Go Back   nV News Forums > Linux Support Forums > NVIDIA Linux

Newegg Daily Deals

Reply
 
Thread Tools
Old 08-15-11, 10:33 AM   #1
johnb
johnb
 
Join Date: Aug 2004
Posts: 11
Default __ioremap_caller() WARNING message with Tesla M2070-Q

Using the latest nvidia driver, version 280.13, we are seeing a
warning message in 2.6.36 kernels in the __ioremap_caller() routine
when the /dev/nvidia file is opened and rm_init_adapter() ends up doing
an ioremap() call to low memory.

The ioremap staring address is 0x9d000 (PFN 9d) and the length is one page
(0x1000). The prot_val is 0, which is _PAGE_CACHE_WB.

The CUDA card is a Tesla M2070-Q.

The system memmap (cat /proc/iomem, etc.) says that this is a RAM page:

0000000000000000-0000000000000fff : reserved
0000000000001000-000000000006bfff : System RAM
000000000006c000-000000000006cfff : ACPI Non-volatile Storage
000000000006d000-000000000009efff : System RAM <<<<<<<<<<<<<<<<<<<<<<<<
000000000009f000-000000000009ffff : ACPI Non-volatile Storage
00000000000a0000-00000000000bffff : PCI Bus 0000:00
0000000000100000-000000007c633fff : System RAM
...
...

This WARN_ON_ONCE() message is in the section in __ioremap_caller()
just after the comment: "Don't allow anybody to remap normal RAM that
we're using.."

We were wondering if this is an issue with the nvidia driver,
or if this is possibly the kernel being overzealous with this
warning?

Thank you for any information that you can provide.

I have a nvidia-bug-report.log.gz, in case you might be interested
in seeing that.

The console message that appears is:

------------[ cut here ]------------
WARNING: at arch/x86/mm/ioremap.c:117 __ioremap_caller+0x18e/0x320()
Hardware name: IBM System x -[7870AC1]-
Modules linked in: nvidia(P) ip6table_filter ip6_tables ebtable_nat ebtables ipt_MASQUERADE iptable_nat nf_nat nf_conntrack_ipv4 nf_defrag_ipv4 xt_state nf_conntrack ipt_REJECT xt_CHECKSUM iptable_mangle iptable_filter ip_tables tun bridge autofs4 nfs lockd nfs_acl auth_rpcgss sunrpc fcoe libfcoe libfc 8021q scsi_transport_fc garp scsi_tgt stp llc cachefiles fscache ipv6 configs vfat fat dm_mirror dm_region_hash dm_log uinput snd_hda_codec_nvhdmi snd_hda_intel snd_hda_codec snd_hwdep snd_seq snd_seq_device snd_pcm snd_timer snd soundcore snd_page_alloc sg cdc_ether usbnet mii microcode serio_raw pcspkr i2c_i801 i2c_core ioatdma dca i7core_edac edac_core shpchp ext4 mbcache jbd2 bnx2x libcrc32c mdio bnx2 sd_mod crc_t10dif mptsas mptscsih mptbase scsi_transport_sas button sr_mod cdrom usb_storage dm_mod [last unloaded: nvidia]
Pid: 15207, comm: reduction Tainted: P 2.6.36.4-RedHawk-6.0.1-razor4-ioremap #2
Call Trace:
[<ffffffff81043709>] warn_slowpath_common+0x85/0x9d
[<ffffffff8104373b>] warn_slowpath_null+0x1a/0x1c
[<ffffffff8102bdc2>] __ioremap_caller+0x18e/0x320
[<ffffffffa168cf22>] ? os_map_kernel_space+0x9e/0xc5 [nvidia]
[<ffffffff8102bf7f>] ioremap_cache+0x14/0x16
[<ffffffffa168cf22>] os_map_kernel_space+0x9e/0xc5 [nvidia]
[<ffffffffa165ad57>] _nv023390rm+0xfb/0x11b [nvidia]
[<ffffffffa104a1ce>] ? _nv025862rm+0x62/0x11b [nvidia]
[<ffffffffa104a320>] ? _nv022528rm+0x99/0xcb [nvidia]
[<ffffffffa104a7b6>] ? _nv022591rm+0x58/0x9e [nvidia]
[<ffffffffa10459f8>] ? _nv022548rm+0xcf/0x301 [nvidia]
[<ffffffffa1045cd5>] ? _nv022598rm+0xab/0x174 [nvidia]
[<ffffffffa1045dee>] ? _nv022547rm+0x50/0x5d [nvidia]
[<ffffffffa104ca5d>] ? _nv022539rm+0x6e/0x78 [nvidia]
[<ffffffffa1661134>] ? _nv019309rm+0x69/0x121 [nvidia]
[<ffffffffa16610b2>] ? _nv019323rm+0xe8/0x101 [nvidia]
[<ffffffffa1089421>] ? _nv004632rm+0x68/0x1f4 [nvidia]
[<ffffffffa1427387>] ? _nv015073rm+0x176/0x4c3 [nvidia]
[<ffffffffa1425eeb>] ? _nv015366rm+0xe9/0x165 [nvidia]
[<ffffffffa1010748>] ? _nv015546rm+0xd/0x12 [nvidia]
[<ffffffffa1660e79>] ? _nv002297rm+0x19d/0x28a [nvidia]
[<ffffffffa1661ee8>] ? _nv002291rm+0x4a5/0x684 [nvidia]
[<ffffffffa1668c84>] ? rm_init_adapter+0x9e/0x1b6 [nvidia]
[<ffffffffa168a399>] ? nv_kern_open+0x589/0x71c [nvidia]
[<ffffffff8110ae31>] ? chrdev_open+0x21a/0x23b
[<ffffffff8110ac17>] ? chrdev_open+0x0/0x23b
[<ffffffff81105c4a>] ? __dentry_open+0x200/0x337
[<ffffffff81105e50>] ? nameidata_to_filp+0x3f/0x50
[<ffffffff811127c8>] ? do_last+0x49d/0x60e
[<ffffffff811145b5>] ? do_filp_open+0x1e3/0x60f
[<ffffffff8109ffa0>] ? ring_buffer_lock_reserve+0xf0/0x11f
[<ffffffff8111db34>] ? alloc_fd+0x116/0x128
[<ffffffff811058c7>] ? do_sys_open+0x60/0x197
[<ffffffff8100ce4b>] ? syscall_trace_enter+0xf7/0x137
[<ffffffff8100cea9>] ? syscall_trace_enter_wrapper+0x1e/0x22
[<ffffffff81105a31>] ? sys_open+0x20/0x22
[<ffffffff8100304e>] ? tracesys+0xcc/0xd1
---[ end trace 076abaf3350a2a5a ]---
johnb is offline   Reply With Quote
Old 08-15-11, 11:04 AM   #2
zander
NVIDIA Corporation
 
zander's Avatar
 
Join Date: Aug 2002
Posts: 3,740
Default Re: __ioremap_caller() WARNING message with Tesla M2070-Q

The most likely reason is that the EBDA isn't accounted for in your system's e820 memory map.
zander is offline   Reply With Quote
Reply


Thread Tools

Posting Rules
You may not post new threads
You may not post replies
You may not post attachments
You may not edit your posts

BB code is On
Smilies are On
[IMG] code is On
HTML code is Off
Forum Jump


All times are GMT -5. The time now is 10:56 AM.


Powered by vBulletin® Version 3.7.1
Copyright ©2000 - 2014, Jelsoft Enterprises Ltd.
Copyright 1998 - 2014, nV News.