[Group.of.nepali.translators] [Bug 1713553] Re: Intel i40e PF reset due to incorrect MDD detection
** Changed in: linux (Ubuntu) Status: In Progress => Fix Released -- You received this bug notification because you are a member of नेपाली भाषा समायोजकहरुको समूह, which is subscribed to Xenial. Matching subscriptions: Ubuntu 16.04 Bugs https://bugs.launchpad.net/bugs/1713553 Title: Intel i40e PF reset due to incorrect MDD detection Status in linux package in Ubuntu: Fix Released Status in linux source package in Xenial: Fix Released Bug description: [Impact] Using an Intel i40e network device, under heavy traffic load with TSO enabled, the device will spontaneously reset itself and issue errors similar to the following: Jun 14 14:09:51 hostname kernel: [4253913.851053] i40e :05:00.1: TX driver issue detected, PF reset issued Jun 14 14:09:53 hostname kernel: [4253915.476283] i40e :05:00.1: TX driver issue detected, PF reset issued Jun 14 14:09:54 hostname kernel: [4253917.411264] i40e :05:00.1: TX driver issue detected, PF reset issued This causes a full reset of the PF, which causes an interruption in traffic flow. This was partially fixed by Xenial commit 12f8cc59d5886b86372f45290166deca57a60d7a, however there is one additional upstream commit required to fully fix the issue: commit 841493a3f64395b60554afbcaa17f4350f90e764 Author: Alexander Duyck Date: Tue Sep 6 18:05:04 2016 -0700 i40e: Limit TX descriptor count in cases where frag size is greater than 16K This fix was never backported into the Xenial 4.4 kernel series, but is already present in the Xenial HWE (and Zesty) 4.10 kernel. [Testcase] In this case, the issue occurs at a customer site using i40e based Intel network cards with SR-IOV enabled. Under heavy load, the card will reset itself as described. [Regression Potential] As with any change to a network card driver, this may cause regressions with network I/O through i40e card(s). However, this specific change only increases the likelyhood that any specific large TSO tx will need to be linearized, which will avoid the PF reset. Linearizing a TSO tx that did not need to be linearized will not cause any failures, it may only decrease performance slightly. However this patch should only cause linearization when required to avoid the MDD detection and PF reset. [Other Info] The previous bug for this issue is bug 1700834. To manage notifications about this bug go to: https://bugs.launchpad.net/ubuntu/+source/linux/+bug/1713553/+subscriptions ___ Mailing list: https://launchpad.net/~group.of.nepali.translators Post to : group.of.nepali.translators@lists.launchpad.net Unsubscribe : https://launchpad.net/~group.of.nepali.translators More help : https://help.launchpad.net/ListHelp
[Group.of.nepali.translators] [Bug 1713553] Re: Intel i40e PF reset due to incorrect MDD detection
This bug was fixed in the package linux - 4.4.0-97.120
---
linux (4.4.0-97.120) xenial; urgency=low
* linux: 4.4.0-97.120 -proposed tracker (LP: #1718149)
* blk-mq: possible deadlock on CPU hot(un)plug (LP: #1670634)
- [Config] s390x -- disable CONFIG_{DM, SCSI}_MQ_DEFAULT
* Xenial update to 4.4.87 stable release (LP: #1715678)
- irqchip: mips-gic: SYNC after enabling GIC region
- i2c: ismt: Don't duplicate the receive length for block reads
- i2c: ismt: Return EMSGSIZE for block reads with bogus length
- ceph: fix readpage from fscache
- cpumask: fix spurious cpumask_of_node() on non-NUMA multi-node configs
- cpuset: Fix incorrect memory_pressure control file mapping
- alpha: uapi: Add support for __SANE_USERSPACE_TYPES__
- CIFS: remove endian related sparse warning
- wl1251: add a missing spin_lock_init()
- xfrm: policy: check policy direction value
- drm/ttm: Fix accounting error when fail to get pages for pool
- kvm: arm/arm64: Fix race in resetting stage2 PGD
- kvm: arm/arm64: Force reading uncached stage2 PGD
- epoll: fix race between ep_poll_callback(POLLFREE) and
ep_free()/ep_remove()
- crypto: algif_skcipher - only call put_page on referenced and used pages
- Linux 4.4.87
* Xenial update to 4.4.86 stable release (LP: #1715430)
- scsi: isci: avoid array subscript warning
- ALSA: au88x0: Fix zero clear of stream->resources
- btrfs: remove duplicate const specifier
- i2c: jz4780: drop superfluous init
- gcov: add support for gcc version >= 6
- gcov: support GCC 7.1
- lightnvm: initialize ppa_addr in dev_to_generic_addr()
- p54: memset(0) whole array
- lpfc: Fix Device discovery failures during switch reboot test.
- arm64: mm: abort uaccess retries upon fatal signal
- x86/io: Add "memory" clobber to insb/insw/insl/outsb/outsw/outsl
- arm64: fpsimd: Prevent registers leaking across exec
- scsi: sg: protect accesses to 'reserved' page array
- scsi: sg: reset 'res_in_use' after unlinking reserved array
- drm/i915: fix compiler warning in drivers/gpu/drm/i915/intel_uncore.c
- Linux 4.4.86
* Xenial update to 4.4.85 stable release (LP: #1714298)
- af_key: do not use GFP_KERNEL in atomic contexts
- dccp: purge write queue in dccp_destroy_sock()
- dccp: defer ccid_hc_tx_delete() at dismantle time
- ipv4: fix NULL dereference in free_fib_info_rcu()
- net_sched/sfq: update hierarchical backlog when drop packet
- ipv4: better IP_MAX_MTU enforcement
- sctp: fully initialize the IPv6 address in sctp_v6_to_addr()
- tipc: fix use-after-free
- ipv6: reset fn->rr_ptr when replacing route
- ipv6: repair fib6 tree in failure case
- tcp: when rearming RTO, if RTO time is in past then fire RTO ASAP
- irda: do not leak initialized list.dev to userspace
- net: sched: fix NULL pointer dereference when action calls some targets
- net_sched: fix order of queue length updates in qdisc_replace()
- mei: me: add broxton pci device ids
- mei: me: add lewisburg device ids
- Input: trackpoint - add new trackpoint firmware ID
- Input: elan_i2c - add ELAN0602 ACPI ID to support Lenovo Yoga310
- ALSA: core: Fix unexpected error at replacing user TLV
- ALSA: hda - Add stereo mic quirk for Lenovo G50-70 (17aa:3978)
- ARCv2: PAE40: Explicitly set MSB counterpart of SLC region ops addresses
- i2c: designware: Fix system suspend
- drm: Release driver tracking before making the object available again
- drm/atomic: If the atomic check fails, return its value first
- drm: rcar-du: lvds: Fix PLL frequency-related configuration
- drm: rcar-du: lvds: Rename PLLEN bit to PLLON
- drm: rcar-du: Fix crash in encoder failure error path
- drm: rcar-du: Fix display timing controller parameter
- drm: rcar-du: Fix H/V sync signal polarity configuration
- tracing: Fix freeing of filter in create_filter() when set_str is false
- cifs: Fix df output for users with quota limits
- cifs: return ENAMETOOLONG for overlong names in cifs_open()/cifs_lookup()
- nfsd: Limit end of page list when decoding NFSv4 WRITE
- perf/core: Fix group {cpu,task} validation
- Bluetooth: hidp: fix possible might sleep error in hidp_session_thread
- Bluetooth: cmtp: fix possible might sleep error in cmtp_session
- Bluetooth: bnep: fix possible might sleep error in bnep_session
- binder: use group leader instead of open thread
- binder: Use wake up hint for synchronous transactions.
- ANDROID: binder: fix proc->tsk check.
- iio: imu: adis16480: Fix acceleration scale factor for adis16480
- iio: hid-sensor-trigger: Fix the race with user space powering up sensors
- staging: rtl8188eu: add RNX-N150NUB support
- ASoC: simple-card: don't fail if sysclk setting is not supported
- ASoC: rsnd: disable SRC.out only when stop timing
- ASoC: rsnd: avoid po
[Group.of.nepali.translators] [Bug 1713553] Re: Intel i40e PF reset due to incorrect MDD detection
** Also affects: linux (Ubuntu Xenial) Importance: Undecided Status: New -- You received this bug notification because you are a member of नेपाली भाषा समायोजकहरुको समूह, which is subscribed to Xenial. Matching subscriptions: Ubuntu 16.04 Bugs https://bugs.launchpad.net/bugs/1713553 Title: Intel i40e PF reset due to incorrect MDD detection Status in linux package in Ubuntu: In Progress Status in linux source package in Xenial: New Bug description: [Impact] Using an Intel i40e network device, under heavy traffic load with TSO enabled, the device will spontaneously reset itself and issue errors similar to the following: Jun 14 14:09:51 hostname kernel: [4253913.851053] i40e :05:00.1: TX driver issue detected, PF reset issued Jun 14 14:09:53 hostname kernel: [4253915.476283] i40e :05:00.1: TX driver issue detected, PF reset issued Jun 14 14:09:54 hostname kernel: [4253917.411264] i40e :05:00.1: TX driver issue detected, PF reset issued This causes a full reset of the PF, which causes an interruption in traffic flow. This was partially fixed by Xenial commit 12f8cc59d5886b86372f45290166deca57a60d7a, however there is one additional upstream commit required to fully fix the issue: commit 841493a3f64395b60554afbcaa17f4350f90e764 Author: Alexander Duyck Date: Tue Sep 6 18:05:04 2016 -0700 i40e: Limit TX descriptor count in cases where frag size is greater than 16K This fix was never backported into the Xenial 4.4 kernel series, but is already present in the Xenial HWE (and Zesty) 4.10 kernel. [Testcase] In this case, the issue occurs at a customer site using i40e based Intel network cards with SR-IOV enabled. Under heavy load, the card will reset itself as described. [Regression Potential] As with any change to a network card driver, this may cause regressions with network I/O through i40e card(s). However, this specific change only increases the likelyhood that any specific large TSO tx will need to be linearized, which will avoid the PF reset. Linearizing a TSO tx that did not need to be linearized will not cause any failures, it may only decrease performance slightly. However this patch should only cause linearization when required to avoid the MDD detection and PF reset. [Other Info] The previous bug for this issue is bug 1700834. To manage notifications about this bug go to: https://bugs.launchpad.net/ubuntu/+source/linux/+bug/1713553/+subscriptions ___ Mailing list: https://launchpad.net/~group.of.nepali.translators Post to : group.of.nepali.translators@lists.launchpad.net Unsubscribe : https://launchpad.net/~group.of.nepali.translators More help : https://help.launchpad.net/ListHelp
