[PATCH] arm64: mm: hugetlb: add support for free vmemmap pages of HugeTLB

[David Hildenbrand]

On 20.05.21 13:54, Anshuman Khandual wrote:
> 
> On 5/19/21 5:33 PM, David Hildenbrand wrote:
>> On 19.05.21 13:45, Anshuman Khandual wrote:
>>>
>>>
>>> On 5/18/21 2:48 PM, Muchun Song wrote:
>>>> The preparation of supporting freeing vmemmap associated with each
>>>> HugeTLB page is ready, so we can support this feature for arm64.
>>>>
>>>> Signed-off-by: Muchun Song <songmuchun at bytedance.com>
>>>> ---
>>>>    arch/arm64/mm/mmu.c | 5 +++++
>>>>    fs/Kconfig          | 2 +-
>>>>    2 files changed, 6 insertions(+), 1 deletion(-)
>>>>
>>>> diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
>>>> index 5d37e461c41f..967b01ce468d 100644
>>>> --- a/arch/arm64/mm/mmu.c
>>>> +++ b/arch/arm64/mm/mmu.c
>>>> @@ -23,6 +23,7 @@
>>>>    #include <linux/mm.h>
>>>>    #include <linux/vmalloc.h>
>>>>    #include <linux/set_memory.h>
>>>> +#include <linux/hugetlb.h>
>>>>      #include <asm/barrier.h>
>>>>    #include <asm/cputype.h>
>>>> @@ -1134,6 +1135,10 @@ int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node,
>>>>        pmd_t *pmdp;
>>>>          WARN_ON((start < VMEMMAP_START) || (end > VMEMMAP_END));
>>>> +
>>>> +    if (is_hugetlb_free_vmemmap_enabled() && !altmap)
>>>> +        return vmemmap_populate_basepages(start, end, node, altmap);
>>>
>>> Not considering the fact that this will force the kernel to have only
>>> base page size mapping for vmemmap (unless altmap is also requested)
>>> which might reduce the performance, it also enables vmemmap mapping to
>>> be teared down or build up at runtime which could potentially collide
>>> with other kernel page table walkers like ptdump or memory hotremove
>>> operation ! How those possible collisions are protected right now ?
>>
>> Hi Anshuman,
>>
>> Memory hotremove is not an issue IIRC. At the time memory is removed, all huge pages either have been migrated away or dissolved; the vmemmap is stable.
> 
> But what happens when a hot remove section's vmemmap area (which is being
> teared down) is nearby another vmemmap area which is either created or
> being destroyed for HugeTLB alloc/free purpose. As you mentioned HugeTLB
> pages inside the hot remove section might be safe. But what about other
> HugeTLB areas whose vmemmap area shares page table entries with vmemmap
> entries for a section being hot removed ? Massive HugeTLB alloc/use/free
> test cycle using memory just adjacent to a memory hotplug area, which is
> always added and removed periodically, should be able to expose this problem.
> 
> IIUC unlike vmalloc(), vmemap mapping areas in the kernel page table were
> always constant unless there are hotplug add or remove operations which
> are protected with a hotplug lock. Now with this change, we could have
> simultaneous walking and add or remove of the vmemap areas without any
> synchronization. Is not this problematic ?
> 
> On arm64 memory hot remove operation empties free portions of the vmemmap
> table after clearing them. Hence all concurrent walkers (hugetlb_vmemmap,
> hot remove, ptdump etc) need to be synchronized against hot remove.
> 
>  From arch/arm64/mm/mmu.c
> 
> void vmemmap_free(unsigned long start, unsigned long end,
>                  struct vmem_altmap *altmap)
> {
> #ifdef CONFIG_MEMORY_HOTPLUG
>          WARN_ON((start < VMEMMAP_START) || (end > VMEMMAP_END));
> 
>          unmap_hotplug_range(start, end, true, altmap);
>          free_empty_tables(start, end, VMEMMAP_START, VMEMMAP_END);
> #endif
> }

You are right, however, AFAIR

1) We always populate base pages, meaning we only modify PTEs and not 
actually add/remove page tables when creating/destroying a hugetlb page. 
Page table walkers should be fine and not suddenly run into a 
use-after-free.

2) For pfn_to_page() users to never fault, we have to do an atomic 
exchange of PTES, meaning, someone traversing a page table looking for 
pte_none() entries (like free_empty_tables() in your example) should 
never get a false positive.

Makes sense, or am I missing something?

> 
>>
>> vmemmap access (accessing the memmap via a virtual address) itself is not an issue. Manually walking (vmemmap) page tables might behave
> 
> Right.
> 
> differently, not sure if ptdump would require any synchronization.
> 
> Dumping an wrong value is probably okay but crashing because a page table
> entry is being freed after ptdump acquired the pointer is bad. On arm64,
> ptdump() is protected against hotremove via [get|put]_online_mems().

Okay, and as the feature in question only exchanges PTEs, we should be 
fine.



-- 
Thanks,

David / dhildenb