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-lib.c
#include <linux/types.h>
#include <linux/string.h>
#include <linux/kernel.h>
#include <linux/export.h>
#include <linux/interrupt.h>
#include <linux/ide.h>
#include <linux/bitops.h>

/**
 *	ide_toggle_bounce	-	handle bounce buffering
 *	@drive: drive to update
 *	@on: on/off boolean
 *
 *	Enable or disable bounce buffering for the device. Drives move
 *	between PIO and DMA and that changes the rules we need.
 */

void ide_toggle_bounce(ide_drive_t *drive, int on)
{
	u64 addr = BLK_BOUNCE_HIGH;	/* dma64_addr_t */

	if (!PCI_DMA_BUS_IS_PHYS) {
		addr = BLK_BOUNCE_ANY;
	} else if (on && drive->media == ide_disk) {
		struct device *dev = drive->hwif->dev;

		if (dev && dev->dma_mask)
			addr = *dev->dma_mask;
	}

	if (drive->queue)
		blk_queue_bounce_limit(drive->queue, addr);
}

u64 ide_get_lba_addr(struct ide_cmd *cmd, int lba48)
{
	struct ide_taskfile *tf = &cmd->tf;
	u32 high, low;

	low  = (tf->lbah << 16) | (tf->lbam << 8) | tf->lbal;
	if (lba48) {
		tf = &cmd->hob;
		high = (tf->lbah << 16) | (tf->lbam << 8) | tf->lbal;
	} else
		high = tf->device & 0xf;

	return ((u64)high << 24) | low;
}
EXPORT_SYMBOL_GPL(ide_get_lba_addr);

static void ide_dump_sector(ide_drive_t *drive)
{
	struct ide_cmd cmd;
	struct ide_taskfile *tf = &cmd.tf;
	u8 lba48 = !!(drive->dev_flags & IDE_DFLAG_LBA48);

	memset(&cmd, 0, sizeof(cmd));
	if (lba48) {
		cmd.valid.in.tf  = IDE_VALID_LBA;
		cmd.valid.in.hob = IDE_VALID_LBA;
		cmd.tf_flags = IDE_TFLAG_LBA48;
	} else
		cmd.valid.in.tf  = IDE_VALID_LBA | IDE_VALID_DEVICE;

	ide_tf_readback(drive, &cmd);

	if (lba48 || (tf->device & ATA_LBA))
		printk(KERN_CONT ", LBAsect=%llu",
			(unsigned long long)ide_get_lba_addr(&cmd, lba48));
	else
		printk(KERN_CONT ", CHS=%d/%d/%d", (tf->lbah << 8) + tf->lbam,
			tf->device & 0xf, tf->lbal);
}

static void ide_dump_ata_error(ide_drive_t *drive, u8 err)
{
	printk(KERN_CONT "{ ");
	if (err & ATA_ABORTED)
		printk(KERN_CONT "DriveStatusError ");
	if (err & ATA_ICRC)
		printk(KERN_CONT "%s",
			(err & ATA_ABORTED) ? "BadCRC " : "BadSector ");
	if (err & ATA_UNC)
		printk(KERN_CONT "UncorrectableError ");
	if (err & ATA_IDNF)
		printk(KERN_CONT "SectorIdNotFound ");
	if (err & ATA_TRK0NF)
		printk(KERN_CONT "TrackZeroNotFound ");
	if (err & ATA_AMNF)
		printk(KERN_CONT "AddrMarkNotFound ");
	printk(KERN_CONT "}");
	if ((err & (ATA_BBK | ATA_ABORTED)) == ATA_BBK ||
	    (err & (ATA_UNC | ATA_IDNF | ATA_AMNF))) {
		struct request *rq = drive->hwif->rq;

		ide_dump_sector(drive);

		if (rq)
			printk(KERN_CONT ", sector=%llu",
			       (unsigned long long)blk_rq_pos(rq));
	}
	printk(KERN_CONT "\n");
}

static void ide_dump_atapi_error(ide_drive_t *drive, u8 err)
{
	printk(KERN_CONT "{ ");
	if (err & ATAPI_ILI)
		printk(KERN_CONT "IllegalLengthIndication ");
	if (err & ATAPI_EOM)
		printk(KERN_CONT "EndOfMedia ");
	if (err & ATA_ABORTED)
		printk(KERN_CONT "AbortedCommand ");
	if (err & ATA_MCR)
		printk(KERN_CONT "MediaChangeRequested ");
	if (err & ATAPI_LFS)
		printk(KERN_CONT "LastFailedSense=0x%02x ",
			(err & ATAPI_LFS) >> 4);
	printk(KERN_CONT "}\n");
}

/**
 *	ide_dump_status		-	translate ATA/ATAPI error
 *	@drive: drive that status applies to
 *	@msg: text message to print
 *	@stat: status byte to decode
 *
 *	Error reporting, in human readable form (luxurious, but a memory hog).
 *	Combines the drive name, message and status byte to provide a
 *	user understandable explanation of the device error.
 */

u8 ide_dump_status(ide_drive_t *drive, const char *msg, u8 stat)
{
	u8 err = 0;

	printk(KERN_ERR "%s: %s: status=0x%02x { ", drive->name, msg, stat);
	if (stat & ATA_BUSY)
		printk(KERN_CONT "Busy ");
	else {
		if (stat & ATA_DRDY)
			printk(KERN_CONT "DriveReady ");
		if (stat & ATA_DF)
			printk(KERN_CONT "DeviceFault ");
		if (stat & ATA_DSC)
			printk(KERN_CONT "SeekComplete ");
		if (stat & ATA_DRQ)
			printk(KERN_CONT "DataRequest ");
		if (stat & ATA_CORR)
			printk(KERN_CONT "CorrectedError ");
		if (stat & ATA_SENSE)
			printk(KERN_CONT "Sense ");
		if (stat & ATA_ERR)
			printk(KERN_CONT "Error ");
	}
	printk(KERN_CONT "}\n");
	if ((stat & (ATA_BUSY | ATA_ERR)) == ATA_ERR) {
		err = ide_read_error(drive);
		printk(KERN_ERR "%s: %s: error=0x%02x ", drive->name, msg, err);
		if (drive->media == ide_disk)
			ide_dump_ata_error(drive, err);
		else
			ide_dump_atapi_error(drive, err);
	}

	printk(KERN_ERR "%s: possibly failed opcode: 0x%02x\n",
		drive->name, drive->hwif->cmd.tf.command);

	return err;
}
EXPORT_SYMBOL(ide_dump_status);
back to top