Received-SPF: pass (google.com: domain of linux-kernel+bounces-199203-linux.lists.archive=gmail.com@vger.kernel.org designates 2604:1380:45e3:2400::1 as permitted sender) client-ip=2604:1380:45e3:2400::1;
Message-ID: <d650c29b-129f-4fac-9a9d-ea1fbdae2c3a@intel.com>
Date: Mon, 3 Jun 2024 06:23:46 -0700
Precedence: bulk
MIME-Version: 1.0
User-Agent: Mozilla Thunderbird
Subject: Re: [PATCH v11 09/12] mm: implement LUF(Lazy Unmap Flush) defering
 tlb flush when folios get unmapped
To: Byungchul Park <byungchul@sk.com>, David Hildenbrand <david@redhat.com>
Cc: Byungchul Park <lkml.byungchul.park@gmail.com>,
 linux-kernel@vger.kernel.org, linux-mm@kvack.org, kernel_team@skhynix.com,
 akpm@linux-foundation.org, ying.huang@intel.com, vernhao@tencent.com,
 mgorman@techsingularity.net, hughd@google.com, willy@infradead.org,
 peterz@infradead.org, luto@kernel.org, tglx@linutronix.de, mingo@redhat.com,
 bp@alien8.de, dave.hansen@linux.intel.com, rjgolo@gmail.com
References: <20240531092001.30428-1-byungchul@sk.com>
 <20240531092001.30428-10-byungchul@sk.com>
 <fab1dd64-c652-4160-93b4-7b483a8874da@intel.com>
 <CAHyrMpxETdVewTH3MCS4qPyD6Xf1zRUfWZf-8SCdpCFj2Pj_Wg@mail.gmail.com>
 <f17f33e8-1c1f-460f-8c5a-713476f524a3@intel.com>
 <26dc4594-430b-483c-a26c-7e68bade74b0@redhat.com>
 <20240603093505.GA12549@system.software.com>
From: Dave Hansen <dave.hansen@intel.com>
Content-Language: en-US
Autocrypt: addr=dave.hansen@intel.com; keydata=
 xsFNBE6HMP0BEADIMA3XYkQfF3dwHlj58Yjsc4E5y5G67cfbt8dvaUq2fx1lR0K9h1bOI6fC
 oAiUXvGAOxPDsB/P6UEOISPpLl5IuYsSwAeZGkdQ5g6m1xq7AlDJQZddhr/1DC/nMVa/2BoY
 2UnKuZuSBu7lgOE193+7Uks3416N2hTkyKUSNkduyoZ9F5twiBhxPJwPtn/wnch6n5RsoXsb
 ygOEDxLEsSk/7eyFycjE+btUtAWZtx+HseyaGfqkZK0Z9bT1lsaHecmB203xShwCPT49Blxz
 VOab8668QpaEOdLGhtvrVYVK7x4skyT3nGWcgDCl5/Vp3TWA4K+IofwvXzX2ON/Mj7aQwf5W
 iC+3nWC7q0uxKwwsddJ0Nu+dpA/UORQWa1NiAftEoSpk5+nUUi0WE+5DRm0H+TXKBWMGNCFn
 c6+EKg5zQaa8KqymHcOrSXNPmzJuXvDQ8uj2J8XuzCZfK4uy1+YdIr0yyEMI7mdh4KX50LO1
 pmowEqDh7dLShTOif/7UtQYrzYq9cPnjU2ZW4qd5Qz2joSGTG9eCXLz5PRe5SqHxv6ljk8mb
 ApNuY7bOXO/A7T2j5RwXIlcmssqIjBcxsRRoIbpCwWWGjkYjzYCjgsNFL6rt4OL11OUF37wL
 QcTl7fbCGv53KfKPdYD5hcbguLKi/aCccJK18ZwNjFhqr4MliQARAQABzUVEYXZpZCBDaHJp
 c3RvcGhlciBIYW5zZW4gKEludGVsIFdvcmsgQWRkcmVzcykgPGRhdmUuaGFuc2VuQGludGVs
 LmNvbT7CwXgEEwECACIFAlQ+9J0CGwMGCwkIBwMCBhUIAgkKCwQWAgMBAh4BAheAAAoJEGg1
 lTBwyZKwLZUP/0dnbhDc229u2u6WtK1s1cSd9WsflGXGagkR6liJ4um3XCfYWDHvIdkHYC1t
 MNcVHFBwmQkawxsYvgO8kXT3SaFZe4ISfB4K4CL2qp4JO+nJdlFUbZI7cz/Td9z8nHjMcWYF
 IQuTsWOLs/LBMTs+ANumibtw6UkiGVD3dfHJAOPNApjVr+M0P/lVmTeP8w0uVcd2syiaU5jB
 aht9CYATn+ytFGWZnBEEQFnqcibIaOrmoBLu2b3fKJEd8Jp7NHDSIdrvrMjYynmc6sZKUqH2
 I1qOevaa8jUg7wlLJAWGfIqnu85kkqrVOkbNbk4TPub7VOqA6qG5GCNEIv6ZY7HLYd/vAkVY
 E8Plzq/NwLAuOWxvGrOl7OPuwVeR4hBDfcrNb990MFPpjGgACzAZyjdmYoMu8j3/MAEW4P0z
 F5+EYJAOZ+z212y1pchNNauehORXgjrNKsZwxwKpPY9qb84E3O9KYpwfATsqOoQ6tTgr+1BR
 CCwP712H+E9U5HJ0iibN/CDZFVPL1bRerHziuwuQuvE0qWg0+0SChFe9oq0KAwEkVs6ZDMB2
 P16MieEEQ6StQRlvy2YBv80L1TMl3T90Bo1UUn6ARXEpcbFE0/aORH/jEXcRteb+vuik5UGY
 5TsyLYdPur3TXm7XDBdmmyQVJjnJKYK9AQxj95KlXLVO38lczsFNBFRjzmoBEACyAxbvUEhd
 GDGNg0JhDdezyTdN8C9BFsdxyTLnSH31NRiyp1QtuxvcqGZjb2trDVuCbIzRrgMZLVgo3upr
 MIOx1CXEgmn23Zhh0EpdVHM8IKx9Z7V0r+rrpRWFE8/wQZngKYVi49PGoZj50ZEifEJ5qn/H
 Nsp2+Y+bTUjDdgWMATg9DiFMyv8fvoqgNsNyrrZTnSgoLzdxr89FGHZCoSoAK8gfgFHuO54B
 lI8QOfPDG9WDPJ66HCodjTlBEr/Cwq6GruxS5i2Y33YVqxvFvDa1tUtl+iJ2SWKS9kCai2DR
 3BwVONJEYSDQaven/EHMlY1q8Vln3lGPsS11vSUK3QcNJjmrgYxH5KsVsf6PNRj9mp8Z1kIG
 qjRx08+nnyStWC0gZH6NrYyS9rpqH3j+hA2WcI7De51L4Rv9pFwzp161mvtc6eC/GxaiUGuH
 BNAVP0PY0fqvIC68p3rLIAW3f97uv4ce2RSQ7LbsPsimOeCo/5vgS6YQsj83E+AipPr09Caj
 0hloj+hFoqiticNpmsxdWKoOsV0PftcQvBCCYuhKbZV9s5hjt9qn8CE86A5g5KqDf83Fxqm/
 vXKgHNFHE5zgXGZnrmaf6resQzbvJHO0Fb0CcIohzrpPaL3YepcLDoCCgElGMGQjdCcSQ+Ci
 FCRl0Bvyj1YZUql+ZkptgGjikQARAQABwsFfBBgBAgAJBQJUY85qAhsMAAoJEGg1lTBwyZKw
 l4IQAIKHs/9po4spZDFyfDjunimEhVHqlUt7ggR1Hsl/tkvTSze8pI1P6dGp2XW6AnH1iayn
 yRcoyT0ZJ+Zmm4xAH1zqKjWplzqdb/dO28qk0bPso8+1oPO8oDhLm1+tY+cOvufXkBTm+whm
 +AyNTjaCRt6aSMnA/QHVGSJ8grrTJCoACVNhnXg/R0g90g8iV8Q+IBZyDkG0tBThaDdw1B2l
 asInUTeb9EiVfL/Zjdg5VWiF9LL7iS+9hTeVdR09vThQ/DhVbCNxVk+DtyBHsjOKifrVsYep
 WpRGBIAu3bK8eXtyvrw1igWTNs2wazJ71+0z2jMzbclKAyRHKU9JdN6Hkkgr2nPb561yjcB8
 sIq1pFXKyO+nKy6SZYxOvHxCcjk2fkw6UmPU6/j/nQlj2lfOAgNVKuDLothIxzi8pndB8Jju
 KktE5HJqUUMXePkAYIxEQ0mMc8Po7tuXdejgPMwgP7x65xtfEqI0RuzbUioFltsp1jUaRwQZ
 MTsCeQDdjpgHsj+P2ZDeEKCbma4m6Ez/YWs4+zDm1X8uZDkZcfQlD9NldbKDJEXLIjYWo1PH
 hYepSffIWPyvBMBTW2W5FRjJ4vLRrJSUoEfJuPQ3vW9Y73foyo/qFoURHO48AinGPZ7PC7TF
 vUaNOTjKedrqHkaOcqB185ahG2had0xnFsDPlx5y
In-Reply-To: <20240603093505.GA12549@system.software.com>
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 7bit

On 6/3/24 02:35, Byungchul Park wrote:
...> In luf's point of view, the points where the deferred flush should be
> performed are simply:
> 
> 	1. when changing the vma maps, that might be luf'ed.
> 	2. when updating data of the pages, that might be luf'ed.

It's simple, but the devil is in the details as always.

> All we need to do is to indentify the points:
> 
> 	1. when changing the vma maps, that might be luf'ed.
> 
> 	   a) mmap and munmap e.i. fault handler or unmap_region().
> 	   b) permission to writable e.i. mprotect or fault handler.
> 	   c) what I'm missing.

I'd say it even more generally: anything that installs a PTE which is
inconsistent with the original PTE.  That, of course, includes writes.
But it also includes crazy things that we do like uprobes.  Take a look
at __replace_page().

I think the page_vma_mapped_walk() checks plus the ptl keep LUF at bay
there.  But it needs some really thorough review.

But the bigger concern is that, if there was a problem, I can't think of
a systematic way to find it.

> 	2. when updating data of the pages, that might be luf'ed.
> 
> 	   a) updating files through vfs e.g. file_end_write().
> 	   b) updating files through writable maps e.i. 1-a) or 1-b).
> 	   c) what I'm missing.

Filesystems or block devices that change content without a "write" from
the local system.  Network filesystems and block devices come to mind.
I honestly don't know what all the rules are around these, but they
could certainly be troublesome.

There appear to be some interactions for NFS between file locking and
page cache flushing.

But, stepping back ...

I'd honestly be a lot more comfortable if there was even a debugging LUF
mode that enforced a rule that said:

  1. A LUF'd PTE can't be rewritten until after a luf_flush() occurs
  2. A LUF'd page's position in the page cache can't be replaced until
     after a luf_flush()

or *some* other independent set of rules that can tell us when something
goes wrong.  That uprobes code, for instance, seems like it will work.
But I can also imagine writing it ten other ways where it would break
when combined with LUF.