[<prev] [next>] [<thread-prev] [day] [month] [year] [list]
Message-ID: <baf4fd6c-1796-47cb-a9bb-72521a217453@vasilevsky.ca>
Date: Sat, 8 Nov 2025 17:24:44 -0500
From: Dave Vasilevsky <dave@...ilevsky.ca>
To: "Ritesh Harjani (IBM)" <ritesh.list@...il.com>,
Madhavan Srinivasan <maddy@...ux.ibm.com>,
Michael Ellerman <mpe@...erman.id.au>, Nicholas Piggin <npiggin@...il.com>,
Christophe Leroy <christophe.leroy@...roup.eu>,
Nadav Amit <nadav.amit@...il.com>,
"Peter Zijlstra (Intel)" <peterz@...radead.org>,
Andrew Morton <akpm@...ux-foundation.org>
Cc: linuxppc-dev@...ts.ozlabs.org, linux-kernel@...r.kernel.org,
stable@...r.kernel.org, linux-mm@...ck.org
Subject: Re: [PATCH] powerpc: Fix mprotect on book3s32
On 2025-11-08 14:16, Ritesh Harjani wrote:
> Shouldn't we flush all if we get tlb_flush request for full mm? e.g.
> Something like this maybe?
>
> +void hash__tlb_flush(struct mmu_gather *tlb)
> +{
> + if (tlb->fullmm || tlb->need_flush_all)
> + hash__flush_tlb_mm(tlb->mm);
> + else
> + hash__flush_range(tlb->mm, tlb->start, tlb->end);
> +}
That seems reasonable, I should be able to test it next by next
weekend and re-submit.
> Thanks again for pointing this out. How did you find this though?
> What hardware do you use?
I'm on an iBook G3 from 2001, running Arch Power:
https://archlinuxpower.org/. I found the bug because SheepShaver has a
configure test for mprotect, which was failing--I was quite surprised!
The bug reproduces easily on qemu (with the `mac99` machine), if you'd
like to try yourself.
-Dave
Powered by blists - more mailing lists