Bug 108771 - scsi: ses: kasan: ses_enclosure_data_process use after free on boot SAS2X28
Summary: scsi: ses: kasan: ses_enclosure_data_process use after free on boot SAS2X28
Status: RESOLVED PATCH_ALREADY_AVAILABLE
Alias: None
Product: IO/Storage
Classification: Unclassified
Component: SCSI (show other bugs)
Hardware: x86-64 Linux
: P1 normal
Assignee: scsi_drivers-other
URL:
Keywords:
Depends on:
Blocks:
 
Reported: 2015-12-02 10:57 UTC by Pavel Tikhomirov
Modified: 2016-12-30 09:54 UTC (History)
2 users (show)

See Also:
Kernel Version: 4.3
Subsystem:
Regression: No
Bisected commit-id:

Attachments
Full /var/log/messagess log and module ses.ko (158.51 KB, application/gzip)
2015-12-02 10:57 UTC, Pavel Tikhomirov 		Details
Add an attachment (proposed patch, testcase, etc.)

Description Pavel Tikhomirov 2015-12-02 10:57:34 UTC 
Created attachment 196301 [details]
Full /var/log/messagess log and module ses.ko

Here is my setup:
Kernel: Linux 4.3 (tag:v4.3 commit:6a13feb9c8)
SCSI ses device: Host: scsi0 Channel: 00 Id: 16 Lun: 00 Vendor: LSI Model: SAS2X28 Rev: 0e12 Type: Enclosure ANSI  SCSI revision: 05

Full /var/log/messagess log in archive attached: debug-kernel-kasan-system-log.txt
Module in archive attached: ses.ko

On debug kernel on boot when attaching enclosure scsi device, KASan detects use after free in ses_enclosure_data_process+0xbe5(see kasan report in the end).


nm -A ./drivers/scsi/ses.ko | grep ses_enclosure_data_process
./drivers/scsi/ses.ko:0000000000002570 t ses_enclosure_data_process

objdump -D -S -l ./drivers/scsi/ses.ko --start-address=0x0000000000002570


On offset 0x3155(0x2570+0xbe5) there is code generated by kasan:


>    3144:       4c 89 5d a0             mov    %r11,-0x60(%rbp)
    3148:       44 89 45 a8             mov    %r8d,-0x58(%rbp)
    314c:       44 89 4d b0             mov    %r9d,-0x50(%rbp)
/vzt/linux/drivers/scsi/ses.c:545
			}
			if (desc_ptr)
				desc_ptr += len;

			if (addl_desc_ptr)
				addl_desc_ptr += addl_desc_ptr[1] + 2;
    3150:	e8 00 00 00 00       	callq  3155 <ses_enclosure_data_process+0xbe5>
    3155:	4c 8b 5d a0          	mov    -0x60(%rbp),%r11
    3159:	44 8b 45 a8          	mov    -0x58(%rbp),%r8d
    315d:	44 8b 4d b0          	mov    -0x50(%rbp),%r9d
    3161:	e9 34 f7 ff ff       	jmpq   289a <ses_enclosure_data_process+0x32a>


To witch we jump from:


/vzt/linux/drivers/scsi/ses.c:545
                                addl_desc_ptr += addl_desc_ptr[1] + 2;
    2877:       49 8d 7c 24 01          lea    0x1(%r12),%rdi
    287c:       48 89 f8                mov    %rdi,%rax
    287f:       48 89 fa                mov    %rdi,%rdx
    2882:       48 c1 e8 03             shr    $0x3,%rax
    2886:       83 e2 07                and    $0x7,%edx
    2889:       42 0f b6 04 28          movzbl (%rax,%r13,1),%eax
    288e:       38 d0                   cmp    %dl,%al
    2890:       7f 08                   jg     289a <ses_enclosure_data_process+0x32a>
    2892:       84 c0                   test   %al,%al
>    2894:       0f 85 aa 08 00 00       jne    3144
>    <ses_enclosure_data_process+0xbd4>
    289a:       41 0f b6 44 24 01       movzbl 0x1(%r12),%eax
    28a0:       4d 8d 64 04 02          lea    0x2(%r12,%rax,1),%r12


Address addl_desc_ptr[1] is not allocated here but we want to read it. Actualy we iterate through ses_dev->page10 here and it ends unexpectedly. We get number of iterations from ses_dev->page1_num_types and ses_dev->page1_types, so it seam that meta-data given by device is not consistent for page 1 and page 10.

My ideas on this:
a) In ses_process_descriptor we get enclosure_component->addr from addl_desc_ptr only for ENCLOSURE_COMPONENT_DEVICE and ENCLOSURE_COMPONENT_ARRAY_DEVICE but iterate for all entries of all types, may be we need to move to next entry in addl_desc_ptr for only those types?

b) May be we need same check as we have for page 7, to stop when we hit a bufer end.

Sorry I'm not too common with SCSI Enclosure Services specification and how it should work.

Thanks in advance for your help, Pavel.

Here is KASan output:

================================================================== 
BUG: KASan: use after free in ses_enclosure_data_process+0xbe5/0xe40 [ses] at addr ffff881fed1c8c01  
Read of size 1 by task systemd-udevd/1348
=============================================================================
BUG kmalloc-512 (Not tainted): kasan: bad access detected 
-----------------------------------------------------------------------------

Disabling lock debugging due to kernel taint
INFO: Slab 0xffffea007fb47200 objects=32 used=30 fp=0xffff881fed1c8800 flags=0x2fffff80004080 
INFO: Object 0xffff881fed1c8c00 @offset=3072 fp=0xffff881fed1c8e00 

Bytes b4 ffff881fed1c8bf0: 0a 08 0b 09 0c 0a 0d 0b ff ff ff ff ff ff ff ff  ................
Object ffff881fed1c8c00: 00 8e 1c ed 1f 88 ff ff 08 8c 1c ed 1f 88 ff ff  ................ 
Object ffff881fed1c8c10: 08 8c 1c ed 1f 88 ff ff 18 8c 1c ed 1f 88 ff ff  ................ 
Object ffff881fed1c8c20: 18 8c 1c ed 1f 88 ff ff c0 ff ff ff 1f 00 00 00  ................ 
Object ffff881fed1c8c30: 30 8c 1c ed 1f 88 ff ff 30 8c 1c ed 1f 88 ff ff  0.......0....... 
Object ffff881fed1c8c40: 70 9e dc 81 ff ff ff ff c0 aa 8a 84 ff ff ff ff  p...............
Object ffff881fed1c8c50: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00  ................
Object ffff881fed1c8c60: c0 dc 79 82 ff ff ff ff 00 00 00 00 00 00 00 00  ..y.............
Object ffff881fed1c8c70: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00  ................
Object ffff881fed1c8c80: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00  ................
Object ffff881fed1c8c90: b0 a0 1b 81 ff ff ff ff 28 8c 1c ed 1f 88 ff ff  ........(.......
Object ffff881fed1c8ca0: 00 00 20 00 ff ff ff ff ff ff ff ff 00 00 00 00  .. .............
Object ffff881fed1c8cb0: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00  ................
Object ffff881fed1c8cc0: 00 00 00 00 00 00 00 00 80 aa 8a 84 ff ff ff ff  ................
Object ffff881fed1c8cd0: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00  ................
Object ffff881fed1c8ce0: 00 dd 79 82 ff ff ff ff 00 00 00 00 00 00 00 00  ..y.............
Object ffff881fed1c8cf0: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00  ................
Object ffff881fed1c8d00: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00  ................
Object ffff881fed1c8d10: 00 00 00 00 00 00 00 00 ab 9e fb ff 00 00 00 00  ................
Object ffff881fed1c8d20: 00 00 00 00 03 00 00 00 00 00 00 00 06 00 00 00  ................
Object ffff881fed1c8d30: 02 00 00 00 00 00 00 00 08 81 9a ea 1f 88 ff ff  ................
Object ffff881fed1c8d40: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00  ................
Object ffff881fed1c8d50: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00  ................
Object ffff881fed1c8d60: 00 00 00 00 c4 00 00 00 00 80 9a ea 1f 88 ff ff  ................
Object ffff881fed1c8d70: 00 19 b4 ef 37 88 ff ff a0 66 dd 81 ff ff ff ff  ....7....f......
Object ffff881fed1c8d80: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00  ................
Object ffff881fed1c8d90: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00  ................
Object ffff881fed1c8da0: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00  ................
Object ffff881fed1c8db0: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00  ................
Object ffff881fed1c8dc0: 00 00 00 00 00 00 00 00 00 00 00 00 01 00 00 00  ................
Object ffff881fed1c8dd0: ff 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00  ................
Object ffff881fed1c8de0: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00  ................
Object ffff881fed1c8df0: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00  ................
CPU: 0 PID: 1348 Comm: systemd-udevd Tainted: G    B           4.3.0 #3
Hardware name: DEPO Computers X9DRi-LN4+/X9DR3-LN4+/X9DRi-LN4+/X9DR3-LN4+, BIOS 3.2 03/04/2015
ffff881fed1c8c00 000000002924ed40 ffff8837ea77f6f8 ffffffff8199df07
ffff881ffd007340 ffff8837ea77f728 ffffffff815af4e9 ffff881ffd007340
ffffea007fb47200 ffff881fed1c8c00 ffff881fe85340c1 ffff8837ea77f750
Call Trace:
[<ffffffff8199df07>] dump_stack+0x4b/0x64
[<ffffffff815af4e9>] print_trailer+0xf9/0x150
[<ffffffff815b5e94>] object_err+0x34/0x40
[<ffffffff815b8a28>] kasan_report_error+0x1e8/0x3f0
[<ffffffff8125a53f>] ? __init_waitqueue_head+0x3f/0xa0
[<ffffffff81d675a9>] ? pm_runtime_init+0x399/0x450
[<ffffffff815b8c91>] __asan_report_load1_noabort+0x61/0x70
[<ffffffffa11fb155>] ? ses_enclosure_data_process+0xbe5/0xe40 [ses]
[<ffffffffa11fb155>] ses_enclosure_data_process+0xbe5/0xe40 [ses] 
[<ffffffffa11fc1ce>] ses_intf_add+0x9ae/0xdf0 [ses] 
[<ffffffff8127c100>] ? trace_hardirqs_on_caller+0x360/0x580
[<ffffffff81d4d1bf>] class_interface_register+0x1ef/0x300
[<ffffffff81d4cfd0>] ? class_dev_iter_exit+0x10/0x10
[<ffffffff81a021a0>] ? debug_object_active_state+0x370/0x370
[<ffffffff815b3b76>] ? kfree+0xe6/0x2a0
[<ffffffff810021a1>] ? do_one_initcall+0x131/0x300
[<ffffffffa1208000>] ? 0xffffffffa1208000
[<ffffffff81de57b8>] scsi_register_interface+0x38/0x50
[<ffffffffa1208013>] ses_init+0x13/0x1000 [ses]
[<ffffffff810021b1>] do_one_initcall+0x141/0x300
[<ffffffff81002070>] ? try_to_run_init_process+0x40/0x40
[<ffffffff815b8156>] ? kasan_unpoison_shadow+0x36/0x50
[<ffffffff815b8156>] ? kasan_unpoison_shadow+0x36/0x50
[<ffffffff815b8267>] ? __asan_register_globals+0x87/0xa0
[<ffffffff814b00ee>] do_init_module+0x1d0/0x5aa
[<ffffffff81332b8f>] load_module+0x409f/0x61e0
[<ffffffff81325e50>] ? __symbol_put+0xc0/0xc0
[<ffffffff8132eaf0>] ? layout_and_allocate+0x3c80/0x3c80
[<ffffffff81619ee0>] ? open_exec+0x50/0x50
[<ffffffff813267ad>] ? copy_module_from_fd.isra.46+0x1dd/0x2f0
[<ffffffff8133502b>] SyS_finit_module+0x12b/0x160
[<ffffffff81334f00>] ? SyS_init_module+0x230/0x230
[<ffffffff81004044>] ? lockdep_sys_exit_thunk+0x12/0x14
[<ffffffff82523bb2>] entry_SYSCALL_64_fastpath+0x12/0x76
Memory state around the buggy address:
ffff881fed1c8b00: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
ffff881fed1c8b80: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
>ffff881fed1c8c00: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
                  ^
ffff881fed1c8c80: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
ffff881fed1c8d00: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
==================================================================
```
Comment 1 Pavel Tikhomirov 2015-12-07 14:01:41 UTC 
Aditional info about enclosue(from that node, but older 3.10 based kernel):

[root@p9 crash]# modprobe sg
[root@p9 crash]#  sg_map -i
/dev/sg0  LSI       SAS2X28           0e12
/dev/sg1  /dev/sda  LSI  MR9260-4i  2.13
[root@p9 crash]# lsscsi -gs
[1:0:16:0]   enclosu LSI      SAS2X28          0e12  -          /dev/sg0        -
[1:2:0:0]    disk    LSI      MR9260-4i        2.13  /dev/sda   /dev/sg1   3.99TB
[root@p9 crash]#  sg_ses /dev/sg0
  LSI       SAS2X28           0e12
Supported diagnostic pages:
  Supported Diagnostic Pages [sdp] [0x0]
  Configuration (SES) [cf] [0x1]
  Enclosure Status/Control (SES) [ec,es] [0x2]
  Element Descriptor (SES) [ed] [0x7]
  Additional Element Status (SES-2) [aes] [0xa]
  Download Microcode (SES-2) [dm] [0xe]
[root@p9 crash]#  sg_ses /dev/sg1
  LSI  MR9260-4i  2.13
    disk device (not an enclosure)
Supported diagnostic pages:
Comment 2 Pavel Tikhomirov 2015-12-09 12:35:21 UTC 
On 12/08/2015 07:16 PM, James Bottomley wrote:
> On Mon, 2015-12-07 at 14:01 +0000, bugzilla-daemon@bugzilla.kernel.org
> wrote:
>> https://bugzilla.kernel.org/show_bug.cgi?id=108771
>>
>> --- Comment #1 from Pavel Tikhomirov <ptikhomirov@virtuozzo.com> ---
>> Aditional info about enclosue(from that node, but older 3.10 based kernel):
>>
>> [root@p9 crash]# modprobe sg
>> [root@p9 crash]#  sg_map -i
>> /dev/sg0  LSI       SAS2X28           0e12
>> /dev/sg1  /dev/sda  LSI  MR9260-4i  2.13
>> [root@p9 crash]# lsscsi -gs
>> [1:0:16:0]   enclosu LSI      SAS2X28          0e12  -          /dev/sg0
>> -
>> [1:2:0:0]    disk    LSI      MR9260-4i        2.13  /dev/sda   /dev/sg1
>> 3.99TB
>> [root@p9 crash]#  sg_ses /dev/sg0
>>    LSI       SAS2X28           0e12
>> Supported diagnostic pages:
>>    Supported Diagnostic Pages [sdp] [0x0]
>>    Configuration (SES) [cf] [0x1]
>>    Enclosure Status/Control (SES) [ec,es] [0x2]
>>    Element Descriptor (SES) [ed] [0x7]
>>    Additional Element Status (SES-2) [aes] [0xa]
>>    Download Microcode (SES-2) [dm] [0xe]
>> [root@p9 crash]#  sg_ses /dev/sg1
>>    LSI  MR9260-4i  2.13
>>      disk device (not an enclosure)
>> Supported diagnostic pages:
>
> OK, can you give us the contents of pages 1, 2 and 10 with
>
> sg_ses --page=1 --hex /dev/sg0
> sg_ses --page=2 --hex /dev/sg0
> sg_ses --page=10 --hex /dev/sg0
>
> The version of the kernel you do this on doesn't really matter.

Here are these pages:

[root@p9 ~]# sg_ses --page=1 --hex /dev/sg0
   LSI       SAS2X28           0e12
Response in hex from diagnostic page: Configuration (SES)
  00     01 00 00 c9 00 00 00 00  11 00 09 2c 50 03 04 80 
...........,P...
  10     00 a7 1e bf 4c 53 49 20  20 20 20 20 53 41 53 32    ....LSI 
  SAS2
  20     58 32 38 20 20 20 20 20  20 20 20 20 30 65 31 32    X28 
  0e12
  30     11 22 33 44 55 00 00 00  17 0c 00 0b 04 01 00 13 
."3DU...........
  40     03 03 00 04 12 02 00 0f  02 02 00 0e 0e 01 00 09 
................
  50     18 01 00 0d 19 0e 00 0e  11 02 00 0e 44 72 69 76 
............Driv
  60     65 20 53 6c 6f 74 73 54  65 6d 70 65 72 61 74 75    e 
SlotsTemperatu
  70     72 65 20 53 65 6e 73 6f  72 73 46 61 6e 73 56 6f    re 
SensorsFansVo
  80     6c 74 61 67 65 20 53 65  6e 73 6f 72 73 50 6f 77    ltage 
SensorsPow
  90     65 72 20 53 75 70 70 6c  69 65 73 45 6e 63 6c 6f    er 
SuppliesEnclo
  a0     73 75 72 65 53 41 53 20  45 78 70 61 6e 64 65 72    sureSAS 
Expander
  b0     73 53 41 53 20 43 6f 6e  6e 65 63 74 6f 72 73 45    sSAS 
ConnectorsE
  c0     74 68 65 72 6e 65 74 20  70 6f 72 74 73             thernet ports
[root@p9 ~]# sg_ses --page=2 --hex /dev/sg0
   LSI       SAS2X28           0e12
Response in hex from diagnostic page: Enclosure Status (SES)
  00     02 00 00 c0 00 00 00 00  00 00 00 00 05 00 00 00 
................
  10     05 00 00 00 01 00 00 00  05 00 00 00 05 00 00 00 
................
  20     01 00 00 00 05 00 00 00  05 00 00 00 01 00 00 00 
................
  30     05 00 00 00 05 00 00 00  01 00 00 00 00 00 00 00 
................
  40     01 00 2c 00 00 00 00 00  05 00 00 50 05 00 00 50 
..,........P...P
  50     05 00 00 50 00 00 00 00  01 00 01 f9 01 00 04 b3 
...P............
  60     00 00 00 00 47 80 00 20  47 80 00 20 00 00 00 00    ....G.. G.. 
....
  70     01 00 00 00 00 00 00 00  01 00 00 00 00 00 00 00 
................
  80     01 11 ff 00 01 11 ff 00  01 20 00 00 01 20 00 00    ......... 
... ..
  90     01 20 00 00 01 20 00 00  01 20 00 00 01 20 00 00    . ... ... 
... ..
  a0     01 20 00 00 01 20 00 00  01 20 00 00 01 20 00 00    . ... ... 
... ..
  b0     01 20 00 00 01 20 00 00  00 00 00 00 00 00 00 00    . ... 
..........
  c0     00 00 00 00                                         ....
[root@p9 ~]# sg_ses --page=10 --hex /dev/sg0
   LSI       SAS2X28           0e12
Response in hex from diagnostic page: Additional Element Status (SES-2)
  00     0a 00 01 fc 00 00 00 00  16 22 00 00 01 00 00 00 
........."......
  10     00 00 00 00 00 00 00 00  00 00 00 00 00 00 00 00 
................
  20     00 00 00 00 00 00 00 00  00 00 00 00 16 22 00 01 
............."..
  30     01 00 00 01 00 00 00 00  00 00 00 00 00 00 00 00 
................
  40     00 00 00 00 00 00 00 00  00 00 00 00 00 00 00 00 
................
  50     16 22 00 02 01 00 00 02  00 00 00 01 50 03 04 80 
."..........P...
  60     00 a7 1e bf 50 03 04 80  00 a7 1e ae 00 00 00 00 
....P...........
  70     00 00 00 00 16 22 00 03  01 00 00 03 00 00 00 00 
....."..........
  80     00 00 00 00 00 00 00 00  00 00 00 00 00 00 00 00 
................
  90     00 00 00 00 00 00 00 00  16 22 00 04 01 00 00 04 
........."......
  a0     00 00 00 00 00 00 00 00  00 00 00 00 00 00 00 00 
................
  b0     00 00 00 00 00 00 00 00  00 00 00 00 16 22 00 05 
............."..
  c0     01 00 00 05 00 00 00 01  50 03 04 80 00 a7 1e bf 
........P.......
  d0     50 03 04 80 00 a7 1e b1  00 00 00 00 00 00 00 00 
P...............
  e0     16 22 00 06 01 00 00 06  00 00 00 00 00 00 00 00 
."..............
  f0     00 00 00 00 00 00 00 00  00 00 00 00 00 00 00 00 
................
  100    00 00 00 00 16 22 00 07  01 00 00 07 00 00 00 00 
....."..........
  110    00 00 00 00 00 00 00 00  00 00 00 00 00 00 00 00 
................
  120    00 00 00 00 00 00 00 00  16 22 00 08 01 00 00 08 
........."......
  130    00 00 00 01 50 03 04 80  00 a7 1e bf 50 03 04 80 
....P.......P...
  140    00 a7 1e b4 00 00 00 00  00 00 00 00 16 22 00 09 
............."..
  150    01 00 00 09 00 00 00 00  00 00 00 00 00 00 00 00 
................
  160    00 00 00 00 00 00 00 00  00 00 00 00 00 00 00 00 
................
  170    16 22 00 0a 01 00 00 0a  00 00 00 00 00 00 00 00 
."..............
  180    00 00 00 00 00 00 00 00  00 00 00 00 00 00 00 00 
................
  190    00 00 00 00 16 22 00 0b  01 00 00 0b 00 00 00 01 
....."..........
  1a0    50 03 04 80 00 a7 1e bf  50 03 04 80 00 a7 1e b7 
P.......P.......
  1b0    00 00 00 00 00 00 00 00  16 46 00 15 1c 40 00 00 
.........F...@..
  1c0    50 03 04 80 00 a7 1e bf  00 ff 00 ff 00 ff 00 ff 
P...............
  1d0    01 ff 01 ff 01 ff 01 ff  ff ff ff ff ff ff ff ff 
................
  1e0    02 00 03 01 04 02 05 03  06 04 07 05 08 06 09 07 
................
  1f0    0a 08 0b 09 0c 0a 0d 0b  ff ff ff ff ff ff ff ff 
................

Thanks a lot,
Pavel

>
> Thanks,
>
> James
>
>
> --
> To unsubscribe from this list: send the line "unsubscribe linux-scsi" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at  http://vger.kernel.org/majordomo-info.html
>
Comment 3 Pavel Tikhomirov 2015-12-11 08:03:27 UTC 
On 12/10/2015 03:43 AM, James Bottomley wrote:
> On Wed, 2015-12-09 at 15:35 +0300, Pavel Tikhomirov wrote:
>>
>> On 12/08/2015 07:16 PM, James Bottomley wrote:
>>> On Mon, 2015-12-07 at 14:01 +0000, bugzilla-daemon@bugzilla.kernel.org
>>> wrote:
>>>> https://bugzilla.kernel.org/show_bug.cgi?id=108771
>>>>
>>>> --- Comment #1 from Pavel Tikhomirov <ptikhomirov@virtuozzo.com> ---
>>>> Aditional info about enclosue(from that node, but older 3.10 based
>>>> kernel):
>>>>
>>>> [root@p9 crash]# modprobe sg
>>>> [root@p9 crash]#  sg_map -i
>>>> /dev/sg0  LSI       SAS2X28           0e12
>>>> /dev/sg1  /dev/sda  LSI  MR9260-4i  2.13
>>>> [root@p9 crash]# lsscsi -gs
>>>> [1:0:16:0]   enclosu LSI      SAS2X28          0e12  -          /dev/sg0
>>>> -
>>>> [1:2:0:0]    disk    LSI      MR9260-4i        2.13  /dev/sda   /dev/sg1
>>>> 3.99TB
>>>> [root@p9 crash]#  sg_ses /dev/sg0
>>>>     LSI       SAS2X28           0e12
>>>> Supported diagnostic pages:
>>>>     Supported Diagnostic Pages [sdp] [0x0]
>>>>     Configuration (SES) [cf] [0x1]
>>>>     Enclosure Status/Control (SES) [ec,es] [0x2]
>>>>     Element Descriptor (SES) [ed] [0x7]
>>>>     Additional Element Status (SES-2) [aes] [0xa]
>>>>     Download Microcode (SES-2) [dm] [0xe]
>>>> [root@p9 crash]#  sg_ses /dev/sg1
>>>>     LSI  MR9260-4i  2.13
>>>>       disk device (not an enclosure)
>>>> Supported diagnostic pages:
>>>
>>> OK, can you give us the contents of pages 1, 2 and 10 with
>>>
>>> sg_ses --page=1 --hex /dev/sg0
>>> sg_ses --page=2 --hex /dev/sg0
>>> sg_ses --page=10 --hex /dev/sg0
>>>
>>> The version of the kernel you do this on doesn't really matter.
>>
>> Here are these pages:
>>
>> [root@p9 ~]# sg_ses --page=1 --hex /dev/sg0
>>     LSI       SAS2X28           0e12
>> Response in hex from diagnostic page: Configuration (SES)
>>    00     01 00 00 c9 00 00 00 00  11 00 09 2c 50 03 04 80
>> ...........,P...
>>    10     00 a7 1e bf 4c 53 49 20  20 20 20 20 53 41 53 32    ....LSI
>>    SAS2
>>    20     58 32 38 20 20 20 20 20  20 20 20 20 30 65 31 32    X28
>>    0e12
>>    30     11 22 33 44 55 00 00 00  17 0c 00 0b 04 01 00 13
>> ."3DU...........
>>    40     03 03 00 04 12 02 00 0f  02 02 00 0e 0e 01 00 09
>> ................
>>    50     18 01 00 0d 19 0e 00 0e  11 02 00 0e 44 72 69 76
>> ............Driv
>>    60     65 20 53 6c 6f 74 73 54  65 6d 70 65 72 61 74 75    e
>> SlotsTemperatu
>>    70     72 65 20 53 65 6e 73 6f  72 73 46 61 6e 73 56 6f    re
>> SensorsFansVo
>>    80     6c 74 61 67 65 20 53 65  6e 73 6f 72 73 50 6f 77    ltage
>> SensorsPow
>>    90     65 72 20 53 75 70 70 6c  69 65 73 45 6e 63 6c 6f    er
>> SuppliesEnclo
>>    a0     73 75 72 65 53 41 53 20  45 78 70 61 6e 64 65 72    sureSAS
>> Expander
>>    b0     73 53 41 53 20 43 6f 6e  6e 65 63 74 6f 72 73 45    sSAS
>> ConnectorsE
>>    c0     74 68 65 72 6e 65 74 20  70 6f 72 74 73             thernet ports
>
> Wow, that's some crazy enclosure.  The description says it's a single
> primary subenclosure with 9 different element types comprising 12 Device
> slots, 1 temperature sensor, 3 fans, 2 voltage sensors, 2 power
> supplies, 1 Enclosure, 1 SAS Expander,  14 SAS connectors, 2
> Communications ports. For 38 total element descriptors
>
>> [root@p9 ~]# sg_ses --page=2 --hex /dev/sg0
>>     LSI       SAS2X28           0e12
>> Response in hex from diagnostic page: Enclosure Status (SES)
>>    00     02 00 00 c0 00 00 00 00  00 00 00 00 05 00 00 00
>> ................
>>    10     05 00 00 00 01 00 00 00  05 00 00 00 05 00 00 00
>> ................
>>    20     01 00 00 00 05 00 00 00  05 00 00 00 01 00 00 00
>> ................
>>    30     05 00 00 00 05 00 00 00  01 00 00 00 00 00 00 00
>> ................
>>    40     01 00 2c 00 00 00 00 00  05 00 00 50 05 00 00 50
>> ..,........P...P
>>    50     05 00 00 50 00 00 00 00  01 00 01 f9 01 00 04 b3
>> ...P............
>>    60     00 00 00 00 47 80 00 20  47 80 00 20 00 00 00 00    ....G.. G..
>> ....
>>    70     01 00 00 00 00 00 00 00  01 00 00 00 00 00 00 00
>> ................
>>    80     01 11 ff 00 01 11 ff 00  01 20 00 00 01 20 00 00    .........
>> ... ..
>>    90     01 20 00 00 01 20 00 00  01 20 00 00 01 20 00 00    . ... ...
>> ... ..
>>    a0     01 20 00 00 01 20 00 00  01 20 00 00 01 20 00 00    . ... ...
>> ... ..
>>    b0     01 20 00 00 01 20 00 00  00 00 00 00 00 00 00 00    . ...
>> ..........
>>    c0     00 00 00 00
>
> Given each type has one overall descriptor followed by the individual
> ones, we have 38 + 9 = 47 total descriptors, which is what we see here.
>
>> [root@p9 ~]# sg_ses --page=10 --hex /dev/sg0
>>     LSI       SAS2X28           0e12
>> Response in hex from diagnostic page: Additional Element Status (SES-2)
>>    00     0a 00 01 fc 00 00 00 00  16 22 00 00 01 00 00 00
>> ........."......
>>    10     00 00 00 00 00 00 00 00  00 00 00 00 00 00 00 00
>> ................
>>    20     00 00 00 00 00 00 00 00  00 00 00 00 16 22 00 01
>> ............."..
>>    30     01 00 00 01 00 00 00 00  00 00 00 00 00 00 00 00
>> ................
>>    40     00 00 00 00 00 00 00 00  00 00 00 00 00 00 00 00
>> ................
>>    50     16 22 00 02 01 00 00 02  00 00 00 01 50 03 04 80
>> ."..........P...
>>    60     00 a7 1e bf 50 03 04 80  00 a7 1e ae 00 00 00 00
>> ....P...........
>>    70     00 00 00 00 16 22 00 03  01 00 00 03 00 00 00 00
>> ....."..........
>>    80     00 00 00 00 00 00 00 00  00 00 00 00 00 00 00 00
>> ................
>>    90     00 00 00 00 00 00 00 00  16 22 00 04 01 00 00 04
>> ........."......
>>    a0     00 00 00 00 00 00 00 00  00 00 00 00 00 00 00 00
>> ................
>>    b0     00 00 00 00 00 00 00 00  00 00 00 00 16 22 00 05
>> ............."..
>>    c0     01 00 00 05 00 00 00 01  50 03 04 80 00 a7 1e bf
>> ........P.......
>>    d0     50 03 04 80 00 a7 1e b1  00 00 00 00 00 00 00 00
>> P...............
>>    e0     16 22 00 06 01 00 00 06  00 00 00 00 00 00 00 00
>> ."..............
>>    f0     00 00 00 00 00 00 00 00  00 00 00 00 00 00 00 00
>> ................
>>    100    00 00 00 00 16 22 00 07  01 00 00 07 00 00 00 00
>> ....."..........
>>    110    00 00 00 00 00 00 00 00  00 00 00 00 00 00 00 00
>> ................
>>    120    00 00 00 00 00 00 00 00  16 22 00 08 01 00 00 08
>> ........."......
>>    130    00 00 00 01 50 03 04 80  00 a7 1e bf 50 03 04 80
>> ....P.......P...
>>    140    00 a7 1e b4 00 00 00 00  00 00 00 00 16 22 00 09
>> ............."..
>>    150    01 00 00 09 00 00 00 00  00 00 00 00 00 00 00 00
>> ................
>>    160    00 00 00 00 00 00 00 00  00 00 00 00 00 00 00 00
>> ................
>>    170    16 22 00 0a 01 00 00 0a  00 00 00 00 00 00 00 00
>> ."..............
>>    180    00 00 00 00 00 00 00 00  00 00 00 00 00 00 00 00
>> ................
>>    190    00 00 00 00 16 22 00 0b  01 00 00 0b 00 00 00 01
>> ....."..........
>>    1a0    50 03 04 80 00 a7 1e bf  50 03 04 80 00 a7 1e b7
>> P.......P.......
>>    1b0    00 00 00 00 00 00 00 00  16 46 00 15 1c 40 00 00
>> .........F...@..
>>    1c0    50 03 04 80 00 a7 1e bf  00 ff 00 ff 00 ff 00 ff
>> P...............
>>    1d0    01 ff 01 ff 01 ff 01 ff  ff ff ff ff ff ff ff ff
>> ................
>>    1e0    02 00 03 01 04 02 05 03  06 04 07 05 08 06 09 07
>> ................
>>    1f0    0a 08 0b 09 0c 0a 0d 0b  ff ff ff ff ff ff ff ff
>> ................
>
> OK, so this is the problem.  There are 12 Array additional descriptors
> and one for the expander.  The standard says (6.1.13.1) that this is all
> in order, so the problem is that ses.c expects every type to have an
> additional element descriptor and we've just never run across an
> enclosure with non-slot components before.
>
> Does this patch fix it?

It looks yes, I no more able to reproduce the warning from Kasan.

[   22.919261] EDAC sbridge:  Ver: 1.1.1
[   22.921993] iTCO_vendor_support: vendor-support=0
[   22.936523] ses 0:0:16:0: Attached Enclosure device

Tested-by: Pavel Tikhomirov <ptikhomirov@virtuozzo.com>

>
> James
>
> ---
>
> diff --git a/drivers/scsi/ses.c b/drivers/scsi/ses.c
> index 1736935..53ef1cb 100644
> --- a/drivers/scsi/ses.c
> +++ b/drivers/scsi/ses.c
> @@ -561,7 +561,15 @@ static void ses_enclosure_data_process(struct
> enclosure_device *edev,
>                       if (desc_ptr)
>                               desc_ptr += len;
>
> -                     if (addl_desc_ptr)
> +                     if (addl_desc_ptr &&
> +                         /* only find additional descriptions for specific
> devices */
> +                         (type_ptr[0] == ENCLOSURE_COMPONENT_DEVICE ||
> +                          type_ptr[0] == ENCLOSURE_COMPONENT_ARRAY_DEVICE ||
> +                          type_ptr[0] == ENCLOSURE_COMPONENT_SAS_EXPANDER ||
> +                          /* these elements are optional */
> +                          type_ptr[0] ==
> ENCLOSURE_COMPONENT_SCSI_TARGET_PORT ||
> +                          type_ptr[0] ==
> ENCLOSURE_COMPONENT_SCSI_INITIATOR_PORT ||
> +                          type_ptr[0] ==
> ENCLOSURE_COMPONENT_CONTROLLER_ELECTRONICS))
>                               addl_desc_ptr += addl_desc_ptr[1] + 2;
>
>               }
> diff --git a/include/linux/enclosure.h b/include/linux/enclosure.h
> index 7be22da..a4cf57c 100644
> --- a/include/linux/enclosure.h
> +++ b/include/linux/enclosure.h
> @@ -29,7 +29,11 @@
>   /* A few generic types ... taken from ses-2 */
>   enum enclosure_component_type {
>       ENCLOSURE_COMPONENT_DEVICE = 0x01,
> +     ENCLOSURE_COMPONENT_CONTROLLER_ELECTRONICS = 0x07,
> +     ENCLOSURE_COMPONENT_SCSI_TARGET_PORT = 0x14,
> +     ENCLOSURE_COMPONENT_SCSI_INITIATOR_PORT = 0x15,
>       ENCLOSURE_COMPONENT_ARRAY_DEVICE = 0x17,
> +     ENCLOSURE_COMPONENT_SAS_EXPANDER = 0x18,
>   };
>
>   /* ses-2 common element status */
>
>
> --
> To unsubscribe from this list: send the line "unsubscribe linux-scsi" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at  http://vger.kernel.org/majordomo-info.html
>
Note You need to log in before you can comment on or make changes to this bug.