Re: [RFC PATCH 2/3] x86/mm: make sure LAM is up-to-date during context switching

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

To: Yosry Ahmed <yosryahmed@xxxxxxxxxx>
Subject: Re: [RFC PATCH 2/3] x86/mm: make sure LAM is up-to-date during context switching
From: "Kirill A. Shutemov" <kirill.shutemov@xxxxxxxxxxxxxxx>
Date: Sat, 9 Mar 2024 18:34:38 +0200
Cc: Dave Hansen <dave.hansen@xxxxxxxxx>, Andy Lutomirski <luto@xxxxxxxxxx>, Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>, Thomas Gleixner <tglx@xxxxxxxxxxxxx>, Ingo Molnar <mingo@xxxxxxxxxx>, Borislav Petkov <bp@xxxxxxxxx>, "Peter Zijlstra (Intel)" <peterz@xxxxxxxxxxxxx>, the arch/x86 maintainers <x86@xxxxxxxxxx>, linux-mm@xxxxxxxxx, Linux Kernel Mailing List <linux-kernel@xxxxxxxxxxxxxxx>
In-reply-to: <ZevHJ5o3G00_nBha@google.com>
References: <20240307133916.3782068-1-yosryahmed@google.com> <20240307133916.3782068-3-yosryahmed@google.com> <420fcb06-c3c3-4e8f-a82d-be2fb2ef444d@app.fastmail.com> <35b670e2-9ef5-4d3a-b6ea-f8016dfa088d@intel.com> <ZevHJ5o3G00_nBha@google.com>

On Sat, Mar 09, 2024 at 02:19:19AM +0000, Yosry Ahmed wrote:
> I don't see how skipping set_tlbstate_lam_mode() for kthreads fixes this
> problem. Do you mind elaborating?

Define what problem is.

Yes, in this scenario kthread gets more permissive LAM mode than it needs.
But nothing breaks.

-- 
  Kiryl Shutsemau / Kirill A. Shutemov

Follow-Ups:
- Re: [RFC PATCH 2/3] x86/mm: make sure LAM is up-to-date during context switching
  - From: Yosry Ahmed

References:
- [RFC PATCH 0/3] x86/mm: LAM fixups and cleanups
  - From: Yosry Ahmed
- [RFC PATCH 2/3] x86/mm: make sure LAM is up-to-date during context switching
  - From: Yosry Ahmed
- Re: [RFC PATCH 2/3] x86/mm: make sure LAM is up-to-date during context switching
  - From: Andy Lutomirski
- Re: [RFC PATCH 2/3] x86/mm: make sure LAM is up-to-date during context switching
  - From: Dave Hansen
- Re: [RFC PATCH 2/3] x86/mm: make sure LAM is up-to-date during context switching
  - From: Yosry Ahmed

Prev by Date: Re: vm_area at addr ffffffffc0800000 is not marked as VM_IOREMAP
Next by Date: BUG selftests/mm]
Previous by thread: Re: [RFC PATCH 2/3] x86/mm: make sure LAM is up-to-date during context switching
Next by thread: Re: [RFC PATCH 2/3] x86/mm: make sure LAM is up-to-date during context switching
Index(es):
- Date
- Thread

[Index of Archives] [Linux ARM Kernel] [Linux ARM] [Linux Omap] [Fedora ARM] [IETF Annouce] [Bugtraq] [Linux OMAP] [Linux MIPS] [eCos] [Asterisk Internet PBX] [Linux API]