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
Raw File
cpuidle-ux500.c
/*
 * Copyright (c) 2012 Linaro : Daniel Lezcano <daniel.lezcano@linaro.org> (IBM)
 *
 * Based on the work of Rickard Andersson <rickard.andersson@stericsson.com>
 * and Jonas Aaberg <jonas.aberg@stericsson.com>.
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License version 2 as
 * published by the Free Software Foundation.
 */

#include <linux/module.h>
#include <linux/cpuidle.h>
#include <linux/spinlock.h>
#include <linux/atomic.h>
#include <linux/smp.h>
#include <linux/mfd/dbx500-prcmu.h>
#include <linux/platform_data/arm-ux500-pm.h>
#include <linux/platform_device.h>

#include <asm/cpuidle.h>

static atomic_t master = ATOMIC_INIT(0);
static DEFINE_SPINLOCK(master_lock);

static inline int ux500_enter_idle(struct cpuidle_device *dev,
				   struct cpuidle_driver *drv, int index)
{
	int this_cpu = smp_processor_id();
	bool recouple = false;

	if (atomic_inc_return(&master) == num_online_cpus()) {

		/* With this lock, we prevent the other cpu to exit and enter
		 * this function again and become the master */
		if (!spin_trylock(&master_lock))
			goto wfi;

		/* decouple the gic from the A9 cores */
		if (prcmu_gic_decouple()) {
			spin_unlock(&master_lock);
			goto out;
		}

		/* If an error occur, we will have to recouple the gic
		 * manually */
		recouple = true;

		/* At this state, as the gic is decoupled, if the other
		 * cpu is in WFI, we have the guarantee it won't be wake
		 * up, so we can safely go to retention */
		if (!prcmu_is_cpu_in_wfi(this_cpu ? 0 : 1))
			goto out;

		/* The prcmu will be in charge of watching the interrupts
		 * and wake up the cpus */
		if (prcmu_copy_gic_settings())
			goto out;

		/* Check in the meantime an interrupt did
		 * not occur on the gic ... */
		if (prcmu_gic_pending_irq())
			goto out;

		/* ... and the prcmu */
		if (prcmu_pending_irq())
			goto out;

		/* Go to the retention state, the prcmu will wait for the
		 * cpu to go WFI and this is what happens after exiting this
		 * 'master' critical section */
		if (prcmu_set_power_state(PRCMU_AP_IDLE, true, true))
			goto out;

		/* When we switch to retention, the prcmu is in charge
		 * of recoupling the gic automatically */
		recouple = false;

		spin_unlock(&master_lock);
	}
wfi:
	cpu_do_idle();
out:
	atomic_dec(&master);

	if (recouple) {
		prcmu_gic_recouple();
		spin_unlock(&master_lock);
	}

	return index;
}

static struct cpuidle_driver ux500_idle_driver = {
	.name = "ux500_idle",
	.owner = THIS_MODULE,
	.states = {
		ARM_CPUIDLE_WFI_STATE,
		{
			.enter		  = ux500_enter_idle,
			.exit_latency	  = 70,
			.target_residency = 260,
			.flags		  = CPUIDLE_FLAG_TIMER_STOP,
			.name		  = "ApIdle",
			.desc		  = "ARM Retention",
		},
	},
	.safe_state_index = 0,
	.state_count = 2,
};

static int dbx500_cpuidle_probe(struct platform_device *pdev)
{
	/* Configure wake up reasons */
	prcmu_enable_wakeups(PRCMU_WAKEUP(ARM) | PRCMU_WAKEUP(RTC) |
			     PRCMU_WAKEUP(ABB));

	return cpuidle_register(&ux500_idle_driver, NULL);
}

static struct platform_driver dbx500_cpuidle_plat_driver = {
	.driver = {
		.name = "cpuidle-dbx500",
	},
	.probe = dbx500_cpuidle_probe,
};

module_platform_driver(dbx500_cpuidle_plat_driver);
back to top