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
it8213.c
/*
 * ITE 8213 IDE driver
 *
 * Copyright (C) 2006 Jack Lee
 * Copyright (C) 2006 Alan Cox
 * Copyright (C) 2007 Bartlomiej Zolnierkiewicz
 */

#include <linux/kernel.h>
#include <linux/types.h>
#include <linux/module.h>
#include <linux/pci.h>
#include <linux/ide.h>
#include <linux/init.h>

#define DRV_NAME "it8213"

/**
 *	it8213_set_pio_mode	-	set host controller for PIO mode
 *	@hwif: port
 *	@drive: drive
 *
 *	Set the interface PIO mode.
 */

static void it8213_set_pio_mode(ide_hwif_t *hwif, ide_drive_t *drive)
{
	struct pci_dev *dev	= to_pci_dev(hwif->dev);
	int is_slave		= drive->dn & 1;
	int master_port		= 0x40;
	int slave_port		= 0x44;
	unsigned long flags;
	u16 master_data;
	u8 slave_data;
	static DEFINE_SPINLOCK(tune_lock);
	int control = 0;
	const u8 pio = drive->pio_mode - XFER_PIO_0;

	static const u8 timings[][2] = {
					{ 0, 0 },
					{ 0, 0 },
					{ 1, 0 },
					{ 2, 1 },
					{ 2, 3 }, };

	spin_lock_irqsave(&tune_lock, flags);
	pci_read_config_word(dev, master_port, &master_data);

	if (pio > 1)
		control |= 1;	/* Programmable timing on */
	if (drive->media != ide_disk)
		control |= 4;	/* ATAPI */
	if (ide_pio_need_iordy(drive, pio))
		control |= 2;	/* IORDY */
	if (is_slave) {
		master_data |=  0x4000;
		master_data &= ~0x0070;
		if (pio > 1)
			master_data = master_data | (control << 4);
		pci_read_config_byte(dev, slave_port, &slave_data);
		slave_data = slave_data & 0xf0;
		slave_data = slave_data | (timings[pio][0] << 2) | timings[pio][1];
	} else {
		master_data &= ~0x3307;
		if (pio > 1)
			master_data = master_data | control;
		master_data = master_data | (timings[pio][0] << 12) | (timings[pio][1] << 8);
	}
	pci_write_config_word(dev, master_port, master_data);
	if (is_slave)
		pci_write_config_byte(dev, slave_port, slave_data);
	spin_unlock_irqrestore(&tune_lock, flags);
}

/**
 *	it8213_set_dma_mode	-	set host controller for DMA mode
 *	@hwif: port
 *	@drive: drive
 *
 *	Tune the ITE chipset for the DMA mode.
 */

static void it8213_set_dma_mode(ide_hwif_t *hwif, ide_drive_t *drive)
{
	struct pci_dev *dev	= to_pci_dev(hwif->dev);
	u8 maslave		= 0x40;
	int a_speed		= 3 << (drive->dn * 4);
	int u_flag		= 1 << drive->dn;
	int v_flag		= 0x01 << drive->dn;
	int w_flag		= 0x10 << drive->dn;
	int u_speed		= 0;
	u16			reg4042, reg4a;
	u8			reg48, reg54, reg55;
	const u8 speed		= drive->dma_mode;

	pci_read_config_word(dev, maslave, &reg4042);
	pci_read_config_byte(dev, 0x48, &reg48);
	pci_read_config_word(dev, 0x4a, &reg4a);
	pci_read_config_byte(dev, 0x54, &reg54);
	pci_read_config_byte(dev, 0x55, &reg55);

	if (speed >= XFER_UDMA_0) {
		u8 udma = speed - XFER_UDMA_0;

		u_speed = min_t(u8, 2 - (udma & 1), udma) << (drive->dn * 4);

		if (!(reg48 & u_flag))
			pci_write_config_byte(dev, 0x48, reg48 | u_flag);
		if (speed >= XFER_UDMA_5)
			pci_write_config_byte(dev, 0x55, (u8) reg55|w_flag);
		else
			pci_write_config_byte(dev, 0x55, (u8) reg55 & ~w_flag);

		if ((reg4a & a_speed) != u_speed)
			pci_write_config_word(dev, 0x4a, (reg4a & ~a_speed) | u_speed);
		if (speed > XFER_UDMA_2) {
			if (!(reg54 & v_flag))
				pci_write_config_byte(dev, 0x54, reg54 | v_flag);
		} else
			pci_write_config_byte(dev, 0x54, reg54 & ~v_flag);
	} else {
		const u8 mwdma_to_pio[] = { 0, 3, 4 };

		if (reg48 & u_flag)
			pci_write_config_byte(dev, 0x48, reg48 & ~u_flag);
		if (reg4a & a_speed)
			pci_write_config_word(dev, 0x4a, reg4a & ~a_speed);
		if (reg54 & v_flag)
			pci_write_config_byte(dev, 0x54, reg54 & ~v_flag);
		if (reg55 & w_flag)
			pci_write_config_byte(dev, 0x55, (u8) reg55 & ~w_flag);

		if (speed >= XFER_MW_DMA_0)
			drive->pio_mode =
				mwdma_to_pio[speed - XFER_MW_DMA_0] + XFER_PIO_0;
		else
			drive->pio_mode = XFER_PIO_2; /* for SWDMA2 */

		it8213_set_pio_mode(hwif, drive);
	}
}

static u8 it8213_cable_detect(ide_hwif_t *hwif)
{
	struct pci_dev *dev = to_pci_dev(hwif->dev);
	u8 reg42h = 0;

	pci_read_config_byte(dev, 0x42, &reg42h);

	return (reg42h & 0x02) ? ATA_CBL_PATA40 : ATA_CBL_PATA80;
}

static const struct ide_port_ops it8213_port_ops = {
	.set_pio_mode		= it8213_set_pio_mode,
	.set_dma_mode		= it8213_set_dma_mode,
	.cable_detect		= it8213_cable_detect,
};

static const struct ide_port_info it8213_chipset = {
	.name		= DRV_NAME,
	.enablebits	= { {0x41, 0x80, 0x80} },
	.port_ops	= &it8213_port_ops,
	.host_flags	= IDE_HFLAG_SINGLE,
	.pio_mask	= ATA_PIO4,
	.swdma_mask	= ATA_SWDMA2_ONLY,
	.mwdma_mask	= ATA_MWDMA12_ONLY,
	.udma_mask	= ATA_UDMA6,
};

/**
 *	it8213_init_one	-	pci layer discovery entry
 *	@dev: PCI device
 *	@id: ident table entry
 *
 *	Called by the PCI code when it finds an ITE8213 controller. As
 *	this device follows the standard interfaces we can use the
 *	standard helper functions to do almost all the work for us.
 */

static int it8213_init_one(struct pci_dev *dev, const struct pci_device_id *id)
{
	return ide_pci_init_one(dev, &it8213_chipset, NULL);
}

static const struct pci_device_id it8213_pci_tbl[] = {
	{ PCI_VDEVICE(ITE, PCI_DEVICE_ID_ITE_8213), 0 },
	{ 0, },
};

MODULE_DEVICE_TABLE(pci, it8213_pci_tbl);

static struct pci_driver it8213_pci_driver = {
	.name		= "ITE8213_IDE",
	.id_table	= it8213_pci_tbl,
	.probe		= it8213_init_one,
	.remove		= ide_pci_remove,
	.suspend	= ide_pci_suspend,
	.resume		= ide_pci_resume,
};

static int __init it8213_ide_init(void)
{
	return ide_pci_register_driver(&it8213_pci_driver);
}

static void __exit it8213_ide_exit(void)
{
	pci_unregister_driver(&it8213_pci_driver);
}

module_init(it8213_ide_init);
module_exit(it8213_ide_exit);

MODULE_AUTHOR("Jack Lee, Alan Cox");
MODULE_DESCRIPTION("PCI driver module for the ITE 8213");
MODULE_LICENSE("GPL");
back to top