Re: [External] Re: [v1 4/6] memblock: introduce MEMBLOCK_RSRV_NOINIT flag

["Mika Penttilä" <mpenttil@redhat.com>]

On 7/28/23 16:47, Usama Arif wrote:
>
>
> On 28/07/2023 05:30, Mika Penttilä wrote:
>> Hi,
>>
>> On 7/27/23 23:46, Usama Arif wrote:
>>
>>> For reserved memory regions marked with this flag,
>>> reserve_bootmem_region is not called during memmap_init_reserved_pages.
>>> This can be used to avoid struct page initialization for
>>> regions which won't need them, for e.g. hugepages with
>>> HVO enabled.
>>>
>>> Signed-off-by: Usama Arif <usama.arif@bytedance.com>
>>> ---
>>>   include/linux/memblock.h |  7 +++++++
>>>   mm/memblock.c            | 32 ++++++++++++++++++++++++++------
>>>   2 files changed, 33 insertions(+), 6 deletions(-)
>>>
>>> diff --git a/include/linux/memblock.h b/include/linux/memblock.h
>>> index f71ff9f0ec81..7f9d06c08592 100644
>>> --- a/include/linux/memblock.h
>>> +++ b/include/linux/memblock.h
>>> @@ -47,6 +47,7 @@ enum memblock_flags {
>>>       MEMBLOCK_MIRROR        = 0x2,    /* mirrored region */
>>>       MEMBLOCK_NOMAP        = 0x4,    /* don't add to kernel direct 
>>> mapping */
>>>       MEMBLOCK_DRIVER_MANAGED = 0x8,    /* always detected via a 
>>> driver */
>>> +    MEMBLOCK_RSRV_NOINIT    = 0x10,    /* don't call 
>>> reserve_bootmem_region for this region */
>>>   };
>>>   /**
>>> @@ -125,6 +126,7 @@ int memblock_clear_hotplug(phys_addr_t base, 
>>> phys_addr_t size);
>>>   int memblock_mark_mirror(phys_addr_t base, phys_addr_t size);
>>>   int memblock_mark_nomap(phys_addr_t base, phys_addr_t size);
>>>   int memblock_clear_nomap(phys_addr_t base, phys_addr_t size);
>>> +int memblock_rsrv_mark_noinit(phys_addr_t base, phys_addr_t size);
>>>   void memblock_free_all(void);
>>>   void memblock_free(void *ptr, size_t size);
>>> @@ -259,6 +261,11 @@ static inline bool memblock_is_nomap(struct 
>>> memblock_region *m)
>>>       return m->flags & MEMBLOCK_NOMAP;
>>>   }
>>> +static inline bool memblock_is_noinit(struct memblock_region *m)
>>> +{
>>> +    return m->flags & MEMBLOCK_RSRV_NOINIT;
>>> +}
>>> +
>>>   static inline bool memblock_is_driver_managed(struct 
>>> memblock_region *m)
>>>   {
>>>       return m->flags & MEMBLOCK_DRIVER_MANAGED;
>>> diff --git a/mm/memblock.c b/mm/memblock.c
>>> index 4fd431d16ef2..3a15708af3b6 100644
>>> --- a/mm/memblock.c
>>> +++ b/mm/memblock.c
>>> @@ -997,6 +997,22 @@ int __init_memblock 
>>> memblock_clear_nomap(phys_addr_t base, phys_addr_t size)
>>>       return memblock_setclr_flag(base, size, 0, MEMBLOCK_NOMAP, 0);
>>>   }
>>> +/**
>>> + * memblock_rsrv_mark_noinit - Mark a reserved memory region with 
>>> flag MEMBLOCK_RSRV_NOINIT.
>>> + * @base: the base phys addr of the region
>>> + * @size: the size of the region
>>> + *
>>> + * For memory regions marked with %MEMBLOCK_RSRV_NOINIT, 
>>> reserve_bootmem_region
>>> + * is not called during memmap_init_reserved_pages, hence struct 
>>> pages are not
>>> + * initialized for this region.
>>> + *
>>> + * Return: 0 on success, -errno on failure.
>>> + */
>>> +int __init_memblock memblock_rsrv_mark_noinit(phys_addr_t base, 
>>> phys_addr_t size)
>>> +{
>>> +    return memblock_setclr_flag(base, size, 1, 
>>> MEMBLOCK_RSRV_NOINIT, 1);
>>> +}
>>> +
>>>   static bool should_skip_region(struct memblock_type *type,
>>>                      struct memblock_region *m,
>>>                      int nid, int flags)
>>> @@ -2113,13 +2129,17 @@ static void __init 
>>> memmap_init_reserved_pages(void)
>>>           memblock_set_node(start, end, &memblock.reserved, nid);
>>>       }
>>> -    /* initialize struct pages for the reserved regions */
>>> +    /*
>>> +     * initialize struct pages for reserved regions that don't have
>>> +     * the MEMBLOCK_RSRV_NOINIT flag set
>>> +     */
>>>       for_each_reserved_mem_region(region) {
>>> -        nid = memblock_get_region_node(region);
>>> -        start = region->base;
>>> -        end = start + region->size;
>>> -
>>> -        reserve_bootmem_region(start, end, nid);
>>> +        if (!memblock_is_noinit(region)) {
>>> +            nid = memblock_get_region_node(region);
>>> +            start = region->base;
>>> +            end = start + region->size;
>>> +            reserve_bootmem_region(start, end, nid);
>>> +        }
>>>       }
>>>   }
>>
>> There's code like:
>>
>> static inline void free_vmemmap_page(struct page *page)
>> {
>>          if (PageReserved(page))
>>                  free_bootmem_page(page);
>>          else
>>                  __free_page(page);
>> }
>>
>> which depends on the PageReserved being in vmempages pages, so I 
>> think you can't skip that part?
>>
>
> free_vmemmap_page_list (free_vmemmap_page) is called on struct pages 
> (refer to as [1]) that point to memory *which contains* the struct 
> pages (refer to as [2]) for the hugepage. The above if 
> (!memblock_is_noinit(region)) to not reserve_bootmem_region is called 
> for the struct pages [2] for the hugepage. struct pages [1] are not 
> changed with my patch.
>
> As an experiment if I run the diff at the bottom with and without 
> these patches I get the same log "HugeTLB: reserved pages 4096, normal 
> pages 0", which means those struct pages are treated the same without 
> and without these patches. (Its 4096 as 262144 struct pages [2] per 
> hugepage * 64 bytes per struct page / PAGE_SIZE = 4096 struct pages [1] )
>
> Also should have mentioned in cover letter, I used cat /proc/meminfo 
> to make sure it was working as expected. Reserving 500 1G hugepages 
> with and without these patches when hugetlb_free_vmemmap=on
> MemTotal:       536207112 kB (511.4G)
>
> when hugetlb_free_vmemmap=off
> MemTotal:       528015112 kB (503G)
>
>
> The expectation is that for 500 1G hugepages, when using HVO we have a 
> saving of 16380K*500=~8GB which is what we see with and without those 
> patches (511.4G - 503G). These patches didnt affect these numbers.
>
>
You are right, thanks for the explanation!


--Mika




>
> diff --git a/mm/hugetlb_vmemmap.c b/mm/hugetlb_vmemmap.c
> index b5b7834e0f42..bc0ec90552b7 100644
> --- a/mm/hugetlb_vmemmap.c
> +++ b/mm/hugetlb_vmemmap.c
> @@ -208,6 +208,8 @@ static int vmemmap_remap_range(unsigned long 
> start, unsigned long end,
>         return 0;
>  }
>
> +static int i = 0, j = 0;
> +
>  /*
>   * Free a vmemmap page. A vmemmap page can be allocated from the 
> memblock
>   * allocator or buddy allocator. If the PG_reserved flag is set, it 
> means
> @@ -216,10 +218,14 @@ static int vmemmap_remap_range(unsigned long 
> start, unsigned long end,
>   */
>  static inline void free_vmemmap_page(struct page *page)
>  {
> -       if (PageReserved(page))
> +       if (PageReserved(page)) {
> +               i++;
>                 free_bootmem_page(page);
> -       else
> +       }
> +       else {
> +               j++;
>                 __free_page(page);
> +       }
>  }
>
>  /* Free a list of the vmemmap pages */
> @@ -380,6 +386,7 @@ static int vmemmap_remap_free(unsigned long start, 
> unsigned long end,
>
>         free_vmemmap_page_list(&vmemmap_pages);
>
> +       pr_err("reserved pages %u, normal pages %u", i, j);
>         return ret;
>  }
>
>
>
>
>
>> --Mika
>>
>>
>