This bug was fixed in the package linux - 4.2.0-34.39
---------------
linux (4.2.0-34.39) wily; urgency=low
[ Brad Figg ]
* Release Tracking Bug
- LP: #1555821
[ Florian Westphal ]
* SAUCE: [nf] netfilter: x_tables: check for size overflow
- LP: #1555353
* SAUCE: [nf,v2] netfilter: x_tables: don't rely on well-behaving
userspace
- LP: #1555338
linux (4.2.0-33.38) wily; urgency=low
[ Brad Figg ]
* Release Tracking Bug
- LP: #1554649
[ Upstream Kernel Changes ]
* Revert "drm/radeon: call hpd_irq_event on resume"
- LP: #1554608
* cxl: Fix PSL timebase synchronization detection
- LP: #1532914
linux (4.2.0-32.37) wily; urgency=low
[ Kamal Mostafa ]
* Release Tracking Bug
- LP: #1550045
[ Kamal Mostafa ]
* Merged back Ubuntu-4.2.0-31.36
linux (4.2.0-31.36) wily; urgency=low
[ Brad Figg ]
* Release Tracking Bug
- LP: #1548579
[ Andy Whitcroft ]
* [Debian] hv: hv_set_ifconfig -- convert to python3
- LP: #1506521
* [Debian] hv: hv_set_ifconfig -- switch to approved indentation
- LP: #1540586
* [Debian] hv: hv_set_ifconfig -- fix numerous parameter handling issues
- LP: #1540586
[ Carol L Soto ]
* SAUCE: IB/IPoIB: Do not set skb truesize since using one linearskb
- LP: #1541326
[ Dan Streetman ]
* SAUCE: nbd: ratelimit error msgs after socket close
- LP: #1505564
[ Tim Gardner ]
* Revert "SAUCE: (noup) cxlflash: Fix to avoid virtual LUN failover
failure"
- LP: #1541635
* Revert "SAUCE: (noup) cxlflash: Fix to escalate LINK_RESET also on port
1"
- LP: #1541635
* [Config] ARMV8_DEPRECATED=y
- LP: #1545542
[ Upstream Kernel Changes ]
* x86/xen/p2m: hint at the last populated P2M entry
- LP: #1542941
* mm: add dma_pool_zalloc() call to DMA API
- LP: #1543737
* sctp: Prevent soft lockup when sctp_accept() is called during a timeout
event
- LP: #1543737
* xen-netback: respect user provided max_queues
- LP: #1543737
* xen-netfront: respect user provided max_queues
- LP: #1543737
* xen-netfront: update num_queues to real created
- LP: #1543737
* iio: adis_buffer: Fix out-of-bounds memory access
- LP: #1543737
* KVM: PPC: Fix emulation of H_SET_DABR/X on POWER8
- LP: #1543737
* KVM: PPC: Fix ONE_REG AltiVec support
- LP: #1543737
* x86/irq: Call chip->irq_set_affinity in proper context
- LP: #1543737
* drm/amdgpu: fix tonga smu resume
- LP: #1543737
* perf kvm record/report: 'unprocessable sample' error while
recording/reporting guest data
- LP: #1543737
* hrtimer: Handle remaining time proper for TIME_LOW_RES
- LP: #1543737
* timerfd: Handle relative timers with CONFIG_TIME_LOW_RES proper
- LP: #1543737
* posix-timers: Handle relative timers with CONFIG_TIME_LOW_RES proper
- LP: #1543737
* itimers: Handle relative timers with CONFIG_TIME_LOW_RES proper
- LP: #1543737
* drm/amdgpu: Use drm_calloc_large for VM page_tables array
- LP: #1543737
* drm/amdgpu: fix amdgpu_bo_pin_restricted VRAM placing v2
- LP: #1543737
* drm/radeon: properly byte swap vce firmware setup
- LP: #1543737
* ACPI: Revert "ACPI / video: Add Dell Inspiron 5737 to the blacklist"
- LP: #1543737
* ACPI / PCI / hotplug: unlock in error path in acpiphp_enable_slot()
- LP: #1543737
* hwmon: (dell-smm) Blacklist Dell Studio XPS 8000
- LP: #1543737
* usb: cdc-acm: handle unlinked urb in acm read callback
- LP: #1543737
* usb: cdc-acm: send zero packet for intel 7260 modem
- LP: #1543737
* cdc-acm:exclude Samsung phone 04e8:685d
- LP: #1543737
* usb: hub: do not clear BOS field during reset device
- LP: #1543737
* USB: cp210x: add ID for IAI USB to RS485 adaptor
- LP: #1543737
* USB: visor: fix null-deref at probe
- LP: #1543737
* USB: serial: visor: fix crash on detecting device without write_urbs
- LP: #1543737
* USB: serial: option: Adding support for Telit LE922
- LP: #1543737
* ALSA: seq: Fix incorrect sanity check at snd_seq_oss_synth_cleanup()
- LP: #1543737
* ALSA: seq: Degrade the error message for too many opens
- LP: #1543737
* USB: serial: ftdi_sio: add support for Yaesu SCU-18 cable
- LP: #1543737
* arm64: kernel: fix architected PMU registers unconditional access
- LP: #1543737
* USB: option: fix Cinterion AHxx enumeration
- LP: #1543737
* ALSA: compress: Disable GET_CODEC_CAPS ioctl for some architectures
- LP: #1543737
* ALSA: usb-audio: Fix TEAC UD-501/UD-503/NT-503 usb delay
- LP: #1543737
* virtio_pci: fix use after free on release
- LP: #1543737
* ALSA: bebob: Use a signed return type for get_formation_index
- LP: #1543737
* arm64: errata: Add -mpc-relative-literal-loads to build flags
- LP: #1533009, #1543737
* arm64: mm: avoid calling apply_to_page_range on empty range
- LP: #1543737
* x86/mm: Fix types used in pgprot cacheability flags translations
- LP: #1543737
* powerpc/eeh: Fix PE location code
- LP: #1543737
* SCSI: fix crashes in sd and sr runtime PM
- LP: #1543737
* tty: Fix unsafe ldisc reference via ioctl(TIOCGETD)
- LP: #1543737
* n_tty: Fix unsafe reference to "other" ldisc
- LP: #1543737
* staging/speakup: Use tty_ldisc_ref() for paste kworker
- LP: #1543737
* tick/nohz: Set the correct expiry when switching to nohz/lowres mode
- LP: #1543737
* irqchip/atmel-aic: Fix wrong bit operation for IRQ priority
- LP: #1543737
* seccomp: always propagate NO_NEW_PRIVS on tsync
- LP: #1543737
* drm/radeon: cleaned up VCO output settings for DP audio
- LP: #1543737
* drm/radeon: Add a common function for DFS handling
- LP: #1543737
* drm/radeon: fix DP audio support for APU with DCE4.1 display engine
- LP: #1543737
* cpufreq: Fix NULL reference crash while accessing policy->governor_data
- LP: #1543737
* cpufreq: pxa2xx: fix pxa_cpufreq_change_voltage prototype
- LP: #1543737
* ALSA: dummy: Disable switching timer backend via sysfs
- LP: #1543737
* drm/vmwgfx: respect 'nomodeset'
- LP: #1543737
* Staging: speakup: Fix getting port information
- LP: #1543737
* x86/mm/pat: Avoid truncation when converting cpa->numpages to address
- LP: #1543737
* serial: 8250_pci: Add Intel Broadwell ports
- LP: #1543737
* perf annotate browser: Fix behaviour of Shift-Tab with nothing focussed
- LP: #1543737
* perf hists: Fix HISTC_MEM_DCACHELINE width setting
- LP: #1543737
* powerpc/perf: Remove PPMU_HAS_SSLOT flag for Power8
- LP: #1543737
* Linux 4.2.8-ckt4
- LP: #1543737
* cxlflash: Resolve oops in wait_port_offline
- LP: #1541635
* cxlflash: Fix to resolve cmd leak after host reset
- LP: #1541635
* cxlflash: Removed driver date print
- LP: #1541635
* cxlflash: drop unlikely before IS_ERR_OR_NULL
- LP: #1541635
* powerpc/powernv: Panic on unhandled Machine Check
- LP: #1541635
* cxlflash: Fix to avoid virtual LUN failover failure
- LP: #1541635
* cxlflash: Fix to escalate LINK_RESET also on port 1
- LP: #1541635
* IB/ipoib: Suppress warning for send only join failures
- LP: #1542444
* IB/ipoib: Expire sendonly multicast joins
- LP: #1542444
* IB/ipoib: increase the max mcast backlog queue
- LP: #1542444
* IB/ipoib: For sendonly join free the multicast group on leave
- LP: #1542444
* qeth: initialize net_device with carrier off
- LP: #1541907
* mwifiex: remove USB8897 chipset support
- LP: #1494593
* powerpc/powernv: Fix stale PE primary bus
- LP: #1546145
* ALSA: usb-audio: avoid freeing umidi object twice
- LP: #1546177
- CVE-2016-2384
-- Brad Figg <brad.f...@canonical.com> Thu, 10 Mar 2016 13:46:44 -0800
** Changed in: linux (Ubuntu Wily)
Status: Fix Committed => Fix Released
** CVE added: http://www.cve.mitre.org/cgi-
bin/cvename.cgi?name=2016-2384
--
You received this bug notification because you are a member of Kernel
Packages, which is subscribed to linux in Ubuntu.
https://bugs.launchpad.net/bugs/1541326
Title:
WARNING: at /build/linux-lts-wily-W0lTWH/linux-lts-
wily-4.2.0/net/core/skbuff.c:4174 (Travis IB)
Status in linux package in Ubuntu:
Fix Released
Status in linux source package in Wily:
Fix Released
Status in linux source package in Xenial:
Fix Released
Bug description:
== Comment: #0 - Manvanthara B. Puttashankar <mputt...@in.ibm.com> -
2016-01-03 10:52:39 ==
---Problem Description---
WARNING: at
/build/linux-lts-wily-W0lTWH/linux-lts-wily-4.2.0/net/core/skbuff.c:4174
Contact Information = mputt...@in.ibm.com
---uname output---
Linux ltcalpine-lp4 4.2.0-21-generic #25~14.04.1-Ubuntu SMP Thu Dec 3
13:55:42 UTC 2015 ppc64le ppc64le ppc64le GNU/Linux
Machine Type = 8408-E8E
---Debugger---
A debugger is not configured
---Steps to Reproduce---
trace was found in syslog within 30 min while running fsstress on travis IB
controller.
NFS server:
root@ubuntu140404:~# mkdir -p /home/share
root@ubuntu140404:~# /sbin/rpcbind start
rpcbind: another rpcbind is already running. Aborting
root@ubuntu140404:~# /sbin/rpcbind status
rpcbind: another rpcbind is already running. Aborting
root@ubuntu140404:~# rpcinfo
program version netid address service owner
100000 4 tcp6 ::.0.111 portmapper superuser
100000 3 tcp6 ::.0.111 portmapper superuser
100000 4 udp6 ::.0.111 portmapper superuser
100000 3 udp6 ::.0.111 portmapper superuser
100000 4 tcp 0.0.0.0.0.111 portmapper superuser
100000 3 tcp 0.0.0.0.0.111 portmapper superuser
100000 2 tcp 0.0.0.0.0.111 portmapper superuser
100000 4 udp 0.0.0.0.0.111 portmapper superuser
100000 3 udp 0.0.0.0.0.111 portmapper superuser
100000 2 udp 0.0.0.0.0.111 portmapper superuser
100000 4 local /run/rpcbind.sock portmapper superuser
100000 3 local /run/rpcbind.sock portmapper superuser
100024 1 udp 0.0.0.0.146.239 status 104
100024 1 tcp 0.0.0.0.175.171 status 104
100024 1 udp6 ::.235.98 status 104
100024 1 tcp6 ::.215.65 status 104
root@ubuntu140404:~# cat /etc/exports
# /etc/exports: the access control list for filesystems which may be exported
# to NFS clients. See exports(5).
#
# Example for NFSv2 and NFSv3:
# /srv/homes hostname1(rw,sync,no_subtree_check)
hostname2(ro,sync,no_subtree_check)
#
# Example for NFSv4:
# /srv/nfs4 gss/krb5i(rw,sync,fsid=0,crossmnt,no_subtree_check)
# /srv/nfs4/homes gss/krb5i(rw,sync,no_subtree_check)
#
/home/share 12.12.12.13(rw,sync,no_subtree_check)
root@ubuntu140404:~# /etc/init.d/nfs-kernel-server start
* Exporting directories for NFS kernel daemon...
...done.
* Starting NFS kernel daemon
...done.
root@ubuntu140404:~# exportfs -av
exporting 12.12.12.13:/home/share
root@ubuntu140404:~# rpcinfo
program version netid address service owner
100000 4 tcp6 ::.0.111 portmapper superuser
100000 3 tcp6 ::.0.111 portmapper superuser
100000 4 udp6 ::.0.111 portmapper superuser
100000 3 udp6 ::.0.111 portmapper superuser
100000 4 tcp 0.0.0.0.0.111 portmapper superuser
100000 3 tcp 0.0.0.0.0.111 portmapper superuser
100000 2 tcp 0.0.0.0.0.111 portmapper superuser
100000 4 udp 0.0.0.0.0.111 portmapper superuser
100000 3 udp 0.0.0.0.0.111 portmapper superuser
100000 2 udp 0.0.0.0.0.111 portmapper superuser
100000 4 local /run/rpcbind.sock portmapper superuser
100000 3 local /run/rpcbind.sock portmapper superuser
100024 1 udp 0.0.0.0.146.239 status 104
100024 1 tcp 0.0.0.0.175.171 status 104
100024 1 udp6 ::.235.98 status 104
100024 1 tcp6 ::.215.65 status 104
100003 2 tcp 0.0.0.0.8.1 nfs superuser
100003 3 tcp 0.0.0.0.8.1 nfs superuser
100003 4 tcp 0.0.0.0.8.1 nfs superuser
100227 2 tcp 0.0.0.0.8.1 - superuser
100227 3 tcp 0.0.0.0.8.1 - superuser
100003 2 udp 0.0.0.0.8.1 nfs superuser
100003 3 udp 0.0.0.0.8.1 nfs superuser
100003 4 udp 0.0.0.0.8.1 nfs superuser
100227 2 udp 0.0.0.0.8.1 - superuser
100227 3 udp 0.0.0.0.8.1 - superuser
100003 2 tcp6 ::.8.1 nfs superuser
100003 3 tcp6 ::.8.1 nfs superuser
100003 4 tcp6 ::.8.1 nfs superuser
100227 2 tcp6 ::.8.1 - superuser
100227 3 tcp6 ::.8.1 - superuser
100003 2 udp6 ::.8.1 nfs superuser
100003 3 udp6 ::.8.1 nfs superuser
100003 4 udp6 ::.8.1 nfs superuser
100227 2 udp6 ::.8.1 - superuser
100227 3 udp6 ::.8.1 - superuser
100021 1 udp 0.0.0.0.191.68 nlockmgr superuser
100021 3 udp 0.0.0.0.191.68 nlockmgr superuser
100021 4 udp 0.0.0.0.191.68 nlockmgr superuser
100021 1 tcp 0.0.0.0.174.157 nlockmgr superuser
100021 3 tcp 0.0.0.0.174.157 nlockmgr superuser
100021 4 tcp 0.0.0.0.174.157 nlockmgr superuser
100021 1 udp6 ::.168.136 nlockmgr superuser
100021 3 udp6 ::.168.136 nlockmgr superuser
100021 4 udp6 ::.168.136 nlockmgr superuser
100021 1 tcp6 ::.138.214 nlockmgr superuser
100021 3 tcp6 ::.138.214 nlockmgr superuser
100021 4 tcp6 ::.138.214 nlockmgr superuser
100005 1 udp 0.0.0.0.147.176 mountd superuser
100005 1 tcp 0.0.0.0.228.2 mountd superuser
100005 1 udp6 ::.144.73 mountd superuser
100005 1 tcp6 ::.205.71 mountd superuser
100005 2 udp 0.0.0.0.232.199 mountd superuser
100005 2 tcp 0.0.0.0.150.167 mountd superuser
100005 2 udp6 ::.149.148 mountd superuser
100005 2 tcp6 ::.178.116 mountd superuser
100005 3 udp 0.0.0.0.223.102 mountd superuser
100005 3 tcp 0.0.0.0.213.191 mountd superuser
100005 3 udp6 ::.169.30 mountd superuser
100005 3 tcp6 ::.233.128 mountd superuser
root@ubuntu140404:~#
--------------------------------------------------------
NFS client:
root@ltcalpine-lp4:~# cat /proc/cpuinfo
processor : 0
cpu : POWER8 (architected), altivec supported
clock : 3026.000000MHz
revision : 2.1 (pvr 004b 0201)
processor : 1
cpu : POWER8 (architected), altivec supported
clock : 3026.000000MHz
revision : 2.1 (pvr 004b 0201)
processor : 2
cpu : POWER8 (architected), altivec supported
clock : 3026.000000MHz
revision : 2.1 (pvr 004b 0201)
processor : 3
cpu : POWER8 (architected), altivec supported
clock : 3026.000000MHz
revision : 2.1 (pvr 004b 0201)
processor : 4
cpu : POWER8 (architected), altivec supported
clock : 3026.000000MHz
revision : 2.1 (pvr 004b 0201)
processor : 5
cpu : POWER8 (architected), altivec supported
clock : 3026.000000MHz
revision : 2.1 (pvr 004b 0201)
processor : 6
cpu : POWER8 (architected), altivec supported
clock : 3026.000000MHz
revision : 2.1 (pvr 004b 0201)
processor : 7
cpu : POWER8 (architected), altivec supported
clock : 3026.000000MHz
revision : 2.1 (pvr 004b 0201)
processor : 8
cpu : POWER8 (architected), altivec supported
clock : 3026.000000MHz
revision : 2.1 (pvr 004b 0201)
processor : 9
cpu : POWER8 (architected), altivec supported
clock : 3026.000000MHz
revision : 2.1 (pvr 004b 0201)
processor : 10
cpu : POWER8 (architected), altivec supported
clock : 3026.000000MHz
revision : 2.1 (pvr 004b 0201)
processor : 11
cpu : POWER8 (architected), altivec supported
clock : 3026.000000MHz
revision : 2.1 (pvr 004b 0201)
processor : 12
cpu : POWER8 (architected), altivec supported
clock : 3026.000000MHz
revision : 2.1 (pvr 004b 0201)
processor : 13
cpu : POWER8 (architected), altivec supported
clock : 3026.000000MHz
revision : 2.1 (pvr 004b 0201)
processor : 14
cpu : POWER8 (architected), altivec supported
clock : 3026.000000MHz
revision : 2.1 (pvr 004b 0201)
processor : 15
cpu : POWER8 (architected), altivec supported
clock : 3026.000000MHz
revision : 2.1 (pvr 004b 0201)
timebase : 512000000
platform : pSeries
model : IBM,8408-E8E
machine : CHRP IBM,8408-E8E
root@ltcalpine-lp4:~#
root@ltcalpine-lp4:~# free -g
total used free shared buffers cached
Mem: 49 0 49 0 0 0
-/+ buffers/cache: 0 49
Swap: 2 0 2
root@ltcalpine-lp4:~# apt-get install nfs-common
root@ltcalpine-lp4:~# mount -t nfs 12.12.12.12:/home/share /mnt
root@ltcalpine-lp4:~/ltp-full-20150420/testcases/kernel/fs/fsstress# echo
"==============GAN fsstress" >> /var/log/syslog
root@ltcalpine-lp4:~/ltp-full-20150420/testcases/kernel/fs/fsstress#
root@ltcalpine-lp4:~/ltp-full-20150420/testcases/kernel/fs/fsstress# nohup
./fsstress -d /mnt -l 0 -n 300 -p 300 -r &
[1] 2400
root@ltcalpine-lp4:~/ltp-full-20150420/testcases/kernel/fs/fsstress# nohup:
ignoring input and appending output to ?nohup.out?
root@ltcalpine-lp4:~# netstat -i
Kernel Interface table
Iface MTU Met RX-OK RX-ERR RX-DRP RX-OVR TX-OK TX-ERR TX-DRP TX-OVR Flg
eth0 1500 0 26078 0 0 0 199 0 0
0 BMRU
ib0 2044 0 169370 0 0 0 60577 0 7
0 BMRU
lo 65536 0 23 0 0 0 23 0 0
0 LRU
root@ltcalpine-lp4:~# tail -f /var/log/syslog
Jan 3 10:20:57 ltcalpine-lp4 kernel: [ 260.938162] Key type id_legacy
registered
Jan 3 10:21:01 ltcalpine-lp4 CRON[2302]: (nobody) CMD (if [ -x /usr/bin/php5
] && [ -f /usr/share/serverstats/update.php ]; then /usr/bin/php5
/usr/share/serverstats/update.php > /dev/null; fi)
Jan 3 10:21:01 ltcalpine-lp4 CRON[2301]: (CRON) info (No MTA installed,
discarding output)
Jan 3 10:22:01 ltcalpine-lp4 CRON[2335]: (nobody) CMD (if [ -x /usr/bin/php5
] && [ -f /usr/share/serverstats/update.php ]; then /usr/bin/php5
/usr/share/serverstats/update.php > /dev/null; fi)
Jan 3 10:22:01 ltcalpine-lp4 CRON[2334]: (CRON) info (No MTA installed,
discarding output)
Jan 3 10:23:01 ltcalpine-lp4 CRON[2367]: (nobody) CMD (if [ -x /usr/bin/php5
] && [ -f /usr/share/serverstats/update.php ]; then /usr/bin/php5
/usr/share/serverstats/update.php > /dev/null; fi)
Jan 3 10:23:01 ltcalpine-lp4 CRON[2366]: (CRON) info (No MTA installed,
discarding output)
==============GAN fsstress
Jan 3 10:24:01 ltcalpine-lp4 CRON[2758]: (nobody) CMD (if [ -x /usr/bin/php5
] && [ -f /usr/share/serverstats/update.php ]; then /usr/bin/php5
/usr/share/serverstats/update.php > /dev/null; fi)
Jan 3 10:24:01 ltcalpine-lp4 CRON[2757]: (CRON) info (No MTA installed,
discarding output)
Jan 3 10:25:01 ltcalpine-lp4 CRON[2864]: (nobody) CMD (if [ -x /usr/bin/php5
] && [ -f /usr/share/serverstats/update.php ]; then /usr/bin/php5
/usr/share/serverstats/update.php > /dev/null; fi)
Jan 3 10:25:01 ltcalpine-lp4 CRON[2863]: (CRON) info (No MTA installed,
discarding output)
Jan 3 10:26:01 ltcalpine-lp4 CRON[2981]: (nobody) CMD (if [ -x /usr/bin/php5
] && [ -f /usr/share/serverstats/update.php ]; then /usr/bin/php5
/usr/share/serverstats/update.php > /dev/null; fi)
Jan 3 10:26:01 ltcalpine-lp4 CRON[2980]: (CRON) info (No MTA installed,
discarding output)
Jan 3 10:26:06 ltcalpine-lp4 kernel: [ 569.229293] ------------[ cut here
]------------
Jan 3 10:26:06 ltcalpine-lp4 kernel: [ 569.229301] WARNING: at
/build/linux-lts-wily-W0lTWH/linux-lts-wily-4.2.0/net/core/skbuff.c:4174
Jan 3 10:26:06 ltcalpine-lp4 kernel: [ 569.229303] Modules linked in:
rpcsec_gss_krb5 nfsv4 nfsd auth_rpcgss nfs_acl nfs lockd grace sunrpc fscache
mlx4_ib ib_ipoib rdma_ucm rdma_cm iw_cm ib_umad ib_ucm ib_cm ib_sa ib_mad
ib_uverbs ib_core ib_addr pseries_rng rtc_generic mlx4_en vxlan ip6_udp_tunnel
udp_tunnel bnx2x mlx4_core mdio libcrc32c
Jan 3 10:26:06 ltcalpine-lp4 kernel: [ 569.229338] CPU: 0 PID: 0 Comm:
swapper/0 Not tainted 4.2.0-21-generic #25~14.04.1-Ubuntu
Jan 3 10:26:06 ltcalpine-lp4 kernel: [ 569.229342] task: c000000001480b30
ti: c000000c7ffdc000 task.ti: c0000000014f8000
Jan 3 10:26:06 ltcalpine-lp4 kernel: [ 569.229344] NIP: c0000000008f484c
LR: c000000000981844 CTR: c0000000009d40e0
Jan 3 10:26:06 ltcalpine-lp4 kernel: [ 569.229347] REGS: c000000c7ffdf2d0
TRAP: 0700 Not tainted (4.2.0-21-generic)
Jan 3 10:26:06 ltcalpine-lp4 kernel: [ 569.229349] MSR: 8000000000029033
<SF,EE,ME,IR,DR,RI,LE> CR: 28008048 XER: 00000000
Jan 3 10:26:06 ltcalpine-lp4 kernel: [ 569.229357] CFAR: c0000000008f46a4
SOFTE: 1
Jan 3 10:26:06 ltcalpine-lp4 kernel: [ 569.229357] GPR00: 0000000000000000
c000000c7ffdf550 c0000000014fdf00 c00000000145df00
Jan 3 10:26:06 ltcalpine-lp4 kernel: [ 569.229357] GPR04: c000000bfa4fec00
0000000000000000 c000000c2aeedb00 c000000bfa4fdb00
Jan 3 10:26:06 ltcalpine-lp4 kernel: [ 569.229357] GPR08: 0000000000000001
c000000c2aeeec00 0000000000000005 0000000bfa4f0000
Jan 3 10:26:06 ltcalpine-lp4 kernel: [ 569.229357] GPR12: 0000000000002200
c00000000e7e0000 0000000000000001 000000000000012c
Jan 3 10:26:06 ltcalpine-lp4 kernel: [ 569.229357] GPR16: 0000000000000000
0000000000000001 c000000c7ffdfd90 0000000000000000
Jan 3 10:26:06 ltcalpine-lp4 kernel: [ 569.229357] GPR20: 000000000000dd86
0000000000000000 c000000000d83070 c000000000d83048
Jan 3 10:26:06 ltcalpine-lp4 kernel: [ 569.229357] GPR24: c000000c6f6c0098
0000000000000234 c000000c7ffdf5d0 0000000000000458
Jan 3 10:26:06 ltcalpine-lp4 kernel: [ 569.229357] GPR28: 0000000000000458
c000000c7ffdf660 c000000c40cf0d00 c000000c40cf9200
Jan 3 10:26:06 ltcalpine-lp4 kernel: [ 569.229390] NIP [c0000000008f484c]
skb_try_coalesce+0x40c/0x450
Jan 3 10:26:06 ltcalpine-lp4 kernel: [ 569.229393] LR [c000000000981844]
tcp_try_coalesce+0x94/0x140
Jan 3 10:26:06 ltcalpine-lp4 kernel: [ 569.229395] Call Trace:
Jan 3 10:26:06 ltcalpine-lp4 kernel: [ 569.229398] [c000000c7ffdf550]
[c000000c7ffdf5b0] 0xc000000c7ffdf5b0 (unreliable)
Jan 3 10:26:06 ltcalpine-lp4 kernel: [ 569.229402] [c000000c7ffdf5b0]
[c000000000981844] tcp_try_coalesce+0x94/0x140
Jan 3 10:26:06 ltcalpine-lp4 kernel: [ 569.229405] [c000000c7ffdf600]
[c000000000983358] tcp_data_queue+0x3f8/0xf90
Jan 3 10:26:06 ltcalpine-lp4 kernel: [ 569.229408] [c000000c7ffdf6d0]
[c0000000009861ac] tcp_rcv_established+0x1cc/0x7a0
Jan 3 10:26:06 ltcalpine-lp4 kernel: [ 569.229412] [c000000c7ffdf730]
[c000000000992104] tcp_v4_do_rcv+0x1b4/0x490
Jan 3 10:26:06 ltcalpine-lp4 kernel: [ 569.229415] [c000000c7ffdf790]
[c000000000995f60] tcp_v4_rcv+0xb40/0xb60
Jan 3 10:26:06 ltcalpine-lp4 kernel: [ 569.229418] [c000000c7ffdf870]
[c000000000963eb8] ip_local_deliver_finish+0x178/0x350
Jan 3 10:26:06 ltcalpine-lp4 kernel: [ 569.229422] [c000000c7ffdf8c0]
[c0000000009646d4] ip_local_deliver+0x54/0x130
Jan 3 10:26:06 ltcalpine-lp4 kernel: [ 569.229424] [c000000c7ffdf930]
[c0000000009641e4] ip_rcv_finish+0x154/0x420
Jan 3 10:26:06 ltcalpine-lp4 kernel: [ 569.229427] [c000000c7ffdf9b0]
[c000000000964a3c] ip_rcv+0x28c/0x430
Jan 3 10:26:06 ltcalpine-lp4 kernel: [ 569.229432] [c000000c7ffdfa40]
[c00000000090ad44] __netif_receive_skb_core+0x754/0xd30
Jan 3 10:26:06 ltcalpine-lp4 kernel: [ 569.229435] [c000000c7ffdfb20]
[c00000000090e3f4] netif_receive_skb_internal+0x34/0xd0
Jan 3 10:26:06 ltcalpine-lp4 kernel: [ 569.229438] [c000000c7ffdfb60]
[c00000000090efe4] dev_gro_receive+0x2d4/0x430
Jan 3 10:26:06 ltcalpine-lp4 kernel: [ 569.229441] [c000000c7ffdfbd0]
[c00000000090f408] napi_gro_receive+0x48/0x1b0
Jan 3 10:26:06 ltcalpine-lp4 kernel: [ 569.229447] [c000000c7ffdfc10]
[d00000000d9846c0] ipoib_ib_handle_rx_wc+0x180/0x310 [ib_ipoib]
Jan 3 10:26:06 ltcalpine-lp4 kernel: [ 569.229452] [c000000c7ffdfcb0]
[d00000000d98571c] ipoib_poll+0x16c/0x250 [ib_ipoib]
Jan 3 10:26:06 ltcalpine-lp4 kernel: [ 569.229455] [c000000c7ffdfd30]
[c00000000090ebb8] net_rx_action+0x2d8/0x430
Jan 3 10:26:06 ltcalpine-lp4 kernel: [ 569.229459] [c000000c7ffdfe40]
[c0000000000ba124] __do_softirq+0x174/0x390
Jan 3 10:26:06 ltcalpine-lp4 kernel: [ 569.229463] [c000000c7ffdff40]
[c0000000000ba6c8] irq_exit+0xc8/0x100
Jan 3 10:26:06 ltcalpine-lp4 kernel: [ 569.229466] [c000000c7ffdff60]
[c0000000000111ec] __do_irq+0x8c/0x190
Jan 3 10:26:06 ltcalpine-lp4 kernel: [ 569.229470] [c000000c7ffdff90]
[c000000000024278] call_do_irq+0x14/0x24
Jan 3 10:26:06 ltcalpine-lp4 kernel: [ 569.229473] [c0000000014fb980]
[c000000000011390] do_IRQ+0xa0/0x120
Jan 3 10:26:06 ltcalpine-lp4 kernel: [ 569.229477] [c0000000014fb9e0]
[c000000000002594] hardware_interrupt_common+0x114/0x180
Jan 3 10:26:06 ltcalpine-lp4 kernel: [ 569.229483] --- interrupt: 501 at
plpar_hcall_norets+0x1c/0x28
Jan 3 10:26:06 ltcalpine-lp4 kernel: [ 569.229483] LR =
check_and_cede_processor+0x34/0x50
Jan 3 10:26:06 ltcalpine-lp4 kernel: [ 569.229488] [c0000000014fbcd0]
[c0000000008a8d90] check_and_cede_processor+0x20/0x50 (unreliable)
Jan 3 10:26:06 ltcalpine-lp4 kernel: [ 569.229492] [c0000000014fbd30]
[c0000000008a8fb8] shared_cede_loop+0x68/0x170
Jan 3 10:26:06 ltcalpine-lp4 kernel: [ 569.229495] [c0000000014fbd70]
[c0000000008a615c] cpuidle_enter_state+0xbc/0x350
Jan 3 10:26:06 ltcalpine-lp4 kernel: [ 569.229499] [c0000000014fbdd0]
[c000000000110f3c] call_cpuidle+0x7c/0xd0
Jan 3 10:26:06 ltcalpine-lp4 kernel: [ 569.229502] [c0000000014fbe10]
[c0000000001112d0] cpu_startup_entry+0x340/0x450
Jan 3 10:26:06 ltcalpine-lp4 kernel: [ 569.229506] [c0000000014fbee0]
[c00000000000bdcc] rest_init+0xac/0xc0
Jan 3 10:26:06 ltcalpine-lp4 kernel: [ 569.229510] [c0000000014fbf00]
[c000000000e13e9c] start_kernel+0x54c/0x568
Jan 3 10:26:06 ltcalpine-lp4 kernel: [ 569.229514] [c0000000014fbf90]
[c000000000008c6c] start_here_common+0x20/0xa8
Jan 3 10:26:06 ltcalpine-lp4 kernel: [ 569.229515] Instruction dump:
Jan 3 10:26:06 ltcalpine-lp4 kernel: [ 569.229517] 61290008 913f0090
4bfffe44 7fa3eb78 4b93441d 60000000 2fa30000 40feff14
Jan 3 10:26:06 ltcalpine-lp4 kernel: [ 569.229523] 4bfffefc 3c62fff6
89032f80 69080001 <0b080000> 2fa80000 41fefe54 39000001
Jan 3 10:26:06 ltcalpine-lp4 kernel: [ 569.229529] ---[ end trace
990311d357d2b2ab ]---
Jan 3 10:27:01 ltcalpine-lp4 CRON[3091]: (nobody) CMD (if [ -x /usr/bin/php5
] && [ -f /usr/share/serverstats/update.php ]; then /usr/bin/php5
/usr/share/serverstats/update.php > /dev/null; fi)
Jan 3 10:27:01 ltcalpine-lp4 CRON[3090]: (CRON) info (No MTA installed,
discarding output)
Jan 3 10:28:01 ltcalpine-lp4 CRON[3218]: (nobody) CMD (if [ -x /usr/bin/php5
] && [ -f /usr/share/serverstats/update.php ]; then /usr/bin/php5
/usr/share/serverstats/update.php > /dev/null; fi)
Jan 3 10:28:01 ltcalpine-lp4 CRON[3217]: (CRON) info (No MTA installed,
discarding output)
Jan 3 10:29:01 ltcalpine-lp4 CRON[3339]: (nobody) CMD (if [ -x /usr/bin/php5
] && [ -f /usr/share/serverstats/update.php ]; then /usr/bin/php5
/usr/share/serverstats/update.php > /dev/null; fi)
Jan 3 10:29:01 ltcalpine-lp4 CRON[3338]: (CRON) info (No MTA installed,
discarding output)
Jan 3 10:30:01 ltcalpine-lp4 CRON[3445]: (nobody) CMD (if [ -x /usr/bin/php5
] && [ -f /usr/share/serverstats/update.php ]; then /usr/bin/php5
/usr/share/serverstats/update.php > /dev/null; fi)
Jan 3 10:30:02 ltcalpine-lp4 CRON[3444]: (CRON) info (No MTA installed,
discarding output)
Jan 3 10:31:01 ltcalpine-lp4 CRON[3560]: (nobody) CMD (if [ -x /usr/bin/php5
] && [ -f /usr/share/serverstats/update.php ]; then /usr/bin/php5
/usr/share/serverstats/update.php > /dev/null; fi)
Jan 3 10:31:01 ltcalpine-lp4 CRON[3559]: (CRON) info (No MTA installed,
discarding output)
Stack trace output:
Jan 3 10:26:06 ltcalpine-lp4 kernel: [ 569.229293] ------------[ cut here
]------------
Jan 3 10:26:06 ltcalpine-lp4 kernel: [ 569.229301] WARNING: at
/build/linux-lts-wily-W0lTWH/linux-lts-wily-4.2.0/net/core/skbuff.c:4174
Jan 3 10:26:06 ltcalpine-lp4 kernel: [ 569.229303] Modules linked in:
rpcsec_gss_krb5 nfsv4 nfsd auth_rpcgss nfs_acl nfs lockd grace sunrpc fscache
mlx4_ib ib_ipoib rdma_ucm rdma_cm iw_cm ib_umad ib_ucm ib_cm ib_sa ib_mad
ib_uverbs ib_core ib_addr pseries_rng rtc_generic mlx4_en vxlan ip6_udp_tunnel
udp_tunnel bnx2x mlx4_core mdio libcrc32c
Jan 3 10:26:06 ltcalpine-lp4 kernel: [ 569.229338] CPU: 0 PID: 0 Comm:
swapper/0 Not tainted 4.2.0-21-generic #25~14.04.1-Ubuntu
Jan 3 10:26:06 ltcalpine-lp4 kernel: [ 569.229342] task: c000000001480b30
ti: c000000c7ffdc000 task.ti: c0000000014f8000
Jan 3 10:26:06 ltcalpine-lp4 kernel: [ 569.229344] NIP: c0000000008f484c
LR: c000000000981844 CTR: c0000000009d40e0
Jan 3 10:26:06 ltcalpine-lp4 kernel: [ 569.229347] REGS: c000000c7ffdf2d0
TRAP: 0700 Not tainted (4.2.0-21-generic)
Jan 3 10:26:06 ltcalpine-lp4 kernel: [ 569.229349] MSR: 8000000000029033
<SF,EE,ME,IR,DR,RI,LE> CR: 28008048 XER: 00000000
Jan 3 10:26:06 ltcalpine-lp4 kernel: [ 569.229357] CFAR: c0000000008f46a4
SOFTE: 1
Jan 3 10:26:06 ltcalpine-lp4 kernel: [ 569.229357] GPR00: 0000000000000000
c000000c7ffdf550 c0000000014fdf00 c00000000145df00
Jan 3 10:26:06 ltcalpine-lp4 kernel: [ 569.229357] GPR04: c000000bfa4fec00
0000000000000000 c000000c2aeedb00 c000000bfa4fdb00
Jan 3 10:26:06 ltcalpine-lp4 kernel: [ 569.229357] GPR08: 0000000000000001
c000000c2aeeec00 0000000000000005 0000000bfa4f0000
Jan 3 10:26:06 ltcalpine-lp4 kernel: [ 569.229357] GPR12: 0000000000002200
c00000000e7e0000 0000000000000001 000000000000012c
Jan 3 10:26:06 ltcalpine-lp4 kernel: [ 569.229357] GPR16: 0000000000000000
0000000000000001 c000000c7ffdfd90 0000000000000000
Jan 3 10:26:06 ltcalpine-lp4 kernel: [ 569.229357] GPR20: 000000000000dd86
0000000000000000 c000000000d83070 c000000000d83048
Jan 3 10:26:06 ltcalpine-lp4 kernel: [ 569.229357] GPR24: c000000c6f6c0098
0000000000000234 c000000c7ffdf5d0 0000000000000458
Jan 3 10:26:06 ltcalpine-lp4 kernel: [ 569.229357] GPR28: 0000000000000458
c000000c7ffdf660 c000000c40cf0d00 c000000c40cf9200
Jan 3 10:26:06 ltcalpine-lp4 kernel: [ 569.229390] NIP [c0000000008f484c]
skb_try_coalesce+0x40c/0x450
Jan 3 10:26:06 ltcalpine-lp4 kernel: [ 569.229393] LR [c000000000981844]
tcp_try_coalesce+0x94/0x140
Jan 3 10:26:06 ltcalpine-lp4 kernel: [ 569.229395] Call Trace:
Jan 3 10:26:06 ltcalpine-lp4 kernel: [ 569.229398] [c000000c7ffdf550]
[c000000c7ffdf5b0] 0xc000000c7ffdf5b0 (unreliable)
Jan 3 10:26:06 ltcalpine-lp4 kernel: [ 569.229402] [c000000c7ffdf5b0]
[c000000000981844] tcp_try_coalesce+0x94/0x140
Jan 3 10:26:06 ltcalpine-lp4 kernel: [ 569.229405] [c000000c7ffdf600]
[c000000000983358] tcp_data_queue+0x3f8/0xf90
Jan 3 10:26:06 ltcalpine-lp4 kernel: [ 569.229408] [c000000c7ffdf6d0]
[c0000000009861ac] tcp_rcv_established+0x1cc/0x7a0
Jan 3 10:26:06 ltcalpine-lp4 kernel: [ 569.229412] [c000000c7ffdf730]
[c000000000992104] tcp_v4_do_rcv+0x1b4/0x490
Jan 3 10:26:06 ltcalpine-lp4 kernel: [ 569.229415] [c000000c7ffdf790]
[c000000000995f60] tcp_v4_rcv+0xb40/0xb60
Jan 3 10:26:06 ltcalpine-lp4 kernel: [ 569.229418] [c000000c7ffdf870]
[c000000000963eb8] ip_local_deliver_finish+0x178/0x350
Jan 3 10:26:06 ltcalpine-lp4 kernel: [ 569.229422] [c000000c7ffdf8c0]
[c0000000009646d4] ip_local_deliver+0x54/0x130
Jan 3 10:26:06 ltcalpine-lp4 kernel: [ 569.229424] [c000000c7ffdf930]
[c0000000009641e4] ip_rcv_finish+0x154/0x420
Jan 3 10:26:06 ltcalpine-lp4 kernel: [ 569.229427] [c000000c7ffdf9b0]
[c000000000964a3c] ip_rcv+0x28c/0x430
Jan 3 10:26:06 ltcalpine-lp4 kernel: [ 569.229432] [c000000c7ffdfa40]
[c00000000090ad44] __netif_receive_skb_core+0x754/0xd30
Jan 3 10:26:06 ltcalpine-lp4 kernel: [ 569.229435] [c000000c7ffdfb20]
[c00000000090e3f4] netif_receive_skb_internal+0x34/0xd0
Jan 3 10:26:06 ltcalpine-lp4 kernel: [ 569.229438] [c000000c7ffdfb60]
[c00000000090efe4] dev_gro_receive+0x2d4/0x430
Jan 3 10:26:06 ltcalpine-lp4 kernel: [ 569.229441] [c000000c7ffdfbd0]
[c00000000090f408] napi_gro_receive+0x48/0x1b0
Jan 3 10:26:06 ltcalpine-lp4 kernel: [ 569.229447] [c000000c7ffdfc10]
[d00000000d9846c0] ipoib_ib_handle_rx_wc+0x180/0x310 [ib_ipoib]
Jan 3 10:26:06 ltcalpine-lp4 kernel: [ 569.229452] [c000000c7ffdfcb0]
[d00000000d98571c] ipoib_poll+0x16c/0x250 [ib_ipoib]
Jan 3 10:26:06 ltcalpine-lp4 kernel: [ 569.229455] [c000000c7ffdfd30]
[c00000000090ebb8] net_rx_action+0x2d8/0x430
Jan 3 10:26:06 ltcalpine-lp4 kernel: [ 569.229459] [c000000c7ffdfe40]
[c0000000000ba124] __do_softirq+0x174/0x390
Jan 3 10:26:06 ltcalpine-lp4 kernel: [ 569.229463] [c000000c7ffdff40]
[c0000000000ba6c8] irq_exit+0xc8/0x100
Jan 3 10:26:06 ltcalpine-lp4 kernel: [ 569.229466] [c000000c7ffdff60]
[c0000000000111ec] __do_irq+0x8c/0x190
Jan 3 10:26:06 ltcalpine-lp4 kernel: [ 569.229470] [c000000c7ffdff90]
[c000000000024278] call_do_irq+0x14/0x24
Jan 3 10:26:06 ltcalpine-lp4 kernel: [ 569.229473] [c0000000014fb980]
[c000000000011390] do_IRQ+0xa0/0x120
Jan 3 10:26:06 ltcalpine-lp4 kernel: [ 569.229477] [c0000000014fb9e0]
[c000000000002594] hardware_interrupt_common+0x114/0x180
Jan 3 10:26:06 ltcalpine-lp4 kernel: [ 569.229483] --- interrupt: 501 at
plpar_hcall_norets+0x1c/0x28
Jan 3 10:26:06 ltcalpine-lp4 kernel: [ 569.229483] LR =
check_and_cede_processor+0x34/0x50
Jan 3 10:26:06 ltcalpine-lp4 kernel: [ 569.229488] [c0000000014fbcd0]
[c0000000008a8d90] check_and_cede_processor+0x20/0x50 (unreliable)
Jan 3 10:26:06 ltcalpine-lp4 kernel: [ 569.229492] [c0000000014fbd30]
[c0000000008a8fb8] shared_cede_loop+0x68/0x170
Jan 3 10:26:06 ltcalpine-lp4 kernel: [ 569.229495] [c0000000014fbd70]
[c0000000008a615c] cpuidle_enter_state+0xbc/0x350
Jan 3 10:26:06 ltcalpine-lp4 kernel: [ 569.229499] [c0000000014fbdd0]
[c000000000110f3c] call_cpuidle+0x7c/0xd0
Jan 3 10:26:06 ltcalpine-lp4 kernel: [ 569.229502] [c0000000014fbe10]
[c0000000001112d0] cpu_startup_entry+0x340/0x450
Jan 3 10:26:06 ltcalpine-lp4 kernel: [ 569.229506] [c0000000014fbee0]
[c00000000000bdcc] rest_init+0xac/0xc0
Jan 3 10:26:06 ltcalpine-lp4 kernel: [ 569.229510] [c0000000014fbf00]
[c000000000e13e9c] start_kernel+0x54c/0x568
Jan 3 10:26:06 ltcalpine-lp4 kernel: [ 569.229514] [c0000000014fbf90]
[c000000000008c6c] start_here_common+0x20/0xa8
Jan 3 10:26:06 ltcalpine-lp4 kernel: [ 569.229515] Instruction dump:
Jan 3 10:26:06 ltcalpine-lp4 kernel: [ 569.229517] 61290008 913f0090
4bfffe44 7fa3eb78 4b93441d 60000000 2fa30000 40feff14
Jan 3 10:26:06 ltcalpine-lp4 kernel: [ 569.229523] 4bfffefc 3c62fff6
89032f80 69080001 <0b080000> 2fa80000 41fefe54 39000001
Jan 3 10:26:06 ltcalpine-lp4 kernel: [ 569.229529] ---[ end trace
990311d357d2b2ab ]---
Oops output:
no
System Dump Info:
The system was configured to capture a dump, however a dump was not
produced.
== Comment: #4 - Pradeep Satyanarayana <prad...@us.ibm.com> - 2016-01-19
18:51:44 ==
Is this just a warning that was printed, or was there a crash as well?
If it is just a warning, it is likely not very serious. It is
indicating that IPoIB (in this case) is not computing the memory
consumption correctly. Hence the warning. Of course that could end up
as OOM in case of a heavily loaded system.
Took a quick look and believe it is coming from
WARN_ON_ONCE(delta < len); in function skb_try_coalesce().
This was supposed to be fixed. Please see :
http://www.spinics.net/lists/netdev/msg204071.html
Is that fix not present? If so, maybe we should ask Canonical to pick
it up.
== Comment: #7 - Carol L. Soto <cls...@us.ibm.com> - 2016-01-19 22:52:30 ==
the problem is that after the patch Pradeep pointed there is another patch
that touches
the truesize value
http://git.kernel.org/cgit/linux/kernel/git/torvalds/linux.git/patch/drivers/infiniband/ulp/ipoib/ipoib_ib.c?id=a44878d100630a34a44f54960115b81e449858db
From a44878d100630a34a44f54960115b81e449858db Mon Sep 17 00:00:00 2001
From: Erez Shitrit <ere...@mellanox.com>
Date: Thu, 2 Apr 2015 13:39:00 +0300
Subject: IB/ipoib: Use one linear skb in RX flow
it looks like maybe UD path will hit it but maybe not connected mode.
(tester can verify this)
SKB_TRUESIZE(skb->len) maybe works ok in x86 but power the cache line size is
different than ppc64 so maybe that is why the warning.
MOFED has this line but I have not run UD in a long time with MOFED because
the new IB cards does not use UD mode.
skb->truesize = skb->len + sizeof(struct sk_buff);
== Comment: #13 - David Z. Dai <z...@us.ibm.com> - 2016-01-20 13:38:07 ==
The test box is actually using Ubuntu-wily release, with kernel at
4.2.0-21-generic.
Regarding the "WARN_ON_ONCE(delta < len);" warning messages, there are 2
related patches:
1) The first one is what Pradeep pointed out:
commit b28ba72665356438e3a6e3be365c3c3071496840
Author: Eric Dumazet <eduma...@google.com>
Date: Tue Jul 10 10:03:41 2012 +0000
IPoIB: fix skb truesize underestimatiom
Or Gerlitz reported triggering of WARN_ON_ONCE(delta < len); in
skb_try_coalesce()
This warning tracks drivers that incorrectly set skb->truesize
IPoIB indeed allocates a full page to store a fragment, but only
accounts in skb->truesize the used part of the page (frame length)
This patch fixes skb truesize underestimation, and
also fixes a performance issue, because RX skbs have not enough tailroom
to allow IP and TCP stacks to pull their header in skb linear part
without an expensive call to pskb_expand_head()
This patch is included in Ubuntu-vivid release with kernel at 3.19.
The main change to fix the WARN_ON_ONCE() warning message is in function
ipoib_ud_skb_put_frags():
@@ -123,7 +123,7 @@ static void ipoib_ud_skb_put_frags(struct ipoib_dev_priv
*priv,
if (ipoib_ud_need_sg(priv->max_ib_mtu)) {
skb_frag_t *frag = &skb_shinfo(skb)->frags[0];
unsigned int size;
/*
* There is only two buffers needed for max_payload = 4K,
* first buf size is IPOIB_UD_HEAD_SIZE
*/
skb->tail += IPOIB_UD_HEAD_SIZE;
skb->len += length;
size = length - IPOIB_UD_HEAD_SIZE;
skb_frag_size_set(frag, size);
- skb->truesize += size;
+ skb->truesize += PAGE_SIZE;
} else
skb_put(skb, length);
2) Next on new Ubuntu-wily relase, it includes the patch Carol pointed out:
commit a44878d100630a34a44f54960115b81e449858db (in wily)
Author: Erez Shitrit <ere...@mellanox.com>
Date: Thu Apr 2 13:39:00 2015 +0300
IB/ipoib: Use one linear skb in RX flow
The current code in the RX flow uses two sg entries for each incoming
packet, the first one was for the IB headers and the second for the rest
of the data, that causes two dma map/unmap and two allocations, and few
more actions that were done at the data path.
Use only one linear skb on each incoming packet, for the data (IB
headers and payload), that reduces the packet processing in the
data-path (only one skb, no frags, the first frag was not used anyway,
less memory allocations) and the dma handling (only one dma map/unmap
over each incoming packet instead of two map/unmap per each incoming
packet).
After commit 73d3fe6d1c6d ("gro: fix aggregation for skb using
frag_list") from
Eric Dumazet, we will get full aggregation for large packets.
When running bandwidth tests before and after the (over the card's numa
node),
using "netperf -H 1.1.1.3 -T -t TCP_STREAM", the results before are
~12Gbs before
and after ~16Gbs on my setup (Mellanox's ConnectX3).
Look at the code change in this patch, it completely removed the functions
ipoib_ud_skb_put_frags(), ipoib_ud_need_sg(),
and just call skb_put() directly in ipoib_ib_handle_rx_wc(), followed by
"skb->truesize = SKB_TRUESIZE(skb->len);":
static int ipoib_ib_post_receive(struct net_device *dev, int id)
@@ -156,18 +126,11 @@ static struct sk_buff *ipoib_alloc_rx_skb(struct
net_device *dev, int id)
ipoib_ud_dma_unmap_rx(priv, mapping);
- ipoib_ud_skb_put_frags(priv, skb, wc->byte_len);
+
+ skb_put(skb, wc->byte_len);
...
skb_pull(skb, IPOIB_ENCAP_LEN);
+ skb->truesize = SKB_TRUESIZE(skb->len);
/* include/linux/skbuff.h */
/* return minimum truesize of one skb containing X bytes of data */
#define SKB_TRUESIZE(X) ((X) + \
SKB_DATA_ALIGN(sizeof(struct sk_buff)) + \
SKB_DATA_ALIGN(sizeof(struct skb_shared_info)))
Looks like the 2nd patch broke the fix in the 1st patch related to the
warning message.
One thought is to keep the 1st patch's code change related to skb->truesize
on top of the 2nd patch.
In ipoib_alloc_rx_skb():
skb_put(skb, wc->byte_len);
...
+ if (ipoib_ud_need_sg(priv->max_ib_mtu)) {
+ skb->truesize += PAGE_SIZE;
+ else
skb->truesize = SKB_TRUESIZE(skb->len);
Will discuss with Pradeep/Carol on the best approach for the fix.
********************************************************************
Also on this Ubuntu-wily test box, please verify what Carol suggested to set
the ipoib in "connected" mode.
# echo 'connected' > /sys/class/net/ib0/mode
(you might need to bring down the test interface ib0/ib1 ip configuration
first before running above command)
After you set it to connected mode, rerun the same stress test, most likely
you will not see the warning message any more.
Please update the test result with the "connected" mode.
To manage notifications about this bug go to:
https://bugs.launchpad.net/ubuntu/+source/linux/+bug/1541326/+subscriptions
--
Mailing list: https://launchpad.net/~kernel-packages
Post to : kernel-packages@lists.launchpad.net
Unsubscribe : https://launchpad.net/~kernel-packages
More help : https://help.launchpad.net/ListHelp
