Skip to main content

Browse the archive

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 
mm/memory_hotplug.c: set zone->wait_table to null after freeing it
 
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
Raw File
blk-mq-cpu.c 
/*
 * CPU notifier helper code for blk-mq
 *
 * Copyright (C) 2013-2014 Jens Axboe
 */
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/init.h>
#include <linux/blkdev.h>
#include <linux/list.h>
#include <linux/llist.h>
#include <linux/smp.h>
#include <linux/cpu.h>

#include <linux/blk-mq.h>
#include "blk-mq.h"

static LIST_HEAD(blk_mq_cpu_notify_list);
static DEFINE_RAW_SPINLOCK(blk_mq_cpu_notify_lock);

static int blk_mq_main_cpu_notify(struct notifier_block *self,
				  unsigned long action, void *hcpu)
{
	unsigned int cpu = (unsigned long) hcpu;
	struct blk_mq_cpu_notifier *notify;
	int ret = NOTIFY_OK;

	raw_spin_lock(&blk_mq_cpu_notify_lock);

	list_for_each_entry(notify, &blk_mq_cpu_notify_list, list) {
		ret = notify->notify(notify->data, action, cpu);
		if (ret != NOTIFY_OK)
			break;
	}

	raw_spin_unlock(&blk_mq_cpu_notify_lock);
	return ret;
}

void blk_mq_register_cpu_notifier(struct blk_mq_cpu_notifier *notifier)
{
	BUG_ON(!notifier->notify);

	raw_spin_lock(&blk_mq_cpu_notify_lock);
	list_add_tail(&notifier->list, &blk_mq_cpu_notify_list);
	raw_spin_unlock(&blk_mq_cpu_notify_lock);
}

void blk_mq_unregister_cpu_notifier(struct blk_mq_cpu_notifier *notifier)
{
	raw_spin_lock(&blk_mq_cpu_notify_lock);
	list_del(&notifier->list);
	raw_spin_unlock(&blk_mq_cpu_notify_lock);
}

void blk_mq_init_cpu_notifier(struct blk_mq_cpu_notifier *notifier,
			      int (*fn)(void *, unsigned long, unsigned int),
			      void *data)
{
	notifier->notify = fn;
	notifier->data = data;
}

void __init blk_mq_cpu_init(void)
{
	hotcpu_notifier(blk_mq_main_cpu_notify, 0);
}
back to top