Re: [PATCH v2 0/6] mm/memory_hotplug: Consider all zones when removing memory

["Aneesh Kumar K.V" <aneesh.kumar@linux.ibm.com>]

David Hildenbrand <david@redhat.com> writes:

> On 26.08.19 18:20, David Hildenbrand wrote:
>> On 26.08.19 18:01, Aneesh Kumar K.V wrote:
>>> On 8/26/19 9:13 PM, David Hildenbrand wrote:
>>>> On 26.08.19 16:53, Aneesh Kumar K.V wrote:
>>>>> David Hildenbrand <david@redhat.com> writes:
>>>>>
>>>>>>
>>>
>>> ....
>>>
>>>>>
>>>>> I did report a variant of the issue at
>>>>>
>>>>> https://lore.kernel.org/linux-mm/20190514025354.9108-1-aneesh.kumar@linux.ibm.com/
>>>>>
>>>>> This patch series still doesn't handle the fact that struct page backing
>>>>> the start_pfn might not be initialized. ie, it results in crash like
>>>>> below
>>>>
>>>> Okay, that's a related but different issue I think.
>>>>
>>>> I can see that current shrink_zone_span() might read-access the
>>>> uninitialized struct page of a PFN if
>>>>
>>>> 1. The zone has holes and we check for "zone all holes". If we get
>>>> pfn_valid(pfn), we check if "page_zone(pfn_to_page(pfn)) != zone".
>>>>
>>>> 2. Via find_smallest_section_pfn() / find_biggest_section_pfn() find a
>>>> spanned pfn_valid(). We check
>>>> - pfn_to_nid(start_pfn) != nid
>>>> - zone != page_zone(pfn_to_page(start_pfn)
>>>>
>>>> So we don't actually use the zone/nid, only use it to sanity check. That
>>>> might result in false-positives (not that bad).
>>>>
>>>> It all boils down to shrink_zone_span() not working only on active
>>>> memory, for which the PFN is not only valid but also initialized
>>>> (something for which we need a new section flag I assume).
>>>>
>>>> Which access triggers the issue you describe? pfn_to_nid()?
>>>>
>>>>>
>>>>>      pc: c0000000004bc1ec: shrink_zone_span+0x1bc/0x290
>>>>>      lr: c0000000004bc1e8: shrink_zone_span+0x1b8/0x290
>>>>>      sp: c0000000dac7f910
>>>>>     msr: 800000000282b033
>>>>>    current = 0xc0000000da2fa000
>>>>>    paca    = 0xc00000000fffb300   irqmask: 0x03   irq_happened: 0x01
>>>>>      pid   = 1224, comm = ndctl
>>>>> kernel BUG at /home/kvaneesh/src/linux/include/linux/mm.h:1088!
>>>>> Linux version 5.3.0-rc6-17495-gc7727d815970-dirty (kvaneesh@ltc-boston123) (gcc version 7.4.0 (Ubuntu 7.4.0-1ubuntu1~18.04.1)) #183 SMP Mon Aug 26 09:37:32 CDT 2019
>>>>> enter ? for help
>>>>
>>>> Which exact kernel BUG are you hitting here? (my tree doesn't seem t
>>>> have any BUG statement around  include/linux/mm.h:1088). 
>>>
>>>
>>>
>>> This is against upstream linus with your patches applied.
>> 
>> I'm
>> 
>>>
>>>
>>> static inline int page_to_nid(const struct page *page)
>>> {
>>> 	struct page *p = (struct page *)page;
>>>
>>> 	return (PF_POISONED_CHECK(p)->flags >> NODES_PGSHIFT) & NODES_MASK;
>>> }
>>>
>>>
>>> #define PF_POISONED_CHECK(page) ({					\
>>> 		VM_BUG_ON_PGFLAGS(PagePoisoned(page), page);		\
>>> 		page; })
>>> #
>>>
>>>
>>> It is the node id access.
>> 
>> A right. A temporary hack would be to assume in these functions
>> (shrink_zone_span() and friends) that we might have invalid NIDs /
>> zonenumbers and simply skip these. After all we're only using them for
>> finding zone boundaries. Not what we ultimately want, but I think until
>> we have a proper SECTION_ACTIVE, it might take a while.
>> 
>
> I am talking about something as hacky as this:
>
> diff --git a/include/linux/mm.h b/include/linux/mm.h
> index 8d1c7313ab3f..57ed3dd76a4f 100644
> --- a/include/linux/mm.h
> +++ b/include/linux/mm.h
> @@ -1099,6 +1099,7 @@ static inline int page_zone_id(struct page *page)
>
>  #ifdef NODE_NOT_IN_PAGE_FLAGS
>  extern int page_to_nid(const struct page *page);
> +#define __page_to_nid page_to_nid
>  #else
>  static inline int page_to_nid(const struct page *page)
>  {
> @@ -1106,6 +1107,10 @@ static inline int page_to_nid(const struct page
> *page)
>
>  	return (PF_POISONED_CHECK(p)->flags >> NODES_PGSHIFT) & NODES_MASK;
>  }
> +static inline int __page_to_nid(const struct page *page)
> +{
> +	return ((page)->flags >> NODES_PGSHIFT) & NODES_MASK;
> +}
>  #endif
>
>  #ifdef CONFIG_NUMA_BALANCING
> @@ -1249,6 +1254,12 @@ static inline struct zone *page_zone(const struct
> page *page)
>  	return &NODE_DATA(page_to_nid(page))->node_zones[page_zonenum(page)];
>  }
>
> +static inline struct zone *__page_zone(const struct page *page)
> +{
> +	return &NODE_DATA(__page_to_nid(page))->node_zones[page_zonenum(page)];
> +}

We don't need that. We can always do an explicity __page_to_nid check
and break from the loop before doing a page_zone() ? Also if the struct
page is poisoned, we should not trust the page_zonenum()? 

> +
> +
>  static inline pg_data_t *page_pgdat(const struct page *page)
>  {
>  	return NODE_DATA(page_to_nid(page));
> diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
> index 49ca3364eb70..378b593d1fe1 100644
> --- a/mm/memory_hotplug.c
> +++ b/mm/memory_hotplug.c
> @@ -334,10 +334,10 @@ static unsigned long find_smallest_section_pfn(int
> nid, struct zone *zone,
>  		if (unlikely(!pfn_valid(start_pfn)))
>  			continue;
>
> -		if (unlikely(pfn_to_nid(start_pfn) != nid))
> +		/* We might have uninitialized memmaps */
> +		if (unlikely(__page_to_nid(pfn_to_page(start_pfn)) != nid))
>  			continue;

if we are here we got non poisoned struct page. Hence we don't need the
below change?

> -
> -		if (zone && zone != page_zone(pfn_to_page(start_pfn)))
> +		if (zone && zone != __page_zone(pfn_to_page(start_pfn)))
>  			continue;
>
>  		return start_pfn;
> @@ -359,10 +359,10 @@ static unsigned long find_biggest_section_pfn(int
> nid, struct zone *zone,
>  		if (unlikely(!pfn_valid(pfn)))
>  			continue;
>
> -		if (unlikely(pfn_to_nid(pfn) != nid))
> +		/* We might have uninitialized memmaps */
> +		if (unlikely(__page_to_nid(pfn_to_page(pfn)) != nid))
>  			continue;

same as above

> -
> -		if (zone && zone != page_zone(pfn_to_page(pfn)))
> +		if (zone && zone != __page_zone(pfn_to_page(pfn)))
>  			continue;
>
>  		return pfn;
> @@ -418,7 +418,10 @@ static void shrink_zone_span(struct zone *zone,
> unsigned long start_pfn,
>  		if (unlikely(!pfn_valid(pfn)))
>  			continue;
>
> -		if (page_zone(pfn_to_page(pfn)) != zone)
> +		/* We might have uninitialized memmaps */
> +		if (unlikely(__page_to_nid(pfn_to_page(pfn)) != nid))
> +			continue;

same as above? 

> +		if (__page_zone(pfn_to_page(pfn)) != zone)
>  			continue;
>
>  		/* Skip range to be removed */
> @@ -483,7 +486,8 @@ static void shrink_pgdat_span(struct pglist_data *pgdat,
>  		if (unlikely(!pfn_valid(pfn)))
>  			continue;
>
> -		if (pfn_to_nid(pfn) != nid)
> +		/* We might have uninitialized memmaps */
> +		if (unlikely(__page_to_nid(pfn_to_page(pfn)) != nid))
>  			continue;
>
>  		/* Skip range to be removed */
>


But I am not sure whether this is the right approach.

-aneesh