42912 – bnx2: Kernel freeze. tcp_input.c:3418 tcp_clean_rtx_queue

Bug 42912 - bnx2: Kernel freeze. tcp_input.c:3418 tcp_clean_rtx_queue

Summary: bnx2: Kernel freeze. tcp_input.c:3418 tcp_clean_rtx_queue

Status:	NEW

Alias:	None

Product:	Networking
Classification:	Unclassified
Component:	IPV4 (show other bugs)
Hardware:	All Linux

Importance:	P1 normal
Assignee:	Stephen Hemminger

URL:
Keywords:

Depends on:
Blocks:

Reported:	2012-03-12 16:21 UTC by Reinis Rozitis
Modified:	2016-02-15 20:37 UTC (History)
CC List:	2 users (show)

See Also:
Kernel Version:	3.3 rc6
Subsystem:
Regression:	No
Bisected commit-id:

Attachments
Add an attachment (proposed patch, testcase, etc.)

Description Reinis Rozitis 2012-03-12 16:21:56 UTC

After some operating time (within a day) server (opensuse 11.3) crashes with:

Mar  8 15:48:19 is52 kernel: [37589.085733] ------------[ cut here ]------------
Mar  8 15:48:19 is52 kernel: [37589.085748] WARNING: at /home/abuild/rpmbuild/BUILD/kernel-default-3.3.rc6/linux-3.3-rc6/net/ipv4/tcp_input.c:3418 tcp_clean_rtx_queue+0x763/0x800()
Mar  8 15:48:19 is52 kernel: [37589.085770] Hardware name: ProLiant DL360 G5
Mar  8 15:48:19 is52 kernel: [37589.085778] Modules linked in: mperf edd loop dm_mod sg i5000_edac edac_core coretemp i5k_amb ipmi_si ipmi_msghandler serio_raw pcspkr mvsas bnx2 libsas iTCO_wdt iTCO_vendor_s
upport hpwdt shpchp scsi_transport_sas pci_hotplug hpilo usbhid button microcode container xfs uhci_hcd radeon ehci_hcd ttm drm_kms_helper drm i2c_algo_bit usbcore usb_common fan thermal processor thermal_sy
s hpsa ata_generic cciss
Mar  8 15:48:19 is52 kernel: [37589.085875] Pid: 0, comm: swapper/2 Tainted: G        W I  3.3.0-rc6-3-default #1
Mar  8 15:48:19 is52 kernel: [37589.085897] Call Trace:
Mar  8 15:48:19 is52 kernel: [37589.085907]  [<ffffffff8100445a>] dump_trace+0x9a/0x260
Mar  8 15:48:19 is52 kernel: [37589.085912]  [<ffffffff81556f4f>] dump_stack+0x69/0x6f
Mar  8 15:48:19 is52 kernel: [37589.085916]  [<ffffffff8103ddab>] warn_slowpath_common+0x7b/0xc0
Mar  8 15:48:19 is52 kernel: [37589.085921]  [<ffffffff8149ada3>] tcp_clean_rtx_queue+0x763/0x800
Mar  8 15:48:19 is52 kernel: [37589.085926]  [<ffffffff8149d944>] tcp_ack+0x2e4/0x570
Mar  8 15:48:19 is52 kernel: [37589.085931]  [<ffffffff8149e9f9>] tcp_rcv_established+0x1c9/0x7c0
Mar  8 15:48:19 is52 kernel: [37589.085935]  [<ffffffff814a6341>] tcp_v4_do_rcv+0x111/0x1b0
Mar  8 15:48:19 is52 kernel: [37589.085939]  [<ffffffff814a7adf>] tcp_v4_rcv+0x55f/0x810
Mar  8 15:48:19 is52 kernel: [37589.085944]  [<ffffffff814850cc>] ip_local_deliver_finish+0xcc/0x270
Mar  8 15:48:19 is52 kernel: [37589.085950]  [<ffffffff81452623>] __netif_receive_skb+0x493/0x510
Mar  8 15:48:19 is52 kernel: [37589.085956]  [<ffffffff8145305a>] netif_receive_skb+0x1a/0x80
Mar  8 15:48:19 is52 kernel: [37589.085959]  [<ffffffff814531c8>] napi_skb_finish+0x38/0x50
Mar  8 15:48:19 is52 kernel: [37589.085967]  [<ffffffffa038d6df>] bnx2_rx_int+0x3df/0x7d0 [bnx2]
Mar  8 15:48:19 is52 kernel: [37589.085986]  [<ffffffffa038db36>] bnx2_poll_work+0x66/0x90 [bnx2]
Mar  8 15:48:19 is52 kernel: [37589.086003]  [<ffffffffa038dc84>] bnx2_poll+0x54/0x1a0 [bnx2]
Mar  8 15:48:19 is52 kernel: [37589.086018]  [<ffffffff814539b1>] net_rx_action+0x121/0x260
Mar  8 15:48:19 is52 kernel: [37589.086023]  [<ffffffff8104500d>] __do_softirq+0x9d/0x1f0
Mar  8 15:48:19 is52 kernel: [37589.086028]  [<ffffffff8157871c>] call_softirq+0x1c/0x30
Mar  8 15:48:19 is52 kernel: [37589.086032]  [<ffffffff810042d5>] do_softirq+0x65/0xa0
Mar  8 15:48:19 is52 kernel: [37589.086036]  [<ffffffff810453de>] irq_exit+0x8e/0xb0
Mar  8 15:48:19 is52 kernel: [37589.086040]  [<ffffffff81003efc>] do_IRQ+0x5c/0xd0
Mar  8 15:48:19 is52 kernel: [37589.086045]  [<ffffffff8156f5ee>] common_interrupt+0x6e/0x6e
Mar  8 15:48:19 is52 kernel: [37589.086050]  [<ffffffff8100ad92>] mwait_idle+0x92/0x210
Mar  8 15:48:19 is52 kernel: [37589.086054]  [<ffffffff810011a9>] cpu_idle+0x89/0xd0
Mar  8 15:48:19 is52 kernel: [37589.086057] ---[ end trace 306e3d00e8ef1b59 ]---
Mar  8 15:48:19 is52 kernel: [37589.086059] ------------[ cut here ]------------
Mar  8 15:48:19 is52 kernel: [37589.086062] WARNING: at /home/abuild/rpmbuild/BUILD/kernel-default-3.3.rc6/linux-3.3-rc6/net/ipv4/tcp_input.c:3048 tcp_fastretrans_alert+0x802/0x860()
Mar  8 15:48:19 is52 kernel: [37589.086065] Hardware name: ProLiant DL360 G5
Mar  8 15:48:19 is52 kernel: [37589.086066] Modules linked in: mperf edd loop dm_mod sg i5000_edac edac_core coretemp i5k_amb ipmi_si ipmi_msghandler serio_raw pcspkr mvsas bnx2 libsas iTCO_wdt iTCO_vendor_s
upport hpwdt shpchp scsi_transport_sas pci_hotplug hpilo usbhid button microcode container xfs uhci_hcd radeon ehci_hcd ttm drm_kms_helper drm i2c_algo_bit usbcore usb_common fan thermal processor thermal_sy
s hpsa ata_generic cciss
Mar  8 15:48:19 is52 kernel: [37589.086084] Pid: 0, comm: swapper/2 Tainted: G        W I  3.3.0-rc6-3-default #1
Mar  8 15:48:19 is52 kernel: [37589.086085] Call Trace:
Mar  8 15:48:19 is52 kernel: [37589.086089]  [<ffffffff8100445a>] dump_trace+0x9a/0x260
Mar  8 15:48:19 is52 kernel: [37589.086093]  [<ffffffff81556f4f>] dump_stack+0x69/0x6f
Mar  8 15:48:19 is52 kernel: [37589.086097]  [<ffffffff8103ddab>] warn_slowpath_common+0x7b/0xc0
Mar  8 15:48:19 is52 kernel: [37589.086101]  [<ffffffff8149d602>] tcp_fastretrans_alert+0x802/0x860
Mar  8 15:48:19 is52 kernel: [37589.086118]  [<ffffffff8149da62>] tcp_ack+0x402/0x570
Mar  8 15:48:19 is52 kernel: [37589.086123]  [<ffffffff8149e9f9>] tcp_rcv_established+0x1c9/0x7c0
Mar  8 15:48:19 is52 kernel: [37589.086127]  [<ffffffff814a6341>] tcp_v4_do_rcv+0x111/0x1b0
Mar  8 15:48:19 is52 kernel: [37589.086131]  [<ffffffff814a7adf>] tcp_v4_rcv+0x55f/0x810
Mar  8 15:48:19 is52 kernel: [37589.086135]  [<ffffffff814850cc>] ip_local_deliver_finish+0xcc/0x270
Mar  8 15:48:19 is52 kernel: [37589.086140]  [<ffffffff81452623>] __netif_receive_skb+0x493/0x510
Mar  8 15:48:19 is52 kernel: [37589.086145]  [<ffffffff8145305a>] netif_receive_skb+0x1a/0x80
Mar  8 15:48:19 is52 kernel: [37589.086149]  [<ffffffff814531c8>] napi_skb_finish+0x38/0x50
Mar  8 15:48:19 is52 kernel: [37589.086155]  [<ffffffffa038d6df>] bnx2_rx_int+0x3df/0x7d0 [bnx2]
Mar  8 15:48:19 is52 kernel: [37589.086172]  [<ffffffffa038db36>] bnx2_poll_work+0x66/0x90 [bnx2]
Mar  8 15:48:19 is52 kernel: [37589.086189]  [<ffffffffa038dc84>] bnx2_poll+0x54/0x1a0 [bnx2]
Mar  8 15:48:19 is52 kernel: [37589.086204]  [<ffffffff814539b1>] net_rx_action+0x121/0x260
Mar  8 15:48:19 is52 kernel: [37589.086209]  [<ffffffff8104500d>] __do_softirq+0x9d/0x1f0
Mar  8 15:48:19 is52 kernel: [37589.086213]  [<ffffffff8157871c>] call_softirq+0x1c/0x30
Mar  8 15:48:19 is52 kernel: [37589.086217]  [<ffffffff810042d5>] do_softirq+0x65/0xa0
Mar  8 15:48:19 is52 kernel: [37589.086221]  [<ffffffff810453de>] irq_exit+0x8e/0xb0
Mar  8 15:48:19 is52 kernel: [37589.086225]  [<ffffffff81003efc>] do_IRQ+0x5c/0xd0
Mar  8 15:48:19 is52 kernel: [37589.086229]  [<ffffffff8156f5ee>] common_interrupt+0x6e/0x6e
Mar  8 15:48:19 is52 kernel: [37589.086233]  [<ffffffff8100ad92>] mwait_idle+0x92/0x210
Mar  8 15:48:19 is52 kernel: [37589.086237]  [<ffffffff810011a9>] cpu_idle+0x89/0xd0
Mar  8 15:48:19 is52 kernel: [37589.086240] ---[ end trace 306e3d00e8ef1b5a ]---
Mar  8 15:48:19 is52 kernel: [37589.086241] ------------[ cut here ]------------
Mar  8 15:48:19 is52 kernel: [37589.086244] WARNING: at /home/abuild/rpmbuild/BUILD/kernel-default-3.3.rc6/linux-3.3-rc6/net/ipv4/tcp_input.c:2885 tcp_try_to_open+0x19a/0x1b0()
Mar  8 15:48:19 is52 kernel: [37589.086247] Hardware name: ProLiant DL360 G5
Mar  8 15:48:19 is52 kernel: [37589.086248] Modules linked in: mperf edd loop dm_mod sg i5000_edac edac_core coretemp i5k_amb ipmi_si ipmi_msghandler serio_raw pcspkr mvsas bnx2 libsas iTCO_wdt iTCO_vendor_s
upport hpwdt shpchp scsi_transport_sas pci_hotplug hpilo usbhid button microcode container xfs uhci_hcd radeon ehci_hcd ttm drm_kms_helper drm i2c_algo_bit usbcore usb_common fan thermal processor thermal_sy
s hpsa ata_generic cciss
Mar  8 15:48:19 is52 kernel: [37589.086266] Pid: 0, comm: swapper/2 Tainted: G        W I  3.3.0-rc6-3-default #1
Mar  8 15:48:19 is52 kernel: [37589.086267] Call Trace:
Mar  8 15:48:19 is52 kernel: [37589.086271]  [<ffffffff8100445a>] dump_trace+0x9a/0x260
Mar  8 15:48:19 is52 kernel: [37589.086275]  [<ffffffff81556f4f>] dump_stack+0x69/0x6f
Mar  8 15:48:19 is52 kernel: [37589.086278]  [<ffffffff8103ddab>] warn_slowpath_common+0x7b/0xc0
Mar  8 15:48:19 is52 kernel: [37589.086282]  [<ffffffff8149c7da>] tcp_try_to_open+0x19a/0x1b0
Mar  8 15:48:19 is52 kernel: [37589.086287]  [<ffffffff8149da62>] tcp_ack+0x402/0x570
Mar  8 15:48:19 is52 kernel: [37589.086292]  [<ffffffff8149e9f9>] tcp_rcv_established+0x1c9/0x7c0
Mar  8 15:48:19 is52 kernel: [37589.086296]  [<ffffffff814a6341>] tcp_v4_do_rcv+0x111/0x1b0
Mar  8 15:48:19 is52 kernel: [37589.086300]  [<ffffffff814a7adf>] tcp_v4_rcv+0x55f/0x810
Mar  8 15:48:19 is52 kernel: [37589.086304]  [<ffffffff814850cc>] ip_local_deliver_finish+0xcc/0x270
Mar  8 15:48:19 is52 kernel: [37589.086309]  [<ffffffff81452623>] __netif_receive_skb+0x493/0x510
Mar  8 15:48:19 is52 kernel: [37589.086314]  [<ffffffff8145305a>] netif_receive_skb+0x1a/0x80
Mar  8 15:48:19 is52 kernel: [37589.086317]  [<ffffffff814531c8>] napi_skb_finish+0x38/0x50
Mar  8 15:48:19 is52 kernel: [37589.086323]  [<ffffffffa038d6df>] bnx2_rx_int+0x3df/0x7d0 [bnx2]
Mar  8 15:48:19 is52 kernel: [37589.086341]  [<ffffffffa038db36>] bnx2_poll_work+0x66/0x90 [bnx2]
Mar  8 15:48:19 is52 kernel: [37589.086357]  [<ffffffffa038dc84>] bnx2_poll+0x54/0x1a0 [bnx2]
Mar  8 15:48:19 is52 kernel: [37589.086372]  [<ffffffff814539b1>] net_rx_action+0x121/0x260
Mar  8 15:48:19 is52 kernel: [37589.086377]  [<ffffffff8104500d>] __do_softirq+0x9d/0x1f0
Mar  8 15:48:19 is52 kernel: [37589.086381]  [<ffffffff8157871c>] call_softirq+0x1c/0x30
Mar  8 15:48:19 is52 kernel: [37589.086385]  [<ffffffff810042d5>] do_softirq+0x65/0xa0
Mar  8 15:48:19 is52 kernel: [37589.086389]  [<ffffffff810453de>] irq_exit+0x8e/0xb0
Mar  8 15:48:19 is52 kernel: [37589.086393]  [<ffffffff81003efc>] do_IRQ+0x5c/0xd0
Mar  8 15:48:19 is52 kernel: [37589.086397]  [<ffffffff8156f5ee>] common_interrupt+0x6e/0x6e
Mar  8 15:48:19 is52 kernel: [37589.086401]  [<ffffffff8100ad92>] mwait_idle+0x92/0x210
Mar  8 15:48:19 is52 kernel: [37589.086405]  [<ffffffff810011a9>] cpu_idle+0x89/0xd0
Mar  8 15:48:19 is52 kernel: [37589.086408] ---[ end trace 306e3d00e8ef1b5b ]---
Mar  8 15:48:19 is52 kernel: [37589.092626] ------------[ cut here ]------------

Comment 1 Reinis Rozitis 2012-03-12 16:23:32 UTC

3.2.0-rc2 is not affected.
but I can reproduce it also with the stable 3.2.9 kernel:

Mar  4 14:10:17 is50 kernel: [35293.175230] WARNING: at /usr/src/packages/BUILD/kernel-default-3.2.9/linux-3.2/net/ipv4/tcp_input.c:3439 tcp_clean_rtx_queue+0x6a2/0x730()
Mar  4 14:10:17 is50 kernel: [35293.175233] Hardware name: ProLiant DL360 G5
Mar  4 14:10:17 is50 kernel: [35293.175235] Modules linked in: mperf edd loop dm_mod sg i5000_edac edac_core iTCO_wdt bnx2 mvsas ipmi_si usbhid hpwdt i5k_amb libsas scsi_transport_sas iTCO_vendor_support hpi
lo ipmi_msghandler pcspkr shpchp pci_hotplug button serio_raw container xfs uhci_hcd radeon ehci_hcd ttm drm_kms_helper drm i2c_algo_bit usbcore usb_common fan thermal processor thermal_sys hpsa ata_generic
cciss
Mar  4 14:10:17 is50 kernel: [35293.175267] Pid: 0, comm: swapper/1 Tainted: G        W I  3.2.9-1-default #1
Mar  4 14:10:17 is50 kernel: [35293.175269] Call Trace:
Mar  4 14:10:17 is50 kernel: [35293.175280]  [<ffffffff81004458>] dump_trace+0x78/0x320
Mar  4 14:10:17 is50 kernel: [35293.175285]  [<ffffffff81568fd5>] dump_stack+0x69/0x6f
Mar  4 14:10:17 is50 kernel: [35293.175290]  [<ffffffff81057a9b>] warn_slowpath_common+0x7b/0xc0
Mar  4 14:10:17 is50 kernel: [35293.175295]  [<ffffffff814ac3a2>] tcp_clean_rtx_queue+0x6a2/0x730
Mar  4 14:10:17 is50 kernel: [35293.175301]  [<ffffffff814af3ab>] tcp_ack+0x21b/0x560
Mar  4 14:10:17 is50 kernel: [35293.175306]  [<ffffffff814b0793>] tcp_rcv_established+0x4a3/0x750
Mar  4 14:10:17 is50 kernel: [35293.175311]  [<ffffffff814b7e11>] tcp_v4_do_rcv+0x111/0x1f0
Mar  4 14:10:17 is50 kernel: [35293.175316]  [<ffffffff814b9be9>] tcp_v4_rcv+0x639/0x900
Mar  4 14:10:17 is50 kernel: [35293.175321]  [<ffffffff81496b24>] ip_local_deliver_finish+0xd4/0x290
Mar  4 14:10:17 is50 kernel: [35293.175327]  [<ffffffff81462d56>] __netif_receive_skb+0x4c6/0x530
Mar  4 14:10:17 is50 kernel: [35293.175333]  [<ffffffff814635c8>] netif_receive_skb+0x58/0x80
Mar  4 14:10:17 is50 kernel: [35293.175337]  [<ffffffff81463708>] napi_skb_finish+0x38/0x50
Mar  4 14:10:17 is50 kernel: [35293.175345]  [<ffffffffa03b1714>] bnx2_rx_int+0x3d4/0x820 [bnx2]
Mar  4 14:10:17 is50 kernel: [35293.175365]  [<ffffffffa03b1bc6>] bnx2_poll_work+0x66/0x90 [bnx2]
Mar  4 14:10:17 is50 kernel: [35293.175381]  [<ffffffffa03b1d14>] bnx2_poll+0x54/0x1bc [bnx2]
Mar  4 14:10:17 is50 kernel: [35293.175397]  [<ffffffff81463f31>] net_rx_action+0x121/0x240
Mar  4 14:10:17 is50 kernel: [35293.175403]  [<ffffffff8105ee01>] __do_softirq+0xa1/0x1b0
Mar  4 14:10:17 is50 kernel: [35293.175408]  [<ffffffff81575fec>] call_softirq+0x1c/0x30
Mar  4 14:10:17 is50 kernel: [35293.175412]  [<ffffffff810043a5>] do_softirq+0x65/0xa0
Mar  4 14:10:17 is50 kernel: [35293.175417]  [<ffffffff8105f186>] irq_exit+0x96/0xc0
Mar  4 14:10:17 is50 kernel: [35293.175421]  [<ffffffff81003fcc>] do_IRQ+0x5c/0xd0
Mar  4 14:10:17 is50 kernel: [35293.175425]  [<ffffffff8156c06e>] common_interrupt+0x6e/0x6e
Mar  4 14:10:17 is50 kernel: [35293.175431]  [<ffffffff8100adac>] mwait_idle+0x8c/0x1c0
Mar  4 14:10:17 is50 kernel: [35293.175436]  [<ffffffff81001216>] cpu_idle+0x86/0xc0
Mar  4 14:10:17 is50 kernel: [35293.175440] ---[ end trace e2ca8a69698d19ea ]---

Comment 2 Reinis Rozitis 2012-03-12 16:24:43 UTC

I have found that a similar bug has been reported with some earlier kernel version ( https://bugzilla.kernel.org/show_bug.cgi?id=31282 ), but the status has never been changed.

Note You need to log in before you can comment on or make changes to this bug.