From: Baolin Wang <baolin.wang@linux.alibaba.com>
To: David Hildenbrand <david@redhat.com>,
John Hubbard <jhubbard@nvidia.com>,
Yang Shi <shy828301@gmail.com>,
peterx@redhat.com, kirill.shutemov@linux.intel.com,
jgg@nvidia.com, hughd@google.com, akpm@linux-foundation.org
Cc: linux-mm@kvack.org, linux-kernel@vger.kernel.org
Subject: Re: [PATCH] mm: gup: fix the fast GUP race against THP collapse
Date: Mon, 5 Sep 2022 18:16:52 +0800 [thread overview]
Message-ID: <0c9d9774-77dd-fd93-b5b6-fc63f3d01b7f@linux.alibaba.com> (raw)
In-Reply-To: <a969abc5-1ad0-4073-a1f9-82f0431a0104@redhat.com>
On 9/5/2022 3:59 PM, David Hildenbrand wrote:
> On 05.09.22 00:29, John Hubbard wrote:
>> On 9/1/22 15:27, Yang Shi wrote:
>>> Since general RCU GUP fast was introduced in commit 2667f50e8b81 ("mm:
>>> introduce a general RCU get_user_pages_fast()"), a TLB flush is no
>>> longer
>>> sufficient to handle concurrent GUP-fast in all cases, it only handles
>>> traditional IPI-based GUP-fast correctly. On architectures that send
>>> an IPI broadcast on TLB flush, it works as expected. But on the
>>> architectures that do not use IPI to broadcast TLB flush, it may have
>>> the below race:
>>>
>>> CPU A CPU B
>>> THP collapse fast GUP
>>> gup_pmd_range() <--
>>> see valid pmd
>>> gup_pte_range()
>>> <-- work on pte
>>> pmdp_collapse_flush() <-- clear pmd and flush
>>> __collapse_huge_page_isolate()
>>> check page pinned <-- before GUP bump refcount
>>> pin the page
>>> check PTE <--
>>> no change
>>> __collapse_huge_page_copy()
>>> copy data to huge page
>>> ptep_clear()
>>> install huge pmd for the huge page
>>> return the
>>> stale page
>>> discard the stale page
>>
>> Hi Yang,
>>
>> Thanks for taking the trouble to write down these notes. I always
>> forget which race we are dealing with, and this is a great help. :)
>>
>> More...
>>
>>>
>>> The race could be fixed by checking whether PMD is changed or not after
>>> taking the page pin in fast GUP, just like what it does for PTE. If the
>>> PMD is changed it means there may be parallel THP collapse, so GUP
>>> should back off.
>>>
>>> Also update the stale comment about serializing against fast GUP in
>>> khugepaged.
>>>
>>> Fixes: 2667f50e8b81 ("mm: introduce a general RCU
>>> get_user_pages_fast()")
>>> Signed-off-by: Yang Shi <shy828301@gmail.com>
>>> ---
>>> mm/gup.c | 30 ++++++++++++++++++++++++------
>>> mm/khugepaged.c | 10 ++++++----
>>> 2 files changed, 30 insertions(+), 10 deletions(-)
>>>
>>> diff --git a/mm/gup.c b/mm/gup.c
>>> index f3fc1f08d90c..4365b2811269 100644
>>> --- a/mm/gup.c
>>> +++ b/mm/gup.c
>>> @@ -2380,8 +2380,9 @@ static void __maybe_unused undo_dev_pagemap(int
>>> *nr, int nr_start,
>>> }
>>> #ifdef CONFIG_ARCH_HAS_PTE_SPECIAL
>>> -static int gup_pte_range(pmd_t pmd, unsigned long addr, unsigned
>>> long end,
>>> - unsigned int flags, struct page **pages, int *nr)
>>> +static int gup_pte_range(pmd_t pmd, pmd_t *pmdp, unsigned long addr,
>>> + unsigned long end, unsigned int flags,
>>> + struct page **pages, int *nr)
>>> {
>>> struct dev_pagemap *pgmap = NULL;
>>> int nr_start = *nr, ret = 0;
>>> @@ -2423,7 +2424,23 @@ static int gup_pte_range(pmd_t pmd, unsigned
>>> long addr, unsigned long end,
>>> goto pte_unmap;
>>> }
>>> - if (unlikely(pte_val(pte) != pte_val(*ptep))) {
>>> + /*
>>> + * THP collapse conceptually does:
>>> + * 1. Clear and flush PMD
>>> + * 2. Check the base page refcount
>>> + * 3. Copy data to huge page
>>> + * 4. Clear PTE
>>> + * 5. Discard the base page
>>> + *
>>> + * So fast GUP may race with THP collapse then pin and
>>> + * return an old page since TLB flush is no longer sufficient
>>> + * to serialize against fast GUP.
>>> + *
>>> + * Check PMD, if it is changed just back off since it
>>> + * means there may be parallel THP collapse.
>>> + */
>>
>> As I mentioned in the other thread, it would be a nice touch to move
>> such discussion into the comment header.
>>
>>> + if (unlikely(pmd_val(pmd) != pmd_val(*pmdp)) ||
>>> + unlikely(pte_val(pte) != pte_val(*ptep))) {
>>
>>
>> That should be READ_ONCE() for the *pmdp and *ptep reads. Because this
>> whole lockless house of cards may fall apart if we try reading the
>> page table values without READ_ONCE().
>
> I came to the conclusion that the implicit memory barrier when grabbing
> a reference on the page is sufficient such that we don't need READ_ONCE
> here.
IMHO the compiler may optimize the code 'pte_val(*ptep)' to be always
get from a register, then we can get an old value if other thread did
set_pte(). I am not sure how the implicit memory barrier can pervent the
compiler optimization? Please correct me if I missed something.
> If we still intend to change that code, we should fixup all GUP-fast
> functions in a similar way. But again, I don't think we need a change here.
>
>
>>> - * After this gup_fast can't run anymore. This also removes
>>> - * any huge TLB entry from the CPU so we won't allow
>>> - * huge and small TLB entries for the same virtual address
>>> - * to avoid the risk of CPU bugs in that area.
>>> + * This removes any huge TLB entry from the CPU so we won't allow
>>> + * huge and small TLB entries for the same virtual address to
>>> + * avoid the risk of CPU bugs in that area.
>>> + *
>>> + * Parallel fast GUP is fine since fast GUP will back off when
>>> + * it detects PMD is changed.
>>> */
>>> _pmd = pmdp_collapse_flush(vma, address, pmd);
>>
>> To follow up on David Hildenbrand's note about this in the nearby
>> thread...
>> I'm also not sure if pmdp_collapse_flush() implies a memory barrier on
>> all arches. It definitely does do an atomic op with a return value on
>> x86,
>> but that's just one arch.
>>
>
> I think a ptep/pmdp clear + TLB flush really has to imply a memory
> barrier, otherwise TLB flushing code might easily mess up with
> surrounding code. But we should better double-check.
>
> s390x executes an IDTE instruction, which performs serialization (->
> memory barrier). arm64 seems to use DSB instructions to enforce memory
> ordering.
>
next prev parent reply other threads:[~2022-09-05 10:18 UTC|newest]
Thread overview: 38+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-09-01 22:27 [PATCH] mm: gup: fix the fast GUP race against THP collapse Yang Shi
2022-09-01 23:26 ` Peter Xu
2022-09-01 23:50 ` Yang Shi
2022-09-02 6:39 ` David Hildenbrand
2022-09-02 15:23 ` Yang Shi
2022-09-02 15:59 ` Peter Xu
2022-09-02 16:04 ` Peter Xu
2022-09-02 17:30 ` Yang Shi
2022-09-02 17:45 ` Yang Shi
2022-09-02 20:33 ` Peter Xu
2022-09-05 8:56 ` Aneesh Kumar K.V
2022-09-05 8:54 ` Aneesh Kumar K.V
2022-09-06 19:07 ` Yang Shi
2022-09-07 4:50 ` Aneesh Kumar K V
2022-09-07 17:08 ` Yang Shi
2022-09-04 22:21 ` John Hubbard
2022-09-02 6:42 ` David Hildenbrand
2022-09-04 22:29 ` John Hubbard
2022-09-05 7:59 ` David Hildenbrand
2022-09-05 10:16 ` Baolin Wang [this message]
2022-09-05 10:24 ` David Hildenbrand
2022-09-05 11:11 ` David Hildenbrand
2022-09-05 14:35 ` Baolin Wang
2022-09-05 14:40 ` David Hildenbrand
2022-09-06 5:53 ` Baolin Wang
2022-09-06 2:12 ` John Hubbard
2022-09-06 12:50 ` David Hildenbrand
2022-09-06 13:47 ` Jason Gunthorpe
2022-09-06 13:57 ` David Hildenbrand
2022-09-06 14:30 ` Jason Gunthorpe
2022-09-06 14:44 ` David Hildenbrand
2022-09-06 15:33 ` Jason Gunthorpe
2022-09-06 19:11 ` Yang Shi
2022-09-06 23:16 ` John Hubbard
2022-09-06 19:01 ` Yang Shi
2022-09-05 9:03 ` Baolin Wang
2022-09-06 18:50 ` Yang Shi
2022-09-06 21:27 ` John Hubbard
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=0c9d9774-77dd-fd93-b5b6-fc63f3d01b7f@linux.alibaba.com \
--to=baolin.wang@linux.alibaba.com \
--cc=akpm@linux-foundation.org \
--cc=david@redhat.com \
--cc=hughd@google.com \
--cc=jgg@nvidia.com \
--cc=jhubbard@nvidia.com \
--cc=kirill.shutemov@linux.intel.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=peterx@redhat.com \
--cc=shy828301@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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).