msg(info->messages[i]);
-	if (info->attr.mq_maxmsg * sizeof(struct msg_msg *) > KMALLOC_MAX_SIZE)
+	if (is_vmalloc_addr(info->messages))
 		vfree(info->messages);
 	else
 		kfree(info->messages);
-- 
1.7.5.2


--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/