Address various issues mentioned by diizzy@

Address issued mentioned by fuz@

In D52968#1234451, @markj wrote:

I see, I missed a chunk of the patch. I uploaded a new version, could you please retest?

In D52968#1234439, @markj wrote:

Could you please show the output of procstat -kk $(pgrep bhyve) while the hang is happening?

In D52968#1229309, @markj wrote:

Apologies for the delay, here's a backport to stable/14: https://people.freebsd.org/~markj/patches/0001-vmm-Fix-a-deadlock-between-vm_smp_rendezvous-and-vcp.patch

Please give it a try and let me know whether it helps (or even makes things worse).

In D52968#1225880, @markj wrote:

Well, that commit is a random whitespace change... and the fix for the deadlock is not in stable/14 at all. I will try to backport it if you can test the resulting patch.

In D52968#1225867, @markj wrote:

Then you don't have the patch at all?

In D52968#1225836, @markj wrote:

What are you testing exactly? The commit that went into the src tree, or a hand-applied patch from this revision?

Can you guys confirm that 300a8977bcfd2f43bc6df81d9bdad6b79a740729 fixes the Windows 11 passthru boot-stuck issue?
D52781 was actually working for me. However, this patch (D52968) results in the same symptoms for me: Windows 11 gets stuck during boot when attempting to passthru a PCIe device.

@corvink Let me know once you'd like me to test the patch again on my machine where I can reliably reproduce the issue.

In D52781#1208610, @jon_xyinn.org wrote:

before I got my first "WHEA_UNCORRECTABLE_ERROR" crash.

I just left a comment in D52781 - seems to work on my end!

I have tested this patch on stable/14 (specifically, d0e8c94631267f07c90465faf5b47dcce0e232be) and I was finally able to pass through a PCIe device to my Windows 11 guest without it locking up during boot.