Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Latest kernel with smsc95xx error while headless #183

Closed
x-magic opened this issue Jan 3, 2013 · 24 comments
Closed

Latest kernel with smsc95xx error while headless #183

x-magic opened this issue Jan 3, 2013 · 24 comments
Assignees
@ghollingworth

Comments

@x-magic
Copy link

x-magic commented Jan 3, 2013 

$ uname -a
Linux BHGsRP-RPiRBL 3.6.11+ #348 PREEMPT Tue Jan 1 16:33:22 GMT 2013 armv6l GNU/Linux

$ /opt/vc/bin/vcgencmd version
Jan  2 2013 23:38:28 
Copyright (c) 2012 Broadcom
version 360331 (release)

Just like issue #149 and #60 when smsc9512 counter a heavy load on usb hub it will show a register read error, with eth0 link down sometimes. But I just spotted some new errors and never happened before I updated to the latest firmware:

Jan  4 02:04:04 raspberrypi kernel: [20535.897405] smsc95xx 1-1.1:1.0: eth0: Failed to read register index 0x00000114
Jan  4 02:04:04 raspberrypi kernel: [20535.897439] smsc95xx 1-1.1:1.0: eth0: Error reading MII_ACCESS
Jan  4 02:04:04 raspberrypi kernel: [20535.897455] smsc95xx 1-1.1:1.0: eth0: MII is busy in smsc95xx_mdio_read
Jan  4 03:26:00 raspberrypi kernel: [25451.696037] smsc95xx 1-1.1:1.0: eth0: Failed to read register index 0x00000114
Jan  4 03:26:00 raspberrypi kernel: [25451.696147] smsc95xx 1-1.1:1.0: eth0: Error reading MII_ACCESS
Jan  4 03:26:00 raspberrypi kernel: [25451.696172] smsc95xx 1-1.1:1.0: eth0: Timed out reading MII reg 01
Jan  4 04:22:41 raspberrypi kernel: [28853.374164] smsc95xx 1-1.1:1.0: eth0: Failed to read register index 0x00000114
Jan  4 04:22:41 raspberrypi kernel: [28853.374198] smsc95xx 1-1.1:1.0: eth0: Error reading MII_ACCESS
Jan  4 04:22:41 raspberrypi kernel: [28853.374214] smsc95xx 1-1.1:1.0: eth0: Timed out reading MII reg 01

Those "MII" related errors are never seen before.

I have my 512MB rev2 Pi powered by GPIO 5V along with a portable harddrive on a 5V 2A adapter(the one come with Nexus 7) with a handmade cable that VCC and GND are connected to Pi and HDD only, while only D+ and D- of HDD is connected to Pi's USB. No another hub is used. No sign shows lack of power from the adapter to both Pi and HDD.

I also tried to power the HDD and Pi separately (5V 1A on Pi's microUSB and 5V 1A on HDD) to run headless and similar errors are found in kernel log.

I did a lot of search through web and it seems whether people didn't focus on this error or their Pi just not show these errors again, magically ;P

Should I worry about?
@davebiffuk
Copy link

I'm also seeing the ethernet drop out after some hours of uptime (typically 24 hours, but it varies).

This is on an original (256MB) model B running latest Raspbian, with only a single USB webcam attached directly to the USB port, it's a 046d:0817 Logitech, Inc. There are also a few 1-wire temperature sensors and a 16x2 LCD display attached to the GPIO lines. The whole lot is powered from the RS-supplied power supply.

I've seen this with kernel #350 and earlier kernels, I've since updated to #354 just a few minutes ago to see if that helps.

Please let me know if there's anything else I can do to help debug this. Thanks!

This is the kernel.log, immediately after the ethernet drops:

Jan 11 17:45:07 raspberrypi kernel: [278472.243617] smsc95xx 1-1.1:1.0: eth0: Failed to read register index 0x00000114
Jan 11 17:45:07 raspberrypi kernel: [278472.243663] smsc95xx 1-1.1:1.0: eth0: Error reading MII_ACCESS
Jan 11 17:45:07 raspberrypi kernel: [278472.243682] smsc95xx 1-1.1:1.0: eth0: MII is busy in smsc95xx_mdio_read
Jan 11 17:45:12 raspberrypi kernel: [278477.243695] smsc95xx 1-1.1:1.0: eth0: Failed to read register index 0x00000114
Jan 11 17:45:12 raspberrypi kernel: [278477.243726] smsc95xx 1-1.1:1.0: eth0: Error reading MII_ACCESS
Jan 11 17:45:12 raspberrypi kernel: [278477.243742] smsc95xx 1-1.1:1.0: eth0: MII is busy in smsc95xx_mdio_read
Jan 11 17:45:19 raspberrypi kernel: [278483.343793] smsc95xx 1-1.1:1.0: eth0: Failed to read register index 0x00000114
Jan 11 17:45:19 raspberrypi kernel: [278483.343824] smsc95xx 1-1.1:1.0: eth0: Error reading MII_ACCESS
Jan 11 17:45:19 raspberrypi kernel: [278483.343841] smsc95xx 1-1.1:1.0: eth0: MII is busy in smsc95xx_mdio_read
Jan 11 17:45:24 raspberrypi kernel: [278488.343865] smsc95xx 1-1.1:1.0: eth0: Failed to read register index 0x00000114
Jan 11 17:45:24 raspberrypi kernel: [278488.343896] smsc95xx 1-1.1:1.0: eth0: Error reading MII_ACCESS
Jan 11 17:45:24 raspberrypi kernel: [278488.343913] smsc95xx 1-1.1:1.0: eth0: MII is busy in smsc95xx_mdio_read
Jan 11 17:45:29 raspberrypi kernel: [278493.644019] smsc95xx 1-1.1:1.0: eth0: Failed to write register index 0x00000014
Jan 11 17:45:29 raspberrypi kernel: [278493.644068] smsc95xx 1-1.1:1.0: eth0: Failed to write HW_CFG_LRST_ bit in HW_CFG
Jan 11 17:45:35 raspberrypi kernel: [278499.644109] smsc95xx 1-1.1:1.0: eth0: Failed to write register index 0x00000014
Jan 11 17:45:35 raspberrypi kernel: [278499.644156] smsc95xx 1-1.1:1.0: eth0: Failed to write HW_CFG_LRST_ bit in HW_CFG

@popcornmix
Copy link
Collaborator

Can you update (rpi-update).
This commit may fix your problem:
0d4c649

@davebiffuk
Copy link

Thanks. I did update yesterday, about 1pm, to kernel #354.

Just now I see these lines in kern.log, but the ethernet has stayed up, which is hopeful. I'll leave it alone to see if there are further "developments".

Jan 15 08:59:07 raspberrypi kernel: [70833.531203] smsc95xx 1-1.1:1.0: eth0: Failed to read register index 0x00000114
Jan 15 08:59:07 raspberrypi kernel: [70833.531237] smsc95xx 1-1.1:1.0: eth0: Error reading MII_ACCESS
Jan 15 08:59:07 raspberrypi kernel: [70833.531254] smsc95xx 1-1.1:1.0: eth0: MII is busy in smsc95xx_mdio_read

@x-magic
Copy link
Author

x-magic commented Jan 15, 2013

An update. I updated to #354 and no issue until now. It's up for over 120000 seconds.

But there's no particular huge traffic over USB. My RPi is a headless download and samba server so I'm not sure if the error mentioned before would come again, but I will keep eye on that.

@davebiffuk
Copy link

Sorry to report kernel #354 still has this problem. Despite my earlier comment, after about 25 hours uptime, these lines appeared in kern.log, and the ethernet dropped. I've done rpi-update again, so now I'm running on #358. Anything else I try to help debug this? Ta.

Jan 15 14:12:07 raspberrypi kernel: [89613.758463] smsc95xx 1-1.1:1.0: eth0: Failed to read register index 0x00000114
Jan 15 14:12:07 raspberrypi kernel: [89613.758497] smsc95xx 1-1.1:1.0: eth0: Error reading MII_ACCESS
Jan 15 14:12:07 raspberrypi kernel: [89613.758513] smsc95xx 1-1.1:1.0: eth0: MII is busy in smsc95xx_mdio_read
(above 3 lines repeated 3 more times, every 5 seconds, then...)
Jan 15 14:12:28 raspberrypi kernel: [89635.068707] smsc95xx 1-1.1:1.0: eth0: Failed to write register index 0x00000014
Jan 15 14:12:28 raspberrypi kernel: [89635.068754] smsc95xx 1-1.1:1.0: eth0: Failed to write HW_CFG_LRST_ bit in HW_CFG
(above 2 lines repeated every 6 seconds)

@ghost ghost assigned ghollingworth Jan 16, 2013
@davebiffuk
Copy link

Ethernet dropped again with #358. Same pattern of messages in /var/log/kern.log as in my previous comment. Uptime was about 71.5 hours. The workload is USB traffic once/minute from the webcam, misc GPIO every 5 minutes for the temperature sensors, and very light Apache load, <100 requests/day.

I've now booted the Pi with
smsc95xx.turbo_mode=N
which is the only other suggestion I've found that might help.

I'm happy to try possible solutions to debug this - just let me know. :-)

@P33M
Copy link
Contributor

P33M commented Jan 19, 2013

davebiffuk: What is your usage case? I.e. are you using the HDD for frequent/sporadic accesses or file server duties?

Can you both post "lsusb -t" and "lsusb" as well.

@x-magic
Copy link
Author

x-magic commented Jan 20, 2013

It seems when smsc95xx.turbo_mode=N is used to boot up, problem's gone with latest kernel. I am using this option all the time and forget to mention it in my post. Sorry for that.

Well I don't need extra boost on USB performance to run a headless server (USB2.0 is much faster than 100BASE-T ethernet, as you see, NIC is the bottle neck)so I am pretty satisfied with the current kernel. Anyway, my pi is up for several days without related errors except an accidental memory overflow(I still don't get it why swap is now helping when some programs eat up all physical memory).

@davebiffuk
Copy link

P33M: in my case there's no HDD, only the SD card. No fileserver duties - the most frequent SD card access is due to capturing an image once a minute from the web cam. After that there's RRD updates every 5 minutes from the temperature sensors.

Here's the lsusb output. There's only one webcam connected - I don't know why it shows up twice in the "-t" output.

pi@raspberrypi ~ $ lsusb -t
/:  Bus 01.Port 1: Dev 1, Class=root_hub, Driver=dwc_otg/1p, 480M
    |__ Port 1: Dev 2, If 0, Class=hub, Driver=hub/3p, 480M
        |__ Port 1: Dev 3, If 0, Class=vend., Driver=smsc95xx, 480M
        |__ Port 3: Dev 4, If 0, Class='bInterfaceClass 0x0e not yet handled', Driver=uvcvideo, 480M
        |__ Port 3: Dev 4, If 1, Class='bInterfaceClass 0x0e not yet handled', Driver=uvcvideo, 480M
pi@raspberrypi ~ $ lsusb
Bus 001 Device 002: ID 0424:9512 Standard Microsystems Corp.
Bus 001 Device 001: ID 1d6b:0002 Linux Foundation 2.0 root hub
Bus 001 Device 003: ID 0424:ec00 Standard Microsystems Corp.
Bus 001 Device 004: ID 046d:0817 Logitech, Inc.
pi@raspberrypi ~ $

Uptime with smsc95xx.turbo_mode=N is 57 hours and counting...

@davebiffuk
Copy link

Sorry to report that running with smsc95xx.turbo_mode=N I got the same ethernet drop after ~84 hours uptime, with the same messages in kern.log.

I've rebooted without that now FWIW. I'm going to write a script to reboot the Pi if the ethernet's down and those errors are present in kern.log - it's a gross hack though :-(

@mupett
Copy link

mupett commented Jan 28, 2013

Same problem here ... :(

@stuartyio
Copy link

I'm experiencing the same. Prolific PL2303 USB to serial adapter plugged in. Ethernet goes down every few days.

@mupett
Copy link

mupett commented Jan 28, 2013

davebiffuk can you please post the script to reboot when eth0 goes down? Kind regards :)

@davebiffuk
Copy link

Funny thing is, having rpi-update'd before the last reboot (to kernel #362, firmware 364243) my Pi's ethernet has been up for 156+ hours now. The firmware commit message "Bump to latest firmware LKG65" doesn't give any clues as to what's been changed though.

I'm still seeing occasional bursts of "Failed to read register index 0x00000114" etc. But the network is not dropping. (Hope I don't jinx it by posting this...)

Therefore my reboot-on-dropped-network is completely untested :-) but help yourself: some modification will be necessary, run it from cron every 5 minutes (say). https://docs.google.com/file/d/0BwU_0Q35xHhGUi1iYzdoWl9TNWs/edit?pli=1

@mupett
Copy link

mupett commented Jan 29, 2013

thanks a lot dave

@davebiffuk
Copy link

Regret to report that after 13.5 days uptime (325 hours) on kernel #362/firmware 364243, the problem recurred. Ethernet dropped while Pi continued running. (Irritatingly my script to reboot the Pi didn't kick in; the perils of debugging odd scripts like that...)

Now rpi-update'd to kernel#368/firmware 366977 and keeping an eye on it.

@stuartyio
Copy link

I've also updated to kernel#368/firmware 366977 this morning. I'll report if Ethernet drops out.

pi@raspberrypi ~ $ lsusb -t
/: Bus 01.Port 1: Dev 1, Class=root_hub, Driver=dwc_otg/1p, 480M
|__ Port 1: Dev 2, If 0, Class=hub, Driver=hub/3p, 480M
|__ Port 1: Dev 3, If 0, Class=vend., Driver=smsc95xx, 480M
|__ Port 3: Dev 4, If 0, Class=vend., Driver=pl2303, 12M
pi@raspberrypi ~ $ lsusb
Bus 001 Device 002: ID 0424:9512 Standard Microsystems Corp.
Bus 001 Device 001: ID 1d6b:0002 Linux Foundation 2.0 root hub
Bus 001 Device 003: ID 0424:ec00 Standard Microsystems Corp.
Bus 001 Device 004: ID 067b:2303 Prolific Technology, Inc. PL2303 Serial Port

@ghost
Copy link

ghost commented Mar 26, 2013

Reporting that my Pi (kernel#339/firmware 379325) drops the USB after only a few seconds when booted. Will check voltage when I can get my hands on a multimeter, but as the errors are exactly the same and it has run before without any problem for over a week without rebooting, I don't suspect my PSU.

Update:
My Pi just recovered. It has been running for a few days now without any crashes. The only thing that has changed is that I moved my router. The wire between the modem and the router was faulty and I've moved it next to my computer instead of under a dusty table in the living room. As an effect, the Pi is now directly connected to the router while first it was through a switch.
I'll keep monitoring it, but there are no signs of impeding doom.

@ghollingworth
Copy link

Assuming the issue is now closed please reopen if you still see this.

@azbesthu
Copy link

Hi,

I got HW_CFG_LRST_ and MII_ACCESS failures after a half minute when I start using the attached Alcor micro AU9540 (058F:9540) smartcard reader. The network is slows down to zero. The same failure occures with direct raspi - card reader and raspi -external hub - card reader setup. Same results with rev1 (0002) powerd from thinkpad usb and rev2 (000f) Pi back powerd from active hub.

Here is some log: https://gist.github.com/azbesthu/7116016

I had to add dwc_otg.speed=1 to cmdline.txt. This seems to resolve the network outage, but 12Mbps usb speed is not enought for usb dvb-t reception and network streeming.

I tried with raspi-update the 3.6.11 #557 kernel with same results. With the previously raspbian and raspbmc it worked fine.

@armgilles armgilles mentioned this issue Dec 19, 2014
Open
popcornmix pushed a commit that referenced this issue Mar 26, 2018
@dledford
RDMA/mlx5: Fix crash while accessing garbage pointer and freed memory
f3f134f 
The failure in rereg_mr flow caused to set garbage value (error value)
into mr->umem pointer. This pointer is accessed at the release stage
and it causes to the following crash.

There is not enough to simply change umem to point to NULL, because the
MR struct is needed to be accessed during MR deregistration phase, so
delay kfree too.

[    6.237617] BUG: unable to handle kernel NULL pointer dereference a 0000000000000228
[    6.238756] IP: ib_dereg_mr+0xd/0x30
[    6.239264] PGD 80000000167eb067 P4D 80000000167eb067 PUD 167f9067 PMD 0
[    6.240320] Oops: 0000 [#1] SMP PTI
[    6.240782] CPU: 0 PID: 367 Comm: dereg Not tainted 4.16.0-rc1-00029-gc198fafe0453 #183
[    6.242120] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.7.5-0-ge51488c-20140602_164612-nilsson.home.kraxel.org 04/01/2014
[    6.244504] RIP: 0010:ib_dereg_mr+0xd/0x30
[    6.245253] RSP: 0018:ffffaf5d001d7d68 EFLAGS: 00010246
[    6.246100] RAX: 0000000000000000 RBX: ffff95d4172daf00 RCX: 0000000000000000
[    6.247414] RDX: 00000000ffffffff RSI: 0000000000000001 RDI: ffff95d41a317600
[    6.248591] RBP: 0000000000000001 R08: 0000000000000000 R09: 0000000000000000
[    6.249810] R10: ffff95d417033c10 R11: 0000000000000000 R12: ffff95d4172c3a80
[    6.251121] R13: ffff95d4172c3720 R14: ffff95d4172c3a98 R15: 00000000ffffffff
[    6.252437] FS:  0000000000000000(0000) GS:ffff95d41fc00000(0000) knlGS:0000000000000000
[    6.253887] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[    6.254814] CR2: 0000000000000228 CR3: 00000000172b4000 CR4: 00000000000006b0
[    6.255943] Call Trace:
[    6.256368]  remove_commit_idr_uobject+0x1b/0x80
[    6.257118]  uverbs_cleanup_ucontext+0xe4/0x190
[    6.257855]  ib_uverbs_cleanup_ucontext.constprop.14+0x19/0x40
[    6.258857]  ib_uverbs_close+0x2a/0x100
[    6.259494]  __fput+0xca/0x1c0
[    6.259938]  task_work_run+0x84/0xa0
[    6.260519]  do_exit+0x312/0xb40
[    6.261023]  ? __do_page_fault+0x24d/0x490
[    6.261707]  do_group_exit+0x3a/0xa0
[    6.262267]  SyS_exit_group+0x10/0x10
[    6.262802]  do_syscall_64+0x75/0x180
[    6.263391]  entry_SYSCALL_64_after_hwframe+0x21/0x86
[    6.264253] RIP: 0033:0x7f1b39c49488
[    6.264827] RSP: 002b:00007ffe2de05b68 EFLAGS: 00000246 ORIG_RAX: 00000000000000e7
[    6.266049] RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007f1b39c49488
[    6.267187] RDX: 0000000000000000 RSI: 000000000000003c RDI: 0000000000000000
[    6.268377] RBP: 00007f1b39f258e0 R08: 00000000000000e7 R09: ffffffffffffff98
[    6.269640] R10: 00007f1b3a147260 R11: 0000000000000246 R12: 00007f1b39f258e0
[    6.270783] R13: 00007f1b39f2ac20 R14: 0000000000000000 R15: 0000000000000000
[    6.271943] Code: 74 07 31 d2 e9 25 d8 6c 00 b8 da ff ff ff c3 0f 1f
44 00 00 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 48 8b 07 53 48 8b
5f 08 <48> 8b 80 28 02 00 00 e8 f7 d7 6c 00 85 c0 75 04 3e ff 4b 18 5b
[    6.274927] RIP: ib_dereg_mr+0xd/0x30 RSP: ffffaf5d001d7d68
[    6.275760] CR2: 0000000000000228
[    6.276200] ---[ end trace a35641f1c474bd20 ]---

Fixes: e126ba9 ("mlx5: Add driver for Mellanox Connect-IB adapters")
Cc: syzkaller <syzkaller@googlegroups.com>
Cc: <stable@vger.kernel.org>
Reported-by: Noa Osherovich <noaos@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>
nathanchance pushed a commit to nathanchance/pi-kernel that referenced this issue Mar 28, 2018
@gregkh
RDMA/mlx5: Fix crash while accessing garbage pointer and freed memory
8f59abb 
commit f3f134f upstream.

The failure in rereg_mr flow caused to set garbage value (error value)
into mr->umem pointer. This pointer is accessed at the release stage
and it causes to the following crash.

There is not enough to simply change umem to point to NULL, because the
MR struct is needed to be accessed during MR deregistration phase, so
delay kfree too.

[    6.237617] BUG: unable to handle kernel NULL pointer dereference a 0000000000000228
[    6.238756] IP: ib_dereg_mr+0xd/0x30
[    6.239264] PGD 80000000167eb067 P4D 80000000167eb067 PUD 167f9067 PMD 0
[    6.240320] Oops: 0000 [raspberrypi#1] SMP PTI
[    6.240782] CPU: 0 PID: 367 Comm: dereg Not tainted 4.16.0-rc1-00029-gc198fafe0453 raspberrypi#183
[    6.242120] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.7.5-0-ge51488c-20140602_164612-nilsson.home.kraxel.org 04/01/2014
[    6.244504] RIP: 0010:ib_dereg_mr+0xd/0x30
[    6.245253] RSP: 0018:ffffaf5d001d7d68 EFLAGS: 00010246
[    6.246100] RAX: 0000000000000000 RBX: ffff95d4172daf00 RCX: 0000000000000000
[    6.247414] RDX: 00000000ffffffff RSI: 0000000000000001 RDI: ffff95d41a317600
[    6.248591] RBP: 0000000000000001 R08: 0000000000000000 R09: 0000000000000000
[    6.249810] R10: ffff95d417033c10 R11: 0000000000000000 R12: ffff95d4172c3a80
[    6.251121] R13: ffff95d4172c3720 R14: ffff95d4172c3a98 R15: 00000000ffffffff
[    6.252437] FS:  0000000000000000(0000) GS:ffff95d41fc00000(0000) knlGS:0000000000000000
[    6.253887] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[    6.254814] CR2: 0000000000000228 CR3: 00000000172b4000 CR4: 00000000000006b0
[    6.255943] Call Trace:
[    6.256368]  remove_commit_idr_uobject+0x1b/0x80
[    6.257118]  uverbs_cleanup_ucontext+0xe4/0x190
[    6.257855]  ib_uverbs_cleanup_ucontext.constprop.14+0x19/0x40
[    6.258857]  ib_uverbs_close+0x2a/0x100
[    6.259494]  __fput+0xca/0x1c0
[    6.259938]  task_work_run+0x84/0xa0
[    6.260519]  do_exit+0x312/0xb40
[    6.261023]  ? __do_page_fault+0x24d/0x490
[    6.261707]  do_group_exit+0x3a/0xa0
[    6.262267]  SyS_exit_group+0x10/0x10
[    6.262802]  do_syscall_64+0x75/0x180
[    6.263391]  entry_SYSCALL_64_after_hwframe+0x21/0x86
[    6.264253] RIP: 0033:0x7f1b39c49488
[    6.264827] RSP: 002b:00007ffe2de05b68 EFLAGS: 00000246 ORIG_RAX: 00000000000000e7
[    6.266049] RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007f1b39c49488
[    6.267187] RDX: 0000000000000000 RSI: 000000000000003c RDI: 0000000000000000
[    6.268377] RBP: 00007f1b39f258e0 R08: 00000000000000e7 R09: ffffffffffffff98
[    6.269640] R10: 00007f1b3a147260 R11: 0000000000000246 R12: 00007f1b39f258e0
[    6.270783] R13: 00007f1b39f2ac20 R14: 0000000000000000 R15: 0000000000000000
[    6.271943] Code: 74 07 31 d2 e9 25 d8 6c 00 b8 da ff ff ff c3 0f 1f
44 00 00 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 48 8b 07 53 48 8b
5f 08 <48> 8b 80 28 02 00 00 e8 f7 d7 6c 00 85 c0 75 04 3e ff 4b 18 5b
[    6.274927] RIP: ib_dereg_mr+0xd/0x30 RSP: ffffaf5d001d7d68
[    6.275760] CR2: 0000000000000228
[    6.276200] ---[ end trace a35641f1c474bd20 ]---

Fixes: e126ba9 ("mlx5: Add driver for Mellanox Connect-IB adapters")
Cc: syzkaller <syzkaller@googlegroups.com>
Cc: <stable@vger.kernel.org>
Reported-by: Noa Osherovich <noaos@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
popcornmix pushed a commit that referenced this issue Mar 29, 2018
@gregkh
RDMA/mlx5: Fix crash while accessing garbage pointer and freed memory
8fe98b2 
commit f3f134f upstream.

The failure in rereg_mr flow caused to set garbage value (error value)
into mr->umem pointer. This pointer is accessed at the release stage
and it causes to the following crash.

There is not enough to simply change umem to point to NULL, because the
MR struct is needed to be accessed during MR deregistration phase, so
delay kfree too.

[    6.237617] BUG: unable to handle kernel NULL pointer dereference a 0000000000000228
[    6.238756] IP: ib_dereg_mr+0xd/0x30
[    6.239264] PGD 80000000167eb067 P4D 80000000167eb067 PUD 167f9067 PMD 0
[    6.240320] Oops: 0000 [#1] SMP PTI
[    6.240782] CPU: 0 PID: 367 Comm: dereg Not tainted 4.16.0-rc1-00029-gc198fafe0453 #183
[    6.242120] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.7.5-0-ge51488c-20140602_164612-nilsson.home.kraxel.org 04/01/2014
[    6.244504] RIP: 0010:ib_dereg_mr+0xd/0x30
[    6.245253] RSP: 0018:ffffaf5d001d7d68 EFLAGS: 00010246
[    6.246100] RAX: 0000000000000000 RBX: ffff95d4172daf00 RCX: 0000000000000000
[    6.247414] RDX: 00000000ffffffff RSI: 0000000000000001 RDI: ffff95d41a317600
[    6.248591] RBP: 0000000000000001 R08: 0000000000000000 R09: 0000000000000000
[    6.249810] R10: ffff95d417033c10 R11: 0000000000000000 R12: ffff95d4172c3a80
[    6.251121] R13: ffff95d4172c3720 R14: ffff95d4172c3a98 R15: 00000000ffffffff
[    6.252437] FS:  0000000000000000(0000) GS:ffff95d41fc00000(0000) knlGS:0000000000000000
[    6.253887] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[    6.254814] CR2: 0000000000000228 CR3: 00000000172b4000 CR4: 00000000000006b0
[    6.255943] Call Trace:
[    6.256368]  remove_commit_idr_uobject+0x1b/0x80
[    6.257118]  uverbs_cleanup_ucontext+0xe4/0x190
[    6.257855]  ib_uverbs_cleanup_ucontext.constprop.14+0x19/0x40
[    6.258857]  ib_uverbs_close+0x2a/0x100
[    6.259494]  __fput+0xca/0x1c0
[    6.259938]  task_work_run+0x84/0xa0
[    6.260519]  do_exit+0x312/0xb40
[    6.261023]  ? __do_page_fault+0x24d/0x490
[    6.261707]  do_group_exit+0x3a/0xa0
[    6.262267]  SyS_exit_group+0x10/0x10
[    6.262802]  do_syscall_64+0x75/0x180
[    6.263391]  entry_SYSCALL_64_after_hwframe+0x21/0x86
[    6.264253] RIP: 0033:0x7f1b39c49488
[    6.264827] RSP: 002b:00007ffe2de05b68 EFLAGS: 00000246 ORIG_RAX: 00000000000000e7
[    6.266049] RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007f1b39c49488
[    6.267187] RDX: 0000000000000000 RSI: 000000000000003c RDI: 0000000000000000
[    6.268377] RBP: 00007f1b39f258e0 R08: 00000000000000e7 R09: ffffffffffffff98
[    6.269640] R10: 00007f1b3a147260 R11: 0000000000000246 R12: 00007f1b39f258e0
[    6.270783] R13: 00007f1b39f2ac20 R14: 0000000000000000 R15: 0000000000000000
[    6.271943] Code: 74 07 31 d2 e9 25 d8 6c 00 b8 da ff ff ff c3 0f 1f
44 00 00 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 48 8b 07 53 48 8b
5f 08 <48> 8b 80 28 02 00 00 e8 f7 d7 6c 00 85 c0 75 04 3e ff 4b 18 5b
[    6.274927] RIP: ib_dereg_mr+0xd/0x30 RSP: ffffaf5d001d7d68
[    6.275760] CR2: 0000000000000228
[    6.276200] ---[ end trace a35641f1c474bd20 ]---

Fixes: e126ba9 ("mlx5: Add driver for Mellanox Connect-IB adapters")
Cc: syzkaller <syzkaller@googlegroups.com>
Cc: <stable@vger.kernel.org>
Reported-by: Noa Osherovich <noaos@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
popcornmix pushed a commit that referenced this issue Jul 30, 2018
@davem330
net: axienet: Fix double deregister of mdio
03bc7ca 
If the registration fails then mdio_unregister is called.
However at unbind the unregister ia attempted again resulting
in the below crash

[   73.544038] kernel BUG at drivers/net/phy/mdio_bus.c:415!
[   73.549362] Internal error: Oops - BUG: 0 [#1] SMP
[   73.554127] Modules linked in:
[   73.557168] CPU: 0 PID: 2249 Comm: sh Not tainted 4.14.0 #183
[   73.562895] Hardware name: xlnx,zynqmp (DT)
[   73.567062] task: ffffffc879e41180 task.stack: ffffff800cbe0000
[   73.572973] PC is at mdiobus_unregister+0x84/0x88
[   73.577656] LR is at axienet_mdio_teardown+0x18/0x30
[   73.582601] pc : [<ffffff80085fa4cc>] lr : [<ffffff8008616858>]
pstate: 20000145
[   73.589981] sp : ffffff800cbe3c30
[   73.593277] x29: ffffff800cbe3c30 x28: ffffffc879e41180
[   73.598573] x27: ffffff8008a21000 x26: 0000000000000040
[   73.603868] x25: 0000000000000124 x24: ffffffc879efe920
[   73.609164] x23: 0000000000000060 x22: ffffffc879e02000
[   73.614459] x21: ffffffc879e02800 x20: ffffffc87b0b8870
[   73.619754] x19: ffffffc879e02800 x18: 000000000000025d
[   73.625050] x17: 0000007f9a719ad0 x16: ffffff8008195bd8
[   73.630345] x15: 0000007f9a6b3d00 x14: 0000000000000010
[   73.635640] x13: 74656e7265687465 x12: 0000000000000030
[   73.640935] x11: 0000000000000030 x10: 0101010101010101
[   73.646231] x9 : 241f394f42533300 x8 : ffffffc8799f6e98
[   73.651526] x7 : ffffffc8799f6f18 x6 : ffffffc87b0ba318
[   73.656822] x5 : ffffffc87b0ba498 x4 : 0000000000000000
[   73.662117] x3 : 0000000000000000 x2 : 0000000000000008
[   73.667412] x1 : 0000000000000004 x0 : ffffffc8799f4000
[   73.672708] Process sh (pid: 2249, stack limit = 0xffffff800cbe0000)

Fix the same by making the bus NULL on unregister.

Signed-off-by: Shubhrajyoti Datta <shubhrajyoti.datta@xilinx.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
nathanchance pushed a commit to nathanchance/pi-kernel that referenced this issue Sep 5, 2018
@gregkh
net: axienet: Fix double deregister of mdio
354e35b 
[ Upstream commit 03bc7ca ]

If the registration fails then mdio_unregister is called.
However at unbind the unregister ia attempted again resulting
in the below crash

[   73.544038] kernel BUG at drivers/net/phy/mdio_bus.c:415!
[   73.549362] Internal error: Oops - BUG: 0 [raspberrypi#1] SMP
[   73.554127] Modules linked in:
[   73.557168] CPU: 0 PID: 2249 Comm: sh Not tainted 4.14.0 raspberrypi#183
[   73.562895] Hardware name: xlnx,zynqmp (DT)
[   73.567062] task: ffffffc879e41180 task.stack: ffffff800cbe0000
[   73.572973] PC is at mdiobus_unregister+0x84/0x88
[   73.577656] LR is at axienet_mdio_teardown+0x18/0x30
[   73.582601] pc : [<ffffff80085fa4cc>] lr : [<ffffff8008616858>]
pstate: 20000145
[   73.589981] sp : ffffff800cbe3c30
[   73.593277] x29: ffffff800cbe3c30 x28: ffffffc879e41180
[   73.598573] x27: ffffff8008a21000 x26: 0000000000000040
[   73.603868] x25: 0000000000000124 x24: ffffffc879efe920
[   73.609164] x23: 0000000000000060 x22: ffffffc879e02000
[   73.614459] x21: ffffffc879e02800 x20: ffffffc87b0b8870
[   73.619754] x19: ffffffc879e02800 x18: 000000000000025d
[   73.625050] x17: 0000007f9a719ad0 x16: ffffff8008195bd8
[   73.630345] x15: 0000007f9a6b3d00 x14: 0000000000000010
[   73.635640] x13: 74656e7265687465 x12: 0000000000000030
[   73.640935] x11: 0000000000000030 x10: 0101010101010101
[   73.646231] x9 : 241f394f42533300 x8 : ffffffc8799f6e98
[   73.651526] x7 : ffffffc8799f6f18 x6 : ffffffc87b0ba318
[   73.656822] x5 : ffffffc87b0ba498 x4 : 0000000000000000
[   73.662117] x3 : 0000000000000000 x2 : 0000000000000008
[   73.667412] x1 : 0000000000000004 x0 : ffffffc8799f4000
[   73.672708] Process sh (pid: 2249, stack limit = 0xffffff800cbe0000)

Fix the same by making the bus NULL on unregister.

Signed-off-by: Shubhrajyoti Datta <shubhrajyoti.datta@xilinx.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <alexander.levin@microsoft.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
popcornmix pushed a commit that referenced this issue May 7, 2019
@davem330
ipv6: fix races in ip6_dst_destroy()
0e23387 
We had many syzbot reports that seem to be caused by use-after-free
of struct fib6_info.

ip6_dst_destroy(), fib6_drop_pcpu_from() and rt6_remove_exception()
are writers vs rt->from, and use non consistent synchronization among
themselves.

Switching to xchg() will solve the issues with no possible
lockdep issues.

BUG: KASAN: user-memory-access in atomic_dec_and_test include/asm-generic/atomic-instrumented.h:747 [inline]
BUG: KASAN: user-memory-access in fib6_info_release include/net/ip6_fib.h:294 [inline]
BUG: KASAN: user-memory-access in fib6_info_release include/net/ip6_fib.h:292 [inline]
BUG: KASAN: user-memory-access in fib6_drop_pcpu_from net/ipv6/ip6_fib.c:927 [inline]
BUG: KASAN: user-memory-access in fib6_purge_rt+0x4f6/0x670 net/ipv6/ip6_fib.c:960
Write of size 4 at addr 0000000000ffffb4 by task syz-executor.1/7649

CPU: 0 PID: 7649 Comm: syz-executor.1 Not tainted 5.1.0-rc6+ #183
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:77 [inline]
 dump_stack+0x172/0x1f0 lib/dump_stack.c:113
 kasan_report.cold+0x5/0x40 mm/kasan/report.c:321
 check_memory_region_inline mm/kasan/generic.c:185 [inline]
 check_memory_region+0x123/0x190 mm/kasan/generic.c:191
 kasan_check_write+0x14/0x20 mm/kasan/common.c:108
 atomic_dec_and_test include/asm-generic/atomic-instrumented.h:747 [inline]
 fib6_info_release include/net/ip6_fib.h:294 [inline]
 fib6_info_release include/net/ip6_fib.h:292 [inline]
 fib6_drop_pcpu_from net/ipv6/ip6_fib.c:927 [inline]
 fib6_purge_rt+0x4f6/0x670 net/ipv6/ip6_fib.c:960
 fib6_del_route net/ipv6/ip6_fib.c:1813 [inline]
 fib6_del+0xac2/0x10a0 net/ipv6/ip6_fib.c:1844
 fib6_clean_node+0x3a8/0x590 net/ipv6/ip6_fib.c:2006
 fib6_walk_continue+0x495/0x900 net/ipv6/ip6_fib.c:1928
 fib6_walk+0x9d/0x100 net/ipv6/ip6_fib.c:1976
 fib6_clean_tree+0xe0/0x120 net/ipv6/ip6_fib.c:2055
 __fib6_clean_all+0x118/0x2a0 net/ipv6/ip6_fib.c:2071
 fib6_clean_all+0x2b/0x40 net/ipv6/ip6_fib.c:2082
 rt6_sync_down_dev+0x134/0x150 net/ipv6/route.c:4057
 rt6_disable_ip+0x27/0x5f0 net/ipv6/route.c:4062
 addrconf_ifdown+0xa2/0x1220 net/ipv6/addrconf.c:3705
 addrconf_notify+0x19a/0x2260 net/ipv6/addrconf.c:3630
 notifier_call_chain+0xc7/0x240 kernel/notifier.c:93
 __raw_notifier_call_chain kernel/notifier.c:394 [inline]
 raw_notifier_call_chain+0x2e/0x40 kernel/notifier.c:401
 call_netdevice_notifiers_info+0x3f/0x90 net/core/dev.c:1753
 call_netdevice_notifiers_extack net/core/dev.c:1765 [inline]
 call_netdevice_notifiers net/core/dev.c:1779 [inline]
 dev_close_many+0x33f/0x6f0 net/core/dev.c:1522
 rollback_registered_many+0x43b/0xfd0 net/core/dev.c:8177
 rollback_registered+0x109/0x1d0 net/core/dev.c:8242
 unregister_netdevice_queue net/core/dev.c:9289 [inline]
 unregister_netdevice_queue+0x1ee/0x2c0 net/core/dev.c:9282
 unregister_netdevice include/linux/netdevice.h:2658 [inline]
 __tun_detach+0xd5b/0x1000 drivers/net/tun.c:727
 tun_detach drivers/net/tun.c:744 [inline]
 tun_chr_close+0xe0/0x180 drivers/net/tun.c:3443
 __fput+0x2e5/0x8d0 fs/file_table.c:278
 ____fput+0x16/0x20 fs/file_table.c:309
 task_work_run+0x14a/0x1c0 kernel/task_work.c:113
 exit_task_work include/linux/task_work.h:22 [inline]
 do_exit+0x90a/0x2fa0 kernel/exit.c:876
 do_group_exit+0x135/0x370 kernel/exit.c:980
 __do_sys_exit_group kernel/exit.c:991 [inline]
 __se_sys_exit_group kernel/exit.c:989 [inline]
 __x64_sys_exit_group+0x44/0x50 kernel/exit.c:989
 do_syscall_64+0x103/0x610 arch/x86/entry/common.c:290
 entry_SYSCALL_64_after_hwframe+0x49/0xbe
RIP: 0033:0x458da9
Code: ad b8 fb ff c3 66 2e 0f 1f 84 00 00 00 00 00 66 90 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 7b b8 fb ff c3 66 2e 0f 1f 84 00 00 00 00
RSP: 002b:00007ffeafc2a6a8 EFLAGS: 00000246 ORIG_RAX: 00000000000000e7
RAX: ffffffffffffffda RBX: 000000000000001c RCX: 0000000000458da9
RDX: 0000000000412a80 RSI: 0000000000a54ef0 RDI: 0000000000000043
RBP: 00000000004be552 R08: 000000000000000c R09: 000000000004c0d1
R10: 0000000002341940 R11: 0000000000000246 R12: 00000000ffffffff
R13: 00007ffeafc2a7f0 R14: 000000000004c065 R15: 00007ffeafc2a800

Fixes: a68886a ("net/ipv6: Make from in rt6_info rcu protected")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Cc: David Ahern <dsahern@gmail.com>
Reviewed-by: David Ahern <dsahern@gmail.com>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Acked-by: Wei Wang <weiwan@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
popcornmix pushed a commit that referenced this issue May 7, 2019
@gregkh
ipv6: fix races in ip6_dst_destroy()
d0aa794 
[ Upstream commit 0e23387 ]

We had many syzbot reports that seem to be caused by use-after-free
of struct fib6_info.

ip6_dst_destroy(), fib6_drop_pcpu_from() and rt6_remove_exception()
are writers vs rt->from, and use non consistent synchronization among
themselves.

Switching to xchg() will solve the issues with no possible
lockdep issues.

BUG: KASAN: user-memory-access in atomic_dec_and_test include/asm-generic/atomic-instrumented.h:747 [inline]
BUG: KASAN: user-memory-access in fib6_info_release include/net/ip6_fib.h:294 [inline]
BUG: KASAN: user-memory-access in fib6_info_release include/net/ip6_fib.h:292 [inline]
BUG: KASAN: user-memory-access in fib6_drop_pcpu_from net/ipv6/ip6_fib.c:927 [inline]
BUG: KASAN: user-memory-access in fib6_purge_rt+0x4f6/0x670 net/ipv6/ip6_fib.c:960
Write of size 4 at addr 0000000000ffffb4 by task syz-executor.1/7649

CPU: 0 PID: 7649 Comm: syz-executor.1 Not tainted 5.1.0-rc6+ #183
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:77 [inline]
 dump_stack+0x172/0x1f0 lib/dump_stack.c:113
 kasan_report.cold+0x5/0x40 mm/kasan/report.c:321
 check_memory_region_inline mm/kasan/generic.c:185 [inline]
 check_memory_region+0x123/0x190 mm/kasan/generic.c:191
 kasan_check_write+0x14/0x20 mm/kasan/common.c:108
 atomic_dec_and_test include/asm-generic/atomic-instrumented.h:747 [inline]
 fib6_info_release include/net/ip6_fib.h:294 [inline]
 fib6_info_release include/net/ip6_fib.h:292 [inline]
 fib6_drop_pcpu_from net/ipv6/ip6_fib.c:927 [inline]
 fib6_purge_rt+0x4f6/0x670 net/ipv6/ip6_fib.c:960
 fib6_del_route net/ipv6/ip6_fib.c:1813 [inline]
 fib6_del+0xac2/0x10a0 net/ipv6/ip6_fib.c:1844
 fib6_clean_node+0x3a8/0x590 net/ipv6/ip6_fib.c:2006
 fib6_walk_continue+0x495/0x900 net/ipv6/ip6_fib.c:1928
 fib6_walk+0x9d/0x100 net/ipv6/ip6_fib.c:1976
 fib6_clean_tree+0xe0/0x120 net/ipv6/ip6_fib.c:2055
 __fib6_clean_all+0x118/0x2a0 net/ipv6/ip6_fib.c:2071
 fib6_clean_all+0x2b/0x40 net/ipv6/ip6_fib.c:2082
 rt6_sync_down_dev+0x134/0x150 net/ipv6/route.c:4057
 rt6_disable_ip+0x27/0x5f0 net/ipv6/route.c:4062
 addrconf_ifdown+0xa2/0x1220 net/ipv6/addrconf.c:3705
 addrconf_notify+0x19a/0x2260 net/ipv6/addrconf.c:3630
 notifier_call_chain+0xc7/0x240 kernel/notifier.c:93
 __raw_notifier_call_chain kernel/notifier.c:394 [inline]
 raw_notifier_call_chain+0x2e/0x40 kernel/notifier.c:401
 call_netdevice_notifiers_info+0x3f/0x90 net/core/dev.c:1753
 call_netdevice_notifiers_extack net/core/dev.c:1765 [inline]
 call_netdevice_notifiers net/core/dev.c:1779 [inline]
 dev_close_many+0x33f/0x6f0 net/core/dev.c:1522
 rollback_registered_many+0x43b/0xfd0 net/core/dev.c:8177
 rollback_registered+0x109/0x1d0 net/core/dev.c:8242
 unregister_netdevice_queue net/core/dev.c:9289 [inline]
 unregister_netdevice_queue+0x1ee/0x2c0 net/core/dev.c:9282
 unregister_netdevice include/linux/netdevice.h:2658 [inline]
 __tun_detach+0xd5b/0x1000 drivers/net/tun.c:727
 tun_detach drivers/net/tun.c:744 [inline]
 tun_chr_close+0xe0/0x180 drivers/net/tun.c:3443
 __fput+0x2e5/0x8d0 fs/file_table.c:278
 ____fput+0x16/0x20 fs/file_table.c:309
 task_work_run+0x14a/0x1c0 kernel/task_work.c:113
 exit_task_work include/linux/task_work.h:22 [inline]
 do_exit+0x90a/0x2fa0 kernel/exit.c:876
 do_group_exit+0x135/0x370 kernel/exit.c:980
 __do_sys_exit_group kernel/exit.c:991 [inline]
 __se_sys_exit_group kernel/exit.c:989 [inline]
 __x64_sys_exit_group+0x44/0x50 kernel/exit.c:989
 do_syscall_64+0x103/0x610 arch/x86/entry/common.c:290
 entry_SYSCALL_64_after_hwframe+0x49/0xbe
RIP: 0033:0x458da9
Code: ad b8 fb ff c3 66 2e 0f 1f 84 00 00 00 00 00 66 90 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 7b b8 fb ff c3 66 2e 0f 1f 84 00 00 00 00
RSP: 002b:00007ffeafc2a6a8 EFLAGS: 00000246 ORIG_RAX: 00000000000000e7
RAX: ffffffffffffffda RBX: 000000000000001c RCX: 0000000000458da9
RDX: 0000000000412a80 RSI: 0000000000a54ef0 RDI: 0000000000000043
RBP: 00000000004be552 R08: 000000000000000c R09: 000000000004c0d1
R10: 0000000002341940 R11: 0000000000000246 R12: 00000000ffffffff
R13: 00007ffeafc2a7f0 R14: 000000000004c065 R15: 00007ffeafc2a800

Fixes: a68886a ("net/ipv6: Make from in rt6_info rcu protected")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Cc: David Ahern <dsahern@gmail.com>
Reviewed-by: David Ahern <dsahern@gmail.com>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Acked-by: Wei Wang <weiwan@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
popcornmix pushed a commit that referenced this issue May 7, 2019
@gregkh
ipv6: fix races in ip6_dst_destroy()
1a9e013 
[ Upstream commit 0e23387 ]

We had many syzbot reports that seem to be caused by use-after-free
of struct fib6_info.

ip6_dst_destroy(), fib6_drop_pcpu_from() and rt6_remove_exception()
are writers vs rt->from, and use non consistent synchronization among
themselves.

Switching to xchg() will solve the issues with no possible
lockdep issues.

BUG: KASAN: user-memory-access in atomic_dec_and_test include/asm-generic/atomic-instrumented.h:747 [inline]
BUG: KASAN: user-memory-access in fib6_info_release include/net/ip6_fib.h:294 [inline]
BUG: KASAN: user-memory-access in fib6_info_release include/net/ip6_fib.h:292 [inline]
BUG: KASAN: user-memory-access in fib6_drop_pcpu_from net/ipv6/ip6_fib.c:927 [inline]
BUG: KASAN: user-memory-access in fib6_purge_rt+0x4f6/0x670 net/ipv6/ip6_fib.c:960
Write of size 4 at addr 0000000000ffffb4 by task syz-executor.1/7649

CPU: 0 PID: 7649 Comm: syz-executor.1 Not tainted 5.1.0-rc6+ #183
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:77 [inline]
 dump_stack+0x172/0x1f0 lib/dump_stack.c:113
 kasan_report.cold+0x5/0x40 mm/kasan/report.c:321
 check_memory_region_inline mm/kasan/generic.c:185 [inline]
 check_memory_region+0x123/0x190 mm/kasan/generic.c:191
 kasan_check_write+0x14/0x20 mm/kasan/common.c:108
 atomic_dec_and_test include/asm-generic/atomic-instrumented.h:747 [inline]
 fib6_info_release include/net/ip6_fib.h:294 [inline]
 fib6_info_release include/net/ip6_fib.h:292 [inline]
 fib6_drop_pcpu_from net/ipv6/ip6_fib.c:927 [inline]
 fib6_purge_rt+0x4f6/0x670 net/ipv6/ip6_fib.c:960
 fib6_del_route net/ipv6/ip6_fib.c:1813 [inline]
 fib6_del+0xac2/0x10a0 net/ipv6/ip6_fib.c:1844
 fib6_clean_node+0x3a8/0x590 net/ipv6/ip6_fib.c:2006
 fib6_walk_continue+0x495/0x900 net/ipv6/ip6_fib.c:1928
 fib6_walk+0x9d/0x100 net/ipv6/ip6_fib.c:1976
 fib6_clean_tree+0xe0/0x120 net/ipv6/ip6_fib.c:2055
 __fib6_clean_all+0x118/0x2a0 net/ipv6/ip6_fib.c:2071
 fib6_clean_all+0x2b/0x40 net/ipv6/ip6_fib.c:2082
 rt6_sync_down_dev+0x134/0x150 net/ipv6/route.c:4057
 rt6_disable_ip+0x27/0x5f0 net/ipv6/route.c:4062
 addrconf_ifdown+0xa2/0x1220 net/ipv6/addrconf.c:3705
 addrconf_notify+0x19a/0x2260 net/ipv6/addrconf.c:3630
 notifier_call_chain+0xc7/0x240 kernel/notifier.c:93
 __raw_notifier_call_chain kernel/notifier.c:394 [inline]
 raw_notifier_call_chain+0x2e/0x40 kernel/notifier.c:401
 call_netdevice_notifiers_info+0x3f/0x90 net/core/dev.c:1753
 call_netdevice_notifiers_extack net/core/dev.c:1765 [inline]
 call_netdevice_notifiers net/core/dev.c:1779 [inline]
 dev_close_many+0x33f/0x6f0 net/core/dev.c:1522
 rollback_registered_many+0x43b/0xfd0 net/core/dev.c:8177
 rollback_registered+0x109/0x1d0 net/core/dev.c:8242
 unregister_netdevice_queue net/core/dev.c:9289 [inline]
 unregister_netdevice_queue+0x1ee/0x2c0 net/core/dev.c:9282
 unregister_netdevice include/linux/netdevice.h:2658 [inline]
 __tun_detach+0xd5b/0x1000 drivers/net/tun.c:727
 tun_detach drivers/net/tun.c:744 [inline]
 tun_chr_close+0xe0/0x180 drivers/net/tun.c:3443
 __fput+0x2e5/0x8d0 fs/file_table.c:278
 ____fput+0x16/0x20 fs/file_table.c:309
 task_work_run+0x14a/0x1c0 kernel/task_work.c:113
 exit_task_work include/linux/task_work.h:22 [inline]
 do_exit+0x90a/0x2fa0 kernel/exit.c:876
 do_group_exit+0x135/0x370 kernel/exit.c:980
 __do_sys_exit_group kernel/exit.c:991 [inline]
 __se_sys_exit_group kernel/exit.c:989 [inline]
 __x64_sys_exit_group+0x44/0x50 kernel/exit.c:989
 do_syscall_64+0x103/0x610 arch/x86/entry/common.c:290
 entry_SYSCALL_64_after_hwframe+0x49/0xbe
RIP: 0033:0x458da9
Code: ad b8 fb ff c3 66 2e 0f 1f 84 00 00 00 00 00 66 90 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 7b b8 fb ff c3 66 2e 0f 1f 84 00 00 00 00
RSP: 002b:00007ffeafc2a6a8 EFLAGS: 00000246 ORIG_RAX: 00000000000000e7
RAX: ffffffffffffffda RBX: 000000000000001c RCX: 0000000000458da9
RDX: 0000000000412a80 RSI: 0000000000a54ef0 RDI: 0000000000000043
RBP: 00000000004be552 R08: 000000000000000c R09: 000000000004c0d1
R10: 0000000002341940 R11: 0000000000000246 R12: 00000000ffffffff
R13: 00007ffeafc2a7f0 R14: 000000000004c065 R15: 00007ffeafc2a800

Fixes: a68886a ("net/ipv6: Make from in rt6_info rcu protected")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Cc: David Ahern <dsahern@gmail.com>
Reviewed-by: David Ahern <dsahern@gmail.com>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Acked-by: Wei Wang <weiwan@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
@ckamas
Copy link

ckamas commented Jul 30, 2019

I am seeing this issue on 4.9.76-rt60-v7+ running on a RPI CM3. Has this issue been resolved, or is it back again? If it is solved, please point me to the correct patch.

[ 3614.344611] smsc95xx 1-1.1:1.0 eth0: Failed to read reg index 0x00000114: -110
[ 3614.344620] smsc95xx 1-1.1:1.0 eth0: Error reading MII_ACCESS
[ 3614.344626] smsc95xx 1-1.1:1.0 eth0: MII is busy in smsc95xx_mdio_read
[ 3614.344632] smsc95xx 1-1.1:1.0 eth0: Failed to read MII_BMSR

[43053.607537] smsc95xx 1-1.5.1:1.0 eth1: Failed to read reg index 0x00000114: -110
[43053.607547] smsc95xx 1-1.5.1:1.0 eth1: Error reading MII_ACCESS
[43053.607553] smsc95xx 1-1.5.1:1.0 eth1: MII is busy in smsc95xx_mdio_read
[43053.607559] smsc95xx 1-1.5.1:1.0 eth1: Failed to read MII_BMSR

@pelwell
Copy link
Contributor

pelwell commented Jul 30, 2019

Please don't resurrect long-closed threads.

@karimcitoh
Copy link

I am seeing this issue on 4.9.76-rt60-v7+ running on a RPI CM3. Has this issue been resolved, or is it back again? If it is solved, please point me to the correct patch.

[ 3614.344611] smsc95xx 1-1.1:1.0 eth0: Failed to read reg index 0x00000114: -110
[ 3614.344620] smsc95xx 1-1.1:1.0 eth0: Error reading MII_ACCESS
[ 3614.344626] smsc95xx 1-1.1:1.0 eth0: MII is busy in smsc95xx_mdio_read
[ 3614.344632] smsc95xx 1-1.1:1.0 eth0: Failed to read MII_BMSR

[43053.607537] smsc95xx 1-1.5.1:1.0 eth1: Failed to read reg index 0x00000114: -110
[43053.607547] smsc95xx 1-1.5.1:1.0 eth1: Error reading MII_ACCESS
[43053.607553] smsc95xx 1-1.5.1:1.0 eth1: MII is busy in smsc95xx_mdio_read
[43053.607559] smsc95xx 1-1.5.1:1.0 eth1: Failed to read MII_BMSR

Same problem here. @ckamas did you open an issue for this one?

@ckamas
Copy link

ckamas commented Oct 29, 2019 via email

popcornmix pushed a commit that referenced this issue Mar 27, 2024
@Vudentz
Bluetooth: af_bluetooth: Fix deadlock
817e813 
[ Upstream commit f7b94bd ]

Attemting to do sock_lock on .recvmsg may cause a deadlock as shown
bellow, so instead of using sock_sock this uses sk_receive_queue.lock
on bt_sock_ioctl to avoid the UAF:

INFO: task kworker/u9:1:121 blocked for more than 30 seconds.
      Not tainted 6.7.6-lemon #183
Workqueue: hci0 hci_rx_work
Call Trace:
 <TASK>
 __schedule+0x37d/0xa00
 schedule+0x32/0xe0
 __lock_sock+0x68/0xa0
 ? __pfx_autoremove_wake_function+0x10/0x10
 lock_sock_nested+0x43/0x50
 l2cap_sock_recv_cb+0x21/0xa0
 l2cap_recv_frame+0x55b/0x30a0
 ? psi_task_switch+0xeb/0x270
 ? finish_task_switch.isra.0+0x93/0x2a0
 hci_rx_work+0x33a/0x3f0
 process_one_work+0x13a/0x2f0
 worker_thread+0x2f0/0x410
 ? __pfx_worker_thread+0x10/0x10
 kthread+0xe0/0x110
 ? __pfx_kthread+0x10/0x10
 ret_from_fork+0x2c/0x50
 ? __pfx_kthread+0x10/0x10
 ret_from_fork_asm+0x1b/0x30
 </TASK>

Fixes: 2e07e83 ("Bluetooth: af_bluetooth: Fix Use-After-Free in bt_sock_recvmsg")
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
popcornmix pushed a commit that referenced this issue Mar 27, 2024
@Vudentz
Bluetooth: af_bluetooth: Fix deadlock
2c9e2df 
[ Upstream commit f7b94bd ]

Attemting to do sock_lock on .recvmsg may cause a deadlock as shown
bellow, so instead of using sock_sock this uses sk_receive_queue.lock
on bt_sock_ioctl to avoid the UAF:

INFO: task kworker/u9:1:121 blocked for more than 30 seconds.
      Not tainted 6.7.6-lemon #183
Workqueue: hci0 hci_rx_work
Call Trace:
 <TASK>
 __schedule+0x37d/0xa00
 schedule+0x32/0xe0
 __lock_sock+0x68/0xa0
 ? __pfx_autoremove_wake_function+0x10/0x10
 lock_sock_nested+0x43/0x50
 l2cap_sock_recv_cb+0x21/0xa0
 l2cap_recv_frame+0x55b/0x30a0
 ? psi_task_switch+0xeb/0x270
 ? finish_task_switch.isra.0+0x93/0x2a0
 hci_rx_work+0x33a/0x3f0
 process_one_work+0x13a/0x2f0
 worker_thread+0x2f0/0x410
 ? __pfx_worker_thread+0x10/0x10
 kthread+0xe0/0x110
 ? __pfx_kthread+0x10/0x10
 ret_from_fork+0x2c/0x50
 ? __pfx_kthread+0x10/0x10
 ret_from_fork_asm+0x1b/0x30
 </TASK>

Fixes: 2e07e83 ("Bluetooth: af_bluetooth: Fix Use-After-Free in bt_sock_recvmsg")
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
popcornmix pushed a commit that referenced this issue Mar 27, 2024
@Vudentz
Bluetooth: af_bluetooth: Fix deadlock
64be3c6 
[ Upstream commit f7b94bd ]

Attemting to do sock_lock on .recvmsg may cause a deadlock as shown
bellow, so instead of using sock_sock this uses sk_receive_queue.lock
on bt_sock_ioctl to avoid the UAF:

INFO: task kworker/u9:1:121 blocked for more than 30 seconds.
      Not tainted 6.7.6-lemon #183
Workqueue: hci0 hci_rx_work
Call Trace:
 <TASK>
 __schedule+0x37d/0xa00
 schedule+0x32/0xe0
 __lock_sock+0x68/0xa0
 ? __pfx_autoremove_wake_function+0x10/0x10
 lock_sock_nested+0x43/0x50
 l2cap_sock_recv_cb+0x21/0xa0
 l2cap_recv_frame+0x55b/0x30a0
 ? psi_task_switch+0xeb/0x270
 ? finish_task_switch.isra.0+0x93/0x2a0
 hci_rx_work+0x33a/0x3f0
 process_one_work+0x13a/0x2f0
 worker_thread+0x2f0/0x410
 ? __pfx_worker_thread+0x10/0x10
 kthread+0xe0/0x110
 ? __pfx_kthread+0x10/0x10
 ret_from_fork+0x2c/0x50
 ? __pfx_kthread+0x10/0x10
 ret_from_fork_asm+0x1b/0x30
 </TASK>

Fixes: 2e07e83 ("Bluetooth: af_bluetooth: Fix Use-After-Free in bt_sock_recvmsg")
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees

@ghollingworth ghollingworth

Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests