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;
Message-ID: <383fec21-9801-9b60-7570-856da2133ea9@redhat.com>
Date:   Mon, 5 Sep 2022 12:24:34 +0200
MIME-Version: 1.0
User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:102.0) Gecko/20100101
 Thunderbird/102.2.0
Subject: Re: [PATCH] mm: gup: fix the fast GUP race against THP collapse
Content-Language: en-US
To:     Baolin Wang <baolin.wang@linux.alibaba.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
References: <20220901222707.477402-1-shy828301@gmail.com>
 <e6ad1084-c301-9f11-1fa7-7614bf859aaf@nvidia.com>
 <a969abc5-1ad0-4073-a1f9-82f0431a0104@redhat.com>
 <0c9d9774-77dd-fd93-b5b6-fc63f3d01b7f@linux.alibaba.com>
From:   David Hildenbrand <david@redhat.com>
Organization: Red Hat
In-Reply-To: <0c9d9774-77dd-fd93-b5b6-fc63f3d01b7f@linux.alibaba.com>
Content-Type: text/plain; charset=UTF-8; format=flowed
Content-Transfer-Encoding: 8bit
Precedence: bulk

On 05.09.22 12:16, Baolin Wang wrote:
> 
> 
> 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.

IIUC, an memory barrier always implies a compiler barrier.

-- 
Thanks,

David / dhildenb