On 8/12/19 4:05 PM, David Hildenbrand wrote:
>>> ---
>>> include/linux/mmzone.h | 11 ++
>>> include/linux/page_reporting.h | 63 +++++++
>>> mm/Kconfig | 6 +
>>> mm/Makefile | 1 +
>>> mm/page_alloc.c | 42 ++++-
>>> mm/page_reporting.c | 332 +++++++++++++++++++++++++++++++++
>>> 6 files changed, 448 insertions(+), 7 deletions(-)
>>> create mode 100644 include/linux/page_reporting.h
>>> create mode 100644 mm/page_reporting.c
>>>
>>> diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
>>> index d77d717c620c..ba5f5b508f25 100644
>>> --- a/include/linux/mmzone.h
>>> +++ b/include/linux/mmzone.h
>>> @@ -559,6 +559,17 @@ struct zone {
>>> /* Zone statistics */
>>> atomic_long_t vm_stat[NR_VM_ZONE_STAT_ITEMS];
>>> atomic_long_t vm_numa_stat[NR_VM_NUMA_STAT_ITEMS];
>>> +#ifdef CONFIG_PAGE_REPORTING
>>> + /* Pointer to the bitmap in PAGE_REPORTING_MIN_ORDER granularity */
>>> + unsigned long *bitmap;
>>> + /* Preserve start and end PFN in case they change due to hotplug */
>>> + unsigned long base_pfn;
>>> + unsigned long end_pfn;
>>> + /* Free pages of granularity PAGE_REPORTING_MIN_ORDER */
>>> + atomic_t free_pages;
>>> + /* Number of bits required in the bitmap */
>>> + unsigned long nbits;
>>> +#endif
>>> } ____cacheline_internodealigned_in_smp;
>> Okay, so the original thing this patch set had going for it was that
>> it was non-invasive. However, now you are adding a bunch of stuff to
>> the zone. That kind of loses the non-invasive argument for this patch
>> set compared to mine.
>>
> Adding something to "struct zone" is certainly less invasive than core
> buddy modifications, just saying (I agree that this is suboptimal. I
> would have guessed that all that's needed is a pointer to some private
> structure here).
I think having just a pointer to a private structure makes sense here.
If I am not wrong then I can probably make an allocation for it for each
populated zone at the time I enable page reporting.
> However, the migratetype thingy below looks fishy to me.
>
>> If we are going to continue further with this patch set then it might
>> be worth looking into dynamically allocating the space you need for
>> this block. At a minimum you could probably look at making the bitmap
>> an RCU based setup so you could define the base and end along with the
>> bitmap. It would probably help to resolve the hotplug issues you still
>> need to address.
> Yeah, I guess that makes sense.
>
> [...]
>>> +
>>> +static int process_free_page(struct page *page,
>>> + struct page_reporting_config *phconf, int count)
>>> +{
>>> + int mt, order, ret = 0;
>>> +
>>> + mt = get_pageblock_migratetype(page);
>>> + order = page_private(page);
>>> + ret = __isolate_free_page(page, order);
>>> +
> I just started looking into the wonderful world of
> isolation/compaction/migration.
>
> I don't think saving/restoring the migratetype is correct here. AFAIK,
> MOVABLE/UNMOVABLE/RECLAIMABLE is just a hint, doesn't mean that e.g.,
> movable pages and up in UNMOVABLE or ordinary kernel allocations on
> MOVABLE. So that shouldn't be an issue - I guess.
>
> 1. You should never allocate something that is no
> MOVABLE/UNMOVABLE/RECLAIMABLE. Especially not, if you have ISOLATE or
> CMA here. There should at least be a !is_migrate_isolate_page() check
> somewhere
>
> 2. set_migratetype_isolate() takes the zone lock, so to avoid racing
> with isolation code, you have to hold the zone lock. Your code seems to
> do that, so at least you cannot race against isolation.
>
> 3. You could end up temporarily allocating something in the
> ZONE_MOVABLE. The pages you allocate are, however, not movable. There
> would have to be a way to make alloc_contig_range()/offlining code
> properly wait until the pages have been processed. Not sure about the
> real implications, though - too many details in the code (I wonder if
> Alex' series has a way of dealing with that)
>
> When you restore the migratetype, you could suddenly overwrite e.g.,
> ISOLATE, which feels wrong.
I was triggering an occasional CPU stall bug earlier, with saving and restoring
the migratetype I was able to fix it.
But I will further look into this to figure out if it is really required.
> [...]
>> So as per your comments in the cover page, the two functions above
>> should also probably be plugged into the zone resizing logic somewhere
>> so if a zone is resized the bitmap is adjusted.
>>
>>> +/**
>>> + * zone_reporting_init - For each zone initializes the page reporting fields
>>> + * and allocates the respective bitmap.
>>> + *
>>> + * This function returns 0 on successful initialization, -ENOMEM otherwise.
>>> + */
>>> +static int zone_reporting_init(void)
>>> +{
>>> + struct zone *zone;
>>> + int ret;
>>> +
>>> + for_each_populated_zone(zone) {
>>> +#ifdef CONFIG_ZONE_DEVICE
>>> + /* we can not report pages which are not in the buddy */
>>> + if (zone_idx(zone) == ZONE_DEVICE)
>>> + continue;
>>> +#endif
>> I'm pretty sure this isn't needed since I don't think the ZONE_DEVICE
>> zone will be considered "populated".
>>
> I think you are right (although it's confusing, we will have present
> sections part of a zone but the zone has no present_pages - screams like
> a re factoring - leftover from ZONE_DEVICE introduction).
I think in that case it is safe to have this check here.
What do you guys suggest?
>
--
Thanks
Nitesh
