linux-kernel - Re: [PATCH] KVM: Remove duplicated zero clear with dirty

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <5a2b21ce-2554-4ee8-bff1-76231ea77703@redhat.com>
Date: Thu, 20 Jun 2024 23:17:58 +0200
From: Paolo Bonzini <pbonzini@...hat.com>
To: maobibo <maobibo@...ngson.cn>,
 Christophe JAILLET <christophe.jaillet@...adoo.fr>
Cc: kvm@...r.kernel.org, linux-kernel@...r.kernel.org
Subject: Re: [PATCH] KVM: Remove duplicated zero clear with dirty_bitmap
 buffer

On 6/14/24 04:45, maobibo wrote:
> I do not know whether KVM_DIRTY_LOG_INITIALLY_SET should be enabled on 
> LoongArch. If it is set, write protection for second MMU will start one 
> by one in function kvm_arch_mmu_enable_log_dirty_pt_masked() when dirty 
> log is cleared if it is set, else write protection will start in 
> function kvm_arch_commit_memory_region() when flag of memslot is changed.
> 
> I do not see the obvious benefits between these two write protect 
> stages. Can anyone give me any hints?

The advantage is that you get (a lot) fewer vmexits to set the dirty 
bitmap, and that write protection is not done in a single expensive 
step.  Instead it is done at the time that userspace first clears the 
bits in the dirty bitmap.  It provides much better performance.

Paolo