All of lore.kernel.org
 help / color / mirror / Atom feed
From: Qi Zheng <zhengqi.arch@bytedance.com>
To: Jason Gunthorpe <jgg@nvidia.com>, David Hildenbrand <david@redhat.com>
Cc: akpm@linux-foundation.org, tglx@linutronix.de,
	hannes@cmpxchg.org, mhocko@kernel.org, vdavydov.dev@gmail.com,
	kirill.shutemov@linux.intel.com, mika.penttila@nextfour.com,
	linux-doc@vger.kernel.org, linux-kernel@vger.kernel.org,
	linux-mm@kvack.org, songmuchun@bytedance.com
Subject: Re: [PATCH v2 6/9] mm: free user PTE page table pages
Date: Thu, 2 Sep 2021 14:53:58 +0800	[thread overview]
Message-ID: <47c7d6fd-056b-0e40-ae30-e2f099a97a95@bytedance.com> (raw)
In-Reply-To: <20210901153247.GJ1721383@nvidia.com>



On 2021/9/1 PM11:32, Jason Gunthorpe wrote:
> 
>>> Also, I don't really understand how this scheme works with
>>> get_user_pages_fast.
>>
>> With the RCU change it in #8 it should work just fine, because RCU
>> synchronize has to wait either until all other CPUs have left the RCU read
>> section, or re-enabled interrupts.
> 
> So at this point in the series fast gup is broken, that does mean the
> series presentation really needs to be reworked. The better
> presentation is to add the API changes, with a
> no-functional-difference implementation, push the new API in well
> split patches to all the consumption sites, then change the API to
> have the new semantics.
> 
> RCU and refcount to free the page levels seems like a reasonable
> approach, but I have to say I haven't thought it through fully - are
> all the contexts that have the pte deref safe to do call_rcu?

See Documentation/RCU/rcubarrier.rst:

"Since call_rcu() never blocks, this code can safely be used from within
IRQ context."

So I think call_rcu() can be safely run in any context.

Thinks,
Qi

> 
> Jason
> 
> 

  parent reply	other threads:[~2021-09-02  6:54 UTC|newest]

Thread overview: 39+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-08-19  3:18 [PATCH v2 0/9] Free user PTE page table pages Qi Zheng
2021-08-19  3:18 ` [PATCH v2 1/9] mm: introduce pmd_install() helper Qi Zheng
2021-08-24 16:26   ` David Hildenbrand
2021-08-25 16:20     ` Qi Zheng
2021-08-25 16:32       ` David Hildenbrand
2021-08-26  3:04         ` Qi Zheng
2021-08-19  3:18 ` [PATCH v2 2/9] mm: remove redundant smp_wmb() Qi Zheng
2021-08-19  3:18 ` [PATCH v2 3/9] mm: rework the parameter of lock_page_or_retry() Qi Zheng
2021-08-19  3:18 ` [PATCH v2 4/9] mm: move pte_alloc{,_map,_map_lock}() to a separate file Qi Zheng
2021-08-19  3:18 ` [PATCH v2 5/9] mm: pte_refcount infrastructure Qi Zheng
2021-08-19  3:18 ` [PATCH v2 6/9] mm: free user PTE page table pages Qi Zheng
2021-08-19  7:01   ` David Hildenbrand
2021-08-19 10:18     ` [External] " Qi Zheng
2021-09-01 13:53   ` Jason Gunthorpe
2021-09-01 13:57     ` David Hildenbrand
2021-09-01 15:32       ` Jason Gunthorpe
2021-09-01 16:13         ` David Hildenbrand
2021-09-01 16:16           ` Jason Gunthorpe
2021-09-01 16:19             ` David Hildenbrand
2021-09-01 17:10               ` Jason Gunthorpe
2021-09-01 17:49                 ` David Hildenbrand
2021-09-01 17:55                   ` Jason Gunthorpe
2021-09-01 17:58                     ` David Hildenbrand
2021-09-01 18:09                       ` Jason Gunthorpe
2021-09-01 18:10                         ` David Hildenbrand
2021-09-02  7:04                     ` Qi Zheng
2021-09-02  6:53         ` Qi Zheng [this message]
2021-08-19  3:18 ` [PATCH v2 7/9] mm: add THP support for pte_ref Qi Zheng
2021-08-19  3:18 ` [PATCH v2 8/9] mm: free PTE page table by using rcu mechanism Qi Zheng
2021-08-19  3:18 ` [PATCH v2 9/9] mm: use mmu_gather to free PTE page table Qi Zheng
2021-09-01 12:32 ` [PATCH v2 0/9] Free user PTE page table pages David Hildenbrand
2021-09-01 16:07   ` Jason Gunthorpe
2021-09-01 16:10     ` David Hildenbrand
2021-09-02  3:37   ` Qi Zheng
2021-09-15 14:52   ` Qi Zheng
2021-09-15 14:59     ` Jason Gunthorpe
2021-09-16  5:32       ` Qi Zheng
2021-09-16  8:30         ` David Hildenbrand
2021-09-16  8:41           ` Qi Zheng

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=47c7d6fd-056b-0e40-ae30-e2f099a97a95@bytedance.com \
    --to=zhengqi.arch@bytedance.com \
    --cc=akpm@linux-foundation.org \
    --cc=david@redhat.com \
    --cc=hannes@cmpxchg.org \
    --cc=jgg@nvidia.com \
    --cc=kirill.shutemov@linux.intel.com \
    --cc=linux-doc@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=mhocko@kernel.org \
    --cc=mika.penttila@nextfour.com \
    --cc=songmuchun@bytedance.com \
    --cc=tglx@linutronix.de \
    --cc=vdavydov.dev@gmail.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body. 
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.