Re: [PATCH] riscv/mm: Add soft-dirty page tracking support

[Chunyan Zhang]

Hi Alex,

On Mon, 15 Jul 2024 at 19:21, Alexandre Ghiti <alex@xxxxxxxx> wrote:
>
> Hi Chunyan,
>
> On 10/07/2024 05:30, Chunyan Zhang wrote:
> > The PTE bit (9) is reserved for software, so we can use it for
> > soft-dirty tracking. This patch adds its standard handlers for
> > PTE, PMD, and swap entry.
>
>
> Unfortunately, ZONE_DEVICE has just used this last bit and should be
> merged in 6.11.

Yes, I read the patch just now.

> I'm currently discussing internally how we can get 2 other PTE bits from
> RVI in order to have the same number of available bits as x86 and arm64.

Yes I noticed that PTE bits reserved for software are too limited on RISC-V.

Besides softdirty, we probably can support uffd write-protect on
RISC-V if we will have two PTE bits for use.

> I guess that for now, if we really have a usecase for softdirty (and I
> think we do with CRIU), we'll have to make ZONE_DEVICE and soft-dirty
> mutually exclusive.

Yes, I also learned that CRIU uses soft-dirty.

> >
> > To add swap PTE soft-dirty tracking, we borrow bit (4) which is
> > available for swap PTEs on RISC-V systems.
> >
> > This patch has been tested with the kselftest mm suite in which
> > soft-dirty and madv_populate run and pass, and no regressions
> > are observed in any of the other tests.
>
>
> Did you give CRIU a try?

I haven't tried CRIU, actually I found soft-dirty was missing on
RISC-V by the way of running mm selftest cases.

I can cook a new patch to implement soft-dirty and ZONE_DEVICE share
the PTE bit(9), and make both features mutually exclusive if this
solution is accepted.

Or not to add soft-dirty until we have more other PTE bits that can be
used for software.

I'm open to listen to suggestions.

Thanks,
Chunyan

>
> Thanks,
>
> Alex
>
>
> >
> > Signed-off-by: Chunyan Zhang <zhangchunyan@xxxxxxxxxxx>
> > ---
> >   arch/riscv/Kconfig                    |  1 +
> >   arch/riscv/include/asm/pgtable-bits.h | 13 ++++++
> >   arch/riscv/include/asm/pgtable.h      | 65 ++++++++++++++++++++++++++-
> >   3 files changed, 78 insertions(+), 1 deletion(-)
> >
> > diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
> > index b94176e25be1..2e3ad2925a6b 100644
> > --- a/arch/riscv/Kconfig
> > +++ b/arch/riscv/Kconfig
> > @@ -118,6 +118,7 @@ config RISCV
> >       select HAVE_ARCH_MMAP_RND_COMPAT_BITS if COMPAT
> >       select HAVE_ARCH_RANDOMIZE_KSTACK_OFFSET
> >       select HAVE_ARCH_SECCOMP_FILTER
> > +     select HAVE_ARCH_SOFT_DIRTY
> >       select HAVE_ARCH_THREAD_STRUCT_WHITELIST
> >       select HAVE_ARCH_TRACEHOOK
> >       select HAVE_ARCH_TRANSPARENT_HUGEPAGE if 64BIT && MMU
> > diff --git a/arch/riscv/include/asm/pgtable-bits.h b/arch/riscv/include/asm/pgtable-bits.h
> > index 179bd4afece4..bab48f5fd1e2 100644
> > --- a/arch/riscv/include/asm/pgtable-bits.h
> > +++ b/arch/riscv/include/asm/pgtable-bits.h
> > @@ -19,6 +19,19 @@
> >   #define _PAGE_SOFT      (3 << 8)    /* Reserved for software */
> >
> >   #define _PAGE_SPECIAL   (1 << 8)    /* RSW: 0x1 */
> > +
> > +#ifdef CONFIG_MEM_SOFT_DIRTY
> > +#define _PAGE_SOFT_DIRTY     (1 << 9)    /* RSW: 0x2 for software dirty tracking */
> > +/*
> > + * BIT 4 is not involved into swap entry computation, so we
> > + * can borrow it for swap page soft-dirty tracking.
> > + */
> > +#define _PAGE_SWP_SOFT_DIRTY _PAGE_USER
> > +#else
> > +#define _PAGE_SOFT_DIRTY     0
> > +#define _PAGE_SWP_SOFT_DIRTY 0
> > +#endif /* CONFIG_MEM_SOFT_DIRTY */
> > +
> >   #define _PAGE_TABLE     _PAGE_PRESENT
> >
> >   /*
> > diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h
> > index aad8b8ca51f1..46f512f52580 100644
> > --- a/arch/riscv/include/asm/pgtable.h
> > +++ b/arch/riscv/include/asm/pgtable.h
> > @@ -408,7 +408,7 @@ static inline pte_t pte_mkwrite_novma(pte_t pte)
> >
> >   static inline pte_t pte_mkdirty(pte_t pte)
> >   {
> > -     return __pte(pte_val(pte) | _PAGE_DIRTY);
> > +     return __pte(pte_val(pte) | _PAGE_DIRTY | _PAGE_SOFT_DIRTY);
> >   }
> >
> >   static inline pte_t pte_mkclean(pte_t pte)
> > @@ -436,6 +436,36 @@ static inline pte_t pte_mkhuge(pte_t pte)
> >       return pte;
> >   }
> >
> > +static inline int pte_soft_dirty(pte_t pte)
> > +{
> > +     return pte_val(pte) & _PAGE_SOFT_DIRTY;
> > +}
> > +
> > +static inline pte_t pte_mksoft_dirty(pte_t pte)
> > +{
> > +     return __pte(pte_val(pte) | _PAGE_SOFT_DIRTY);
> > +}
> > +
> > +static inline pte_t pte_clear_soft_dirty(pte_t pte)
> > +{
> > +     return __pte(pte_val(pte) & ~(_PAGE_SOFT_DIRTY));
> > +}
> > +
> > +static inline int pte_swp_soft_dirty(pte_t pte)
> > +{
> > +     return pte_val(pte) & _PAGE_SWP_SOFT_DIRTY;
> > +}
> > +
> > +static inline pte_t pte_swp_mksoft_dirty(pte_t pte)
> > +{
> > +     return __pte(pte_val(pte) | _PAGE_SWP_SOFT_DIRTY);
> > +}
> > +
> > +static inline pte_t pte_swp_clear_soft_dirty(pte_t pte)
> > +{
> > +     return __pte(pte_val(pte) & ~(_PAGE_SWP_SOFT_DIRTY));
> > +}
> > +
> >   #ifdef CONFIG_RISCV_ISA_SVNAPOT
> >   #define pte_leaf_size(pte)  (pte_napot(pte) ?                               \
> >                                       napot_cont_size(napot_cont_order(pte)) :\
> > @@ -721,6 +751,38 @@ static inline pmd_t pmd_mkdirty(pmd_t pmd)
> >       return pte_pmd(pte_mkdirty(pmd_pte(pmd)));
> >   }
> >
> > +static inline int pmd_soft_dirty(pmd_t pmd)
> > +{
> > +     return pte_soft_dirty(pmd_pte(pmd));
> > +}
> > +
> > +static inline pmd_t pmd_mksoft_dirty(pmd_t pmd)
> > +{
> > +     return pte_pmd(pte_mksoft_dirty(pmd_pte(pmd)));
> > +}
> > +
> > +static inline pmd_t pmd_clear_soft_dirty(pmd_t pmd)
> > +{
> > +     return pte_pmd(pte_clear_soft_dirty(pmd_pte(pmd)));
> > +}
> > +
> > +#ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION
> > +static inline int pmd_swp_soft_dirty(pmd_t pmd)
> > +{
> > +     return pte_swp_soft_dirty(pmd_pte(pmd));
> > +}
> > +
> > +static inline pmd_t pmd_swp_mksoft_dirty(pmd_t pmd)
> > +{
> > +     return pte_pmd(pte_swp_mksoft_dirty(pmd_pte(pmd)));
> > +}
> > +
> > +static inline pmd_t pmd_swp_clear_soft_dirty(pmd_t pmd)
> > +{
> > +     return pte_pmd(pte_swp_clear_soft_dirty(pmd_pte(pmd)));
> > +}
> > +#endif /* CONFIG_ARCH_ENABLE_THP_MIGRATION */
> > +
> >   static inline void set_pmd_at(struct mm_struct *mm, unsigned long addr,
> >                               pmd_t *pmdp, pmd_t pmd)
> >   {
> > @@ -811,6 +873,7 @@ extern pmd_t pmdp_collapse_flush(struct vm_area_struct *vma,
> >    * Format of swap PTE:
> >    *  bit            0:       _PAGE_PRESENT (zero)
> >    *  bit       1 to 3:       _PAGE_LEAF (zero)
> > + *   bit            4:       _PAGE_SWP_SOFT_DIRTY
> >    *  bit            5:       _PAGE_PROT_NONE (zero)
> >    *  bit            6:       exclusive marker
> >    *  bits      7 to 11:      swap type