Received-SPF: pass (google.com: domain of linux-kernel+bounces-140997-linux.lists.archive=gmail.com@vger.kernel.org designates 147.75.80.249 as permitted sender) client-ip=147.75.80.249;
Message-ID: <ac5ebf6d-fbe2-4354-8a9d-8f269dfd3a1a@arm.com>
Date: Thu, 11 Apr 2024 16:37:55 +0100
Precedence: bulk
MIME-Version: 1.0
User-Agent: Mozilla Thunderbird
Subject: Re: [PATCH v2 3/4] arm64: mm: Don't remap pgtables for allocate vs
 populate
Content-Language: en-GB
To: Mark Rutland <mark.rutland@arm.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>, Will Deacon <will@kernel.org>,
 Ard Biesheuvel <ardb@kernel.org>, David Hildenbrand <david@redhat.com>,
 Donald Dutile <ddutile@redhat.com>, Eric Chanudet <echanude@redhat.com>,
 linux-arm-kernel@lists.infradead.org, linux-kernel@vger.kernel.org,
 Itaru Kitayama <itaru.kitayama@fujitsu.com>
References: <20240404143308.2224141-1-ryan.roberts@arm.com>
 <20240404143308.2224141-4-ryan.roberts@arm.com>
 <ZhffSyrqCQsMV2pG@FVFF77S0Q05N>
 <37d4c278-3780-49ce-bd7e-e8f2ff4501fd@arm.com>
 <Zhf4LqNhQFN8ezx1@FVFF77S0Q05N>
 <d9582c0e-af24-46a1-9c3e-b9dc68af20d8@arm.com>
 <ZhgA8WDkZDbYIDHg@FVFF77S0Q05N>
From: Ryan Roberts <ryan.roberts@arm.com>
In-Reply-To: <ZhgA8WDkZDbYIDHg@FVFF77S0Q05N>
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 7bit

On 11/04/2024 16:25, Mark Rutland wrote:
> On Thu, Apr 11, 2024 at 03:57:04PM +0100, Ryan Roberts wrote:
>> On 11/04/2024 15:48, Mark Rutland wrote:
>>> On Thu, Apr 11, 2024 at 02:37:49PM +0100, Ryan Roberts wrote:
>>>> On 11/04/2024 14:02, Mark Rutland wrote:
>>>>> but the logic remains fairly simple, and I suspect the overhead for late
>>>>> allocations might not matter since the bulk of late changes are non-allocating.
>>>>
>>>> Its just the fixmap overhead that remains...
>>>
>>> True; my thinking there is that almost all of the later changes are for smaller
>>> ranges than the linear map (~10s of MB vs GBs in your test data), so I'd expect
>>> the overhead of those to be dominated by the cost of mappin the linear map.
>>>
>>> The only big exception is arch_add_memory(), but memory hotplug is incredibly
>>> rare, and we're not making it massively slower than it already was...
>>
>> What about something like coco guest mem (or whatever its called). Isn't that
>> scrubbed out of the linear map? So if a coco VM is started with GBs of memory,
>> could that be a real case we want to optimize?
> 
> I think that's already handled -- the functions we have to carve portions out
> of the linear map use apply_to_page_range(), which doesn't use the fixmap. See
> set_memory_*() and set_direct_map_*() in arch/arm64/mm/pageattr.c.

Ahh gottya. Yet another table walker :)

> 
> Note that apply_to_page_range() does what its name implies and *only* handles
> mappings at page granularity. Hence not using that for
> mark_linear_text_alias_ro() and mark_rodata_ro() which need to be able to
> handle blocks.
> 
> Mark.