[Bug 293382] Dead lock and kernel crash around closefp_impl

From: <bugzilla-noreply_at_freebsd.org>
Date: Thu, 16 Apr 2026 23:41:35 UTC
https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=293382

--- Comment #86 from Konstantin Belousov <kib@FreeBSD.org> ---
(In reply to Kyle Evans from comment #84)
Again to my amusement, there is a very close errata
1455 PCID-Based INVLPGB May Fail to Flush Global Translations
but not quite.  We do not specify PCID for global invalidation.

Otherwise I do not see anything wrong with the code and description.
But indeed, the formulation "to increment the virtual address at the 2M
boundary"
sounds strange.  Why not say plain "to increment the virtual address by 2M"?
Is there some english language nuance that I miss?

-- 
You are receiving this mail because:
You are the assignee for the bug.