Function kswapd_stop() will be called to destroy the kswapd work thread
when all memory of a NUMA node has been offlined. But kswapd_stop() only
terminates the work thread without resetting NODE_DATA(nid)->kswapd to NULL.
The stale pointer will prevent kswapd_run() from creating a new work thread
when adding memory to the memory-less NUMA node again. Eventually the stale
pointer may cause invalid memory access.
Signed-off-by: Xishi Qiu <[email protected]>
Signed-off-by: Jiang Liu <[email protected]>
Acked-by: KAMEZAWA Hiroyuki <[email protected]>
Acked-by: KOSAKI Motohiro <[email protected]>
Acked-by: Mel Gorman <[email protected]>
Acked-by: David Rientjes <[email protected]>
Reviewed-by: Minchan Kim <[email protected]>
---
An example stack dump as below. It's reproduced with 2.6.32, but latest
kernel has the same issue.
BUG: unable to handle kernel NULL pointer dereference at (null)
IP: [<ffffffff81051a94>] exit_creds+0x12/0x78
PGD 0
Oops: 0000 [#1] SMP
last sysfs file: /sys/devices/system/memory/memory391/state
CPU 11
Modules linked in: cpufreq_conservative cpufreq_userspace cpufreq_powersave acpi_cpufreq microcode fuse loop dm_mod tpm_tis rtc_cmos i2c_i801 rtc_core tpm serio_raw pcspkr sg tpm_bios igb i2c_core iTCO_wdt rtc_lib mptctl iTCO_vendor_support button dca bnx2 usbhid hid uhci_hcd ehci_hcd usbcore sd_mod crc_t10dif edd ext3 mbcache jbd fan ide_pci_generic ide_core ata_generic ata_piix libata thermal processor thermal_sys hwmon mptsas mptscsih mptbase scsi_transport_sas scsi_mod
Pid: 7949, comm: sh Not tainted 2.6.32.12-qiuxishi-5-default #92 Tecal RH2285
RIP: 0010:[<ffffffff81051a94>] [<ffffffff81051a94>] exit_creds+0x12/0x78
RSP: 0018:ffff8806044f1d78 EFLAGS: 00010202
RAX: 0000000000000000 RBX: ffff880604f22140 RCX: 0000000000019502
RDX: 0000000000000000 RSI: 0000000000000202 RDI: 0000000000000000
RBP: ffff880604f22150 R08: 0000000000000000 R09: ffffffff81a4dc10
R10: 00000000000032a0 R11: ffff880006202500 R12: 0000000000000000
R13: 0000000000c40000 R14: 0000000000008000 R15: 0000000000000001
FS: 00007fbc03d066f0(0000) GS:ffff8800282e0000(0000) knlGS:0000000000000000
CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b
CR2: 0000000000000000 CR3: 000000060f029000 CR4: 00000000000006e0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400
Process sh (pid: 7949, threadinfo ffff8806044f0000, task ffff880603d7c600)
Stack:
ffff880604f22140 ffffffff8103aac5 ffff880604f22140 ffffffff8104d21e
<0> ffff880006202500 0000000000008000 0000000000c38000 ffffffff810bd5b1
<0> 0000000000000000 ffff880603d7c600 00000000ffffdd29 0000000000000003
Call Trace:
[<ffffffff8103aac5>] __put_task_struct+0x5d/0x97
[<ffffffff8104d21e>] kthread_stop+0x50/0x58
[<ffffffff810bd5b1>] offline_pages+0x324/0x3da
[<ffffffff8121111f>] memory_block_change_state+0x179/0x1db
[<ffffffff8121121f>] store_mem_state+0x9e/0xbb
[<ffffffff8111a1f1>] sysfs_write_file+0xd0/0x107
[<ffffffff810c7fe0>] vfs_write+0xad/0x169
[<ffffffff810c8158>] sys_write+0x45/0x6e
[<ffffffff8100296b>] system_call_fastpath+0x16/0x1b
[<00007fbc0344df60>] 0x7fbc0344df60
Code: ff 4d 00 0f 94 c0 84 c0 74 08 48 89 ef e8 1f fd ff ff 5b 5d 31 c0 41 5c c3 53 48 8b 87 20 06 00 00 48 89 fb 48 8b bf 18 06 00 00 <8b> 00 48 c7 83 18 06 00 00 00 00 00 00 f0 ff 0f 0f 94 c0 84 c0
RIP [<ffffffff81051a94>] exit_creds+0x12/0x78
RSP <ffff8806044f1d78>
CR2: 0000000000000000
---[ end trace 75959287252338a5 ]---
---
mm/vmscan.c | 4 +++-
1 files changed, 3 insertions(+), 1 deletions(-)
diff --git a/mm/vmscan.c b/mm/vmscan.c
index eeb3bc9..7585101 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2961,8 +2961,10 @@ void kswapd_stop(int nid)
{
struct task_struct *kswapd = NODE_DATA(nid)->kswapd;
- if (kswapd)
+ if (kswapd) {
kthread_stop(kswapd);
+ NODE_DATA(nid)->kswapd = NULL;
+ }
}
static int __init kswapd_init(void)
--
1.7.1
On Wed, 20 Jun 2012 17:21:53 +0800
Jiang Liu <[email protected]> wrote:
> Function kswapd_stop() will be called to destroy the kswapd work thread
> when all memory of a NUMA node has been offlined. But kswapd_stop() only
> terminates the work thread without resetting NODE_DATA(nid)->kswapd to NULL.
> The stale pointer will prevent kswapd_run() from creating a new work thread
> when adding memory to the memory-less NUMA node again. Eventually the stale
> pointer may cause invalid memory access.
whoops.
>
> ...
>
> --- a/mm/vmscan.c
> +++ b/mm/vmscan.c
> @@ -2961,8 +2961,10 @@ void kswapd_stop(int nid)
> {
> struct task_struct *kswapd = NODE_DATA(nid)->kswapd;
>
> - if (kswapd)
> + if (kswapd) {
> kthread_stop(kswapd);
> + NODE_DATA(nid)->kswapd = NULL;
> + }
> }
>
> static int __init kswapd_init(void)
OK.
This function is full of races (ones which we'll never hit ;)) unless
the caller provides locking. It appears that lock_memory_hotplug() is
the locking, so I propose this addition:
--- a/mm/vmscan.c~memory-hotplug-fix-invalid-memory-access-caused-by-stale-kswapd-pointer-fix
+++ a/mm/vmscan.c
@@ -2955,7 +2955,8 @@ int kswapd_run(int nid)
}
/*
- * Called by memory hotplug when all memory in a node is offlined.
+ * Called by memory hotplug when all memory in a node is offlined. Caller must
+ * hold lock_memory_hotplug().
*/
void kswapd_stop(int nid)
{
--- a/include/linux/mmzone.h~memory-hotplug-fix-invalid-memory-access-caused-by-stale-kswapd-pointer-fix
+++ a/include/linux/mmzone.h
@@ -693,7 +693,7 @@ typedef struct pglist_data {
range, including holes */
int node_id;
wait_queue_head_t kswapd_wait;
- struct task_struct *kswapd;
+ struct task_struct *kswapd; /* Protected by lock_memory_hotplug() */
int kswapd_max_order;
enum zone_type classzone_idx;
} pg_data_t;
_
Also, I think kswapd_lock() and perhaps pglist_data.kswapd itself could
be placed under CONFIG_MEMORY_HOTPLUG to save a bit of space.
On Wed, Jun 20, 2012 at 5:07 PM, Andrew Morton
<[email protected]> wrote:
> On Wed, 20 Jun 2012 17:21:53 +0800
> Jiang Liu <[email protected]> wrote:
>
>> Function kswapd_stop() will be called to destroy the kswapd work thread
>> when all memory of a NUMA node has been offlined. But kswapd_stop() only
>> terminates the work thread without resetting NODE_DATA(nid)->kswapd to NULL.
>> The stale pointer will prevent kswapd_run() from creating a new work thread
>> when adding memory to the memory-less NUMA node again. Eventually the stale
>> pointer may cause invalid memory access.
>
> whoops.
>
>>
>> ...
>>
>> --- a/mm/vmscan.c
>> +++ b/mm/vmscan.c
>> @@ -2961,8 +2961,10 @@ void kswapd_stop(int nid)
>> ?{
>> ? ? ? struct task_struct *kswapd = NODE_DATA(nid)->kswapd;
>>
>> - ? ? if (kswapd)
>> + ? ? if (kswapd) {
>> ? ? ? ? ? ? ? kthread_stop(kswapd);
>> + ? ? ? ? ? ? NODE_DATA(nid)->kswapd = NULL;
>> + ? ? }
>> ?}
>>
>> ?static int __init kswapd_init(void)
>
> OK.
>
> This function is full of races (ones which we'll never hit ;)) unless
> the caller provides locking. ?It appears that lock_memory_hotplug() is
> the locking, so I propose this addition:
>
> --- a/mm/vmscan.c~memory-hotplug-fix-invalid-memory-access-caused-by-stale-kswapd-pointer-fix
> +++ a/mm/vmscan.c
> @@ -2955,7 +2955,8 @@ int kswapd_run(int nid)
> ?}
>
> ?/*
> - * Called by memory hotplug when all memory in a node is offlined.
> + * Called by memory hotplug when all memory in a node is offlined. ?Caller must
> + * hold lock_memory_hotplug().
> ?*/
> ?void kswapd_stop(int nid)
> ?{
> --- a/include/linux/mmzone.h~memory-hotplug-fix-invalid-memory-access-caused-by-stale-kswapd-pointer-fix
> +++ a/include/linux/mmzone.h
> @@ -693,7 +693,7 @@ typedef struct pglist_data {
> ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? range, including holes */
> ? ? ? ?int node_id;
> ? ? ? ?wait_queue_head_t kswapd_wait;
> - ? ? ? struct task_struct *kswapd;
> + ? ? ? struct task_struct *kswapd; ? ? /* Protected by lock_memory_hotplug() */
except
"system_state == SYSTEM_BOOTING"?