On Thu, Aug 27, 2015 at 10:22 AM, Aaron Laws wrote:

On Tue, Aug 25, 2015 at 3:02 PM, David C. Rankin < drankinatty@suddenlinkmail.com> wrote:

...

All,

... I need to know if anyone has seen this and if there is a fix. Everything works fine after it boots, but it is horrible looking at the errors on boot. Specifically, here is what is logged: ... Anybody have any idea how to fix this?

-- David C. Rankin, J.D.,P.E.

Sorry, I don't have an answer for you.

What chip do you have? I see

[ 0.150863] smpboot: CPU0: AMD FX(tm)-9590 Eight-Core Processor (fam: 15, model: 02, stepping: 00)

(of course, I have the same board.) I don't have any page faults in dmesg or on boot. In /etc/default/grub, I have GRUB_CMDLINE_LINUX_DEFAULT="iommu=soft" (don't forget grub-mkconfig!).

I did have these kinds of errors earlier, but I don't remember what my configuration was. I'm pretty sure it had something to do with iommu. Good luck!

Aaron

I'm running a Gigabyte 970A-D3P, and with "iommu=soft" kernel parameter set up, I don't have those errors either. (I did have them before turning iommu on in bios and setting the kernel parameter).

On Fri, Aug 28, 2015 at 3:54 PM, David C. Rankin < drankinatty@suddenlinkmail.com> wrote:

On 08/27/2015 02:29 PM, Casey Peter wrote:

...

I'm running a Gigabyte 970A-D3P, and with "iommu=soft" kernel parameter set up, I don't have those errors either. (I did have them before turning iommu on in bios and setting the kernel parameter).

I think we are getting somewhere, there is a mce on the number of CPUs:

[ 0.000000] Initializing cgroup subsys cpuset [ 0.000000] Initializing cgroup subsys cpu [ 0.000000] Initializing cgroup subsys cpuacct [ 0.000000] smpboot: Allowing 8 CPUs, 0 hotplug CPUs [ 0.000000] Booting paravirtualized kernel on bare hardware [ 0.000000] setup_percpu: NR_CPUS:128 nr_cpumask_bits:128 nr_cpu_ids:8 nr_node_ids:1 [ 0.000000] PERCPU: Embedded 33 pages/cpu @ffff88042ec00000 s95576 r8192 d31400 u262144 [ 0.000000] pcpu-alloc: s95576 r8192 d31400 u262144 alloc=1*2097152 [ 0.000000] pcpu-alloc: [0] 0 1 2 3 4 5 6 7 [ 0.000000] Kernel command line: BOOT_IMAGE=/vmlinuz-linux root=UUID=515ef9dc-769f-4548-9a08-3a92fa83d86b rw quiet [ 0.000000] Memory: 16395952K/16740972K available (5699K kernel code, 893K rwdata, 1732K rodata, 1180K init, 1152K bss, 345020K reserved, 0K cma-reserved) [ 0.000000] SLUB: HWalign=64, Order=0-3, MinObjects=0, CPUs=8, Nodes=1 [ 0.000000] RCU restricting CPUs from NR_CPUS=128 to nr_cpu_ids=8. [ 0.000000] RCU: Adjusting geometry for rcu_fanout_leaf=16, nr_cpu_ids=8 [ 0.009332] CPU: Physical Processor ID: 0 [ 0.009333] CPU: Processor Core ID: 0 [ 0.009334] mce: CPU supports 7 MCE banks [ 0.230921] smpboot: CPU0: AMD FX(tm)-8350 Eight-Core Processor (fam: 15, model: 02, stepping: 00) [ 0.247684] NMI watchdog: enabled on all CPUs, permanently consumes one hw-PMU counter. [ 0.254353] .... node #0, CPUs: #1 #2 #3 #4 #5 #6 #7 [ 0.364267] x86: Booted up 1 node, 8 CPUs [ 0.391139] cpuidle: using governor ladder [ 0.404490] cpuidle: using governor menu [ 0.405039] mtrr: your CPUs had inconsistent variable MTRR settings [ 0.405040] mtrr: probably your BIOS does not setup all CPUs.

I've tried setting "amd_iommu=on" in default/grub. I'll try iommu=soft and report back. Is there anything else to check? Funny, my IOMMU doesn't seem to trigger any issue:

[ 0.792454] Unpacking initramfs... [ 0.843735] Freeing initrd memory: 3924K (ffff880037846000 - ffff880037c1b000) [ 0.844350] AMD-Vi: Found IOMMU at 0000:00:00.2 cap 0x40 [ 0.844351] AMD-Vi: Interrupt remapping enabled [ 0.855146] AMD-Vi: Lazy IO/TLB flushing enabled

My issue explodes after xhci_hcd:

[ 1.159635] ohci-pci: OHCI PCI platform driver [ 1.165660] ehci-pci 0000:00:12.2: USB 2.0 started, EHCI 1.00 [ 1.165859] hub 1-0:1.0: USB hub found [ 1.165868] hub 1-0:1.0: 5 ports detected [ 1.166060] xhci_hcd 0000:02:00.0: xHCI Host Controller [ 1.166068] xhci_hcd 0000:02:00.0: new USB bus registered, assigned bus number 2 [ 1.166126] AMD-Vi: Event logged [IO_PAGE_FAULT device=02:00.0 domain=0x0016 address=0x00000000ce9f9880 flags=0x0010] [ 1.167066] AMD-Vi: Event logged [IO_PAGE_FAULT device=02:00.0 domain=0x0016 address=0x00000000ce9f9880 flags=0x0010] [ 1.168025] AMD-Vi: Event logged [IO_PAGE_FAULT device=02:00.0 domain=0x0016 address=0x00000000ce9f9880 flags=0x0010]

<snip repeated>

[ 1.202519] AMD-Vi: Event logged [ [ 1.202571] input: AT Translated Set 2 keyboard as /devices/platform/i8042/serio0/input/input0 [ 1.202829] IO_PAGE_FAULT device=02:00.0 domain=0x0016 address=0x00000000ce9f9880 flags=0x0010] [ 1.202843] AMD-Vi: Event logged [IO_PAGE_FAULT device=02:00.0 domain=0x0016 address=0x00000000ce9f9880 flags=0x0010]

<snip repeated>

[ 1.216256] AMD-Vi: Event logged [ [ 1.216326] firewire_ohci 0000:04:0e.0: added OHCI v1.10 device as card 0, 4 IR + 8 IT contexts, quirks 0x11 [ 1.216547] IO_PAGE_FAULT device=02:00.0 domain=0x0016 address=0x00000000ce9f9880 flags=0x0010] [ 1.216563] AMD-Vi: Event logged [IO_PAGE_FAULT device=02:00.0 domain=0x0016 address=0x00000000ce9f9880 flags=0x0010]

<snip repeated>

[ 1.716168] firewire_core 0000:04:0e.0: created device fw0: GUID 0014aafc64aa2c00, S400 [ 1.716813] AMD-Vi: Event logged [IO_PAGE_FAULT device=02:00.0 domain=0x0016 address=0x00000000ce9f9880 flags=0x0010]

<snip repeated>

[ 1.932839] tsc: Refined TSC clocksource calibration: 4018.289 MHz [ 1.932842] clocksource tsc: mask: 0xffffffffffffffff max_cycles: 0x39ebd986d5e, max_idle_ns: 440795317543 ns [ 1.935061] AMD-Vi: Event logged [IO_PAGE_FAULT device=02:00.0 domain=0x0016 address=0x00000000ce9f9880 flags=0x0010]

<snip repeated>

[ 2.937205] AMD-Vi: Event logged [ [ 2.937208] Switched to clocksource tsc [ 2.937495] IO_PAGE_FAULT device=02:00.0 domain=0x0016 address=0x00000000ce9f9880 flags=0x0010] [ 2.941453] AMD-Vi: Event logged [IO_PAGE_FAULT device=02:00.0 domain=0x0016 address=0x00000000ce9f9880 flags=0x0010]

<snip repeated>

[ 20.090108] xhci_hcd 0000:02:00.0: can't setup: -110 [ 20.094746] xhci_hcd 0000:02:00.0: USB bus 2 deregistered [ 20.094771] ehci-pci 0000:00:13.2: EHCI Host Controller [ 20.094778] ehci-pci 0000:00:13.2: new USB bus registered, assigned bus number 2 [ 20.094783] ehci-pci 0000:00:13.2: applying AMD SB700/SB800/Hudson-2/3 EHCI dummy qh workaround [ 20.094791] ehci-pci 0000:00:13.2: debug port 1 [ 20.094796] xhci_hcd 0000:02:00.0: init 0000:02:00.0 fail, -110 [ 20.094837] ehci-pci 0000:00:13.2: irq 17, io mem 0xfe507000 [ 20.099716] xhci_hcd: probe of 0000:02:00.0 failed with error -110 [ 20.104621] ehci-pci 0000:00:13.2: USB 2.0 started, EHCI 1.00 [ 20.104805] hub 2-0:1.0: USB hub found [ 20.104811] hub 2-0:1.0: 5 ports detected [ 20.105034] ehci-pci 0000:00:16.2: EHCI Host Controller [ 20.105039] ehci-pci 0000:00:16.2: new USB bus registered, assigned bus number 3 [ 20.105042] ehci-pci 0000:00:16.2: applying AMD SB700/SB800/Hudson-2/3 EHCI dummy qh workaround [ 20.105050] ehci-pci 0000:00:16.2: debug port 1 [ 20.105073] ehci-pci 0000:00:16.2: irq 17, io mem 0xfe504000 [ 20.114633] ehci-pci 0000:00:16.2: USB 2.0 started, EHCI 1.00 [ 20.114787] hub 3-0:1.0: USB hub found [ 20.114794] hub 3-0:1.0: 4 ports detected [ 20.115031] ohci-pci 0000:00:12.0: OHCI PCI host controller [ 20.115039] ohci-pci 0000:00:12.0: new USB bus registered, assigned bus number 4 [ 20.115065] ohci-pci 0000:00:12.0: irq 18, io mem 0xfe50a000 [ 20.172168] hub 4-0:1.0: USB hub found [ 20.172177] hub 4-0:1.0: 5 ports detected [ 20.172396] ohci-pci 0000:00:13.0: OHCI PCI host controller [ 20.172401] ohci-pci 0000:00:13.0: new USB bus registered, assigned bus number 5 [ 20.172418] ohci-pci 0000:00:13.0: irq 18, io mem 0xfe508000 [ 20.228880] hub 5-0:1.0: USB hub found [ 20.228889] hub 5-0:1.0: 5 ports detected [ 20.229111] ohci-pci 0000:00:14.5: OHCI PCI host controller [ 20.229117] ohci-pci 0000:00:14.5: new USB bus registered, assigned bus number 6 [ 20.229134] ohci-pci 0000:00:14.5: irq 18, io mem 0xfe506000 [ 20.285567] hub 6-0:1.0: USB hub found [ 20.285575] hub 6-0:1.0: 2 ports detected [ 20.285739] ohci-pci 0000:00:16.0: OHCI PCI host controller [ 20.285744] ohci-pci 0000:00:16.0: new USB bus registered, assigned bus number 7 [ 20.285759] ohci-pci 0000:00:16.0: irq 18, io mem 0xfe505000

<snip boot continues normally>

I'll keep digging, but this is got me stumped.

-- David C. Rankin, J.D.,P.E.

Have been seeing these posts for a week now, and I think it's time to ask: is this really Arch Linux relevant? Sounds like you bought a wonky board, your issues might be more relevant in another forum.

Your problems are not specific to Arch. And not necessarily kernel specific either. I'm glad you have solved your problem, but this wasn't the appropriate medium for it. On Fri, Aug 28, 2015 at 9:31 PM, David C. Rankin < drankinatty@suddenlinkmail.com> wrote:

On 08/28/2015 08:14 PM, David Kaylor wrote:

...

Have been seeing these posts for a week now, and I think it's time to ask: is this really Arch Linux relevant? Sounds like you bought a wonky board, your issues might be more relevant in another forum.

It is if you are running Arch on one of these boards.

The solution:

In the bios set: IOMMU - Enabled In /etc/default/grub, set - GRUB_CMDLINE_LINUX="iommu=soft"

David,

If you don't want to read the post, or can't be botherd to help - use the [Del] key.

-- David C. Rankin, J.D.,P.E.

On Fri, Aug 28, 2015 at 9:21 PM, Kyle Bassett wrote:

On Aug 28, 2015 9:40 PM, "David Kaylor" wrote:

...

Your problems are not specific to Arch. And not necessarily kernel

specific

...

either. I'm glad you have solved your problem, but this wasn't the appropriate medium for it.

David K, I suggest you review your post and see if it meets your own requirements. No reason for a negative tone in this ML.

I found this thread informative and helpful, David R. did his homework, and uses Arch. I wish all the OP posts in my inbox were like his! David R., glad you got it working.

+1 for the [del] key.

I'll add that I resolved my ARCH issue as well with the kernel setting prior to this thread popping up, and offered help because of my experience with the ARCH SPECIFIC problem. This issue cropped with a new Gigabyte board and ONLY on Arch. Three other distros had no issue, whatsoever, with IOMMU one way or another....Arch did.

On Fri, Aug 28, 2015 at 11:21 PM, Kyle Bassett wrote:

On Aug 28, 2015 9:40 PM, "David Kaylor" wrote:

...

Your problems are not specific to Arch. And not necessarily kernel

specific

...

either. I'm glad you have solved your problem, but this wasn't the appropriate medium for it.

David K, I suggest you review your post and see if it meets your own requirements. No reason for a negative tone in this ML.

Am I somehow the only person who has ever told a poster their issue is not Arch relevant? I'm perfectly at ease with my "tone", as you refer to it.

I found this thread informative and helpful, David R. did his homework, and uses Arch. I wish all the OP posts in my inbox were like his! David R., glad you got it working.

I'm glad the OP solved his issue. But I DON'T want my inbox full of questions about none-Arch relevant hardware quirks caused by sloppy manufacturers. At the very least, that stuff should go in the forums, where it is easy to sort out less relevant info.