Hide Forgot
---Problem Description--- With sufficient memory and the dynamic DMA window enabled, RHEL6.1 kernels will produce spurious messages like: INFO: task modprobe:3333 blocked for more than 120 seconds. "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. modprobe D 0000008060df9708 0 3333 2795 0x00008000 Call Trace: [c0000016f2217670] [c0000016f2217720] 0xc0000016f2217720 (unreliable) [c0000016f2217840] [c000000000014288] .__switch_to+0xf8/0x1d0 [c0000016f22178d0] [c00000000059cc68] .schedule+0x408/0xd30 [c0000016f2217bb0] [c0000000003aefd4] .wait_for_device_probe+0x64/0xc0 [c0000016f2217c70] [d00000001d1e0014] .wait_scan_init+0x10/0xc4 [scsi_wait_scan] [c0000016f2217ce0] [c00000000000976c] .do_one_initcall+0x5c/0x200 [c0000016f2217d90] [c0000000000dd5dc] .SyS_init_module+0x14c/0x2c0 [c0000016f2217e30] [c000000000008564] syscall_exit+0x0/0x40 while firmware is setting up the TCEs. This is fixed upstream by commit eca590f402332ab873d13f2d8d00fa0b91cfff36 in benh's tree to only sleep in the RTAS delay loop if something else could be done. This changed the order of time required for the DDW initialization from minutes to seconds. ---uname output--- Linux ahi02.upt.austin.ibm.com 2.6.32-131.0.10.el6.ppc64 #1 SMP Wed Apr 27 15:28:11 EDT 2011 ppc64 ppc64 ppc64 GNU/Linux Machine Type = CHRP IBM,7891-74X (P7 Falcon Double Wide Blade) ---Steps to Reproduce--- Boot the current 6.1 kernel with a 64-bit adapter under P7IOC and suitable firmware on a Falcon platform. Dynamic DMA windows will be initialized for those adapters and a spurious timeout message will occur.
Created attachment 497373 [details] Backport of eca590f402332ab873d13f2d8d00fa0b91cfff36
This request was evaluated by Red Hat Product Management for inclusion in a Red Hat Enterprise Linux maintenance release. Product Management has requested further review of this request by Red Hat Engineering, for potential inclusion in a Red Hat Enterprise Linux Update release for currently deployed products. This request is not yet committed for inclusion in an Update release.
posted to rh-kernel mailing list http://post-office.corp.redhat.com/archives/rhkernel-list/2011-May/msg00542.html
Patch(es) available on kernel-2.6.32-153.el6
------- Comment From nacc.com 2011-10-04 14:27 EDT------- Hello Redhat, We would request this fix be backported to 6.1.z, per the following customer impact: There is a large IBM customer who is seeing this bug. He has tried out the patch that Anton submitted and confirms that it fixes his problem. This customer is interested in learning if this will make it to RHEL 6.1 z-strream. One (z-stream) is due out tomorrow. However, I suspect we would have known by now if this was going into that one. If not, can we push for the next one expected in about 6 weeks? BTW, the slow boot problem was recreated with DDR adapters too (with a ps704) at the customer site. Thanks, Nish
Since the problem described in this bug report should be resolved in a recent advisory, it has been closed with a resolution of ERRATA. For information on the advisory, and where to find the updated files, follow the link below. If the solution does not work for you, open a new bug report. http://rhn.redhat.com/errata/RHSA-2011-1530.html