Re: NVIDIA / Mellanox ConnectX-6 Lx support

2023-09-06 Thread Jonathan Gray
On Wed, Sep 06, 2023 at 05:38:28PM +0200, Olivier Croquin wrote: > Hi, > > recently, we have bought servers with Mellanox Ethernet Adaptors of the > MT2894 > Family [ConnectX‑6 Lx] : > - OCP3 form factor : MCX631432AS-ADAI > - PCIe form factor : MCX631102AS-ADAT > > We want to run OpenBSD on

Re: Use counters_read(9) from ddb(4)

2023-09-06 Thread Alexander Bluhm
On Wed, Sep 06, 2023 at 12:23:33PM -0500, Scott Cheloha wrote: > On Wed, Sep 06, 2023 at 01:04:19PM +0100, Martin Pieuchot wrote: > > Debugging OOM is hard. UVM uses per-CPU counters and sadly > > counters_read(9) needs to allocate memory. This is not acceptable in > > ddb(4). As a result I

Re: Use counters_read(9) from ddb(4)

2023-09-06 Thread Klemens Nanni
On Wed, Sep 06, 2023 at 12:23:33PM -0500, Scott Cheloha wrote: > On Wed, Sep 06, 2023 at 01:04:19PM +0100, Martin Pieuchot wrote: > > Debugging OOM is hard. UVM uses per-CPU counters and sadly > > counters_read(9) needs to allocate memory. This is not acceptable in > > ddb(4). As a result I

Re: vmd/vmm: remove an ioctl from the vcpu hotpath, go brrr

2023-09-06 Thread Mischa
On 2023-09-06 19:38, Dave Voutila wrote: Mischa writes: On 2023-09-06 05:36, Dave Voutila wrote: Mischa writes: On 2023-09-05 14:27, Dave Voutila wrote: Mike Larkin writes: On Mon, Sep 04, 2023 at 07:57:18PM +0200, Mischa wrote: On 2023-09-04 18:58, Mischa wrote: > On 2023-09-04 18:55,

Re: vmd/vmm: remove an ioctl from the vcpu hotpath, go brrr

2023-09-06 Thread Dave Voutila
Mischa writes: > On 2023-09-06 05:36, Dave Voutila wrote: >> Mischa writes: >>> On 2023-09-05 14:27, Dave Voutila wrote: Mike Larkin writes: > On Mon, Sep 04, 2023 at 07:57:18PM +0200, Mischa wrote: >> On 2023-09-04 18:58, Mischa wrote: >> > On 2023-09-04 18:55, Mischa

Re: Use counters_read(9) from ddb(4)

2023-09-06 Thread Scott Cheloha
On Wed, Sep 06, 2023 at 01:04:19PM +0100, Martin Pieuchot wrote: > Debugging OOM is hard. UVM uses per-CPU counters and sadly > counters_read(9) needs to allocate memory. This is not acceptable in > ddb(4). As a result I cannot see the content of UVM counters in OOM > situations. > > Diff

Re: vmd/vmm: remove an ioctl from the vcpu hotpath, go brrr

2023-09-06 Thread Mischa
On 2023-09-06 05:36, Dave Voutila wrote: Mischa writes: On 2023-09-05 14:27, Dave Voutila wrote: Mike Larkin writes: On Mon, Sep 04, 2023 at 07:57:18PM +0200, Mischa wrote: On 2023-09-04 18:58, Mischa wrote: > On 2023-09-04 18:55, Mischa wrote: /snip > > Adding the sleep 2 does indeed

NVIDIA / Mellanox ConnectX-6 Lx support

2023-09-06 Thread Olivier Croquin
Hi, recently, we have bought servers with Mellanox Ethernet Adaptors of the MT2894 Family [ConnectX‑6 Lx] : - OCP3 form factor : MCX631432AS-ADAI - PCIe form factor : MCX631102AS-ADAT We want to run OpenBSD on those servers. But, looking at the source code, we figured out that the MT2894

Re: bsd.port.mk.5: Ev for NO_ARCH

2023-09-06 Thread Ingo Schwarze
Hi Caspar, Caspar Schutijser wrote on Wed, Sep 06, 2023 at 01:46:45PM +0200: > The patch below marks up "NO_ARCH" consistently with the other > variables. I noticed because on man.openbsd.org, NO_ARCH looks off > compared to the others: > https://man.openbsd.org/bsd.port.mk.5#MULTI_PACKAGES

Re: Add Intel Optane P1600X to pcidevs

2023-09-06 Thread Jonathan Gray
On Sun, Sep 03, 2023 at 03:08:13PM +0200, Andreas Bartelt wrote: > Hi, > > forgot to include the corresponding dmesg output: > nvme1 at pci20 dev 0 function 0 "Intel P1600X" rev 0x00: msix, NVMe 1.1 > nvme1: INTEL SSDPEK1A118GA, firmware U5110550, serial BTOC14120X9P118B > > Could this please be

Use counters_read(9) from ddb(4)

2023-09-06 Thread Martin Pieuchot
Debugging OOM is hard. UVM uses per-CPU counters and sadly counters_read(9) needs to allocate memory. This is not acceptable in ddb(4). As a result I cannot see the content of UVM counters in OOM situations. Diff below introduces a *_static() variant of counters_read(9) that takes a secondary

bsd.port.mk.5: Ev for NO_ARCH

2023-09-06 Thread Caspar Schutijser
Hi, The patch below marks up "NO_ARCH" consistently with the other variables. I noticed because on man.openbsd.org, NO_ARCH looks off compared to the others: https://man.openbsd.org/bsd.port.mk.5#MULTI_PACKAGES Comments or OKs? Caspar Index: bsd.port.mk.5

wsdisplay: disable keyboard backlight with screen burner

2023-09-06 Thread Tobias Heider
Hi, the diff below disables and restores the keyboard backlight together with the screen on idle timeout to save a bit of battery. ok? diff 848795b17df6d7aac8fe7242132657e294ce39df 0bb6b11cdeac4d4755e336594acf830b859e9d34 commit - 848795b17df6d7aac8fe7242132657e294ce39df commit +

Re: riscv64 possible alignment issue?

2023-09-06 Thread Peter J. Philipp
On Tue, Sep 05, 2023 at 11:40:42PM +0200, Peter J. Philipp wrote: > Hi, > > I'm porting OpenBSD to the Mango Pi D1. Most of the work is done but now > is the time to try to get a RAMDISK kernel to boot. > > I'm having an issue with atomic_store_64() as shown here (line 1192): > >1184