Re: [PATCH v8 1/2] kho: fix deferred initialization of scratch areas

[Michał Cłapiński]

On Thu, Apr 16, 2026 at 4:45 PM Mike Rapoport <rppt@xxxxxxxxxx> wrote:
>
> Hi Michal,
>
> On Thu, Apr 16, 2026 at 01:06:53PM +0200, Michal Clapinski wrote:
> > Currently, if CONFIG_DEFERRED_STRUCT_PAGE_INIT is enabled,
> > kho_release_scratch() will initialize the struct pages and set migratetype
> > of KHO scratch. Unless the whole scratch fits below first_deferred_pfn,
> > some of that will be overwritten either by deferred_init_pages() or
> > memmap_init_reserved_range().
> >
> > To fix it, make memmap_init_range(), deferred_init_memmap_chunk() and
> > memmap_init_reserved_range() recognize KHO scratch regions and set
> > migratetype of pageblocks in those regions to MIGRATE_CMA.
> >
> > Signed-off-by: Michal Clapinski <mclapinski@xxxxxxxxxx>
> > Co-developed-by: Mike Rapoport (Microsoft) <rppt@xxxxxxxxxx>
> > Signed-off-by: Mike Rapoport (Microsoft) <rppt@xxxxxxxxxx>
>
> Your signed-off should be last here :)
> https://docs.kernel.org/process/submitting-patches.html#when-to-use-acked-by-cc-and-co-developed-by
>
> > ---
> >  include/linux/memblock.h           |  7 +++--
> >  kernel/liveupdate/kexec_handover.c | 25 ------------------
> >  mm/memblock.c                      | 41 ++++++++++++++----------------
> >  mm/mm_init.c                       | 27 ++++++++++++++------
> >  4 files changed, 43 insertions(+), 57 deletions(-)
> >
> > diff --git a/include/linux/memblock.h b/include/linux/memblock.h
> > index 6ec5e9ac0699..410f2a399691 100644
> > --- a/include/linux/memblock.h
> > +++ b/include/linux/memblock.h
> > @@ -614,11 +614,14 @@ static inline void memtest_report_meminfo(struct seq_file *m) { }
> >  #ifdef CONFIG_MEMBLOCK_KHO_SCRATCH
> >  void memblock_set_kho_scratch_only(void);
> >  void memblock_clear_kho_scratch_only(void);
> > -void memmap_init_kho_scratch_pages(void);
> > +bool memblock_is_kho_scratch_memory(phys_addr_t addr);
> >  #else
> >  static inline void memblock_set_kho_scratch_only(void) { }
> >  static inline void memblock_clear_kho_scratch_only(void) { }
> > -static inline void memmap_init_kho_scratch_pages(void) {}
> > +static inline bool memblock_is_kho_scratch_memory(phys_addr_t addr)
> > +{
> > +     return false;
> > +}
> >  #endif
> >
> >  #endif /* _LINUX_MEMBLOCK_H */
> > diff --git a/kernel/liveupdate/kexec_handover.c b/kernel/liveupdate/kexec_handover.c
> > index 18509d8082ea..a507366a2cf9 100644
> > --- a/kernel/liveupdate/kexec_handover.c
> > +++ b/kernel/liveupdate/kexec_handover.c
> > @@ -1576,35 +1576,10 @@ static __init int kho_init(void)
> >  }
> >  fs_initcall(kho_init);
> >
> > -static void __init kho_release_scratch(void)
> > -{
> > -     phys_addr_t start, end;
> > -     u64 i;
> > -
> > -     memmap_init_kho_scratch_pages();
> > -
> > -     /*
> > -      * Mark scratch mem as CMA before we return it. That way we
> > -      * ensure that no kernel allocations happen on it. That means
> > -      * we can reuse it as scratch memory again later.
> > -      */
> > -     __for_each_mem_range(i, &memblock.memory, NULL, NUMA_NO_NODE,
> > -                          MEMBLOCK_KHO_SCRATCH, &start, &end, NULL) {
> > -             ulong start_pfn = pageblock_start_pfn(PFN_DOWN(start));
> > -             ulong end_pfn = pageblock_align(PFN_UP(end));
> > -             ulong pfn;
> > -
> > -             for (pfn = start_pfn; pfn < end_pfn; pfn += pageblock_nr_pages)
> > -                     init_pageblock_migratetype(pfn_to_page(pfn),
> > -                                                MIGRATE_CMA, false);
> > -     }
> > -}
> > -
> >  void __init kho_memory_init(void)
> >  {
> >       if (kho_in.scratch_phys) {
> >               kho_scratch = phys_to_virt(kho_in.scratch_phys);
> > -             kho_release_scratch();
> >
> >               if (kho_mem_retrieve(kho_get_fdt()))
> >                       kho_in.fdt_phys = 0;
> > diff --git a/mm/memblock.c b/mm/memblock.c
> > index 4224fdaa8918..fab234f732c3 100644
> > --- a/mm/memblock.c
> > +++ b/mm/memblock.c
> > @@ -17,6 +17,7 @@
> >  #include <linux/seq_file.h>
> >  #include <linux/memblock.h>
> >  #include <linux/mutex.h>
> > +#include <linux/page-isolation.h>
> >
> >  #ifdef CONFIG_KEXEC_HANDOVER
> >  #include <linux/libfdt.h>
> > @@ -959,28 +960,6 @@ __init void memblock_clear_kho_scratch_only(void)
> >  {
> >       kho_scratch_only = false;
> >  }
> > -
> > -__init void memmap_init_kho_scratch_pages(void)
> > -{
> > -     phys_addr_t start, end;
> > -     unsigned long pfn;
> > -     int nid;
> > -     u64 i;
> > -
> > -     if (!IS_ENABLED(CONFIG_DEFERRED_STRUCT_PAGE_INIT))
> > -             return;
> > -
> > -     /*
> > -      * Initialize struct pages for free scratch memory.
> > -      * The struct pages for reserved scratch memory will be set up in
> > -      * memmap_init_reserved_pages()
> > -      */
> > -     __for_each_mem_range(i, &memblock.memory, NULL, NUMA_NO_NODE,
> > -                          MEMBLOCK_KHO_SCRATCH, &start, &end, &nid) {
> > -             for (pfn = PFN_UP(start); pfn < PFN_DOWN(end); pfn++)
> > -                     init_deferred_page(pfn, nid);
> > -     }
> > -}
> >  #endif
> >
> >  /**
> > @@ -1971,6 +1950,18 @@ bool __init_memblock memblock_is_map_memory(phys_addr_t addr)
> >       return !memblock_is_nomap(&memblock.memory.regions[i]);
> >  }
> >
> > +#ifdef CONFIG_MEMBLOCK_KHO_SCRATCH
> > +bool __init_memblock memblock_is_kho_scratch_memory(phys_addr_t addr)
>
> We already have a block under #ifdef CONFIG_MEMBLOCK_KHO_SCRATCH, please
> add this function to that block.
>
> > +{
> > +     int i = memblock_search(&memblock.memory, addr);
> > +
> > +     if (i == -1)
> > +             return false;
> > +
> > +     return memblock_is_kho_scratch(&memblock.memory.regions[i]);
> > +}
> > +#endif
> > +
> >  int __init_memblock memblock_search_pfn_nid(unsigned long pfn,
> >                        unsigned long *start_pfn, unsigned long *end_pfn)
> >  {
> > @@ -2262,6 +2253,12 @@ static void __init memmap_init_reserved_range(phys_addr_t start,
> >                * access it yet.
> >                */
> >               __SetPageReserved(page);
> > +
> > +#ifdef CONFIG_MEMBLOCK_KHO_SCRATCH
>
> No need for #ifdef here, there's a stub returning false for
> CONFIG_MEMBLOCK_KHO_SCRATCH=n case.

In all 3 places the #ifdef is there because MIGRATE_CMA might be
undefined. I already broke mm-new branch in the past because of that.

> > +             if (memblock_is_kho_scratch_memory(PFN_PHYS(pfn)) &&
> > +                 pageblock_aligned(pfn))
> > +                     init_pageblock_migratetype(page, MIGRATE_CMA, false);
> > +#endif
> >       }
> >  }
> >
> > diff --git a/mm/mm_init.c b/mm/mm_init.c
> > index f9f8e1af921c..890c3ae21ba0 100644
> > --- a/mm/mm_init.c
> > +++ b/mm/mm_init.c
> > @@ -916,8 +916,15 @@ void __meminit memmap_init_range(unsigned long size, int nid, unsigned long zone
> >                * over the place during system boot.
> >                */
> >               if (pageblock_aligned(pfn)) {
> > -                     init_pageblock_migratetype(page, migratetype,
> > -                                     isolate_pageblock);
> > +                     int mt = migratetype;
> > +
> > +#ifdef CONFIG_MEMBLOCK_KHO_SCRATCH
>
> Ditto.
>
> > +                     if (memblock_is_kho_scratch_memory(page_to_phys(page)))
> > +                             mt = MIGRATE_CMA;
> > +#endif
>
> memmap_init_zone_range() is called each time for a region in
> memblock.memory. This means either entire range will be KHO_SCRATHC or not
> and we can check for memblock_is_kho_scratch_memory() once for every region
> in memmap_init_zone_range().

Thanks, I didn't notice for_each_mem_pfn_range iterates over regions. Will do.

> > +
> > +                     init_pageblock_migratetype(page, mt,
> > +                                                isolate_pageblock);
> >                       cond_resched();
> >               }
> >               pfn++;
> > @@ -1970,7 +1977,7 @@ unsigned long __init node_map_pfn_alignment(void)
> >
> >  #ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
> >  static void __init deferred_free_pages(unsigned long pfn,
> > -             unsigned long nr_pages)
> > +             unsigned long nr_pages, enum migratetype mt)
> >  {
> >       struct page *page;
> >       unsigned long i;
> > @@ -1983,8 +1990,7 @@ static void __init deferred_free_pages(unsigned long pfn,
> >       /* Free a large naturally-aligned chunk if possible */
> >       if (nr_pages == MAX_ORDER_NR_PAGES && IS_MAX_ORDER_ALIGNED(pfn)) {
> >               for (i = 0; i < nr_pages; i += pageblock_nr_pages)
> > -                     init_pageblock_migratetype(page + i, MIGRATE_MOVABLE,
> > -                                     false);
> > +                     init_pageblock_migratetype(page + i, mt, false);
> >               __free_pages_core(page, MAX_PAGE_ORDER, MEMINIT_EARLY);
> >               return;
> >       }
> > @@ -1994,8 +2000,7 @@ static void __init deferred_free_pages(unsigned long pfn,
> >
> >       for (i = 0; i < nr_pages; i++, page++, pfn++) {
> >               if (pageblock_aligned(pfn))
> > -                     init_pageblock_migratetype(page, MIGRATE_MOVABLE,
> > -                                     false);
> > +                     init_pageblock_migratetype(page, mt, false);
> >               __free_pages_core(page, 0, MEMINIT_EARLY);
> >       }
> >  }
> > @@ -2051,6 +2056,7 @@ deferred_init_memmap_chunk(unsigned long start_pfn, unsigned long end_pfn,
> >       u64 i = 0;
> >
> >       for_each_free_mem_range(i, nid, 0, &start, &end, NULL) {
> > +             enum migratetype mt = MIGRATE_MOVABLE;
> >               unsigned long spfn = PFN_UP(start);
> >               unsigned long epfn = PFN_DOWN(end);
> >
> > @@ -2060,12 +2066,17 @@ deferred_init_memmap_chunk(unsigned long start_pfn, unsigned long end_pfn,
> >               spfn = max(spfn, start_pfn);
> >               epfn = min(epfn, end_pfn);
> >
> > +#ifdef CONFIG_MEMBLOCK_KHO_SCRATCH
>
> No need for #ifdef here as well.
>
> > +             if (memblock_is_kho_scratch_memory(PFN_PHYS(spfn)))
> > +                     mt = MIGRATE_CMA;
> > +#endif
> > +
> >               while (spfn < epfn) {
> >                       unsigned long mo_pfn = ALIGN(spfn + 1, MAX_ORDER_NR_PAGES);
> >                       unsigned long chunk_end = min(mo_pfn, epfn);
> >
> >                       nr_pages += deferred_init_pages(zone, spfn, chunk_end);
> > -                     deferred_free_pages(spfn, chunk_end - spfn);
> > +                     deferred_free_pages(spfn, chunk_end - spfn, mt);
> >
> >                       spfn = chunk_end;
> >
> > --
> > 2.54.0.rc1.555.g9c883467ad-goog
> >
>
> --
> Sincerely yours,
> Mike.