Re: wired memory leak?

[Greg Troxel <gdt%lexort.com@localhost>]

Manuel Bouyer <bouyer%antioche.eu.org@localhost> writes:

> My laptop has this CPU:
> cpu0: "Intel(R) Core(TM) i5-7200U CPU @ 2.50GHz"
> cpu0: Intel 7th or 8th gen Core (Kaby Lake, Coffee Lake) or Xeon E (Coffee Lake) (686-class), 2712.00 MHz
> cpu0: CPU base freq 2700000000 Hz
> cpu0: CPU max freq 3100000000 Hz
> cpu0: TSC freq CPUID 2712000000 Hz
> cpu0: family 0x6 model 0x8e stepping 0x9 (id 0x806e9)
>
> This is the same generation as my workstation, but not exactly the
> same graphics. On my workstation:
> pchb0 at pci0 dev 0 function 0: Intel Core 8G (S) Host Bridge, DRAM (rev. 0x07)
> i915drmkms0 at pci0 dev 2 function 0: Intel UHD Graphics 630 (rev. 0x00)
>
> and on my laptop:
> pchb0 at pci0 dev 0 function 0: Intel Core 7G (U) Host Bridge, DRAM (rev. 0x02)
> i915drmkms0 at pci0 dev 2 function 0: Intel HD Graphics 620 (GT2) (rev. 0x02)

My desktop has the wired growth problem, and

  cpu0: "Intel(R) Core(TM) i7-9700 CPU @ 3.00GHz"
  cpu0: Intel 7th or 8th gen Core (Kaby Lake, Coffee Lake) or Xeon E (Coffee Lake) (686-class), 3000.00 MHz
  cpu0: CPU base freq 3000000000 Hz
  cpu0: CPU max freq 4700000000 Hz
  cpu0: TSC freq CPUID 3000000000 Hz
  cpu0: family 0x6 model 0x9e stepping 0xd (id 0x906ed)

  pchb0 at pci0 dev 0 function 0: Intel Xeon E (S, Desktop) Host Bridge, DRAM (rev. 0x0d)
  i915drmkms0 at pci0 dev 2 function 0: Intel UHD Graphics 630 (rev. 0x02)

The "UHD Graphics 630" is an exact match.  My CPU is 9th generation vs
7th, and i7 vs i5.   I'm guessing the bug is in code specific to UHD
Graphics 630.

Does anybody have a machine where the following two theories are falsified?

  On NetBSD 11 with base system X, Intel UHD Graphics 630 with glxgears
  or firefox leads to unrecoverable wired pages growth.  On NetBSD 10,
  there is no problem.

  Other kinds of graphics leads to no observed wired pages growth.