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
clk-pwm.c
/*
 * Copyright (C) 2014 Philipp Zabel, Pengutronix
 *
 * 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.
 *
 * PWM (mis)used as clock output
 */
#include <linux/clk-provider.h>
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/of.h>
#include <linux/platform_device.h>
#include <linux/pwm.h>

struct clk_pwm {
	struct clk_hw hw;
	struct pwm_device *pwm;
	u32 fixed_rate;
};

static inline struct clk_pwm *to_clk_pwm(struct clk_hw *hw)
{
	return container_of(hw, struct clk_pwm, hw);
}

static int clk_pwm_prepare(struct clk_hw *hw)
{
	struct clk_pwm *clk_pwm = to_clk_pwm(hw);

	return pwm_enable(clk_pwm->pwm);
}

static void clk_pwm_unprepare(struct clk_hw *hw)
{
	struct clk_pwm *clk_pwm = to_clk_pwm(hw);

	pwm_disable(clk_pwm->pwm);
}

static unsigned long clk_pwm_recalc_rate(struct clk_hw *hw,
					 unsigned long parent_rate)
{
	struct clk_pwm *clk_pwm = to_clk_pwm(hw);

	return clk_pwm->fixed_rate;
}

static const struct clk_ops clk_pwm_ops = {
	.prepare = clk_pwm_prepare,
	.unprepare = clk_pwm_unprepare,
	.recalc_rate = clk_pwm_recalc_rate,
};

static int clk_pwm_probe(struct platform_device *pdev)
{
	struct device_node *node = pdev->dev.of_node;
	struct clk_init_data init;
	struct clk_pwm *clk_pwm;
	struct pwm_device *pwm;
	const char *clk_name;
	struct clk *clk;
	int ret;

	clk_pwm = devm_kzalloc(&pdev->dev, sizeof(*clk_pwm), GFP_KERNEL);
	if (!clk_pwm)
		return -ENOMEM;

	pwm = devm_pwm_get(&pdev->dev, NULL);
	if (IS_ERR(pwm))
		return PTR_ERR(pwm);

	if (!pwm->period) {
		dev_err(&pdev->dev, "invalid PWM period\n");
		return -EINVAL;
	}

	if (of_property_read_u32(node, "clock-frequency", &clk_pwm->fixed_rate))
		clk_pwm->fixed_rate = NSEC_PER_SEC / pwm->period;

	if (pwm->period != NSEC_PER_SEC / clk_pwm->fixed_rate &&
	    pwm->period != DIV_ROUND_UP(NSEC_PER_SEC, clk_pwm->fixed_rate)) {
		dev_err(&pdev->dev,
			"clock-frequency does not match PWM period\n");
		return -EINVAL;
	}

	ret = pwm_config(pwm, (pwm->period + 1) >> 1, pwm->period);
	if (ret < 0)
		return ret;

	clk_name = node->name;
	of_property_read_string(node, "clock-output-names", &clk_name);

	init.name = clk_name;
	init.ops = &clk_pwm_ops;
	init.flags = CLK_IS_BASIC | CLK_IS_ROOT;
	init.num_parents = 0;

	clk_pwm->pwm = pwm;
	clk_pwm->hw.init = &init;
	clk = devm_clk_register(&pdev->dev, &clk_pwm->hw);
	if (IS_ERR(clk))
		return PTR_ERR(clk);

	return of_clk_add_provider(node, of_clk_src_simple_get, clk);
}

static int clk_pwm_remove(struct platform_device *pdev)
{
	of_clk_del_provider(pdev->dev.of_node);

	return 0;
}

static const struct of_device_id clk_pwm_dt_ids[] = {
	{ .compatible = "pwm-clock" },
	{ }
};
MODULE_DEVICE_TABLE(of, clk_pwm_dt_ids);

static struct platform_driver clk_pwm_driver = {
	.probe = clk_pwm_probe,
	.remove = clk_pwm_remove,
	.driver = {
		.name = "pwm-clock",
		.of_match_table = of_match_ptr(clk_pwm_dt_ids),
	},
};

module_platform_driver(clk_pwm_driver);

MODULE_AUTHOR("Philipp Zabel <p.zabel@pengutronix.de>");
MODULE_DESCRIPTION("PWM clock driver");
MODULE_LICENSE("GPL");
back to top