Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
MIME-Version: 1.0
References: <20220712231328.5294-6-kirill.shutemov@linux.intel.com> <20220713150200.17080-1-kirill.shutemov@linux.intel.com>
In-Reply-To: <20220713150200.17080-1-kirill.shutemov@linux.intel.com>
From:   Alexander Potapenko <glider@google.com>
Date:   Wed, 20 Jul 2022 10:57:01 +0200
Message-ID: <CAG_fn=VVBOe8cvbWSMLfJf577yirThABQOMmihNW4pg55Sfhfg@mail.gmail.com>
Subject: Re: [PATCHv5.1 04/13] x86/mm: Handle LAM on context switch
To:     "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Cc:     Andi Kleen <ak@linux.intel.com>,
        Andrey Konovalov <andreyknvl@gmail.com>,
        Dave Hansen <dave.hansen@linux.intel.com>,
        Dmitriy Vyukov <dvyukov@google.com>,
        "H.J. Lu" <hjl.tools@gmail.com>,
        Kostya Serebryany <kcc@google.com>,
        LKML <linux-kernel@vger.kernel.org>,
        Linux Memory Management List <linux-mm@kvack.org>,
        Andy Lutomirski <luto@kernel.org>,
        Peter Zijlstra <peterz@infradead.org>,
        Rick Edgecombe <rick.p.edgecombe@intel.com>,
        Andrey Ryabinin <ryabinin.a.a@gmail.com>,
        Taras Madan <tarasmadan@google.com>,
        "the arch/x86 maintainers" <x86@kernel.org>
Content-Type: text/plain; charset="UTF-8"
Precedence: bulk

>         /*
> @@ -491,6 +493,8 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
>  {
>         struct mm_struct *real_prev = this_cpu_read(cpu_tlbstate.loaded_mm);
>         u16 prev_asid = this_cpu_read(cpu_tlbstate.loaded_mm_asid);
> +       unsigned long prev_lam = tlbstate_lam_cr3_mask();
Note: this variable is never used if CONFIG_DEBUG_VM is off.

>  #ifdef CONFIG_DEBUG_VM
> -       if (WARN_ON_ONCE(__read_cr3() != build_cr3(real_prev->pgd, prev_asid))) {
> +       if (WARN_ON_ONCE(__read_cr3() != build_cr3(real_prev->pgd, prev_asid, prev_lam))) {
>                 /*
>                  * If we were to BUG here, we'd be very likely to kill
>                  * the system so hard that we don't see the call trace.