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
Makefile
#
# link order is important here
#

ccflags-y				:= -Idrivers/ide

ide-core-y += ide.o ide-ioctls.o ide-io.o ide-iops.o ide-lib.o ide-probe.o \
	      ide-taskfile.o ide-pm.o ide-park.o ide-sysfs.o ide-devsets.o \
	      ide-io-std.o ide-eh.o

# core IDE code
ide-core-$(CONFIG_IDE_XFER_MODE)	+= ide-pio-blacklist.o ide-xfer-mode.o
ide-core-$(CONFIG_IDE_TIMINGS)		+= ide-timings.o
ide-core-$(CONFIG_IDE_ATAPI)		+= ide-atapi.o
ide-core-$(CONFIG_BLK_DEV_IDEPCI)	+= setup-pci.o
ide-core-$(CONFIG_BLK_DEV_IDEDMA)	+= ide-dma.o
ide-core-$(CONFIG_BLK_DEV_IDEDMA_SFF)	+= ide-dma-sff.o
ide-core-$(CONFIG_IDE_PROC_FS)		+= ide-proc.o
ide-core-$(CONFIG_BLK_DEV_IDEACPI)	+= ide-acpi.o
ide-core-$(CONFIG_IDE_LEGACY)		+= ide-legacy.o

obj-$(CONFIG_IDE)			+= ide-core.o

obj-$(CONFIG_BLK_DEV_ALI14XX)		+= ali14xx.o
obj-$(CONFIG_BLK_DEV_UMC8672)		+= umc8672.o
obj-$(CONFIG_BLK_DEV_DTC2278)		+= dtc2278.o
obj-$(CONFIG_BLK_DEV_HT6560B)		+= ht6560b.o
obj-$(CONFIG_BLK_DEV_QD65XX)		+= qd65xx.o
obj-$(CONFIG_BLK_DEV_4DRIVES)		+= ide-4drives.o

obj-$(CONFIG_BLK_DEV_GAYLE)		+= gayle.o
obj-$(CONFIG_BLK_DEV_FALCON_IDE)	+= falconide.o
obj-$(CONFIG_BLK_DEV_MAC_IDE)		+= macide.o
obj-$(CONFIG_BLK_DEV_Q40IDE)		+= q40ide.o
obj-$(CONFIG_BLK_DEV_BUDDHA)		+= buddha.o

obj-$(CONFIG_BLK_DEV_AEC62XX)		+= aec62xx.o
obj-$(CONFIG_BLK_DEV_ALI15X3)		+= alim15x3.o
obj-$(CONFIG_BLK_DEV_AMD74XX)		+= amd74xx.o
obj-$(CONFIG_BLK_DEV_ATIIXP)		+= atiixp.o
obj-$(CONFIG_BLK_DEV_CMD64X)		+= cmd64x.o
obj-$(CONFIG_BLK_DEV_CS5520)		+= cs5520.o
obj-$(CONFIG_BLK_DEV_CS5530)		+= cs5530.o
obj-$(CONFIG_BLK_DEV_CS5535)		+= cs5535.o
obj-$(CONFIG_BLK_DEV_CS5536)		+= cs5536.o
obj-$(CONFIG_BLK_DEV_SC1200)		+= sc1200.o
obj-$(CONFIG_BLK_DEV_CY82C693)		+= cy82c693.o
obj-$(CONFIG_BLK_DEV_DELKIN)		+= delkin_cb.o
obj-$(CONFIG_BLK_DEV_HPT366)		+= hpt366.o
obj-$(CONFIG_BLK_DEV_IT8172)		+= it8172.o
obj-$(CONFIG_BLK_DEV_IT8213)		+= it8213.o
obj-$(CONFIG_BLK_DEV_IT821X)		+= it821x.o
obj-$(CONFIG_BLK_DEV_JMICRON)		+= jmicron.o
obj-$(CONFIG_BLK_DEV_NS87415)		+= ns87415.o
obj-$(CONFIG_BLK_DEV_OPTI621)		+= opti621.o
obj-$(CONFIG_BLK_DEV_PDC202XX_OLD)	+= pdc202xx_old.o
obj-$(CONFIG_BLK_DEV_PDC202XX_NEW)	+= pdc202xx_new.o
obj-$(CONFIG_BLK_DEV_PIIX)		+= piix.o
obj-$(CONFIG_BLK_DEV_RZ1000)		+= rz1000.o
obj-$(CONFIG_BLK_DEV_SVWKS)		+= serverworks.o
obj-$(CONFIG_BLK_DEV_SGIIOC4)		+= sgiioc4.o
obj-$(CONFIG_BLK_DEV_SIIMAGE)		+= siimage.o
obj-$(CONFIG_BLK_DEV_SIS5513)		+= sis5513.o
obj-$(CONFIG_BLK_DEV_SL82C105)		+= sl82c105.o
obj-$(CONFIG_BLK_DEV_SLC90E66)		+= slc90e66.o
obj-$(CONFIG_BLK_DEV_TC86C001)		+= tc86c001.o
obj-$(CONFIG_BLK_DEV_TRIFLEX)		+= triflex.o
obj-$(CONFIG_BLK_DEV_TRM290)		+= trm290.o
obj-$(CONFIG_BLK_DEV_VIA82CXXX)		+= via82cxxx.o

# Must appear at the end of the block
obj-$(CONFIG_BLK_DEV_GENERIC)		+= ide-pci-generic.o

obj-$(CONFIG_IDEPCI_PCIBUS_ORDER)	+= ide-scan-pci.o

obj-$(CONFIG_BLK_DEV_CMD640)		+= cmd640.o

obj-$(CONFIG_BLK_DEV_IDE_PMAC)		+= pmac.o

obj-$(CONFIG_IDE_GENERIC)		+= ide-generic.o
obj-$(CONFIG_BLK_DEV_IDEPNP)		+= ide-pnp.o

ide-gd_mod-y += ide-gd.o
ide-cd_mod-y += ide-cd.o ide-cd_ioctl.o ide-cd_verbose.o

ifeq ($(CONFIG_IDE_GD_ATA), y)
	ide-gd_mod-y += ide-disk.o ide-disk_ioctl.o
ifeq ($(CONFIG_IDE_PROC_FS), y)
	ide-gd_mod-y += ide-disk_proc.o
endif
endif

ifeq ($(CONFIG_IDE_GD_ATAPI), y)
	ide-gd_mod-y += ide-floppy.o ide-floppy_ioctl.o
ifeq ($(CONFIG_IDE_PROC_FS), y)
	ide-gd_mod-y += ide-floppy_proc.o
endif
endif

obj-$(CONFIG_IDE_GD)			+= ide-gd_mod.o
obj-$(CONFIG_BLK_DEV_IDECD)		+= ide-cd_mod.o
obj-$(CONFIG_BLK_DEV_IDETAPE)		+= ide-tape.o

obj-$(CONFIG_BLK_DEV_IDECS)		+= ide-cs.o

obj-$(CONFIG_BLK_DEV_PLATFORM)		+= ide_platform.o

obj-$(CONFIG_BLK_DEV_IDE_ICSIDE)	+= icside.o
obj-$(CONFIG_BLK_DEV_IDE_RAPIDE)	+= rapide.o
obj-$(CONFIG_BLK_DEV_PALMCHIP_BK3710)	+= palm_bk3710.o

obj-$(CONFIG_BLK_DEV_IDE_AU1XXX)	+= au1xxx-ide.o

obj-$(CONFIG_BLK_DEV_IDE_TX4938)	+= tx4938ide.o
obj-$(CONFIG_BLK_DEV_IDE_TX4939)	+= tx4939ide.o
back to top