Description of problem: When the NIC (Broadcom BCM5906M, in an Lenovo Ideapad S10) is somewhat loaded, after a while the WARNING below appears and the interface is not usable any more. "ifconfig p2p1 down" and "up" again does not help, but unloading and reloading the "tg3" driver did the trick so far. ------------[ cut here ]------------ WARNING: at net/sched/sch_generic.c:256 dev_watchdog+0x1d7/0x1e0() Hardware name: Lenovo NETDEV WATCHDOG: p2p1 (tg3): transmit queue 0 timed out Modules linked in: nfs nfs_acl auth_rpcgss fscache lockd sunrpc ipt_MASQUERADE nf_conntrack_netbios_ns nf_conntrack_broadcast ip6table_mangle ip6t_REJECT nf_conntrack_ipv6 nf_defrag_ipv6 ip6table_filter ip6_tables iptable_nat nf_nat iptable_mangle nf_conntrack_ipv4 nf_defrag_ipv4 xt_conntrack nf_conntrack sha256_generic dm_crypt arc4 b43 bcma mac80211 cfg80211 microcode ideapad_laptop sparse_keymap rfkill ssb tg3 mmc_core uinput wmi usb_storage i915 video i2c_algo_bit drm_kms_helper drm i2c_core [last unloaded: scsi_wait_scan] Pid: 0, comm: swapper/0 Not tainted 3.3.4-5.fc17.i686 #1 Call Trace: [<c04372f2>] warn_slowpath_common+0x72/0xa0 [<c0852077>] ? dev_watchdog+0x1d7/0x1e0 [<c0852077>] ? dev_watchdog+0x1d7/0x1e0 [<c04373c3>] warn_slowpath_fmt+0x33/0x40 [<c0852077>] dev_watchdog+0x1d7/0x1e0 [<c0851ea0>] ? dev_deactivate_queue.constprop.32+0x60/0x60 [<c0444df1>] run_timer_softirq+0xf1/0x2a0 [<c0851ea0>] ? dev_deactivate_queue.constprop.32+0x60/0x60 [<c043dd77>] __do_softirq+0x97/0x190 [<c043dce0>] ? remote_softirq_receive+0x40/0x40 [<c043dce0>] ? remote_softirq_receive+0x40/0x40 <IRQ> [<c043e0bd>] ? irq_exit+0x9d/0xb0 [<c040508b>] ? do_IRQ+0x4b/0xc0 [<c092b833>] ? notifier_call_chain+0x43/0x60 [<c092f470>] ? common_interrupt+0x30/0x38 [<c04300e0>] ? aes_dec_blk+0x77c/0xb6c [<c06a2c20>] ? intel_idle+0xd0/0x130 [<c07ffdd6>] ? cpuidle_idle_call+0xa6/0x1f0 [<c04023cc>] ? cpu_idle+0x9c/0xe0 [<c0908c85>] ? rest_init+0x5d/0x68 [<c0bb2751>] ? start_kernel+0x357/0x35d [<c0bb217f>] ? loglevel+0x2b/0x2b [<c0bb2078>] ? i386_start_kernel+0x78/0x7d ---[ end trace 63a55f6565db3c43 ]--- tg3 0000:02:00.0: p2p1: transmit timed out, resetting hrtimer: interrupt took 7973146 ns After the warning, the following lines are printed: tg3 0000:02:00.0: p2p1: 0x00000000: 0x171314e4, 0x00100406, 0x02000002, 0x00000010 I'll attach a full log later on. Version-Release number of selected component (if applicable): Fedora release 17 (Beefy Miracle) Linux len.housecafe.de 3.3.4-5.fc17.i686 #1 SMP Mon May 7 17:45:26 UTC 2012 i686 i686 i386 GNU/Linux $ ethtool -i p2p1 driver: tg3 version: 3.122 firmware-version: sb v3.04 bus-info: 0000:02:00.0 supports-statistics: yes supports-test: yes supports-eeprom-access: yes supports-register-dump: yes supports-priv-flags: no $ lspci -v [...] 02:00.0 Ethernet controller: Broadcom Corporation NetLink BCM5906M Fast Ethernet PCI Express (rev 02) Subsystem: Lenovo IdeaPad S10e Flags: bus master, fast devsel, latency 0, IRQ 43 Memory at f0200000 (64-bit, non-prefetchable) [size=64K] Expansion ROM at <ignored> [disabled] Capabilities: [48] Power Management version 3 Capabilities: [50] Vital Product Data Capabilities: [58] Vendor Specific Information: Len=78 <?> Capabilities: [e8] MSI: Enable+ Count=1/1 Maskable- 64bit+ Capabilities: [d0] Express Endpoint, MSI 00 Capabilities: [100] Advanced Error Reporting Capabilities: [13c] Virtual Channel Capabilities: [160] Device Serial Number 00-23-8b-ff-fe-35-65-95 Kernel driver in use: tg3 How reproducible: This happened two times so far (with a reboot inbetween), at both times the NIC was somewhat busy (constant ~200 KB/s TX & RX). Steps to Reproduce: 1. Boot system 2. Generate some network load 3. Wait a few hours Actual results: WARNING is printed, tg3 stops working Expected results: NIC continues to work. Additional info: There are similar bugs filed with "WARNING: at net/sched/sch_generic.c:256" (e.g. #715137, #717211, #552288) but none for the tg3 driver, AFAICS.
Created attachment 586799 [details] kernel.log Careful, the decompressed kernel-log.txt is ~70 MB! But I wanted to include it, for the sake of completeness.
*** Bug 825122 has been marked as a duplicate of this bug. ***
Since this is happening to vanilla kernels as well, I've reported this upstream: http://lkml.indiana.edu/hypermail/linux/kernel/1206.0/01259.html
Workaround is to disable scatter/gather: ethtool -K p2p1 sg off No more errors, interface keeps working.
This got fixed upstream: https://git.kernel.org/?p=linux/kernel/git/davem/net.git;a=commit;h=b7abee6ef888117f92db370620ebf116a38e3f4d
Fixed in Fedora git for f16/f17
kernel-3.4.4-5.fc17 has been submitted as an update for Fedora 17. https://admin.fedoraproject.org/updates/kernel-3.4.4-5.fc17
kernel-3.4.4-4.fc16 has been submitted as an update for Fedora 16. https://admin.fedoraproject.org/updates/kernel-3.4.4-4.fc16
Package kernel-3.4.4-4.fc16: * should fix your issue, * was pushed to the Fedora 16 testing repository, * should be available at your local mirror within two days. Update it with: # su -c 'yum update --enablerepo=updates-testing kernel-3.4.4-4.fc16' as soon as you are able to, then reboot. Please go to the following url: https://admin.fedoraproject.org/updates/FEDORA-2012-10319/kernel-3.4.4-4.fc16 then log in and leave karma (feedback).
kernel-3.4.4-5.fc17 has been pushed to the Fedora 17 stable repository. If problems still persist, please make note of it in this bug report.
I've been running kernel-3.4.4-5.fc17 since yesterday evening with sg=on and the interface is still working while network traffic is steady as usual. Thanks!
kernel-3.4.4-4.fc16 has been pushed to the Fedora 16 stable repository. If problems still persist, please make note of it in this bug report.