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:   Tue, 5 Jul 2022 13:11:16 +0100
From:   Will Deacon <will@kernel.org>
To:     "guanghui.fgh" <guanghuifeng@linux.alibaba.com>
Cc:     Ard Biesheuvel <ardb@kernel.org>, baolin.wang@linux.alibaba.com,
        catalin.marinas@arm.com, akpm@linux-foundation.org,
        david@redhat.com, jianyong.wu@arm.com, james.morse@arm.com,
        quic_qiancai@quicinc.com, christophe.leroy@csgroup.eu,
        jonathan@marek.ca, mark.rutland@arm.com,
        thunder.leizhen@huawei.com, anshuman.khandual@arm.com,
        linux-arm-kernel@lists.infradead.org, linux-kernel@vger.kernel.org,
        rppt@kernel.org, geert+renesas@glider.be, linux-mm@kvack.org,
        yaohongbo@linux.alibaba.com, alikernel-developer@linux.alibaba.com
Subject: Re: [PATCH v4] arm64: mm: fix linear mem mapping access performance
 degradation
Message-ID: <20220705121115.GB1012@willie-the-truck>
References: <20220704111402.GA31553@willie-the-truck>
 <4accaeda-572f-f72d-5067-2d0999e4d00a@linux.alibaba.com>
 <20220704131516.GC31684@willie-the-truck>
 <2ae1cae0-ee26-aa59-7ed9-231d67194dce@linux.alibaba.com>
 <20220704142313.GE31684@willie-the-truck>
 <6977c692-78ca-5a67-773e-0389c85f2650@linux.alibaba.com>
 <20220704163815.GA32177@willie-the-truck>
 <CAMj1kXEvY5QXOUrXZ7rBp9As=65uTTFRSSq+FPt-n4M2P-_VtQ@mail.gmail.com>
 <20220705095231.GB552@willie-the-truck>
 <5d044fdd-a61a-d60f-d294-89e17de37712@linux.alibaba.com>
MIME-Version: 1.0
Content-Type: text/plain; charset=utf-8
Content-Disposition: inline
Content-Transfer-Encoding: 8bit
In-Reply-To: <5d044fdd-a61a-d60f-d294-89e17de37712@linux.alibaba.com>
User-Agent: Mutt/1.10.1 (2018-07-13)
Precedence: bulk

On Tue, Jul 05, 2022 at 08:07:07PM +0800, guanghui.fgh wrote:
> 
> 
> 在 2022/7/5 17:52, Will Deacon 写道:
> > On Mon, Jul 04, 2022 at 07:09:23PM +0200, Ard Biesheuvel wrote:
> > > On Mon, 4 Jul 2022 at 18:38, Will Deacon <will@kernel.org> wrote:
> > > > 
> > > > On Mon, Jul 04, 2022 at 10:34:07PM +0800, guanghui.fgh wrote:
> > > > > Thanks.
> > > > > 
> > > > > 在 2022/7/4 22:23, Will Deacon 写道:
> > > > > > On Mon, Jul 04, 2022 at 10:11:27PM +0800, guanghui.fgh wrote:
> > > ...
> > > > > > > Namely, it's need to use non block/section mapping for crashkernel mem
> > > > > > > before shringking.
> > > > > > 
> > > > > > Well, yes, but we can change arch_kexec_[un]protect_crashkres() not to do
> > > > > > that if we're leaving the thing mapped, no?
> > > > > > 
> > > > > I think we should use arch_kexec_[un]protect_crashkres for crashkernel mem.
> > > > > 
> > > > > Because when invalid crashkernel mem pagetable, there is no chance to rd/wr
> > > > > the crashkernel mem by mistake.
> > > > > 
> > > > > If we don't use arch_kexec_[un]protect_crashkres to invalid crashkernel mem
> > > > > pagetable, there maybe some write operations to these mem by mistake which
> > > > > may cause crashkernel boot error and vmcore saving error.
> > > > 
> > > > I don't really buy this line of reasoning. The entire main kernel is
> > > > writable, so why do we care about protecting the crashkernel so much? The
> > > > _code_ to launch the crash kernel is writable! If you care about preventing
> > > > writes to memory which should not be writable, then you should use
> > > > rodata=full.
> > > > 
> > > 
> > > This is not entirely true - the core kernel text and rodata are
> > > remapped r/o in the linear map, whereas all module code and rodata are
> > > left writable when rodata != full.
> > 
> > Yes, sorry, you're quite right. The kernel text is only writable if
> > rodata=off.
> > 
> > But I still think it makes sense to protect the crashkernel only if
> > rodata=full (which is the default on arm64) as this allows us to rely
> > on page mappings and I think fits well with what we do for modules.
> > 
> > > But the conclusion is the same, imo: if you can't be bothered to
> > > protect a good chunk of the code and rodata that the kernel relies on,
> > > why should the crashkernel be treated any differently?
> > 
> > Thanks.
> > 
> > Will
> Thanks.
> 
> 1.The rodata full is harm to the performance and has been disabled in-house.
> 
> 2.When using crashkernel with rodata non full, the kernel also will use non
> block/section mapping which cause high d-TLB miss and degrade performance
> greatly.
> This patch fix it to use block/section mapping as far as possible.
> 
> bool can_set_direct_map(void)
> {
> 	return rodata_full || debug_pagealloc_enabled();
> }
> 
> map_mem:
> if (can_set_direct_map() || IS_ENABLED(CONFIG_KFENCE))
> 	flags |= NO_BLOCK_MAPPINGS | NO_CONT_MAPPINGS;
> 
> 3.When rodata full is disabled, crashkernel also need protect(keep
> arch_kexec_[un]protect_crashkres using).
> I think crashkernel should't depend on radata full(Maybe other architecture
> don't support radata full now).

I think this is going round in circles :/

As a first step, can we please leave the crashkernel mapped unless
rodata=full? It should be a much simpler patch to write, review and maintain
and it gives you the performance you want when crashkernel is being used.

Will