You are not logged in.

#1 2020-02-13 11:01:00

daren_k
Member
Registered: 2020-02-13
Posts: 37
Website

Instability with Ryzen 9 3950X and updated X570 BIOS

First of all my Setup:
CPU: AMD Ryzen 9 3950X
GPU: AMD Radeon VII
MB: Gigabyte X570 UD
Memory: 2x 16GB Corsair Vengeance DDR4 3600MHz

$ dmesg | grep -i micro       
[    4.434524] microcode: CPU0: patch_level=0x08701013

The MB was delivered with a default F1 BIOS:
https://www.gigabyte.com/Motherboard/X5 … rt-dl-bios

After the kernel bootup complained about RDRAND returning bad values, I read about people suggesting to do a BIOS update. Decided to update to the latest F11 BIOS (2019/12/09), messages about RDRAND during bootup gone.

But after compiling a lot of stuff from the AUR and adapting PKGBUILDs, eventually the makepkg command issued a segfault with no output, pacman also affected, still tried to install stuff though. Other software seemed to have still worked somewhat, lots of my browser tabs crashed though. This happened a couple days ago with kernel 5.5.2:

[root@daren-pc ~]# pacman -S linux linux-headers
warning: linux-5.5.2.arch2-2 is up to date -- reinstalling
warning: linux-headers-5.5.2.arch2-2 is up to date -- reinstalling
resolving dependencies...
looking for conflicting packages...

Packages (2) linux-5.5.2.arch2-2  linux-headers-5.5.2.arch2-2

Total Installed Size:  190.12 MiB
Net Upgrade Size:        0.00 MiB

:: Proceed with installation? [Y/n]
(2/2) checking keys in keyring                                  [##################################] 100%
(2/2) checking package integrity                                [##################################] 100%
(2/2) loading package files                                     [##################################] 100%
(2/2) checking for file conflicts                               [##################################] 100%
(2/2) checking available disk space                             [##################################] 100%
:: Running pre-transaction hooks...
(1/1) Remove DKMS modules
==> dkms remove blackmagic/11.4a14 -k 5.5.2-arch2-2
==> dkms remove blackmagic-io/11.4a14 -k 5.5.2-arch2-2
:: Processing package changes...
(1/2) reinstalling linux                                        [##################################] 100%
(2/2) reinstalling linux-headers                                [##################################] 100%
:: Running post-transaction hooks...
(1/4) Arming ConditionNeedsUpdate...
(2/4) Updating module dependencies...
(3/4) Install DKMS modules
==> dkms install blackmagic/11.4a14 -k 5.5.2-arch2-2
/usr/lib/dkms/alpm-hook: line 21: 270363 Segmentation fault      "$@" > /dev/null
==> dkms install blackmagic-io/11.4a14 -k 5.5.2-arch2-2
(4/4) Updating linux initcpios...
==> Building image from preset: /etc/mkinitcpio.d/linux.preset: 'default'
  -> -k /boot/vmlinuz-linux -c /etc/mkinitcpio.conf -g /boot/initramfs-linux.img
==> Starting build: 5.5.2-arch2-2
  -> Running build hook: [base]
  -> Running build hook: [udev]
  -> Running build hook: [autodetect]
  -> Running build hook: [modconf]
  -> Running build hook: [block]
/usr/bin/mkinitcpio: line 274: 271123 Segmentation fault      MKINITCPIO_PROCESS_PRESET=1 "$0" "${preset_cmd[@]}"
==> Building image from preset: /etc/mkinitcpio.d/linux.preset: 'fallback'
  -> -k /boot/vmlinuz-linux -c /etc/mkinitcpio.conf -g /boot/initramfs-linux-fallback.img -S autodetect
==> Starting build: 5.5.2-arch2-2
  -> Running build hook: [base]
  -> Running build hook: [udev]
  -> Running build hook: [modconf]
  -> Running build hook: [block]
==> WARNING: Possibly missing firmware for module: aic94xx
==> WARNING: Possibly missing firmware for module: wd719x
/usr/bin/mkinitcpio: line 274: 271492 Segmentation fault      MKINITCPIO_PROCESS_PRESET=1 "$0" "${preset_cmd[@]}"
error: command failed to execute correctly
[root@daren-pc ~]# makepkg
Segmentation fault
[root@daren-pc ~]#

Tried this even though this issue was for Zen 1 Ryzen Processors:
https://github.com/Oxalin/ryzen-test

Makes stuff break as above within minutes with the F11 BIOS (not related to out-of-memory, I got 32GB installed, this needs less for the 32 threads spawned, maybe 20GB)
EDIT: stuff breaks when running that in combination with trying to compile rocblas which issues rocminfo that segfaults.

Went back to F1, no such issues.

Tried F4b BIOS as well, RDRAND messages gone. kill-ryzen.sh script from ryzen-test eventually dumps some kernel messages containing register dumps just before locking up. Seems to me like it is somehow breaking kernel space.

Back again to F1... stable.

What could be the cause of this?
Anyone else having issues like this?

Last edited by daren_k (2020-02-19 10:43:05)

Offline

#2 2020-02-13 11:32:51

sabroad
Member
Registered: 2015-05-24
Posts: 242

Re: Instability with Ryzen 9 3950X and updated X570 BIOS

daren_k wrote:

The MB was delivered with a default F1 BIOS:
https://www.gigabyte.com/Motherboard/X5 … rt-dl-bios

Tried F4b BIOS as well,
Back again to F1... stable.
What could be the cause of this?

It looks like F2 might enable "XMP DDR". Have you tried memtest from the Arch iso with F11 to rule out memory issues due to tighter timings?

Last edited by sabroad (2020-02-13 11:33:33)


--
saint_abroad

Offline

#3 2020-02-13 11:41:36

Ropid
Member
Registered: 2015-03-09
Posts: 1,069

Re: Instability with Ryzen 9 3950X and updated X570 BIOS

Do you see anything interesting happening in the system log?

Maybe experiment with a memory test like mentioned by sabroad. There's a package named "memtest86-efi" in the AUR. You can use that package to install memtest86 into your EFI partition and add it to your boot loader's menu. The results would be interesting to see because the test will run outside of Linux.

If you find errors with the memory test, then test with XMP disabled and the RAM running at the slow default speeds.

Last edited by Ropid (2020-02-13 11:43:18)

Offline

#4 2020-02-13 12:23:06

daren_k
Member
Registered: 2020-02-13
Posts: 37
Website

Re: Instability with Ryzen 9 3950X and updated X570 BIOS

XMP is there in the F1 BIOS as well and it seems to support my 2x 16GB Corsair Vengeance DDR4 3600MHz modules as it sets them to 1.35V and 3600MHz. This runs fine when I enable it in F1 though...

XMP is disabled by default when loading optimized defaults and after flashing the BIOS.
Not sure if I got it to go instable/hang with the default memory setting to rule that out... will test that.

Will definitely do the memtest thing after work with an updated BIOS with and without XMP.

system log with

journalctl -xe

right?

Offline

#5 2020-02-13 13:06:45

Lone_Wolf
Member
From: Netherlands, Europe
Registered: 2005-10-04
Posts: 11,866

Re: Instability with Ryzen 9 3950X and updated X570 BIOS

man journalctl wrote:

       -x, --catalog
           Augment log lines with explanation texts from the message catalog. This will add explanatory help texts to log messages in the
           output where this is available. These short help texts will explain the context of an error or log event, possible solutions, as
           well as pointers to support forums, developer documentation, and any other relevant manuals. Note that help texts are not
           available for all messages, but only for selected ones. For more information on the message catalog, please refer to the Message
           Catalog Developer Documentation[5].

           Note: when attaching journalctl output to bug reports, please do not use -x.

SYSTEMD_LESS=FRXMK journalctl -b

is a better choice I think.

Last edited by Lone_Wolf (2020-02-13 13:06:54)


Disliking systemd intensely, but not satisfied with alternatives so focusing on taming systemd.


(A works at time B)  && (time C > time B ) ≠  (A works at time C)

Offline

#6 2020-02-13 18:41:41

daren_k
Member
Registered: 2020-02-13
Posts: 37
Website

Re: Instability with Ryzen 9 3950X and updated X570 BIOS

Didn't do any more testing yet, but one thing I forgot to mention was that I run the STREAM benchmark to check the memory bandwidth.

With F1  BIOS it was around 43.5 GB/s @ 3600MHz DDR4 frequency (XMP)
With F11 BIOS it was around 44.5 GB/s @ 3600MHz DDR4 frequency (XMP)

This makes it plausible that they put tighter timings in the XMP profile... back to testing.

Offline

#7 2020-02-13 20:49:14

Ropid
Member
Registered: 2015-03-09
Posts: 1,069

Re: Instability with Ryzen 9 3950X and updated X570 BIOS

The XMP profile contains only a few of the memory timings. There's many more timings that are not part of the XMP profile. Those other timings are chosen by the board's manufacturer.

You should take photos of the BIOS pages with the memory timings. The BIOS (probably) shows the currently used values there, next to the input boxes that show "Auto". You could then manually input the values that the old BIOS used.

But you should first use a memory test tool to make sure that this really is the problem.

Because you use 32GB RAM, there's also another thing you should know about: there's "resistances" for the signal on the wiring that can be tweaked on Ryzen. The defaults for those resistances often don't work for high memory speeds for systems that use all four memory slots, or that use "dual-rank" memory sticks (that's most 16GB sized sticks). Here's what to try with dual-rank sticks or with four sticks:

ProcODT = 48 Ohm or 53 Ohm or 60 Ohm
RttNom = off
RttWr = RZQ/3 (80 Ohm)
RttPark = RZQ/1 (240 Ohm)

The important ones here are the RttPark and RttWr settings.

Offline

#8 2020-02-13 21:08:30

daren_k
Member
Registered: 2020-02-13
Posts: 37
Website

Re: Instability with Ryzen 9 3950X and updated X570 BIOS

Did some memtest86+ with the F11 BIOS and XMP profile on, DDR4@3600MHz.

Couple of passes with 8-bit pattern and block move test with all cores, no errors.
Any specific tests I should try there?

Currently trying if linux-lts breaks with F11 BIOS and XMP disabled... so far so good.

Offline

#9 2020-02-13 21:20:41

Ropid
Member
Registered: 2015-03-09
Posts: 1,069

Re: Instability with Ryzen 9 3950X and updated X570 BIOS

Did you use "memtest86+" or "memtest86"? The one with the "+" wasn't good for me. I had issues once where memtest86+ didn't find errors, but memtes86 would find them.

About what tests in memtest86 to try, when I play around with memory overclocking, tests 5 and 7 and 8 are the ones that find the errors, I think because the other tests are just slow. I usually disable everything besides test 8, and increase the number of loops. To be clear, I mean these tests here:

Test 5 [Moving inversions, random pattern]
Test 7 [Moving inversions, 32 bit pattern]
Test 8 [Random number sequence]

Offline

#10 2020-02-13 21:24:59

daren_k
Member
Registered: 2020-02-13
Posts: 37
Website

Re: Instability with Ryzen 9 3950X and updated X570 BIOS

I booted memtest86+ from the arch iso without UEFI.

memtest86 is the proprietary one? Is that somewhere in the repositories/AUR?

Edit:
This one I guess: https://aur.archlinux.org/packages/memtest86-efi/

Also was unable to break linux-lts, F11 BIOS, XMP=disabled.

Last edited by daren_k (2020-02-13 21:26:40)

Offline

#11 2020-02-14 08:36:13

daren_k
Member
Registered: 2020-02-13
Posts: 37
Website

Re: Instability with Ryzen 9 3950X and updated X570 BIOS

Did the memtest86 thing yesterday with the 3 tests you mentioned.

No errors with XMP enabled (2 passes) and for good measure, 1 pass with XMP disabled, no errors as well.

Will have time again next week to dig further... this weekend I need a stable system, so back to F1 BIOS.

Offline

#12 2020-02-18 22:10:07

daren_k
Member
Registered: 2020-02-13
Posts: 37
Website

Re: Instability with Ryzen 9 3950X and updated X570 BIOS

Last thing I did though before switching back to F1 BIOS was to screenshot the memory settings:

XMP settings: Gigabyte X570 UD w/ F11 BIOS
https://imgur.com/a/LgP7VNg

XMP settings: Gigabyte X570 UD w/ F1  BIOS
https://imgur.com/a/UVQk0fr

The values don't change between BIOS versions (F1 <-> F11). I doubt it is related to memory.

Can now test the F11 BIOS again and see if it goes instable again.

Offline

#13 2020-02-18 23:07:26

daren_k
Member
Registered: 2020-02-13
Posts: 37
Website

Re: Instability with Ryzen 9 3950X and updated X570 BIOS

I think I found the culprit:

Feb 18 23:41:53 daren-pc audit[2500339]: ANOM_ABEND auid=1000 uid=1000 gid=985 ses=3 pid=2500339 comm="rocminfo" exe="/opt/rocm/bin/rocminfo" sig=11 res=1
Feb 18 23:41:53 daren-pc kernel: [drm:amdgpu_ttm_backend_bind [amdgpu]] *ERROR* failed to pin userptr
Feb 18 23:41:53 daren-pc kernel: init_user_pages: failed to validate BO
Feb 18 23:41:53 daren-pc kernel: [drm:amdgpu_ttm_backend_bind [amdgpu]] *ERROR* failed to pin userptr
Feb 18 23:41:53 daren-pc kernel: init_user_pages: failed to validate BO
Feb 18 23:41:53 daren-pc kernel: rocminfo[2500339]: segfault at 0 ip 00007f8580dbb565 sp 00007ffe221dcfe0 error 6 in libhsa-runtime64.so.1.1.9[7f8580da4000+7f000]
Feb 18 23:41:53 daren-pc kernel: Code: 8d 4c 24 04 48 8d b8 30 02 00 00 48 8d 54 24 10 48 8d 74 24 08 ff 90 48 02 00 00 48 8d 78 08 48 89 83 b8 03 00 00 48 83 e7 f8 <48> c7 00 00 00 00 00 48 c7 80 f8 1f 00 00 00 00 00 00 48 29 f8 8d
Feb 18 23:41:53 daren-pc kernel: audit: type=1701 audit(1582065713.664:4228): auid=1000 uid=1000 gid=985 ses=3 pid=2500339 comm="rocminfo" exe="/opt/rocm/bin/rocminfo" sig=11 res=1
Feb 18 23:41:53 daren-pc systemd[1]: Created slice system-systemd\x2dcoredump.slice.
Feb 18 23:41:53 daren-pc systemd[1]: Started Process Core Dump (PID 2500581/UID 0).
Feb 18 23:41:53 daren-pc audit[1]: SERVICE_START pid=1 uid=0 auid=4294967295 ses=4294967295 msg='unit=systemd-coredump@0-2500581-0 comm="systemd" exe="/usr/lib/systemd/systemd" hostname=? addr=? terminal=? res=success'
Feb 18 23:41:53 daren-pc kernel: audit: type=1130 audit(1582065713.671:4229): pid=1 uid=0 auid=4294967295 ses=4294967295 msg='unit=systemd-coredump@0-2500581-0 comm="systemd" exe="/usr/lib/systemd/systemd" hostname=? addr=? terminal=? res=success'
Feb 18 23:41:53 daren-pc kernel: Evicting PASID 0x8006 queues
Feb 18 23:41:53 daren-pc systemd-coredump[2500599]: Process 2500339 (rocminfo) of user 1000 dumped core.
                                                    
                                                    Stack trace of thread 2500339:
                                                    #0  0x00007f8580dbb565 n/a (libhsa-runtime64.so.1 + 0x2a565)
                                                    #1  0x00007f8580dbd6d1 n/a (libhsa-runtime64.so.1 + 0x2c6d1)
                                                    #2  0x00007f8580de3326 n/a (libhsa-runtime64.so.1 + 0x52326)
                                                    #3  0x00007f8580dc9a9a n/a (libhsa-runtime64.so.1 + 0x38a9a)
                                                    #4  0x0000565185ef1817 main (rocminfo + 0xc817)
                                                    #5  0x00007f85809b4023 __libc_start_main (libc.so.6 + 0x27023)
                                                    #6  0x0000565185eeb47e _start (rocminfo + 0x647e)
                                                    
                                                    Stack trace of thread 2500578:
                                                    #0  0x00007f8580de905f n/a (libhsa-runtime64.so.1 + 0x5805f)
                                                    #1  0x00007f8580dd411a n/a (libhsa-runtime64.so.1 + 0x4311a)
                                                    #2  0x00007f8580de17b0 n/a (libhsa-runtime64.so.1 + 0x507b0)
                                                    #3  0x00007f8580daedf7 n/a (libhsa-runtime64.so.1 + 0x1ddf7)
                                                    #4  0x00007f858091046f start_thread (libpthread.so.0 + 0x946f)
                                                    #5  0x00007f8580a8c3d3 __clone (libc.so.6 + 0xff3d3)
Feb 18 23:41:53 daren-pc systemd[1]: systemd-coredump@0-2500581-0.service: Succeeded.
Feb 18 23:41:53 daren-pc audit[1]: SERVICE_STOP pid=1 uid=0 auid=4294967295 ses=4294967295 msg='unit=systemd-coredump@0-2500581-0 comm="systemd" exe="/usr/lib/systemd/systemd" hostname=? addr=? terminal=? res=success'
Feb 18 23:41:53 daren-pc kernel: audit: type=1131 audit(1582065713.864:4230): pid=1 uid=0 auid=4294967295 ses=4294967295 msg='unit=systemd-coredump@0-2500581-0 comm="systemd" exe="/usr/lib/systemd/systemd" hostname=? addr=? terminal=? res=success'
Feb 18 23:41:54 daren-pc kernel: ------------[ cut here ]------------
Feb 18 23:41:54 daren-pc kernel: WARNING: CPU: 3 PID: 232 at drivers/iommu/dma-iommu.c:471 __iommu_dma_unmap+0xe8/0x100
Feb 18 23:41:54 daren-pc kernel: Modules linked in: zram msr xfs libcrc32c rfkill nls_iso8859_1 nls_cp437 vfat fat fuse amdgpu edac_mce_amd joydev mousedev input_leds hid_lg_g15 gpu_sched i2c_algo_bit ttm kvm snd_hda_codec_realtek snd_usb_audio snd_hda_codec_generic drm_kms_helper ledtrig_audio snd_hda_codec_hdmi snd_hda_intel irqbypass snd_usbmidi_lib snd_intel_dspcfg crct10dif_pclmul wmi_bmof snd_hda_codec crc32_pclmul drm snd_rawmidi ghash_clmulni_intel snd_hda_core snd_seq_device mc snd_hwdep snd_pcm agpgart syscopyarea aesni_intel ccp r8169 snd_timer sysfillrect crypto_simd cryptd sp5100_tco sysimgblt snd realtek fb_sys_fops glue_helper rng_core blackmagic(POE) k10temp i2c_piix4 soundcore libphy wmi pinctrl_amd evdev mac_hid acpi_cpufreq pkcs8_key_parser sg vhba(OE) crypto_user ip_tables x_tables hid_generic sd_mod usbhid hid dm_mod ahci libahci libata xhci_pci xhci_hcd scsi_mod ext4 crc32c_generic crc32c_intel crc16 mbcache jbd2
Feb 18 23:41:54 daren-pc kernel: CPU: 3 PID: 232 Comm: kworker/3:1 Tainted: P           OE     5.5.4-arch1-1 #1
Feb 18 23:41:54 daren-pc kernel: Hardware name: Gigabyte Technology Co., Ltd. X570 UD/X570 UD, BIOS F11 12/06/2019
Feb 18 23:41:54 daren-pc kernel: Workqueue: events ttm_bo_delayed_workqueue [ttm]
Feb 18 23:41:54 daren-pc kernel: RIP: 0010:__iommu_dma_unmap+0xe8/0x100
Feb 18 23:41:54 daren-pc kernel: Code: c0 74 0b 48 89 e6 4c 89 f7 e8 a4 c1 5c 00 48 c7 44 24 08 00 00 00 00 48 c7 44 24 10 00 00 00 00 48 c7 04 24 ff ff ff ff eb a1 <0f> 0b eb 93 e8 4f c8 a5 ff 66 66 2e 0f 1f 84 00 00 00 00 00 0f 1f
Feb 18 23:41:54 daren-pc kernel: RSP: 0018:ffffa65e40977d40 EFLAGS: 00010206
Feb 18 23:41:54 daren-pc kernel: RAX: 0000000040000000 RBX: 0000000000001000 RCX: 0000000000000015
Feb 18 23:41:54 daren-pc kernel: RDX: 0000000100000000 RSI: ffffffffc0000000 RDI: 0000000000000000
Feb 18 23:41:54 daren-pc kernel: RBP: 0000000100000000 R08: ffffa65e40977ca8 R09: 0000000000000000
Feb 18 23:41:54 daren-pc kernel: R10: 0000000000000002 R11: 0000000000000001 R12: 0000000000002000
Feb 18 23:41:54 daren-pc kernel: R13: ffff93a5f518c800 R14: ffff93a5f97d3820 R15: ffff93a1fa218148
Feb 18 23:41:54 daren-pc kernel: FS:  0000000000000000(0000) GS:ffff93a5fe8c0000(0000) knlGS:0000000000000000
Feb 18 23:41:54 daren-pc kernel: CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
Feb 18 23:41:54 daren-pc kernel: CR2: 000055ad59112000 CR3: 00000003f1ce2000 CR4: 0000000000340ee0
Feb 18 23:41:54 daren-pc kernel: Call Trace:
Feb 18 23:41:54 daren-pc kernel:  ttm_unmap_and_unpopulate_pages+0xa9/0x130 [ttm]
Feb 18 23:41:54 daren-pc kernel:  ttm_tt_destroy.part.0+0x49/0x50 [ttm]
Feb 18 23:41:54 daren-pc kernel:  ttm_bo_cleanup_memtype_use+0x32/0x80 [ttm]
Feb 18 23:41:54 daren-pc kernel:  ttm_bo_cleanup_refs+0x11b/0x200 [ttm]
Feb 18 23:41:54 daren-pc kernel:  ttm_bo_delayed_delete+0x14a/0x250 [ttm]
Feb 18 23:41:54 daren-pc kernel:  ttm_bo_delayed_workqueue+0x18/0x40 [ttm]
Feb 18 23:41:54 daren-pc kernel:  process_one_work+0x1e1/0x3d0
Feb 18 23:41:54 daren-pc kernel:  worker_thread+0x4a/0x3d0
Feb 18 23:41:54 daren-pc kernel:  kthread+0xfb/0x130
Feb 18 23:41:54 daren-pc kernel:  ? process_one_work+0x3d0/0x3d0
Feb 18 23:41:54 daren-pc kernel:  ? kthread_park+0x90/0x90
Feb 18 23:41:54 daren-pc kernel:  ret_from_fork+0x22/0x40
Feb 18 23:41:54 daren-pc kernel: ---[ end trace c2b667440c191eda ]---
Feb 18 23:41:54 daren-pc kernel: [TTM] Erroneous page count. Leaking pages.
Feb 18 23:41:54 daren-pc kernel: general protection fault: 0000 [#1] PREEMPT SMP NOPTI
Feb 18 23:41:54 daren-pc kernel: CPU: 3 PID: 2501214 Comm: rocminfo Tainted: P        W  OE     5.5.4-arch1-1 #1
Feb 18 23:41:54 daren-pc kernel: Hardware name: Gigabyte Technology Co., Ltd. X570 UD/X570 UD, BIOS F11 12/06/2019
Feb 18 23:41:54 daren-pc kernel: RIP: 0010:kmem_cache_alloc_trace+0x89/0x220
Feb 18 23:41:54 daren-pc kernel: Code: 5b 48 8b 70 08 48 39 f2 75 e7 4c 8b 30 4d 85 f6 0f 84 77 01 00 00 41 8b 5f 20 49 8b 3f 48 8d 8a 00 02 00 00 4c 89 f0 4c 01 f3 <48> 33 1b 49 33 9f 70 01 00 00 65 48 0f c7 0f 0f 94 c0 84 c0 74 ae
Feb 18 23:41:54 daren-pc kernel: RSP: 0018:ffffa65e4e1ffae8 EFLAGS: 00010286
Feb 18 23:41:54 daren-pc kernel: RAX: c77b4313b80220d4 RBX: c77b4313b80220d4 RCX: 00000000005c3a03
Feb 18 23:41:54 daren-pc kernel: RDX: 00000000005c3803 RSI: 00000000005c3803 RDI: 0000000000032060
Feb 18 23:41:54 daren-pc kernel: RBP: 0000000000000010 R08: ffff93a1fa21e808 R09: ffff939eadc99740
Feb 18 23:41:54 daren-pc kernel: R10: 8000000479bdf067 R11: ffff93a383909090 R12: ffff93a5fb4079c0
Feb 18 23:41:54 daren-pc kernel: R13: 0000000000000dc0 R14: c77b4313b80220d4 R15: ffff93a5fb4079c0
Feb 18 23:41:54 daren-pc kernel: FS:  00007f7c307b9780(0000) GS:ffff93a5fe8c0000(0000) knlGS:0000000000000000
Feb 18 23:41:54 daren-pc kernel: CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
Feb 18 23:41:54 daren-pc kernel: CR2: 00007f7c30e3c800 CR3: 00000003f1ce2000 CR4: 0000000000340ee0
Feb 18 23:41:54 daren-pc kernel: Call Trace:
Feb 18 23:41:54 daren-pc kernel:  ? amdgpu_ttm_tt_populate+0x8b/0x100 [amdgpu]
Feb 18 23:41:54 daren-pc kernel:  amdgpu_ttm_tt_populate+0x8b/0x100 [amdgpu]
Feb 18 23:41:54 daren-pc kernel:  ttm_tt_populate.part.0+0x1e/0x60 [ttm]
Feb 18 23:41:54 daren-pc kernel:  ttm_tt_bind+0x48/0x60 [ttm]
Feb 18 23:41:54 daren-pc kernel:  ttm_bo_handle_move_mem+0x29c/0x5a0 [ttm]
Feb 18 23:41:54 daren-pc kernel:  ttm_bo_validate+0x146/0x160 [ttm]
Feb 18 23:41:54 daren-pc kernel:  amdgpu_amdkfd_gpuvm_alloc_memory_of_gpu+0x3c5/0x760 [amdgpu]
Feb 18 23:41:54 daren-pc kernel:  kfd_ioctl_alloc_memory_of_gpu+0xee/0x1f0 [amdgpu]
Feb 18 23:41:54 daren-pc kernel:  kfd_ioctl+0x10b/0x3d0 [amdgpu]
Feb 18 23:41:54 daren-pc kernel:  ? kfd_dev_is_large_bar+0xb0/0xb0 [amdgpu]
Feb 18 23:41:54 daren-pc kernel:  do_vfs_ioctl+0x4b7/0x730
Feb 18 23:41:54 daren-pc kernel:  ? syscall_trace_enter+0x19c/0x2e0
Feb 18 23:41:54 daren-pc kernel:  ksys_ioctl+0x5e/0x90
Feb 18 23:41:54 daren-pc kernel:  __x64_sys_ioctl+0x16/0x20
Feb 18 23:41:54 daren-pc kernel:  do_syscall_64+0x4e/0x150
Feb 18 23:41:54 daren-pc kernel:  entry_SYSCALL_64_after_hwframe+0x44/0xa9
Feb 18 23:41:54 daren-pc kernel: RIP: 0033:0x7f7c30b082eb
Feb 18 23:41:54 daren-pc kernel: Code: 0f 1e fa 48 8b 05 a5 8b 0c 00 64 c7 00 26 00 00 00 48 c7 c0 ff ff ff ff c3 66 0f 1f 44 00 00 f3 0f 1e fa b8 10 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 8b 0d 75 8b 0c 00 f7 d8 64 89 01 48
Feb 18 23:41:54 daren-pc kernel: RSP: 002b:00007ffc8d4b2138 EFLAGS: 00000246 ORIG_RAX: 0000000000000010
Feb 18 23:41:54 daren-pc kernel: RAX: ffffffffffffffda RBX: 00007ffc8d4b2180 RCX: 00007f7c30b082eb
Feb 18 23:41:54 daren-pc kernel: RDX: 00007ffc8d4b2180 RSI: 00000000c0284b16 RDI: 0000000000000004
Feb 18 23:41:54 daren-pc kernel: RBP: 00000000c0284b16 R08: 0000000000000001 R09: 00000000c4000004
Feb 18 23:41:54 daren-pc kernel: R10: 0000000084000000 R11: 0000000000000246 R12: 00000000c4000004
Feb 18 23:41:54 daren-pc kernel: R13: 0000000000000004 R14: 00007ffc8d4b2228 R15: 00007f7c309ec100
Feb 18 23:41:54 daren-pc kernel: Modules linked in: zram msr xfs libcrc32c rfkill nls_iso8859_1 nls_cp437 vfat fat fuse amdgpu edac_mce_amd joydev mousedev input_leds hid_lg_g15 gpu_sched i2c_algo_bit ttm kvm snd_hda_codec_realtek snd_usb_audio snd_hda_codec_generic drm_kms_helper ledtrig_audio snd_hda_codec_hdmi snd_hda_intel irqbypass snd_usbmidi_lib snd_intel_dspcfg crct10dif_pclmul wmi_bmof snd_hda_codec crc32_pclmul drm snd_rawmidi ghash_clmulni_intel snd_hda_core snd_seq_device mc snd_hwdep snd_pcm agpgart syscopyarea aesni_intel ccp r8169 snd_timer sysfillrect crypto_simd cryptd sp5100_tco sysimgblt snd realtek fb_sys_fops glue_helper rng_core blackmagic(POE) k10temp i2c_piix4 soundcore libphy wmi pinctrl_amd evdev mac_hid acpi_cpufreq pkcs8_key_parser sg vhba(OE) crypto_user ip_tables x_tables hid_generic sd_mod usbhid hid dm_mod ahci libahci libata xhci_pci xhci_hcd scsi_mod ext4 crc32c_generic crc32c_intel crc16 mbcache jbd2
Feb 18 23:41:54 daren-pc kernel: ---[ end trace c2b667440c191edb ]---
Feb 18 23:41:54 daren-pc kernel: RIP: 0010:kmem_cache_alloc_trace+0x89/0x220
Feb 18 23:41:54 daren-pc kernel: Code: 5b 48 8b 70 08 48 39 f2 75 e7 4c 8b 30 4d 85 f6 0f 84 77 01 00 00 41 8b 5f 20 49 8b 3f 48 8d 8a 00 02 00 00 4c 89 f0 4c 01 f3 <48> 33 1b 49 33 9f 70 01 00 00 65 48 0f c7 0f 0f 94 c0 84 c0 74 ae
Feb 18 23:41:54 daren-pc kernel: RSP: 0018:ffffa65e4e1ffae8 EFLAGS: 00010286
Feb 18 23:41:54 daren-pc kernel: RAX: c77b4313b80220d4 RBX: c77b4313b80220d4 RCX: 00000000005c3a03
Feb 18 23:41:54 daren-pc kernel: RDX: 00000000005c3803 RSI: 00000000005c3803 RDI: 0000000000032060
Feb 18 23:41:54 daren-pc kernel: RBP: 0000000000000010 R08: ffff93a1fa21e808 R09: ffff939eadc99740
Feb 18 23:41:54 daren-pc kernel: R10: 8000000479bdf067 R11: ffff93a383909090 R12: ffff93a5fb4079c0
Feb 18 23:41:54 daren-pc kernel: R13: 0000000000000dc0 R14: c77b4313b80220d4 R15: ffff93a5fb4079c0
Feb 18 23:41:54 daren-pc kernel: FS:  00007f7c307b9780(0000) GS:ffff93a5fe8c0000(0000) knlGS:0000000000000000
Feb 18 23:41:54 daren-pc kernel: CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
Feb 18 23:41:54 daren-pc kernel: CR2: 00007f7c30e3c800 CR3: 00000003f1ce2000 CR4: 0000000000340ee0
Feb 18 23:41:54 daren-pc kernel: Evicting PASID 0x8006 queues
Feb 18 23:41:54 daren-pc kernel: general protection fault: 0000 [#2] PREEMPT SMP NOPTI
Feb 18 23:41:54 daren-pc kernel: CPU: 3 PID: 1722014 Comm: gnome-system-mo Tainted: P      D W  OE     5.5.4-arch1-1 #1
Feb 18 23:41:54 daren-pc kernel: Hardware name: Gigabyte Technology Co., Ltd. X570 UD/X570 UD, BIOS F11 12/06/2019
Feb 18 23:41:54 daren-pc kernel: RIP: 0010:kmem_cache_alloc_trace+0x89/0x220
Feb 18 23:41:54 daren-pc kernel: Code: 5b 48 8b 70 08 48 39 f2 75 e7 4c 8b 30 4d 85 f6 0f 84 77 01 00 00 41 8b 5f 20 49 8b 3f 48 8d 8a 00 02 00 00 4c 89 f0 4c 01 f3 <48> 33 1b 49 33 9f 70 01 00 00 65 48 0f c7 0f 0f 94 c0 84 c0 74 ae
Feb 18 23:41:54 daren-pc kernel: RSP: 0018:ffffa65e79b97c18 EFLAGS: 00010286
Feb 18 23:41:54 daren-pc kernel: RAX: c77b4313b80220d4 RBX: c77b4313b80220d4 RCX: 00000000005c3a03
Feb 18 23:41:54 daren-pc kernel: RDX: 00000000005c3803 RSI: 00000000005c3803 RDI: 0000000000032060
Feb 18 23:41:54 daren-pc kernel: RBP: 000000000000000b R08: 0000000000000001 R09: 74656e2f666c6573
Feb 18 23:41:54 daren-pc kernel: R10: ffffffffa4b64ea0 R11: 0000007fffffffff R12: ffff93a5fb4079c0
Feb 18 23:41:54 daren-pc kernel: R13: 0000000000000cc0 R14: c77b4313b80220d4 R15: ffff93a5fb4079c0
Feb 18 23:41:54 daren-pc kernel: FS:  00007f9e834e3480(0000) GS:ffff93a5fe8c0000(0000) knlGS:0000000000000000
Feb 18 23:41:54 daren-pc kernel: CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
Feb 18 23:41:54 daren-pc kernel: CR2: 00007f7c30e3c800 CR3: 00000003fa240000 CR4: 0000000000340ee0
Feb 18 23:41:54 daren-pc kernel: Call Trace:
Feb 18 23:41:54 daren-pc kernel:  ? proc_self_get_link+0x58/0xb0
Feb 18 23:41:54 daren-pc kernel:  proc_self_get_link+0x58/0xb0
Feb 18 23:41:54 daren-pc kernel:  link_path_walk+0x4f9/0x560
Feb 18 23:41:54 daren-pc kernel:  path_openat+0x9e/0x1550
Feb 18 23:41:54 daren-pc kernel:  ? seq_vprintf+0x30/0x50
Feb 18 23:41:54 daren-pc kernel:  ? seq_printf+0x5b/0x80
Feb 18 23:41:54 daren-pc kernel:  do_filp_open+0xab/0x120
Feb 18 23:41:54 daren-pc kernel:  ? unuse_pde+0x20/0x20
Feb 18 23:41:54 daren-pc kernel:  do_sys_open+0x19e/0x240
Feb 18 23:41:54 daren-pc kernel:  do_syscall_64+0x4e/0x150
Feb 18 23:41:54 daren-pc kernel:  entry_SYSCALL_64_after_hwframe+0x44/0xa9
Feb 18 23:41:54 daren-pc kernel: RIP: 0033:0x7f9e87ee62a4
Feb 18 23:41:54 daren-pc kernel: Code: 24 20 eb 8f 66 90 44 89 54 24 0c e8 26 57 f9 ff 44 8b 54 24 0c 44 89 e2 48 89 ee 41 89 c0 bf 9c ff ff ff b8 01 01 00 00 0f 05 <48> 3d 00 f0 ff ff 77 32 44 89 c7 89 44 24 0c e8 58 57 f9 ff 8b 44
Feb 18 23:41:54 daren-pc kernel: RSP: 002b:00007ffda4395d60 EFLAGS: 00000293 ORIG_RAX: 0000000000000101
Feb 18 23:41:54 daren-pc kernel: RAX: ffffffffffffffda RBX: 000055ab118e0ac0 RCX: 00007f9e87ee62a4
Feb 18 23:41:54 daren-pc kernel: RDX: 0000000000000000 RSI: 00007f9e868ddff5 RDI: 00000000ffffff9c
Feb 18 23:41:54 daren-pc kernel: RBP: 00007f9e868ddff5 R08: 0000000000000000 R09: 0000000000000001
Feb 18 23:41:54 daren-pc kernel: R10: 0000000000000000 R11: 0000000000000293 R12: 0000000000000000
Feb 18 23:41:54 daren-pc kernel: R13: 000055ab118e0ac0 R14: 0000000000000001 R15: 000055ab1207f6f0
Feb 18 23:41:54 daren-pc kernel: Modules linked in: zram msr xfs libcrc32c rfkill nls_iso8859_1 nls_cp437 vfat fat fuse amdgpu edac_mce_amd joydev mousedev input_leds hid_lg_g15 gpu_sched i2c_algo_bit ttm kvm snd_hda_codec_realtek snd_usb_audio snd_hda_codec_generic drm_kms_helper ledtrig_audio snd_hda_codec_hdmi snd_hda_intel irqbypass snd_usbmidi_lib snd_intel_dspcfg crct10dif_pclmul wmi_bmof snd_hda_codec crc32_pclmul drm snd_rawmidi ghash_clmulni_intel snd_hda_core snd_seq_device mc snd_hwdep snd_pcm agpgart syscopyarea aesni_intel ccp r8169 snd_timer sysfillrect crypto_simd cryptd sp5100_tco sysimgblt snd realtek fb_sys_fops glue_helper rng_core blackmagic(POE) k10temp i2c_piix4 soundcore libphy wmi pinctrl_amd evdev mac_hid acpi_cpufreq pkcs8_key_parser sg vhba(OE) crypto_user ip_tables x_tables hid_generic sd_mod usbhid hid dm_mod ahci libahci libata xhci_pci xhci_hcd scsi_mod ext4 crc32c_generic crc32c_intel crc16 mbcache jbd2
Feb 18 23:41:54 daren-pc kernel: ---[ end trace c2b667440c191edc ]---
Feb 18 23:41:54 daren-pc kernel: RIP: 0010:kmem_cache_alloc_trace+0x89/0x220
Feb 18 23:41:54 daren-pc kernel: Code: 5b 48 8b 70 08 48 39 f2 75 e7 4c 8b 30 4d 85 f6 0f 84 77 01 00 00 41 8b 5f 20 49 8b 3f 48 8d 8a 00 02 00 00 4c 89 f0 4c 01 f3 <48> 33 1b 49 33 9f 70 01 00 00 65 48 0f c7 0f 0f 94 c0 84 c0 74 ae
Feb 18 23:41:54 daren-pc kernel: RSP: 0018:ffffa65e4e1ffae8 EFLAGS: 00010286
Feb 18 23:41:54 daren-pc kernel: RAX: c77b4313b80220d4 RBX: c77b4313b80220d4 RCX: 00000000005c3a03
Feb 18 23:41:54 daren-pc kernel: RDX: 00000000005c3803 RSI: 00000000005c3803 RDI: 0000000000032060
Feb 18 23:41:54 daren-pc kernel: RBP: 0000000000000010 R08: ffff93a1fa21e808 R09: ffff939eadc99740
Feb 18 23:41:54 daren-pc kernel: R10: 8000000479bdf067 R11: ffff93a383909090 R12: ffff93a5fb4079c0
Feb 18 23:41:54 daren-pc kernel: R13: 0000000000000dc0 R14: c77b4313b80220d4 R15: ffff93a5fb4079c0
Feb 18 23:41:54 daren-pc kernel: FS:  00007f9e834e3480(0000) GS:ffff93a5fe8c0000(0000) knlGS:0000000000000000
Feb 18 23:41:54 daren-pc kernel: CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
Feb 18 23:41:54 daren-pc kernel: CR2: 00007f7c30e3c800 CR3: 00000003fa240000 CR4: 0000000000340ee0
Feb 18 23:41:55 daren-pc kernel: general protection fault: 0000 [#3] PREEMPT SMP NOPTI
Feb 18 23:41:55 daren-pc kernel: CPU: 3 PID: 890 Comm: Xorg:cs0 Tainted: P      D W  OE     5.5.4-arch1-1 #1
Feb 18 23:41:55 daren-pc kernel: Hardware name: Gigabyte Technology Co., Ltd. X570 UD/X570 UD, BIOS F11 12/06/2019
Feb 18 23:41:55 daren-pc kernel: RIP: 0010:__kmalloc_node+0x1b6/0x310
Feb 18 23:41:55 daren-pc kernel: Code: ff 0d c6 c8 58 5b 0f 85 65 ff ff ff e8 61 76 d7 ff e9 5b ff ff ff 41 8b 58 20 49 8b 38 48 8d 8a 00 02 00 00 4c 89 e0 4c 01 e3 <48> 33 1b 49 33 98 70 01 00 00 65 48 0f c7 0f 0f 94 c0 84 c0 0f 84
Feb 18 23:41:55 daren-pc kernel: RSP: 0018:ffffa65e4150faa8 EFLAGS: 00010286
Feb 18 23:41:55 daren-pc kernel: RAX: c77b4313b80220d4 RBX: c77b4313b80220d4 RCX: 00000000005c3a03
Feb 18 23:41:55 daren-pc kernel: RDX: 00000000005c3803 RSI: 00000000005c3803 RDI: 0000000000032060
Feb 18 23:41:55 daren-pc kernel: RBP: 0000000000000010 R08: ffff93a5fb4079c0 R09: 0000000000000020
Feb 18 23:41:55 daren-pc kernel: R10: 0000000040000000 R11: 0000000000000000 R12: c77b4313b80220d4
Feb 18 23:41:55 daren-pc kernel: R13: 00000000ffffffff R14: ffff93a5fb4079c0 R15: 0000000000000cc0
Feb 18 23:41:55 daren-pc kernel: FS:  00007f2ee2c43700(0000) GS:ffff93a5fe8c0000(0000) knlGS:0000000000000000
Feb 18 23:41:55 daren-pc kernel: CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
Feb 18 23:41:55 daren-pc kernel: CR2: 00007efde9a7d4e0 CR3: 00000007e54e4000 CR4: 0000000000340ee0
Feb 18 23:41:55 daren-pc kernel: Call Trace:
Feb 18 23:41:55 daren-pc kernel:  ? amdgpu_bo_create_list_entry_array+0x33/0x110 [amdgpu]
Feb 18 23:41:55 daren-pc kernel:  amdgpu_bo_create_list_entry_array+0x33/0x110 [amdgpu]
Feb 18 23:41:55 daren-pc kernel:  amdgpu_cs_ioctl+0x1253/0x1e90 [amdgpu]
Feb 18 23:41:55 daren-pc kernel:  ? kmem_cache_free+0x2a1/0x2c0
Feb 18 23:41:55 daren-pc kernel:  ? amdgpu_cs_find_mapping+0x110/0x110 [amdgpu]
Feb 18 23:41:55 daren-pc kernel:  drm_ioctl_kernel+0xb2/0x100 [drm]
Feb 18 23:41:55 daren-pc kernel:  drm_ioctl+0x209/0x360 [drm]
Feb 18 23:41:55 daren-pc kernel:  ? amdgpu_cs_find_mapping+0x110/0x110 [amdgpu]
Feb 18 23:41:55 daren-pc kernel:  amdgpu_drm_ioctl+0x49/0x80 [amdgpu]
Feb 18 23:41:55 daren-pc kernel:  do_vfs_ioctl+0x4b7/0x730
Feb 18 23:41:55 daren-pc kernel:  ksys_ioctl+0x5e/0x90
Feb 18 23:41:55 daren-pc kernel:  __x64_sys_ioctl+0x16/0x20
Feb 18 23:41:55 daren-pc kernel:  do_syscall_64+0x4e/0x150
Feb 18 23:41:55 daren-pc kernel:  entry_SYSCALL_64_after_hwframe+0x44/0xa9
Feb 18 23:41:55 daren-pc kernel: RIP: 0033:0x7f2eec4ef2eb
Feb 18 23:41:55 daren-pc kernel: Code: 0f 1e fa 48 8b 05 a5 8b 0c 00 64 c7 00 26 00 00 00 48 c7 c0 ff ff ff ff c3 66 0f 1f 44 00 00 f3 0f 1e fa b8 10 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 8b 0d 75 8b 0c 00 f7 d8 64 89 01 48
Feb 18 23:41:55 daren-pc kernel: RSP: 002b:00007f2ee2c429e8 EFLAGS: 00000246 ORIG_RAX: 0000000000000010
Feb 18 23:41:55 daren-pc kernel: RAX: ffffffffffffffda RBX: 00007f2ee2c42a50 RCX: 00007f2eec4ef2eb
Feb 18 23:41:55 daren-pc kernel: RDX: 00007f2ee2c42a50 RSI: 00000000c0186444 RDI: 000000000000000e
Feb 18 23:41:55 daren-pc kernel: RBP: 00000000c0186444 R08: 00007f2ee2c42b60 R09: 0000000000000020
Feb 18 23:41:55 daren-pc kernel: R10: 00007f2ee2c42b60 R11: 0000000000000246 R12: 0000563a8fa9c0e0
Feb 18 23:41:55 daren-pc kernel: R13: 000000000000000e R14: 0000000000000000 R15: 0000563a8fab7588
Feb 18 23:41:55 daren-pc kernel: Modules linked in: zram msr xfs libcrc32c rfkill nls_iso8859_1 nls_cp437 vfat fat fuse amdgpu edac_mce_amd joydev mousedev input_leds hid_lg_g15 gpu_sched i2c_algo_bit ttm kvm snd_hda_codec_realtek snd_usb_audio snd_hda_codec_generic drm_kms_helper ledtrig_audio snd_hda_codec_hdmi snd_hda_intel irqbypass snd_usbmidi_lib snd_intel_dspcfg crct10dif_pclmul wmi_bmof snd_hda_codec crc32_pclmul drm snd_rawmidi ghash_clmulni_intel snd_hda_core snd_seq_device mc snd_hwdep snd_pcm agpgart syscopyarea aesni_intel ccp r8169 snd_timer sysfillrect crypto_simd cryptd sp5100_tco sysimgblt snd realtek fb_sys_fops glue_helper rng_core blackmagic(POE) k10temp i2c_piix4 soundcore libphy wmi pinctrl_amd evdev mac_hid acpi_cpufreq pkcs8_key_parser sg vhba(OE) crypto_user ip_tables x_tables hid_generic sd_mod usbhid hid dm_mod ahci libahci libata xhci_pci xhci_hcd scsi_mod ext4 crc32c_generic crc32c_intel crc16 mbcache jbd2
Feb 18 23:41:55 daren-pc kernel: ---[ end trace c2b667440c191edd ]---
Feb 18 23:41:55 daren-pc kernel: RIP: 0010:kmem_cache_alloc_trace+0x89/0x220
Feb 18 23:41:55 daren-pc kernel: Code: 5b 48 8b 70 08 48 39 f2 75 e7 4c 8b 30 4d 85 f6 0f 84 77 01 00 00 41 8b 5f 20 49 8b 3f 48 8d 8a 00 02 00 00 4c 89 f0 4c 01 f3 <48> 33 1b 49 33 9f 70 01 00 00 65 48 0f c7 0f 0f 94 c0 84 c0 74 ae
Feb 18 23:41:55 daren-pc kernel: RSP: 0018:ffffa65e4e1ffae8 EFLAGS: 00010286
Feb 18 23:41:55 daren-pc kernel: RAX: c77b4313b80220d4 RBX: c77b4313b80220d4 RCX: 00000000005c3a03
Feb 18 23:41:55 daren-pc kernel: RDX: 00000000005c3803 RSI: 00000000005c3803 RDI: 0000000000032060
Feb 18 23:41:55 daren-pc kernel: RBP: 0000000000000010 R08: ffff93a1fa21e808 R09: ffff939eadc99740
Feb 18 23:41:55 daren-pc kernel: R10: 8000000479bdf067 R11: ffff93a383909090 R12: ffff93a5fb4079c0
Feb 18 23:41:55 daren-pc kernel: R13: 0000000000000dc0 R14: c77b4313b80220d4 R15: ffff93a5fb4079c0
Feb 18 23:41:55 daren-pc kernel: FS:  00007f2ee2c43700(0000) GS:ffff93a5fe8c0000(0000) knlGS:0000000000000000
Feb 18 23:41:55 daren-pc kernel: CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
Feb 18 23:41:55 daren-pc kernel: CR2: 00007efde9a7d4e0 CR3: 00000007e54e4000 CR4: 0000000000340ee0
Feb 18 23:41:55 daren-pc kernel: general protection fault: 0000 [#4] PREEMPT SMP NOPTI
Feb 18 23:41:55 daren-pc kernel: CPU: 3 PID: 2506049 Comm: configure Tainted: P      D W  OE     5.5.4-arch1-1 #1
Feb 18 23:41:55 daren-pc kernel: Hardware name: Gigabyte Technology Co., Ltd. X570 UD/X570 UD, BIOS F11 12/06/2019
Feb 18 23:41:55 daren-pc kernel: RIP: 0010:__kmalloc_node+0x1b6/0x310
Feb 18 23:41:55 daren-pc kernel: Code: ff 0d c6 c8 58 5b 0f 85 65 ff ff ff e8 61 76 d7 ff e9 5b ff ff ff 41 8b 58 20 49 8b 38 48 8d 8a 00 02 00 00 4c 89 e0 4c 01 e3 <48> 33 1b 49 33 98 70 01 00 00 65 48 0f c7 0f 0f 94 c0 84 c0 0f 84
Feb 18 23:41:55 daren-pc kernel: RSP: 0018:ffffa65e72187d28 EFLAGS: 00010286
Feb 18 23:41:55 daren-pc kernel: RAX: 8a5cd9e13a7a4882 RBX: 8a5cd9e13a7a4882 RCX: 0000000005f5f603
Feb 18 23:41:55 daren-pc kernel: RDX: 0000000005f5f403 RSI: 0000000005f5f403 RDI: 0000000000032080
Feb 18 23:41:55 daren-pc kernel: RBP: 0000000000000020 R08: ffff93a5fb407800 R09: ffff93a5fa5f5c00
Feb 18 23:41:55 daren-pc kernel: R10: ffffa65e40000000 R11: ffffa65e7218c000 R12: 8a5cd9e13a7a4882
Feb 18 23:41:55 daren-pc kernel: R13: 00000000ffffffff R14: ffff93a5fb407800 R15: 0000000000000dc0
Feb 18 23:41:55 daren-pc kernel: FS:  00007f2e3e4e2b80(0000) GS:ffff93a5fe8c0000(0000) knlGS:0000000000000000
Feb 18 23:41:55 daren-pc kernel: CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
Feb 18 23:41:55 daren-pc kernel: CR2: 000055c3f08a3660 CR3: 0000000767acc000 CR4: 0000000000340ee0
Feb 18 23:41:55 daren-pc kernel: Call Trace:
Feb 18 23:41:55 daren-pc kernel:  ? __vmalloc_node_range+0xd5/0x220
Feb 18 23:41:55 daren-pc kernel:  __vmalloc_node_range+0xd5/0x220
Feb 18 23:41:55 daren-pc kernel:  copy_process+0x8ba/0x1b80
Feb 18 23:41:55 daren-pc kernel:  ? _do_fork+0x94/0x3f0
Feb 18 23:41:55 daren-pc kernel:  ? do_wp_page+0x95/0x490
Feb 18 23:41:55 daren-pc kernel:  _do_fork+0x94/0x3f0
Feb 18 23:41:55 daren-pc kernel:  __x64_sys_clone+0x81/0xa0
Feb 18 23:41:55 daren-pc kernel:  do_syscall_64+0x4e/0x150
Feb 18 23:41:55 daren-pc kernel:  entry_SYSCALL_64_after_hwframe+0x44/0xa9
Feb 18 23:41:55 daren-pc kernel: RIP: 0033:0x7f2e3e621c6f
Feb 18 23:41:55 daren-pc kernel: Code: ed 0f 85 f4 00 00 00 64 4c 8b 0c 25 10 00 00 00 45 31 c0 4d 8d 91 d0 02 00 00 31 d2 31 f6 bf 11 00 20 01 b8 38 00 00 00 0f 05 <48> 3d 00 f0 ff ff 0f 87 8d 00 00 00 41 89 c5 85 c0 0f 85 9a 00 00
Feb 18 23:41:55 daren-pc kernel: RSP: 002b:00007fff79575550 EFLAGS: 00000246 ORIG_RAX: 0000000000000038
Feb 18 23:41:55 daren-pc kernel: RAX: ffffffffffffffda RBX: 0000000000000001 RCX: 00007f2e3e621c6f
Feb 18 23:41:55 daren-pc kernel: RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000001200011
Feb 18 23:41:55 daren-pc kernel: RBP: 0000000000000000 R08: 0000000000000000 R09: 00007f2e3e4e2b80
Feb 18 23:41:55 daren-pc kernel: R10: 00007f2e3e4e2e50 R11: 0000000000000246 R12: 0000000000000000
Feb 18 23:41:55 daren-pc kernel: R13: 00007fff79575610 R14: 0000000000000000 R15: 000055c3eec48d58
Feb 18 23:41:55 daren-pc kernel: Modules linked in: zram msr xfs libcrc32c rfkill nls_iso8859_1 nls_cp437 vfat fat fuse amdgpu edac_mce_amd joydev mousedev input_leds hid_lg_g15 gpu_sched i2c_algo_bit ttm kvm snd_hda_codec_realtek snd_usb_audio snd_hda_codec_generic drm_kms_helper ledtrig_audio snd_hda_codec_hdmi snd_hda_intel irqbypass snd_usbmidi_lib snd_intel_dspcfg crct10dif_pclmul wmi_bmof snd_hda_codec crc32_pclmul drm snd_rawmidi ghash_clmulni_intel snd_hda_core snd_seq_device mc snd_hwdep snd_pcm agpgart syscopyarea aesni_intel ccp r8169 snd_timer sysfillrect crypto_simd cryptd sp5100_tco sysimgblt snd realtek fb_sys_fops glue_helper rng_core blackmagic(POE) k10temp i2c_piix4 soundcore libphy wmi pinctrl_amd evdev mac_hid acpi_cpufreq pkcs8_key_parser sg vhba(OE) crypto_user ip_tables x_tables hid_generic sd_mod usbhid hid dm_mod ahci libahci libata xhci_pci xhci_hcd scsi_mod ext4 crc32c_generic crc32c_intel crc16 mbcache jbd2
Feb 18 23:41:55 daren-pc kernel: ---[ end trace c2b667440c191ede ]---
Feb 18 23:41:55 daren-pc kernel: RIP: 0010:kmem_cache_alloc_trace+0x89/0x220
Feb 18 23:41:55 daren-pc kernel: Code: 5b 48 8b 70 08 48 39 f2 75 e7 4c 8b 30 4d 85 f6 0f 84 77 01 00 00 41 8b 5f 20 49 8b 3f 48 8d 8a 00 02 00 00 4c 89 f0 4c 01 f3 <48> 33 1b 49 33 9f 70 01 00 00 65 48 0f c7 0f 0f 94 c0 84 c0 74 ae
Feb 18 23:41:55 daren-pc kernel: RSP: 0018:ffffa65e4e1ffae8 EFLAGS: 00010286
Feb 18 23:41:55 daren-pc kernel: RAX: c77b4313b80220d4 RBX: c77b4313b80220d4 RCX: 00000000005c3a03
Feb 18 23:41:55 daren-pc kernel: RDX: 00000000005c3803 RSI: 00000000005c3803 RDI: 0000000000032060
Feb 18 23:41:55 daren-pc kernel: RBP: 0000000000000010 R08: ffff93a1fa21e808 R09: ffff939eadc99740
Feb 18 23:41:55 daren-pc kernel: R10: 8000000479bdf067 R11: ffff93a383909090 R12: ffff93a5fb4079c0

It sort of always happened when I tried to build rocblas (https://aur.archlinux.org/packages/rocblas/) that seems to issue /opt/rocm/bin/rocminfo to get the underlying GPU specs, segfaults in kernel space and takes the kernel with it.

Screenshot of the system freezing during that incident:
https://imgur.com/a/H0k9mrL

For some reason I can't reprocude this on BIOS F1 though...

Edit:
For the record, my GPU is an AMD Radeon VII and I want to get ROCm running on Arch which is why I compile the ROCm stuff.

Last edited by daren_k (2020-02-18 23:16:06)

Offline

#14 2020-02-18 23:41:06

Ropid
Member
Registered: 2015-03-09
Posts: 1,069

Re: Instability with Ryzen 9 3950X and updated X570 BIOS

I think I'd still blame memory (settings). In the description for the F11 BIOS on Gigabyte's website, they write that they improved something about memory compatibility. Maybe they broke things for you. You are using 16GB sized memory sticks and 16GB is usually "dual-rank", and that's perhaps a bit unusual because what sells most are 8GB sized memory sticks which are "single-rank". Maybe Gigabyte concentrated on improving things for 8GB sticks and broke things for 16GB sticks. I mentioned a set of values for the Rtt* and ProcODT settings in post #7. I'd try to set those manually instead of using "auto" because what's good for single-rank is very different than what's good for dual-rank.

Something else I noticed recently on my Ryzen 2700X CPU and X470 board here is, I saw "PCI AER (= advanced error reporting)" warnings happening while the CPU was under full load. Those warnings mentioned the PCIe address of the graphics card. The warnings went away when I added "pcie_aspm=off" to the kernel command line. That kernel parameter disables a sleep state for the PCIe bus.

Last edited by Ropid (2020-02-18 23:46:25)

Offline

#15 2020-02-19 00:21:04

daren_k
Member
Registered: 2020-02-13
Posts: 37
Website

Re: Instability with Ryzen 9 3950X and updated X570 BIOS

I compiled HCC(LLVM) during the kill-ryzen.sh script that spawned 32 threads that try to compile GCC for like 15 minutes - stable.

Tried to build rocblas afterwards while kill-ryzen.sh was still running and it instantly locked up there with the first fishy kernel messages (see screenshot I posted).

rocminfo consistently segfaults and makes the system instable afterwards.

$ /opt/rocm/bin/rocminfo
ROCk module is loaded
daren is not member of "video" group, the default DRM access group. Users must be a member of the "video" group or another DRM access group in order for ROCm applications to run successfully.
[1]    2620 segmentation fault (core dumped)  /opt/rocm/bin/rocminfo

System was instable after. After rebooting and adding myself to the video group:

$ /opt/rocm/bin/rocminfo
ROCk module is loaded
daren is member of video group
[1]    2965 segmentation fault (core dumped)  /opt/rocm/bin/rocminfo

System again instable.

There is apparently something similar happening with the Vega GPUs: https://github.com/RadeonOpenCompute/rocminfo/issues/8

Offline

#16 2020-02-19 09:06:23

daren_k
Member
Registered: 2020-02-13
Posts: 37
Website

Re: Instability with Ryzen 9 3950X and updated X570 BIOS

Back to F1, with F11 the BIOS reset itself after every reboot when I set XMP, it doesn't seem a stable release honestly.

/opt/rocm/bin/rocminfo works with this F1 BIOS and outputs the CPU/GPU specs without an issue.

For the record my STREAM outputs with the 2 BIOSes.

Compiled with Intel C/C++ Compiler 19.1.0:

icc -o stream stream.c -Ofast -fopenmp -march=core-avx2 -DSTREAM_ARRAY_SIZE=800000000 -DNTIMES=5 -mcmodel large -nolib-inline

stream_bios=F1_xmp=on_kernel=5.5.4.arch1-1:

-------------------------------------------------------------
STREAM version $Revision: 5.10 $
-------------------------------------------------------------
This system uses 8 bytes per array element.
-------------------------------------------------------------
Array size = 800000000 (elements), Offset = 0 (elements)
Memory per array = 6103.5 MiB (= 6.0 GiB).
Total memory required = 18310.5 MiB (= 17.9 GiB).
Each kernel will be executed 5 times.
 The *best* time for each kernel (excluding the first iteration)
 will be used to compute the reported bandwidth.
-------------------------------------------------------------
Number of Threads requested = 32
Number of Threads counted = 32
-------------------------------------------------------------
Your clock granularity/precision appears to be 1 microseconds.
Each test below will take on the order of 351923 microseconds.
   (= 351923 clock ticks)
Increase the size of the arrays if this shows that
you are not getting at least 20 clock ticks per test.
-------------------------------------------------------------
WARNING -- The above is only a rough guideline.
For best results, please be sure you know the
precision of your system timer.
-------------------------------------------------------------
Function    Best Rate MB/s  Avg time     Min time     Max time
Copy:           43227.1     0.296258     0.296111     0.296380
Scale:          43188.1     0.296849     0.296378     0.297384
Add:            43085.1     0.446700     0.445630     0.447733
Triad:          42945.1     0.448662     0.447082     0.451456
-------------------------------------------------------------
Solution Validates: avg error less than 1.000000e-13 on all three arrays
-------------------------------------------------------------

stream_bios=F11_xmp=on_kernel=5.5.4.arch1-1:

-------------------------------------------------------------
STREAM version $Revision: 5.10 $
-------------------------------------------------------------
This system uses 8 bytes per array element.
-------------------------------------------------------------
Array size = 800000000 (elements), Offset = 0 (elements)
Memory per array = 6103.5 MiB (= 6.0 GiB).
Total memory required = 18310.5 MiB (= 17.9 GiB).
Each kernel will be executed 5 times.
 The *best* time for each kernel (excluding the first iteration)
 will be used to compute the reported bandwidth.
-------------------------------------------------------------
Number of Threads requested = 32
Number of Threads counted = 32
-------------------------------------------------------------
Your clock granularity/precision appears to be 1 microseconds.
Each test below will take on the order of 340751 microseconds.
   (= 340751 clock ticks)
Increase the size of the arrays if this shows that
you are not getting at least 20 clock ticks per test.
-------------------------------------------------------------
WARNING -- The above is only a rough guideline.
For best results, please be sure you know the
precision of your system timer.
-------------------------------------------------------------
Function    Best Rate MB/s  Avg time     Min time     Max time
Copy:           44518.2     0.289187     0.287523     0.293895
Scale:          44470.4     0.288417     0.287832     0.288814
Add:            44520.1     0.433086     0.431266     0.434156
Triad:          44346.1     0.433709     0.432958     0.433984
-------------------------------------------------------------
Solution Validates: avg error less than 1.000000e-13 on all three arrays
-------------------------------------------------------------

I will notify upstream (Gigabyte and rocminfo maintainer) about the issues and just set "nordrand" kernel parameter for now.

Last edited by daren_k (2020-02-19 09:09:04)

Offline

#17 2020-02-22 11:56:00

daren_k
Member
Registered: 2020-02-13
Posts: 37
Website

Re: Instability with Ryzen 9 3950X and updated X570 BIOS

Testing F2 for good measure, /opt/rocm/bin/rocminfo segfaults and takes the system down to hell as well and I got a browser tab crashing on another boot during running kill-ryzen.sh:

[KERN] 2020-02-22T12:24:50+0100 daren-pc kernel: DedicatedWorker[696448]: segfault at 396c8de40030 ip 00002b7389427ca6 sp 00007fb4b1e779e0 error 4
[KERN] 2020-02-22T12:24:50+0100 daren-pc kernel: Code: 45 c0 48 3b 27 0f 86 44 04 00 00 48 8b 7b 0b 4c 8b 43 4f 45 8b 48 18 45 8b 58 18 41 83 c3 30 45 89 58 18 44 8b da 46 8b 24 1f <41> 8b 7c 3c 30 4c 8b 63 43 81 e7 ff 01 00 00 4c 8b 73 3b 81 c7 76
[KERN] 2020-02-22T12:24:50+0100 daren-pc kernel: audit: type=1701 audit(1582370690.285:112): auid=1000 uid=1000 gid=985 ses=2 pid=665892 comm="DedicatedWorker" exe="/opt/vivaldi/vivaldi-bin" sig=11 res=1
[KERN] 2020-02-22T12:24:50+0100 daren-pc kernel: audit: type=1130 audit(1582370690.299:113): pid=1 uid=0 auid=4294967295 ses=4294967295 msg='unit=systemd-coredump@0-2487352-0 comm="systemd" exe="/usr/lib/systemd/systemd" hostname=? addr=? terminal=? res=success'
[KERN] 2020-02-22T12:24:52+0100 daren-pc kernel: audit: type=1131 audit(1582370692.579:114): pid=1 uid=0 auid=4294967295 ses=4294967295 msg='unit=systemd-coredump@0-2487352-0 comm="systemd" exe="/usr/lib/systemd/systemd" hostname=? addr=? terminal=? res=success'

That I had not happen ever with F1 BIOS.

Edit:
RDRAND issue gone with this F2 BIOS as well, can see an upped memory bandwidth by around ~1GB/s.

Tested the

pcie_aspm=off

kernel parameter as well, with it rocminfo segfaults as well.

Last edited by daren_k (2020-02-22 12:02:42)

Offline

#18 2020-02-22 17:14:29

Ropid
Member
Registered: 2015-03-09
Posts: 1,069

Re: Instability with Ryzen 9 3950X and updated X570 BIOS

Did you try looking into that RTT resistances stuff I mentioned in post #7?

Offline

#19 2020-02-22 22:15:55

daren_k
Member
Registered: 2020-02-13
Posts: 37
Website

Re: Instability with Ryzen 9 3950X and updated X570 BIOS

I'm not that deep into memory overclocking, so not inclined to fiddle with values that could potentially fry my RAM or something.

I noticed something else though...
In the meantime I installed Ubuntu 18.04 to check out ROCm (sadly arch only supports Tensorflow with proprietary NVIDIA CUDA/cudnn currently) software stack for once, I noticed that the rocminfo utility doesn't segfault with a recent BIOS there.

Considered booting Arch with linux-lts afterwards to check if the kernel has something to do with it, turns out it doesn't segfault with the F10 BIOS I installed currently... interesting.

Could this be an issue with the (recent) linux kernel? (not sure if related, but I had crashing tabs as well on my laptop during linux 5.5.2 a couple weeks back, not before, not after updating that)

Will try to keep rolling this linux-lts with a F11 BIOS that I'm gonna install again in just a bit for stability testing.

Offline

#20 2020-02-22 23:46:51

Ropid
Member
Registered: 2015-03-09
Posts: 1,069

Re: Instability with Ryzen 9 3950X and updated X570 BIOS

The way I understood things, the resistances are about how the signal on the wires is getting muffled to suppress noise. I think it can't do anything harmful to the hardware. It's not like increasing voltage. A wrong setting just makes it so the signal won't reach the other side.

I was forced to look into that stuff because on my Zen+ 2700X CPU, the problems with my 2x16GB dual-rank memory already start with just 3000MHz speeds. The Zen 2 CPUs supposedly are much better about memory compatibility at high speeds, but I found a spreadsheet here where you can see most people with 2x16GB memory using the same RTT settings on Zen 2 as well, not just Zen+:

https://docs.google.com/spreadsheets/d/ … tkkfN78tSo

That's where I got the idea that maybe using Auto just doesn't work for dual-rank and only works with single-rank (dual-rank = 16GB sized sticks, single-rank = 8GB sized).

While I tried to find out what that Rtt stuff is about, I could also find something about that in a PDF from Micron:

https://www.micron.com/-/media/client/g … 4_dram.pdf

There's a table about Rtt settings on page 252 of that PDF. The footnotes point to which rows are for single-rank and dual-rank. Enabling RttPark gets recommended for dual-rank in that table.

Offline

#21 2020-02-24 23:00:44

daren_k
Member
Registered: 2020-02-13
Posts: 37
Website

Re: Instability with Ryzen 9 3950X and updated X570 BIOS

I don't think it's the RAM, I've been running linux-lts and Ubuntu with 5.3.0 kernel with practically no issue with this F11 BIOS in the last few days.

The only thing I had happen on linux-lts was that after running the kill-ryzen.sh script stopped and I fell asleep, after a good bunch of minutes of idling this was written in that same terminal:

[KERN] 2020-02-23T01:55:07+0100 daren-pc kernel: mce: [Hardware Error]: Machine check events logged
[KERN] 2020-02-23T01:55:07+0100 daren-pc kernel: [Hardware Error]: Corrected error, no action required.
[KERN] 2020-02-23T01:55:07+0100 daren-pc kernel: [Hardware Error]: CPU:0 (17:71:0) MC27_STATUS[-|CE|MiscV|-|-|-|SyndV|-|-|-]: 0x982000000002080b
[KERN] 2020-02-23T01:55:07+0100 daren-pc kernel: [Hardware Error]: IPID: 0x0001002e00000500, Syndrome: 0x000000005a020005
[KERN] 2020-02-23T01:55:07+0100 daren-pc kernel: [Hardware Error]: Power, Interrupts, etc. Ext. Error Code: 2, Link Error.
[KERN] 2020-02-23T01:55:07+0100 daren-pc kernel: [Hardware Error]: cache level: L3/GEN, mem/io: IO, mem-tx: GEN, part-proc: SRC (no timeout)

But it didn't seem to affect system stability.

Back to linux 5.5.5 for stress testing:
Tried to run the kill-ryzen.sh script + some FurMark test from the gputest AUR package, this happened.

$ start_furmark_windowed_1024x640.sh 
/usr/bin/start_furmark_windowed_1024x640.sh: line 3: 3512977 Segmentation fault      (core dumped) ./GpuTest /test=fur /width=1024 /height=640
[TEMP] 2020-02-24T23:48:08+01:00 +80.5
[KERN] 2020-02-24T23:48:21+0100 daren-pc kernel: [drm:amdgpu_ttm_backend_bind [amdgpu]] *ERROR* failed to pin userptr
[KERN] 2020-02-24T23:48:21+0100 daren-pc kernel: init_user_pages: failed to validate BO
[KERN] 2020-02-24T23:48:21+0100 daren-pc kernel: [drm:amdgpu_ttm_backend_bind [amdgpu]] *ERROR* failed to pin userptr
[KERN] 2020-02-24T23:48:21+0100 daren-pc kernel: init_user_pages: failed to validate BO
[KERN] 2020-02-24T23:48:21+0100 daren-pc kernel: GpuTest[3512977]: segfault at 0 ip 00007f68131a6565 sp 00007fff1aff8210 error 6 in libhsa-runtime64.so.1.1.9[7f681318f000+7f000]
[KERN] 2020-02-24T23:48:21+0100 daren-pc kernel: Code: 8d 4c 24 04 48 8d b8 30 02 00 00 48 8d 54 24 10 48 8d 74 24 08 ff 90 48 02 00 00 48 8d 78 08 48 89 83 b8 03 00 00 48 83 e7 f8 <48> c7 00 00 00 00 00 48 c7 80 f8 1f 00 00 00 00 00 00 48 29 f8 8d
[KERN] 2020-02-24T23:48:21+0100 daren-pc kernel: audit: type=1701 audit(1582584501.966:114): auid=1000 uid=1000 gid=985 ses=3 pid=3512977 comm="GpuTest" exe="/opt/gputest/GpuTest" sig=11 res=1
[KERN] 2020-02-24T23:48:22+0100 daren-pc kernel: audit: type=1130 audit(1582584501.996:115): pid=1 uid=0 auid=4294967295 ses=4294967295 msg='unit=systemd-coredump@0-3513022-0 comm="systemd" exe="/usr/lib/systemd/systemd" hostname=? addr=? terminal=? res=success'
[KERN] 2020-02-24T23:48:22+0100 daren-pc kernel: Evicting PASID 0x8006 queues
[KERN] 2020-02-24T23:48:22+0100 daren-pc kernel: audit: type=1131 audit(1582584502.326:116): pid=1 uid=0 auid=4294967295 ses=4294967295 msg='unit=systemd-coredump@0-3513022-0 comm="systemd" exe="/usr/lib/systemd/systemd" hostname=? addr=? terminal=? res=success'
[TEMP] 2020-02-24T23:49:08+01:00 +78.1
[TEMP] 2020-02-24T23:50:08+01:00 +78.0

That FurMark benchmark works with linux-lts.

All this seems like some upstream amdgpu kernel issue coupled with the BIOS update to me.

Edit:
These BIOS resets I was mentioning were likely due to a faulty 50GB SSD I tried to put another OS on (CentOS 7), was throwing ata3 error messages to the terminal booting into that and I wasn't even able to update the packages.
Ever since I removed that, the BIOS hasn't reset.

Last edited by daren_k (2020-02-24 23:29:04)

Offline

#22 2020-03-07 10:42:59

daren_k
Member
Registered: 2020-02-13
Posts: 37
Website

Re: Instability with Ryzen 9 3950X and updated X570 BIOS

Still the case with linux-5.5.8 by the way...

I sure hope linux-lts doesn't switch to the buggy kernel any time soon.

Offline

#23 2020-03-08 04:20:59

Ropid
Member
Registered: 2015-03-09
Posts: 1,069

Re: Instability with Ryzen 9 3950X and updated X570 BIOS

According to my pacman.log file, the previous linux-lts 4.19.x stayed at 4.19.x for about a year. The switch to 5.4.x was just last month. Maybe things repeat and you'll have one year with 5.4.x.

Offline

#24 2020-03-08 11:17:33

Lone_Wolf
Member
From: Netherlands, Europe
Registered: 2005-10-04
Posts: 11,866

Re: Instability with Ryzen 9 3950X and updated X570 BIOS

https://www.kernel.org/category/releases.html

Since 2014 there every 5th kernel release was a LTS version .
That suggests next LTS kernel will be 5.9.x .


Disliking systemd intensely, but not satisfied with alternatives so focusing on taming systemd.


(A works at time B)  && (time C > time B ) ≠  (A works at time C)

Offline

#25 2020-03-11 08:26:28

orlfman
Member
Registered: 2007-11-20
Posts: 138

Re: Instability with Ryzen 9 3950X and updated X570 BIOS

i really think its ram. with my 3800x build i had nothing but problems with two hynix kits. one 3200mhz corsair hynix based, and one 3600mhz gskill hynix based. the gskill hynix i thought was stable but after two weeks i started to get random boot problems. then after that a random crash here or there. the 3200mhz hynix corsair refused to boot at all. all on a asus x570 tuf. different bios did have different levels of stability. older version my 3600mhz could boot 90% of the time. newer one was no different than my 3200 hynix kit. then i picked up a micron based, crucial 3200mhz kit and its been smooth sailing. my buddy with a 3950x has a gskill 3600mhz micron based with no problems too. your symptoms sound like ram man. older bios could be more stable with xmp. the linux kernel issue could be whatever changes made in the newer causes the stability to last longer. sooner or later it will probably be unstable in something.

Last edited by orlfman (2020-03-11 08:28:27)

Offline

Board footer

Powered by FluxBB