[PATCH v9 02/10] mm: Non-pmd-mappable, large folios for folio_add_new_anon_rmap()

[Ryan Roberts]

On 24/01/2024 12:06, Jiri Olsa wrote:
> On Wed, Jan 24, 2024 at 12:02:53PM +0000, Ryan Roberts wrote:
>> On 24/01/2024 11:19, Jiri Olsa wrote:
>>> On Wed, Jan 24, 2024 at 12:15:52PM +0100, Sven Schnelle wrote:
>>>> Ryan Roberts <ryan.roberts at arm.com> writes:
>>>>
>>>>> On 14/01/2024 20:55, Jiri Olsa wrote:
>>>>>> On Sun, Jan 14, 2024 at 06:33:56PM +0100, David Hildenbrand wrote:
>>>>>>> On 13.01.24 23:42, Jiri Olsa wrote:
>>>>>>>> On Thu, Dec 07, 2023 at 04:12:03PM +0000, Ryan Roberts wrote:
>>>>>>>>> In preparation for supporting anonymous multi-size THP, improve
>>>>>>>>> folio_add_new_anon_rmap() to allow a non-pmd-mappable, large folio to be
>>>>>>>>> passed to it. In this case, all contained pages are accounted using the
>>>>>>>>> order-0 folio (or base page) scheme.
>>>>>>>>>
>>>>>>>>> Reviewed-by: Yu Zhao <yuzhao at google.com>
>>>>>>>>> Reviewed-by: Yin Fengwei <fengwei.yin at intel.com>
>>>>>>>>> Reviewed-by: David Hildenbrand <david at redhat.com>
>>>>>>>>> Reviewed-by: Barry Song <v-songbaohua at oppo.com>
>>>>>>>>> Tested-by: Kefeng Wang <wangkefeng.wang at huawei.com>
>>>>>>>>> Tested-by: John Hubbard <jhubbard at nvidia.com>
>>>>>>>>> Signed-off-by: Ryan Roberts <ryan.roberts at arm.com>
>>>>>>>>> ---
>>>>>>>>>   mm/rmap.c | 28 ++++++++++++++++++++--------
>>>>>>>>>   1 file changed, 20 insertions(+), 8 deletions(-)
>>>>>>>>>
>>>>>>>>> diff --git a/mm/rmap.c b/mm/rmap.c
>>>>>>>>> index 2a1e45e6419f..846fc79f3ca9 100644
>>>>>>>>> --- a/mm/rmap.c
>>>>>>>>> +++ b/mm/rmap.c
>>>>>>>>> @@ -1335,32 +1335,44 @@ void page_add_anon_rmap(struct page *page, struct vm_area_struct *vma,
>>>>>>>>>    * This means the inc-and-test can be bypassed.
>>>>>>>>>    * The folio does not have to be locked.
>>>>>>>>>    *
>>>>>>>>> - * If the folio is large, it is accounted as a THP.  As the folio
>>>>>>>>> + * If the folio is pmd-mappable, it is accounted as a THP.  As the folio
>>>>>>>>>    * is new, it's assumed to be mapped exclusively by a single process.
>>>>>>>>>    */
>>>>>>>>>   void folio_add_new_anon_rmap(struct folio *folio, struct vm_area_struct *vma,
>>>>>>>>>   		unsigned long address)
>>>>>>>>>   {
>>>>>>>>> -	int nr;
>>>>>>>>> +	int nr = folio_nr_pages(folio);
>>>>>>>>> -	VM_BUG_ON_VMA(address < vma->vm_start || address >= vma->vm_end, vma);
>>>>>>>>> +	VM_BUG_ON_VMA(address < vma->vm_start ||
>>>>>>>>> +			address + (nr << PAGE_SHIFT) > vma->vm_end, vma);
>>>>>>>>
>>>>>>>> hi,
>>>>>>>> I'm hitting this bug (console output below) with adding uprobe
>>>>>>>> on simple program like:
>>>>>>>>
>>>>>>>>    $ cat up.c
>>>>>>>>    int main(void)
>>>>>>>>    {
>>>>>>>>       return 0;
>>>>>>>>    }
>>>>>>>>
>>>>>>>>    # bpftrace -e 'uprobe:/home/jolsa/up:_start {}'
>>>>>>>>
>>>>>>>>    $ ./up
>>>>>>>>
>>>>>>>> it's on top of current linus tree master:
>>>>>>>>    052d534373b7 Merge tag 'exfat-for-6.8-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/linkinjeon/exfat
>>>>>>>>
>>>>>>>> before this patch it seems to work, I can send my .config if needed
>>>>>
>>>>> Thanks for the bug report!
>>>>
>>>> I just hit the same bug in our CI, but can't find the fix in -next. Is
>>>> this in the queue somewhere?
>>>
>>> we hit it as well, but I can see the fix in linux-next/master
>>>
>>>   4c137bc28064 uprobes: use pagesize-aligned virtual address when replacing pages
>>
>> Yes that's the one. Just to confirm: you are still hitting the VM_BUG_ON despite
>> having this change in your kernel? Could you please send over the full bug log?
> 
> ah sorry.. I meant the change fixes the problem for us, it just did not
> yet propagate through the merge cycle into bpf trees.. but I can see it
> in linux-next tree, so it's probably just matter of time

OK great! How about you, Sven? Do you have this change in your kernel? Hopefully
it should fix your problem.

> 
> jirka