Revision 85bd839983778fcd0c1c043327b14a046e979b39 authored by Gu Zheng on 10 June 2015, 18:14:43 UTC, committed by Linus Torvalds on 10 June 2015, 23:43:43 UTC
Izumi found the following oops when hot re-adding a node:
BUG: unable to handle kernel paging request at ffffc90008963690
IP: __wake_up_bit+0x20/0x70
Oops: 0000 [#1] SMP
CPU: 68 PID: 1237 Comm: rs:main Q:Reg Not tainted 4.1.0-rc5 #80
Hardware name: FUJITSU PRIMEQUEST2800E/SB, BIOS PRIMEQUEST 2000 Series BIOS Version 1.87 04/28/2015
task: ffff880838df8000 ti: ffff880017b94000 task.ti: ffff880017b94000
RIP: 0010:[<ffffffff810dff80>] [<ffffffff810dff80>] __wake_up_bit+0x20/0x70
RSP: 0018:ffff880017b97be8 EFLAGS: 00010246
RAX: ffffc90008963690 RBX: 00000000003c0000 RCX: 000000000000a4c9
RDX: 0000000000000000 RSI: ffffea101bffd500 RDI: ffffc90008963648
RBP: ffff880017b97c08 R08: 0000000002000020 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000000 R12: ffff8a0797c73800
R13: ffffea101bffd500 R14: 0000000000000001 R15: 00000000003c0000
FS: 00007fcc7ffff700(0000) GS:ffff880874800000(0000) knlGS:0000000000000000
CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: ffffc90008963690 CR3: 0000000836761000 CR4: 00000000001407e0
Call Trace:
unlock_page+0x6d/0x70
generic_write_end+0x53/0xb0
xfs_vm_write_end+0x29/0x80 [xfs]
generic_perform_write+0x10a/0x1e0
xfs_file_buffered_aio_write+0x14d/0x3e0 [xfs]
xfs_file_write_iter+0x79/0x120 [xfs]
__vfs_write+0xd4/0x110
vfs_write+0xac/0x1c0
SyS_write+0x58/0xd0
system_call_fastpath+0x12/0x76
Code: 5d c3 66 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 55 48 89 e5 48 83 ec 20 65 48 8b 04 25 28 00 00 00 48 89 45 f8 31 c0 48 8d 47 48 <48> 39 47 48 48 c7 45 e8 00 00 00 00 48 c7 45 f0 00 00 00 00 48
RIP [<ffffffff810dff80>] __wake_up_bit+0x20/0x70
RSP <ffff880017b97be8>
CR2: ffffc90008963690
Reproduce method (re-add a node)::
Hot-add nodeA --> remove nodeA --> hot-add nodeA (panic)
This seems an use-after-free problem, and the root cause is
zone->wait_table was not set to *NULL* after free it in
try_offline_node.
When hot re-add a node, we will reuse the pgdat of it, so does the zone
struct, and when add pages to the target zone, it will init the zone
first (including the wait_table) if the zone is not initialized. The
judgement of zone initialized is based on zone->wait_table:
static inline bool zone_is_initialized(struct zone *zone)
{
return !!zone->wait_table;
}
so if we do not set the zone->wait_table to *NULL* after free it, the
memory hotplug routine will skip the init of new zone when hot re-add
the node, and the wait_table still points to the freed memory, then we
will access the invalid address when trying to wake up the waiting
people after the i/o operation with the page is done, such as mentioned
above.
Signed-off-by: Gu Zheng <guz.fnst@cn.fujitsu.com>
Reported-by: Taku Izumi <izumi.taku@jp.fujitsu.com>
Reviewed by: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Tang Chen <tangchen@cn.fujitsu.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
1 parent 5879ae5
noop-iosched.c
/*
* elevator noop
*/
#include <linux/blkdev.h>
#include <linux/elevator.h>
#include <linux/bio.h>
#include <linux/module.h>
#include <linux/slab.h>
#include <linux/init.h>
struct noop_data {
struct list_head queue;
};
static void noop_merged_requests(struct request_queue *q, struct request *rq,
struct request *next)
{
list_del_init(&next->queuelist);
}
static int noop_dispatch(struct request_queue *q, int force)
{
struct noop_data *nd = q->elevator->elevator_data;
if (!list_empty(&nd->queue)) {
struct request *rq;
rq = list_entry(nd->queue.next, struct request, queuelist);
list_del_init(&rq->queuelist);
elv_dispatch_sort(q, rq);
return 1;
}
return 0;
}
static void noop_add_request(struct request_queue *q, struct request *rq)
{
struct noop_data *nd = q->elevator->elevator_data;
list_add_tail(&rq->queuelist, &nd->queue);
}
static struct request *
noop_former_request(struct request_queue *q, struct request *rq)
{
struct noop_data *nd = q->elevator->elevator_data;
if (rq->queuelist.prev == &nd->queue)
return NULL;
return list_entry(rq->queuelist.prev, struct request, queuelist);
}
static struct request *
noop_latter_request(struct request_queue *q, struct request *rq)
{
struct noop_data *nd = q->elevator->elevator_data;
if (rq->queuelist.next == &nd->queue)
return NULL;
return list_entry(rq->queuelist.next, struct request, queuelist);
}
static int noop_init_queue(struct request_queue *q, struct elevator_type *e)
{
struct noop_data *nd;
struct elevator_queue *eq;
eq = elevator_alloc(q, e);
if (!eq)
return -ENOMEM;
nd = kmalloc_node(sizeof(*nd), GFP_KERNEL, q->node);
if (!nd) {
kobject_put(&eq->kobj);
return -ENOMEM;
}
eq->elevator_data = nd;
INIT_LIST_HEAD(&nd->queue);
spin_lock_irq(q->queue_lock);
q->elevator = eq;
spin_unlock_irq(q->queue_lock);
return 0;
}
static void noop_exit_queue(struct elevator_queue *e)
{
struct noop_data *nd = e->elevator_data;
BUG_ON(!list_empty(&nd->queue));
kfree(nd);
}
static struct elevator_type elevator_noop = {
.ops = {
.elevator_merge_req_fn = noop_merged_requests,
.elevator_dispatch_fn = noop_dispatch,
.elevator_add_req_fn = noop_add_request,
.elevator_former_req_fn = noop_former_request,
.elevator_latter_req_fn = noop_latter_request,
.elevator_init_fn = noop_init_queue,
.elevator_exit_fn = noop_exit_queue,
},
.elevator_name = "noop",
.elevator_owner = THIS_MODULE,
};
static int __init noop_init(void)
{
return elv_register(&elevator_noop);
}
static void __exit noop_exit(void)
{
elv_unregister(&elevator_noop);
}
module_init(noop_init);
module_exit(noop_exit);
MODULE_AUTHOR("Jens Axboe");
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("No-op IO scheduler");
Computing file changes ...
