lkml.org 
[lkml]   [2013]   [Dec]   [2]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
Patch in this message
/
Date
From
SubjectRe: GPF in aio_migratepage
Hi Kristian, Dave,

Could you please help to check whether the following patch can fix this issue?


Signed-off-by: Gu Zheng <guz.fnst@cn.fujitsu.com>
---
fs/aio.c | 28 ++++++++++------------------
1 files changed, 10 insertions(+), 18 deletions(-)

diff --git a/fs/aio.c b/fs/aio.c
index 08159ed..fc1fd0a 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -223,33 +223,25 @@ static int __init aio_setup(void)
}
__initcall(aio_setup);

-static void put_aio_ring_file(struct kioctx *ctx)
-{
- struct file *aio_ring_file = ctx->aio_ring_file;
- if (aio_ring_file) {
- truncate_setsize(aio_ring_file->f_inode, 0);
-
- /* Prevent further access to the kioctx from migratepages */
- spin_lock(&aio_ring_file->f_inode->i_mapping->private_lock);
- aio_ring_file->f_inode->i_mapping->private_data = NULL;
- ctx->aio_ring_file = NULL;
- spin_unlock(&aio_ring_file->f_inode->i_mapping->private_lock);
-
- fput(aio_ring_file);
- }
-}
-
static void aio_free_ring(struct kioctx *ctx)
{
+ struct file *aio_ring_file = ctx->aio_ring_file;
int i;

+ BUG_ON(!aio_ring_file);
+
+ spin_lock(&aio_ring_file->f_inode->i_mapping->private_lock);
for (i = 0; i < ctx->nr_pages; i++) {
pr_debug("pid(%d) [%d] page->count=%d\n", current->pid, i,
page_count(ctx->ring_pages[i]));
put_page(ctx->ring_pages[i]);
}
-
- put_aio_ring_file(ctx);
+ truncate_setsize(aio_ring_file->f_inode, 0);
+ /* Prevent further access to the kioctx from migratepages */
+ aio_ring_file->f_inode->i_mapping->private_data = NULL;
+ ctx->aio_ring_file = NULL;
+ spin_unlock(&aio_ring_file->f_inode->i_mapping->private_lock);
+ fput(aio_ring_file);

if (ctx->ring_pages && ctx->ring_pages != ctx->internal_pages) {
kfree(ctx->ring_pages);
--
1.7.7


On 11/30/2013 11:28 PM, Kristian Nielsen wrote:

> Benjamin LaHaise <bcrl@kvack.org> writes:
>
>> For Dave: what line is this bug on? Is it the dereference of ctx when
>> doing spin_lock_irqsave(&ctx->completion_lock, flags); or is the
>> ctx->ring_pages[idx] = new; ? From the 64 bit splat, I'm thinking the
>> former, which is quite strange given that the clearing of
>> mapping->private_data is protected by mapping->private_lock. If it's
>> the latter, we might well need to check if ctx->ring_pages is NULL during
>> setup.
>
> I think I got the same BUG (at least it looks very similar, full details
> below).
>
> The bug is on this line:
>
> ctx->ring_pages[idx] = new;
>
> Disassembly:
>
> af7: 48 89 2c d1 mov %rbp,(%rcx,%rdx,8)
>
> ctx->ring_pages is 0xffffffffffffffff (this is x86_64). idx is 13.
>
> RCX: ffffffffffffffff RDX: 000000000000000d
> BUG: unable to handle kernel NULL pointer dereference at 0000000000000067
>
> So we are de-referencing a pointer that is (page **)-1, causing the crash.
>
> If you look closer at the 32-bit dump that Dave gave, you can see that it is
> similar:
>
> 7a2: 89 34 82 mov %esi,(%edx,%eax,4)
>
> RAX: 6b6b6b6b6b6b6b6b RDX: 0000000000000000
>
> Though in this case ctx->ring_pages seems to be NULL and idx=old->index seems
> to be 6b6b6b6b6b6b6b6b, so not completely the same (or maybe I read his dump
> incorrectly).
>
> This is 3.13-rc1. Unfortunately, I do not have a way to reproduce (so far I
> only saw it this once). But I can see if it turns up again, or should I
> install -rc2 and see if it goes away?
>
> I was not doing anything special at the time, normal desktop load (I was using
> the evince pdf viewer).
>
> Let me know if there is anything else I can do to help track this down?
>
> - Kristian.
>
> Full details:
>
> I put my .config here:
>
> http://knielsen-hq.org/config-3.13-rc1-gpf-in-aio-migratepage.txt
>
> BUG output:
>
> BUG: unable to handle kernel NULL pointer dereference at 0000000000000067
> IP: [<ffffffff8113d73f>] aio_migratepage+0xb3/0xe4
> PGD 0
> Oops: 0002 [#1] SMP
> Modules linked in: tun parport_pc ppdev lp parport bnep rfcomm bluetooth cpufreq_userspace cpufreq_stats cpufreq_powersave cpufreq_conservative binfmt_misc uinput fuse nfsd auth_rpcgss oid_registry nfs_acl nfs lockd fscache sunrpc ext3 jbd loop snd_hda_codec_hdmi hid_generic usbhid hid joydev ums_realtek usb_storage snd_hda_codec_realtek iTCO_wdt iTCO_vendor_support arc4 brcmsmac cordic brcmutil b43 mac80211 cfg80211 ssb mmc_core rfkill rng_core pcmcia pcmcia_core nouveau mxm_wmi wmi x86_pkg_temp_thermal coretemp snd_hda_intel kvm_intel snd_hda_codec snd_hwdep snd_pcm_oss kvm snd_mixer_oss snd_seq_midi snd_seq_midi_event snd_pcm crc32c_intel snd_rawmidi snd_page_alloc snd_seq ghash_clmulni_intel snd_timer snd_seq_device lpc_ich aesni_intel mfd_core ttm battery aes_x86_64 ablk_helper drm_kms_helper cryptd lrw gf128mul drm glue_helper psmouse snd pcspkr serio_raw i2c_i801 evdev ehci_pci soundcore ehci_hcd bcma ac acpi_cpufreq video button processor ext4 crc16 jbd2 mbc
> r_mod cdrom crc_t10dif crct10dif_common microcode ahci libahci xhci_hcd libata usbcore scsi_mod usb_common fan thermal thermal_sys r8169 mii
> CPU: 2 PID: 15596 Comm: evince Not tainted 3.13.0-rc1-kn #1
> Hardware name: Compal PBL2021/Base Board Product Name, BIOS 2.40 08/26/2011
> task: ffff88010322f7c0 ti: ffff880102b48000 task.ti: ffff880102b48000
> RIP: 0010:[<ffffffff8113d73f>] [<ffffffff8113d73f>] aio_migratepage+0xb3/0xe4
> RSP: 0018:ffff880102b49798 EFLAGS: 00010213
> RAX: 0000000000000286 RBX: ffffea00038f1640 RCX: ffffffffffffffff
> RDX: 000000000000000d RSI: ffffea00038f1640 RDI: ffffea00038f1640
> RBP: ffffea0007b6a800 R08: 0000000000000000 R09: 000000000000000d
> R10: 0000000000000038 R11: ffffea0007b6a800 R12: ffff880144a30d00
> R13: 0000000000000000 R14: ffff88014ba5b1f8 R15: ffff880144a30ec4
> FS: 00007f68ecfe8960(0000) GS:ffff88024f480000(0000) knlGS:0000000000000000
> CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
> CR2: 0000000000000067 CR3: 0000000051ee8000 CR4: 00000000000407e0
> Stack:
> 000000000000000e 0000000000000286 ffff88024f7f6d80 ffffea00038f1640
> ffffea0007b6a800 0000000000000000 ffff88014ba5b170 0000000000000001
> 0000000000000001 ffffffff810ffc68 ffff88014ba5b1a8 0000000000000000
> Call Trace:
> [<ffffffff810ffc68>] ? move_to_new_page+0x84/0x1ab
> [<ffffffff810cbcbd>] ? get_page+0x9/0x25
> [<ffffffff8110019e>] ? migrate_pages+0x330/0x524
> [<ffffffff810dac77>] ? isolate_freepages_block+0x237/0x237
> [<ffffffff810db651>] ? compact_zone+0x13a/0x301
> [<ffffffff810dba3e>] ? compact_zone_order+0x94/0xa7
> [<ffffffff810dbae9>] ? try_to_compact_pages+0x98/0xec
> [<ffffffff8138ef42>] ? __alloc_pages_direct_compact+0xa9/0x19a
> [<ffffffff810c8567>] ? __alloc_pages_nodemask+0x46f/0x7f3
> [<ffffffff812cf2bc>] ? __kmalloc_reserve.isra.42+0x2a/0x6d
> [<ffffffff810f64df>] ? alloc_pages_current+0xac/0xc6
> [<ffffffff812cbd47>] ? sock_alloc_send_pskb+0x1fc/0x345
> [<ffffffff812d2625>] ? memcpy_fromiovecend+0x48/0x6f
> [<ffffffff812d2ac5>] ? skb_copy_datagram_from_iovec+0x128/0x1f2
> [<ffffffff812ca529>] ? sk_wake_async+0x19/0x3c
> [<ffffffff8134c605>] ? unix_stream_sendmsg+0x12e/0x2e9
> [<ffffffff812c8001>] ? sock_aio_write+0xc0/0xd5
> [<ffffffff81115581>] ? set_restore_sigmask+0x2d/0x2d
> [<ffffffff81106da4>] ? do_sync_readv_writev+0x48/0x6b
> [<ffffffff812c7f41>] ? sock_alloc_file+0x119/0x119
> [<ffffffff81107e9c>] ? do_readv_writev+0xb4/0x121
> [<ffffffff812c7f41>] ? sock_alloc_file+0x119/0x119
> [<ffffffff810015d7>] ? __switch_to+0x1b1/0x3de
> [<ffffffff8111c1ce>] ? fget_light+0x6b/0x7c
> [<ffffffff81106d10>] ? fdget+0xe/0x17
> [<ffffffff8110807d>] ? SyS_writev+0x51/0xaa
> [<ffffffff813997e2>] ? system_call_fastpath+0x16/0x1b
> Code: 48 89 de 48 89 ef 48 89 44 24 08 e8 03 22 fc ff 48 8b 53 10 49 3b 94 24 a0 00 00 00 48 8b 44 24 08 73 0c 49 8b 8c 24 98 00 00 00 <48> 89 2c d1 48 89 c6 4c 89 ff e8 74 6e 25 00 eb 06 41 bd f0 ff
> RIP [<ffffffff8113d73f>] aio_migratepage+0xb3/0xe4
> RSP <ffff880102b49798>
> CR2: 0000000000000067
> ---[ end trace be5b4877a98efec5 ]---
> ------------[ cut here ]------------
>
>
> After this I got lots of stuff like
>
> WARNING: CPU: 4 PID: 15642 at kernel/watchdog.c:245 watchdog_overflow_callback+0x80/0xa3()
> Watchdog detected hard LOCKUP on cpu 4
> BUG: soft lockup - CPU#3 stuck for 22s! [EvJobScheduler:15653]
>
> But I assume that is just due to crashing with two spinlocks held.
>
>
> Disassembly of aio_migratepage():
>
> 0000000000000a44 <aio_migratepage>:
> a44: 41 57 push %r15
> a46: 41 56 push %r14
> a48: 41 55 push %r13
> a4a: 41 54 push %r12
> a4c: 55 push %rbp
> a4d: 53 push %rbx
> a4e: 48 89 d3 mov %rdx,%rbx
> a51: 48 83 ec 18 sub $0x18,%rsp
> a55: 48 8b 02 mov (%rdx),%rax
> a58: f6 c4 20 test $0x20,%ah
> a5b: 74 02 je a5f <aio_migratepage+0x1b>
> a5d: 0f 0b ud2
> a5f: 49 89 fc mov %rdi,%r12
> a62: 48 89 d7 mov %rdx,%rdi
> a65: 48 89 f5 mov %rsi,%rbp
> a68: 89 4c 24 08 mov %ecx,0x8(%rsp)
> a6c: e8 00 00 00 00 callq a71 <aio_migratepage+0x2d>
> a71: 44 8b 44 24 08 mov 0x8(%rsp),%r8d
> a76: 31 c9 xor %ecx,%ecx
> a78: 48 89 da mov %rbx,%rdx
> a7b: 48 89 ee mov %rbp,%rsi
> a7e: 4c 89 e7 mov %r12,%rdi
> a81: e8 00 00 00 00 callq a86 <aio_migratepage+0x42>
> a86: 85 c0 test %eax,%eax
> a88: 41 89 c5 mov %eax,%r13d
> a8b: 74 0a je a97 <aio_migratepage+0x53>
> a8d: 48 89 df mov %rbx,%rdi
> a90: e8 92 ff ff ff callq a27 <get_page>
> a95: eb 7f jmp b16 <aio_migratepage+0xd2>
> a97: 4d 8d b4 24 88 00 00 lea 0x88(%r12),%r14
> a9e: 00
> a9f: 48 89 ef mov %rbp,%rdi
> aa2: e8 80 ff ff ff callq a27 <get_page>
> aa7: 4c 89 f7 mov %r14,%rdi
> aaa: e8 00 00 00 00 callq aaf <aio_migratepage+0x6b>
> aaf: 4d 8b a4 24 a0 00 00 mov 0xa0(%r12),%r12
> ab6: 00
> ab7: 4d 85 e4 test %r12,%r12
> aba: 74 4c je b08 <aio_migratepage+0xc4>
> abc: 4d 8d bc 24 c4 01 00 lea 0x1c4(%r12),%r15
> ac3: 00
> ac4: 4c 89 ff mov %r15,%rdi
> ac7: e8 00 00 00 00 callq acc <aio_migratepage+0x88>
> acc: 48 89 de mov %rbx,%rsi
> acf: 48 89 ef mov %rbp,%rdi
> ad2: 48 89 44 24 08 mov %rax,0x8(%rsp)
> ad7: e8 00 00 00 00 callq adc <aio_migratepage+0x98>
> adc: 48 8b 53 10 mov 0x10(%rbx),%rdx
> ae0: 49 3b 94 24 a0 00 00 cmp 0xa0(%r12),%rdx
> ae7: 00
> ae8: 48 8b 44 24 08 mov 0x8(%rsp),%rax
> aed: 73 0c jae afb <aio_migratepage+0xb7>
> aef: 49 8b 8c 24 98 00 00 mov 0x98(%r12),%rcx
> af6: 00
> # We get the crash on this next instruction, %rcx is 0xffffffffffffffff
> af7: 48 89 2c d1 mov %rbp,(%rcx,%rdx,8)
> afb: 48 89 c6 mov %rax,%rsi
> afe: 4c 89 ff mov %r15,%rdi
> b01: e8 00 00 00 00 callq b06 <aio_migratepage+0xc2>
> b06: eb 06 jmp b0e <aio_migratepage+0xca>
> b08: 41 bd f0 ff ff ff mov $0xfffffff0,%r13d
> b0e: 4c 89 f7 mov %r14,%rdi
> b11: e8 b7 fa ff ff callq 5cd <spin_unlock>
> b16: 48 83 c4 18 add $0x18,%rsp
> b1a: 44 89 e8 mov %r13d,%eax
> b1d: 5b pop %rbx
> b1e: 5d pop %rbp
> b1f: 41 5c pop %r12
> b21: 41 5d pop %r13
> b23: 41 5e pop %r14
> b25: 41 5f pop %r15
> b27: c3 retq
> --
> To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at http://vger.kernel.org/majordomo-info.html
> Please read the FAQ at http://www.tux.org/lkml/
>




\
 
 \ /
  Last update: 2013-12-02 11:41    [W:1.802 / U:0.400 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site