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;
Date:   Thu, 16 Jun 2022 12:00:57 +0200
From:   Peter Zijlstra <peterz@infradead.org>
To:     "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Cc:     Dave Hansen <dave.hansen@linux.intel.com>,
        Andy Lutomirski <luto@kernel.org>, x86@kernel.org,
        Kostya Serebryany <kcc@google.com>,
        Andrey Ryabinin <ryabinin.a.a@gmail.com>,
        Andrey Konovalov <andreyknvl@gmail.com>,
        Alexander Potapenko <glider@google.com>,
        Dmitry Vyukov <dvyukov@google.com>,
        "H . J . Lu" <hjl.tools@gmail.com>,
        Andi Kleen <ak@linux.intel.com>,
        Rick Edgecombe <rick.p.edgecombe@intel.com>,
        linux-mm@kvack.org, linux-kernel@vger.kernel.org
Subject: Re: [PATCHv3 OPTIONAL 8/8] x86/mm: Extend LAM to support to LAM_U48
Message-ID: <Yqr/WdgRb1IEDMVk@hirez.programming.kicks-ass.net>
References: <20220610143527.22974-1-kirill.shutemov@linux.intel.com>
 <20220610143527.22974-9-kirill.shutemov@linux.intel.com>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <20220610143527.22974-9-kirill.shutemov@linux.intel.com>
Precedence: bulk

On Fri, Jun 10, 2022 at 05:35:27PM +0300, Kirill A. Shutemov wrote:
> LAM_U48 allows to encode 15 bits of tags into address.
> 
> LAM_U48 steals bits above 47-bit for tags and makes it impossible for
> userspace to use full address space on 5-level paging machine.
> 
> Make these features mutually exclusive: whichever gets enabled first
> blocks the other one.

This patch is broken in that it doesn't fix untag_pointer()

*If* you really want to continue down this road; you'll need something
like:

#define untagged_addr(mm, addr)        ({                              \
       u64 __addr = (__force u64)(addr);                               \
       s64 sign = (s64)__addr >> 63;                                   \
       __addr ^= sign;                                                 \
       __addr &= (mm)->context.untag_mask[sign & 1];                   \
       __addr ^= sign;                                                 \
       (__force __typeof__(addr))__addr;                               \
})

Which uses a different mask for kernel and user pointers.

Anyway, without this U48 patch on, the mask could be a constant, no need
to keep this variable, we can unconditionally unmask U57.

Let me go reply to that other mail too.