Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18;
Subject: Re: [RFC][PATCH v2 12/21] x86/pti: Use PTI stack instead of
 trampoline stack
To:     Andy Lutomirski <luto@kernel.org>
Cc:     Thomas Gleixner <tglx@linutronix.de>,
        Ingo Molnar <mingo@redhat.com>, Borislav Petkov <bp@alien8.de>,
        "H. Peter Anvin" <hpa@zytor.com>, X86 ML <x86@kernel.org>,
        Dave Hansen <dave.hansen@linux.intel.com>,
        Peter Zijlstra <peterz@infradead.org>,
        LKML <linux-kernel@vger.kernel.org>,
        Tom Lendacky <thomas.lendacky@amd.com>,
        Joerg Roedel <jroedel@suse.de>,
        Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>,
        jan.setjeeilers@oracle.com, Junaid Shahid <junaids@google.com>,
        oweisse@google.com, Mike Rapoport <rppt@linux.vnet.ibm.com>,
        Alexander Graf <graf@amazon.de>, mgross@linux.intel.com,
        kuzuno@gmail.com
References: <20201116144757.1920077-1-alexandre.chartre@oracle.com>
 <20201116144757.1920077-13-alexandre.chartre@oracle.com>
 <CALCETrUSCwtR41CCo_cAQf_BwG7istH6fM=bxWh_VfOjSNFmSw@mail.gmail.com>
 <bc8a254e-deaa-388e-99ea-0291f5625b5b@oracle.com>
 <CALCETrUJQJRi6fE=bs3iAySgM8wjmGU1f464FqOuU+PiBwwnQQ@mail.gmail.com>
From:   Alexandre Chartre <alexandre.chartre@oracle.com>
Message-ID: <93d1f346-7513-069f-dcd9-24f2ea009145@oracle.com>
Date:   Mon, 16 Nov 2020 20:37:03 +0100
User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:68.0) Gecko/20100101
 Thunderbird/68.12.0
MIME-Version: 1.0
In-Reply-To: <CALCETrUJQJRi6fE=bs3iAySgM8wjmGU1f464FqOuU+PiBwwnQQ@mail.gmail.com>
Content-Type: text/plain; charset=utf-8; format=flowed
Content-Language: en-US
Content-Transfer-Encoding: 7bit
Precedence: bulk


On 11/16/20 7:34 PM, Andy Lutomirski wrote:
> On Mon, Nov 16, 2020 at 10:10 AM Alexandre Chartre
> <alexandre.chartre@oracle.com> wrote:
>>
>>
>> On 11/16/20 5:57 PM, Andy Lutomirski wrote:
>>> On Mon, Nov 16, 2020 at 6:47 AM Alexandre Chartre
>>> <alexandre.chartre@oracle.com> wrote:
>>>>
>>>> When entering the kernel from userland, use the per-task PTI stack
>>>> instead of the per-cpu trampoline stack. Like the trampoline stack,
>>>> the PTI stack is mapped both in the kernel and in the user page-table.
>>>> Using a per-task stack which is mapped into the kernel and the user
>>>> page-table instead of a per-cpu stack will allow executing more code
>>>> before switching to the kernel stack and to the kernel page-table.
>>>
>>> Why?
>>
>> When executing more code in the kernel, we are likely to reach a point
>> where we need to sleep while we are using the user page-table, so we need
>> to be using a per-thread stack.
>>
>>> I can't immediately evaluate how nasty the page table setup is because
>>> it's not in this patch.
>>
>> The page-table is the regular page-table as introduced by PTI. It is just
>> augmented with a few additional mapping which are in patch 11 (x86/pti:
>> Extend PTI user mappings).
>>
>>>   But AFAICS the only thing that this enables is sleeping with user pagetables.
>>
>> That's precisely the point, it allows to sleep with the user page-table.
>>
>>> Do we really need to do that?
>>
>> Actually, probably not with this particular patchset, because I do the page-table
>> switch at the very beginning and end of the C handler. I had some code where I
>> moved the page-table switch deeper in the kernel handler where you definitively
>> can sleep (for example, if you switch back to the user page-table before
>> exit_to_user_mode_prepare()).
>>
>> So a first step should probably be to not introduce the per-task PTI trampoline stack,
>> and stick with the existing trampoline stack. The per-task PTI trampoline stack can
>> be introduced later when the page-table switch is moved deeper in the C handler and
>> we can effectively sleep while using the user page-table.
> 
> Seems reasonable.
> 
> Where is the code that allocates and frees these stacks hiding?  I
> think I should at least read it.

Stacks are allocated/freed with the task stack, this code is unchanged (see
alloc_thread_stack_node()). The trick is that I have doubled the THREAD_SIZE
(patch 8 "x86/pti: Introduce per-task PTI trampoline stack"). Half the stack
is a used as the kernel stack (mapped only in the kernel page-table), the
other half is used as the PTI stack (mapped in the kernel and user page-table).
The mapping to the user page-table is done in mm_map_task() in fork.c (patch 11
"x86/pti: Extend PTI user mappings").

alex.