On Tue, Jul 19, 2022 at 5:47 PM Huang, Ying <ying.huang@xxxxxxxxx> wrote:
>
> Barry Song <21cnbao@xxxxxxxxx> writes:
>
> > On Tue, Jul 19, 2022 at 3:59 PM Barry Song <21cnbao@xxxxxxxxx> wrote:
> >>
> >> On Tue, Jul 19, 2022 at 3:35 PM Anshuman Khandual
> >> <anshuman.khandual@xxxxxxx> wrote:
> >> >
> >> >
> >> >
> >> > On 7/19/22 08:58, Huang, Ying wrote:
> >> > > Anshuman Khandual <anshuman.khandual@xxxxxxx> writes:
> >> > >
> >> > >> On 7/19/22 06:53, Barry Song wrote:
> >> > >>> On Tue, Jul 19, 2022 at 12:44 PM Huang, Ying <ying.huang@xxxxxxxxx> wrote:
> >> > >>>>
> >> > >>>> Barry Song <21cnbao@xxxxxxxxx> writes:
> >> > >>>>
> >> > >>>>> From: Barry Song <v-songbaohua@xxxxxxxx>
> >> > >>>>>
> >> > >>>>> THP_SWAP has been proven to improve the swap throughput significantly
> >> > >>>>> on x86_64 according to commit bd4c82c22c367e ("mm, THP, swap: delay
> >> > >>>>> splitting THP after swapped out").
> >> > >>>>> As long as arm64 uses 4K page size, it is quite similar with x86_64
> >> > >>>>> by having 2MB PMD THP. THP_SWAP is architecture-independent, thus,
> >> > >>>>> enabling it on arm64 will benefit arm64 as well.
> >> > >>>>> A corner case is that MTE has an assumption that only base pages
> >> > >>>>> can be swapped. We won't enable THP_SWAP for ARM64 hardware with
> >> > >>>>> MTE support until MTE is reworked to coexist with THP_SWAP.
> >> > >>>>>
> >> > >>>>> A micro-benchmark is written to measure thp swapout throughput as
> >> > >>>>> below,
> >> > >>>>>
> >> > >>>>> unsigned long long tv_to_ms(struct timeval tv)
> >> > >>>>> {
> >> > >>>>> return tv.tv_sec * 1000 + tv.tv_usec / 1000;
> >> > >>>>> }
> >> > >>>>>
> >> > >>>>> main()
> >> > >>>>> {
> >> > >>>>> struct timeval tv_b, tv_e;;
> >> > >>>>> #define SIZE 400*1024*1024
> >> > >>>>> volatile void *p = mmap(NULL, SIZE, PROT_READ | PROT_WRITE,
> >> > >>>>> MAP_PRIVATE | MAP_ANONYMOUS, -1, 0);
> >> > >>>>> if (!p) {
> >> > >>>>> perror("fail to get memory");
> >> > >>>>> exit(-1);
> >> > >>>>> }
> >> > >>>>>
> >> > >>>>> madvise(p, SIZE, MADV_HUGEPAGE);
> >> > >>>>> memset(p, 0x11, SIZE); /* write to get mem */
> >> > >>>>>
> >> > >>>>> gettimeofday(&tv_b, NULL);
> >> > >>>>> madvise(p, SIZE, MADV_PAGEOUT);
> >> > >>>>> gettimeofday(&tv_e, NULL);
> >> > >>>>>
> >> > >>>>> printf("swp out bandwidth: %ld bytes/ms\n",
> >> > >>>>> SIZE/(tv_to_ms(tv_e) - tv_to_ms(tv_b)));
> >> > >>>>> }
> >> > >>>>>
> >> > >>>>> Testing is done on rk3568 64bit quad core processor Quad Core
> >> > >>>>> Cortex-A55 platform - ROCK 3A.
> >> > >>>>> thp swp throughput w/o patch: 2734bytes/ms (mean of 10 tests)
> >> > >>>>> thp swp throughput w/ patch: 3331bytes/ms (mean of 10 tests)
> >> > >>>>>
> >> > >>>>> Cc: "Huang, Ying" <ying.huang@xxxxxxxxx>
> >> > >>>>> Cc: Minchan Kim <minchan@xxxxxxxxxx>
> >> > >>>>> Cc: Johannes Weiner <hannes@xxxxxxxxxxx>
> >> > >>>>> Cc: Hugh Dickins <hughd@xxxxxxxxxx>
> >> > >>>>> Cc: Andrea Arcangeli <aarcange@xxxxxxxxxx>
> >> > >>>>> Cc: Anshuman Khandual <anshuman.khandual@xxxxxxx>
> >> > >>>>> Cc: Steven Price <steven.price@xxxxxxx>
> >> > >>>>> Cc: Yang Shi <shy828301@xxxxxxxxx>
> >> > >>>>> Signed-off-by: Barry Song <v-songbaohua@xxxxxxxx>
> >> > >>>>> ---
> >> > >>>>> -v3:
> >> > >>>>> * refine the commit log;
> >> > >>>>> * add a benchmark result;
> >> > >>>>> * refine the macro of arch_thp_swp_supported
> >> > >>>>> Thanks to the comments of Anshuman, Andrew, Steven
> >> > >>>>>
> >> > >>>>> arch/arm64/Kconfig | 1 +
> >> > >>>>> arch/arm64/include/asm/pgtable.h | 6 ++++++
> >> > >>>>> include/linux/huge_mm.h | 12 ++++++++++++
> >> > >>>>> mm/swap_slots.c | 2 +-
> >> > >>>>> 4 files changed, 20 insertions(+), 1 deletion(-)
> >> > >>>>>
> >> > >>>>> diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
> >> > >>>>> index 1652a9800ebe..e1c540e80eec 100644
> >> > >>>>> --- a/arch/arm64/Kconfig
> >> > >>>>> +++ b/arch/arm64/Kconfig
> >> > >>>>> @@ -101,6 +101,7 @@ config ARM64
> >> > >>>>> select ARCH_WANT_HUGETLB_PAGE_OPTIMIZE_VMEMMAP
> >> > >>>>> select ARCH_WANT_LD_ORPHAN_WARN
> >> > >>>>> select ARCH_WANTS_NO_INSTR
> >> > >>>>> + select ARCH_WANTS_THP_SWAP if ARM64_4K_PAGES
> >> > >>>>> select ARCH_HAS_UBSAN_SANITIZE_ALL
> >> > >>>>> select ARM_AMBA
> >> > >>>>> select ARM_ARCH_TIMER
> >> > >>>>> diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
> >> > >>>>> index 0b6632f18364..78d6f6014bfb 100644
> >> > >>>>> --- a/arch/arm64/include/asm/pgtable.h
> >> > >>>>> +++ b/arch/arm64/include/asm/pgtable.h
> >> > >>>>> @@ -45,6 +45,12 @@
> >> > >>>>> __flush_tlb_range(vma, addr, end, PUD_SIZE, false, 1)
> >> > >>>>> #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
> >> > >>>>>
> >> > >>>>> +static inline bool arch_thp_swp_supported(void)
> >> > >>>>> +{
> >> > >>>>> + return !system_supports_mte();
> >> > >>>>> +}
> >> > >>>>> +#define arch_thp_swp_supported arch_thp_swp_supported
> >> > >>>>> +
> >> > >>>>> /*
> >> > >>>>> * Outside of a few very special situations (e.g. hibernation), we always
> >> > >>>>> * use broadcast TLB invalidation instructions, therefore a spurious page
> >> > >>>>> diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
> >> > >>>>> index de29821231c9..4ddaf6ad73ef 100644
> >> > >>>>> --- a/include/linux/huge_mm.h
> >> > >>>>> +++ b/include/linux/huge_mm.h
> >> > >>>>> @@ -461,4 +461,16 @@ static inline int split_folio_to_list(struct folio *folio,
> >> > >>>>> return split_huge_page_to_list(&folio->page, list);
> >> > >>>>> }
> >> > >>>>>
> >> > >>>>> +/*
> >> > >>>>> + * archs that select ARCH_WANTS_THP_SWAP but don't support THP_SWP due to
> >> > >>>>> + * limitations in the implementation like arm64 MTE can override this to
> >> > >>>>> + * false
> >> > >>>>> + */
> >> > >>>>> +#ifndef arch_thp_swp_supported
> >> > >>>>> +static inline bool arch_thp_swp_supported(void)
> >> > >>>>> +{
> >> > >>>>> + return true;
> >> > >>>>> +}
> >> > >>>>
> >> > >>>> How about the following?
> >> > >>>>
> >> > >>>> static inline bool arch_wants_thp_swap(void)
> >> > >>>> {
> >> > >>>> return IS_ENABLED(ARCH_WANTS_THP_SWAP);
> >> > >>>> }
> >> > >>>
> >> > >>> This looks good. then i'll need to change arm64 to
> >> > >>>
> >> > >>> +static inline bool arch_thp_swp_supported(void)
> >> > >>> +{
> >> > >>> + return IS_ENABLED(ARCH_WANTS_THP_SWAP) && !system_supports_mte();
> >> > >>> +}
> >> > >>
> >> > >> Why ? CONFIG_THP_SWAP depends on ARCH_WANTS_THP_SWAP. In folio_alloc_swap(),
> >> > >> IS_ENABLED(CONFIG_THP_SWAP) enabled, will also imply ARCH_WANTS_THP_SWAP too
> >> > >> is enabled. Hence checking for ARCH_WANTS_THP_SWAP again does not make sense
> >> > >> either in the generic fallback stub, or in arm64 platform override. Because
> >> > >> without ARCH_WANTS_THP_SWAP enabled, arch_thp_swp_supported() should never
> >> > >> be called in the first place.
> >> > >
> >> > > For the only caller now, the checking looks redundant. But the original
> >> > > proposed implementation as follows,
> >> > >
> >> > > static inline bool arch_thp_swp_supported(void)
> >> > > {
> >> > > return true;
> >> > > }
> >> > >
> >> > > will return true even on architectures that don't support/want THP swap.
> >> >
> >> > But the function will never be called on for those platforms.
> >> >
> >> > > That will confuse people too.
> >> >
> >> > I dont see how.
> >> >
> >> > >
> >> > > And the "redundant" checking has no run time overhead, because compiler
> >> > > will do the trick.
> >> > I understand that, but dont think this indirection is necessary.
> >>
> >> Hi Anshuman, Hi Ying,
> >> Thanks for the comments of both of you. Does the below look ok?
> >>
> >> generic,
> >>
> >> static inline bool arch_wants_thp_swap(void)
> >> {
> >> return IS_ENABLED(CONFIG_THP_SWAP);
> >> }
> >>
> >
> > sorry, i actually meant arch_thp_swp_supported() but not
> > arch_wants_thp_swap() in generic code,
> >
> > static inline bool arch_thp_swp_supported(void)
> > {
> > return IS_ENABLED(CONFIG_THP_SWAP);
> > }
>
> IS_ENABLED(CONFIG_THP_SWAP) doesn't match the name too. It's an option
> selected by users. arch_thp_swp_supported() is to report the
> capability.
Hi Ying,
CONFIG_THP_SWAP implicitly includes ARCH_WANTS_THP_SWAP. So it seems
a bit odd to have still another arch_wants_thp_swap().
if the name of arch_thp_swp_supported is not sensible to you, will
thp_swp_supported()
without arch_ make more sense? a similar example is,
static inline bool gigantic_page_runtime_supported(void)
{
return IS_ENABLED(CONFIG_ARCH_HAS_GIGANTIC_PAGE);
}
Otherwise, can we just keep the code as is according to Anshuman's suggestion?
Thanks
Barry
}
>
> Best Regards,
> Huang, Ying
>
> >> arm64,
> >>
> >> static inline bool arch_thp_swp_supported(void)
> >> {
> >> return IS_ENABLED(CONFIG_THP_SWAP) && !system_supports_mte();
> >> }
> >>
> >> caller,
> >>
> >> folio_alloc_swap(struct folio *folio)
> >> {
> >>
> >> if (folio_test_large(folio)) {
> >> - if (IS_ENABLED(CONFIG_THP_SWAP))
> >> + if (arch_thp_swp_supported())
> >> get_swap_pages(1, &entry, folio_nr_pages(folio));
> >> goto out;
> >> }
> >>
> >> Thanks
> >> Barry
