Hi,
same here on Dell PowerEdge R6615 with the debusine kernel build:
Okt 03 23:07:44 kernel: bnxt_en 0000:c3:00.0: AMD-Vi: Event logged
[IO_PAGE_FAULT domain=0x000b address=0xf23b0000 flags=0x0000]
Okt 03 23:07:44 kernel: bnxt_en 0000:c3:00.1 linkB: Fatal firmware reset
event, data1: 0x201, data2: 0xda27, min wait 1300 ms, max wait 4200 ms
Okt 03 23:07:44 kernel: bnxt_en 0000:c3:00.0 linkA: Abandoning msg {0x23
0x90ab} len: 0 due to firmware status: 0x2000001
Okt 03 23:07:44 kernel: bnxt_en 0000:c3:00.0 linkA: Abandoning msg {0xb4
0x90ac} len: 0 due to firmware status: 0x2000001
Okt 03 23:07:45 kernel: bnxt_en 0000:c3:00.1 linkB: Device requests max
timeout of 100 seconds, may trigger hung task watchdog (kernel default 120s)
Okt 03 23:07:45 kernel: bnxt_en 0000:c3:00.1 linkB: NIC Link is Down
Okt 03 23:07:46 kernel: bnxt_en 0000:c3:00.0 linkA: Abandoning msg {0x23
0x90af} len: 0 due to firmware status: 0x2000001
Okt 03 23:07:46 kernel: bnxt_en 0000:c3:00.0 linkA: Abandoning msg {0xb4
0x90b0} len: 0 due to firmware status: 0x2000001
Okt 03 23:07:46 kernel: bnxt_en 0000:c3:00.1 linkB: NIC Link is Up, 25000
Mbps (NRZ) full duplex, Flow control: none
Okt 03 23:07:46 kernel: bnxt_en 0000:c3:00.1 linkB: FEC autoneg off
encoding: None
Okt 03 23:07:47 kernel: bnxt_en 0000:c3:00.0 linkA: Abandoning msg {0x23
0x90b1} len: 0 due to firmware status: 0x2000001
Okt 03 23:07:47 kernel: bnxt_en 0000:c3:00.0 linkA: Abandoning msg {0xb4
0x90b2} len: 0 due to firmware status: 0x2000001
[...]
Okt 04 04:47:40 kernel: bnxt_en 0000:c3:00.1: AMD-Vi: Event logged
[IO_PAGE_FAULT domain=0x000c address=0xf6c4f000 flags=0x0000]
Okt 04 04:47:41 kernel: bnxt_en 0000:c3:00.1 linkB: hwrm req_type 0x23 seq
id 0x9575 error 0xf
Okt 04 04:47:41 kernel: bnxt_en 0000:c3:00.1 linkB: hwrm req_type 0xb4 seq
id 0x9576 error 0xf
Okt 04 04:47:42 kernel: bnxt_en 0000:c3:00.1 linkB: Abandoning msg {0x23
0x9577} len: 0 due to firmware status: 0x2000001
Okt 04 04:47:42 kernel: bnxt_en 0000:c3:00.1 linkB: Abandoning msg {0xb4
0x9578} len: 0 due to firmware status: 0x2000001
Okt 04 04:47:43 kernel: bnxt_en 0000:c3:00.1 linkB: Abandoning msg {0x23
0x9579} len: 0 due to firmware portstatus: 0x2000001
What I can see here: when the first NIC dies, the second NIC briefly resets
as well, only to then die completely a few hours later.
System boot was at 19:59 (all timestamps local time), so it took ~ 3 hours
for the first NIC and almost 9 hours for the second.
Cheers,
Rudi
Am So., 4. Okt. 2026 um 00:01 Uhr schrieb Bernhard Schmidt <[email protected]
>:
> On 03/10/26 04:34 PM, Salvatore Bonaccorso wrote:
> > >
> > > > v6.18.53: c8050386a2209b2a474c1eb4bd1574dc19129bfb bnxt_en:
> Propagate TPA buffer allocation failures in bnxt_queue_mem_alloc()
> > > > v7.2.7: 37e08dc821a57fe0592c917486b638caa888b46d bnxt_en: Propagate
> TPA buffer allocation failures in bnxt_queue_mem_alloc()
> > > > v7.3-rc3: b814dfbfeb0a68c9a52073f2caa05a2d5247a329 bnxt_en:
> Propagate TPA buffer allocation failures in bnxt_queue_mem_alloc()
> > > >
> > > > -> this one was not backported to 6.11.y, but looks fine as the code
> > > > was only introduced in v6.13-rc2 (and backported to v6.12.20).
> > >
> > > And now this still got backported to the v6.12.112 released today.
> > >
> > > > v6.18.53: 8ade95619cbfd1fc57f0f1a9a5ebdca2345a8d27 bnxt_en: Don't
> free the live ring's TPA state on queue restart failure
> > > > v7.2.7: 0596a7caa6fc283e142716739099c038d8714082 bnxt_en: Don't free
> the live ring's TPA state on queue restart failure
> > > > v7.3-rc3: 5ce7f36c334d723954855ac769ede2fe0e8f89c8 bnxt_en: Don't
> free the live ring's TPA state on queue restart failure
> > > >
> > > > Same as above.
> > >
> > > And this as well
> > >
> > > Aurelien, Bernhard, while I'm working on importing and rebasing
> > > 6.12.112 for the next update in trixie, would it be possible you pick
> > > those two commits on top to see if they fix the problem? (It might
> > > though be possible they do not apply clieanly without more depending
> > > fixes which were included in 6.12.112).
> > >
> > > If that will not work I can provide you preliminary builds somehwere
> > > for 6.12.112 instread.
> >
> > Unofficial builds for the unsigned images will appear trough:
> > https://debusine.debian.net/debian/developers/work-request/1411088/
> > (that is a version without debian/changelog cleanup et al).
>
> Took about an hour, but still crashed :-(
>
> Oct 03 22:43:51 nm3 kernel: Linux version 6.12+unreleased-amd64 (
> [email protected]) (x86_64-linux-gnu-gcc-14 (Debian
> 14.2.0-19) 14.2.0, GNU ld (GNU Binutils for Debian) 2.44) #1 SMP
> PREEMPT_DYNAMIC Debian 6.12.112->
> Oct 03 22:43:51 nm3 kernel: Command line:
> BOOT_IMAGE=/boot/vmlinuz-6.12+unreleased-amd64 root=/dev/mapper/sysvg-root
> ro quiet
> [...]
> Oct 03 23:47:24 nm3 kernel: DMAR: DRHD: handling fault status reg 2
> Oct 03 23:47:24 nm3 kernel: DMAR: [DMA Read NO_PASID] Request device
> [19:00.0] fault addr 0xde00b000 [fault reason 0x06] PTE Read access is not
> set
> Oct 03 23:47:24 nm3 kernel: bnxt_en 0000:19:00.1 eno2np1: Fatal firmware
> reset event, data1: 0x201, data2: 0xda27, min wait 1300 ms, max wait 4200 ms
> Oct 03 23:47:24 nm3 systemd-networkd[1237]: eno2np1: Lost carrier
> Oct 03 23:47:24 nm3 kernel: bond0: (slave eno2np1): link status definitely
> down, disabling slave
> Oct 03 23:47:25 nm3 kernel: bnxt_en 0000:19:00.0 eno1np0: Abandoning msg
> {0x23 0x2c5b} len: 0 due to firmware status: 0x2000001
> Oct 03 23:47:25 nm3 kernel: bnxt_en 0000:19:00.0 eno1np0: Abandoning msg
> {0xb4 0x2c5c} len: 0 due to firmware status: 0x2000001
>
> I still don't get why my bisection attempt failed so badly,
> 6.12.111-stable (the one compiled from the kernel.org stable tree
> following your bisection instructions) has been running for 36+ hours
> before I voluntarily rebooted into your 6.12.112 kernel.
>
> Bernhard
>
> --
> To unsubscribe, send mail to [email protected].
>
--
Rudolph Bott - [email protected]
Telefon: +49 (0)211-63 55 55-55
Telefax: +49 (0)211-63 55 55-22
sipgate GmbH - Gladbacher Str. 74 - 40219 Düsseldorf
HRB Düsseldorf 39841 - Geschäftsführer: Thilo Salmon, Tim Mois
Steuernummer: 106/5724/7147, Umsatzsteuer-ID: DE219349391
www.sipgate.de - www.sipgate.co.uk
