[PATCH v2 2/3] powerpc/mm/hash: Avoid multiple HPT resize-ups on memory hotplug

[Leonardo Brás]

On Mon, 2021-06-07 at 15:10 +1000, David Gibson wrote:
> On Fri, Apr 30, 2021 at 11:36:08AM -0300, Leonardo Bras wrote:
> > Every time a memory hotplug happens, and the memory limit crosses a
> > 2^n
> > value, it may be necessary to perform HPT resizing-up, which can
> > take
> > some time (over 100ms in my tests).
> > 
> > It usually is not an issue, but it can take some time if a lot of
> > memory
> > is added to a guest with little starting memory:
> > Adding 256G to a 2GB guest, for example will require 8 HPT resizes.
> > 
> > Perform an HPT resize before memory hotplug, updating HPT to its
> > final size (considering a successful hotplug), taking the number of
> > HPT resizes to at most one per memory hotplug action.
> > 
> > Signed-off-by: Leonardo Bras <leobras.c at gmail.com>
> 
> Reviewed-by: David Gibson <david at gibson.dropbear.id.au>

Thanks David!

> 
> > ---
> >  arch/powerpc/include/asm/book3s/64/hash.h     |  2 ++
> >  arch/powerpc/mm/book3s64/hash_utils.c         | 20
> > +++++++++++++++++++
> >  .../platforms/pseries/hotplug-memory.c        |  9 +++++++++
> >  3 files changed, 31 insertions(+)
> > 
> > diff --git a/arch/powerpc/include/asm/book3s/64/hash.h
> > b/arch/powerpc/include/asm/book3s/64/hash.h
> > index d959b0195ad9..fad4af8b8543 100644
> > --- a/arch/powerpc/include/asm/book3s/64/hash.h
> > +++ b/arch/powerpc/include/asm/book3s/64/hash.h
> > @@ -255,6 +255,8 @@ int hash__create_section_mapping(unsigned long
> > start, unsigned long end,
> >                                  int nid, pgprot_t prot);
> >  int hash__remove_section_mapping(unsigned long start, unsigned
> > long end);
> >  
> > +void hash_batch_expand_prepare(unsigned long newsize);
> > +
> >  #endif /* !__ASSEMBLY__ */
> >  #endif /* __KERNEL__ */
> >  #endif /* _ASM_POWERPC_BOOK3S_64_HASH_H */
> > diff --git a/arch/powerpc/mm/book3s64/hash_utils.c
> > b/arch/powerpc/mm/book3s64/hash_utils.c
> > index 608e4ed397a9..3fa395b3fe57 100644
> > --- a/arch/powerpc/mm/book3s64/hash_utils.c
> > +++ b/arch/powerpc/mm/book3s64/hash_utils.c
> > @@ -859,6 +859,26 @@ int hash__remove_section_mapping(unsigned long
> > start, unsigned long end)
> >  
> >         return rc;
> >  }
> > +
> > +void hash_batch_expand_prepare(unsigned long newsize)
> > +{
> > +       const u64 starting_size = ppc64_pft_size;
> > +
> > +       /*
> > +        * Resizing-up HPT should never fail, but there are some
> > cases system starts with higher
> > +        * SHIFT than required, and we go through the funny case of
> > resizing HPT down while
> > +        * adding memory
> > +        */
> > +
> > +       while (resize_hpt_for_hotplug(newsize, false) == -ENOSPC) {
> > +               newsize *= 2;
> > +               pr_warn("Hash collision while resizing HPT\n");
> > +
> > +               /* Do not try to resize to the starting size, or
> > bigger value */
> > +               if (htab_shift_for_mem_size(newsize) >=
> > starting_size)
> > +                       break;
> > +       }
> > +}
> >  #endif /* CONFIG_MEMORY_HOTPLUG */
> >  
> >  static void __init hash_init_partition_table(phys_addr_t
> > hash_table,
> > diff --git a/arch/powerpc/platforms/pseries/hotplug-memory.c
> > b/arch/powerpc/platforms/pseries/hotplug-memory.c
> > index 8377f1f7c78e..48b2cfe4ce69 100644
> > --- a/arch/powerpc/platforms/pseries/hotplug-memory.c
> > +++ b/arch/powerpc/platforms/pseries/hotplug-memory.c
> > @@ -13,6 +13,7 @@
> >  #include <linux/memory.h>
> >  #include <linux/memory_hotplug.h>
> >  #include <linux/slab.h>
> > +#include <linux/pgtable.h>
> >  
> >  #include <asm/firmware.h>
> >  #include <asm/machdep.h>
> > @@ -671,6 +672,10 @@ static int dlpar_memory_add_by_count(u32
> > lmbs_to_add)
> >         if (lmbs_available < lmbs_to_add)
> >                 return -EINVAL;
> >  
> > +       if (!radix_enabled())
> > +               hash_batch_expand_prepare(memblock_phys_mem_size()
> > +
> > +                                                lmbs_to_add *
> > drmem_lmb_size());
> > +
> >         for_each_drmem_lmb(lmb) {
> >                 if (lmb->flags & DRCONF_MEM_ASSIGNED)
> >                         continue;
> > @@ -788,6 +793,10 @@ static int dlpar_memory_add_by_ic(u32
> > lmbs_to_add, u32 drc_index)
> >         if (lmbs_available < lmbs_to_add)
> >                 return -EINVAL;
> >  
> > +       if (!radix_enabled())
> > +               hash_batch_expand_prepare(memblock_phys_mem_size()
> > +
> > +                                         lmbs_to_add *
> > drmem_lmb_size());
> > +
> >         for_each_drmem_lmb_in_range(lmb, start_lmb, end_lmb) {
> >                 if (lmb->flags & DRCONF_MEM_ASSIGNED)
> >                         continue;
> 
> -- 
> David Gibson                    | I'll have my music baroque, and my
> code
> david AT gibson.dropbear.id.au  | minimalist, thank you.  NOT _the_
> _other_
>                                 | _way_ _around_!
> http://www.ozlabs.org/~dgibson