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
ide_platform.c
/*
 * Platform IDE driver
 *
 * Copyright (C) 2007 MontaVista Software
 *
 * Maintainer: Kumar Gala <galak@kernel.crashing.org>
 *
 * This program is free software; you can redistribute  it and/or modify it
 * under  the terms of  the GNU General  Public License as published by the
 * Free Software Foundation;  either version 2 of the  License, or (at your
 * option) any later version.
 */

#include <linux/types.h>
#include <linux/init.h>
#include <linux/kernel.h>
#include <linux/ide.h>
#include <linux/ioport.h>
#include <linux/module.h>
#include <linux/ata_platform.h>
#include <linux/platform_device.h>
#include <linux/interrupt.h>
#include <linux/io.h>

static void plat_ide_setup_ports(struct ide_hw *hw, void __iomem *base,
				 void __iomem *ctrl,
				 struct pata_platform_info *pdata, int irq)
{
	unsigned long port = (unsigned long)base;
	int i;

	hw->io_ports.data_addr = port;

	port += (1 << pdata->ioport_shift);
	for (i = 1; i <= 7;
	     i++, port += (1 << pdata->ioport_shift))
		hw->io_ports_array[i] = port;

	hw->io_ports.ctl_addr = (unsigned long)ctrl;

	hw->irq = irq;
}

static const struct ide_port_info platform_ide_port_info = {
	.host_flags		= IDE_HFLAG_NO_DMA,
	.chipset		= ide_generic,
};

static int plat_ide_probe(struct platform_device *pdev)
{
	struct resource *res_base, *res_alt, *res_irq;
	void __iomem *base, *alt_base;
	struct pata_platform_info *pdata;
	struct ide_host *host;
	int ret = 0, mmio = 0;
	struct ide_hw hw, *hws[] = { &hw };
	struct ide_port_info d = platform_ide_port_info;

	pdata = dev_get_platdata(&pdev->dev);

	/* get a pointer to the register memory */
	res_base = platform_get_resource(pdev, IORESOURCE_IO, 0);
	res_alt = platform_get_resource(pdev, IORESOURCE_IO, 1);

	if (!res_base || !res_alt) {
		res_base = platform_get_resource(pdev, IORESOURCE_MEM, 0);
		res_alt = platform_get_resource(pdev, IORESOURCE_MEM, 1);
		if (!res_base || !res_alt) {
			ret = -ENOMEM;
			goto out;
		}
		mmio = 1;
	}

	res_irq = platform_get_resource(pdev, IORESOURCE_IRQ, 0);
	if (!res_irq) {
		ret = -EINVAL;
		goto out;
	}

	if (mmio) {
		base = devm_ioremap(&pdev->dev,
			res_base->start, resource_size(res_base));
		alt_base = devm_ioremap(&pdev->dev,
			res_alt->start, resource_size(res_alt));
	} else {
		base = devm_ioport_map(&pdev->dev,
			res_base->start, resource_size(res_base));
		alt_base = devm_ioport_map(&pdev->dev,
			res_alt->start, resource_size(res_alt));
	}

	memset(&hw, 0, sizeof(hw));
	plat_ide_setup_ports(&hw, base, alt_base, pdata, res_irq->start);
	hw.dev = &pdev->dev;

	d.irq_flags = res_irq->flags & IRQF_TRIGGER_MASK;
	if (res_irq->flags & IORESOURCE_IRQ_SHAREABLE)
		d.irq_flags |= IRQF_SHARED;

	if (mmio)
		d.host_flags |= IDE_HFLAG_MMIO;

	ret = ide_host_add(&d, hws, 1, &host);
	if (ret)
		goto out;

	platform_set_drvdata(pdev, host);

	return 0;

out:
	return ret;
}

static int plat_ide_remove(struct platform_device *pdev)
{
	struct ide_host *host = dev_get_drvdata(&pdev->dev);

	ide_host_remove(host);

	return 0;
}

static struct platform_driver platform_ide_driver = {
	.driver = {
		.name = "pata_platform",
	},
	.probe = plat_ide_probe,
	.remove = plat_ide_remove,
};

module_platform_driver(platform_ide_driver);

MODULE_DESCRIPTION("Platform IDE driver");
MODULE_LICENSE("GPL");
MODULE_ALIAS("platform:pata_platform");
back to top