[RESEND PATCH V4 2/3] riscv: mm: Add soft-dirty page tracking support
Chunyan Zhang
zhang.lyra at gmail.com
Thu Aug 29 19:31:55 PDT 2024
Hi Jinjie,
On Fri, 30 Aug 2024 at 09:31, Jinjie Ruan <ruanjinjie at huawei.com> wrote:
>
>
>
> On 2024/8/30 9:11, Chunyan Zhang wrote:
> > The PTE bit(9) is reserved for software, now used by DEVMAP,
> > this patch reuse bit(9) for soft-dirty which is enabled only
> > if !CONFIG_ARCH_HAS_PTE_DEVMAP, in other words, soft-dirty
> > and devmap will be mutually exclusive on RISC-V.
> >
> > To add swap PTE soft-dirty tracking, we borrow bit (4) which is
> > available for swap PTEs on RISC-V systems.
> >
> > Signed-off-by: Chunyan Zhang <zhangchunyan at iscas.ac.cn>
> > ---
> > arch/riscv/Kconfig | 27 ++++++++++-
> > arch/riscv/include/asm/pgtable-bits.h | 12 +++++
> > arch/riscv/include/asm/pgtable.h | 69 ++++++++++++++++++++++++++-
> > 3 files changed, 106 insertions(+), 2 deletions(-)
> >
> > diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
> > index 0f3cd7c3a436..f1460fc01cd4 100644
> > --- a/arch/riscv/Kconfig
> > +++ b/arch/riscv/Kconfig
> > @@ -39,7 +39,6 @@ config RISCV
> > select ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE
> > select ARCH_HAS_PMEM_API
> > select ARCH_HAS_PREPARE_SYNC_CORE_CMD
> > - select ARCH_HAS_PTE_DEVMAP if 64BIT && MMU
> > select ARCH_HAS_PTE_SPECIAL
> > select ARCH_HAS_SET_DIRECT_MAP if MMU
> > select ARCH_HAS_SET_MEMORY if MMU
> > @@ -948,6 +947,32 @@ config RANDOMIZE_BASE
> >
> > If unsure, say N.
> >
> > +choice
> > + prompt "PET RSW Bit(9) used for"
> > + default RISCV_HAS_PTE_DEVMEP
> > + depends on MMU && 64BIT
> > + help
> > + RISC-V PTE bit(9) is reserved for software, and used by more than
> > + one kernel features which cannot be supported at the same time.
> > + So we have to select one for it.
> > +
> > +config RISCV_HAS_PTE_DEVMEP
> > + bool "DEVMAP mark"
> > + select ARCH_HAS_PTE_DEVMAP
> > + help
> > + The PTE bit(9) is used for DEVMAP mark. ZONE_DEVICE pages need DEVMAP
> > + PTEs support to function.
> > +
> > + So if you want to use ZONE_DEVICE, select this.
> > +
> > +config RISCV_HAS_SOFT_DIRTY
> > + bool "soft dirty"
> > + select HAVE_ARCH_SOFT_DIRTY
> > + help
> > + The PTE bit(9) is used for soft-dirty tracking.
> > +
> > +endchoice
> > +
>
> Hi, ARCH_HAS_PTE_DEVMAP will be removed in following patch, I guess
> riscv will too:
>
> https://lore.kernel.org/all/47c26640cd85f3db2e0a2796047199bb984d1b3f.1719386613.git-series.apopple@nvidia.com/
Thanks for sharing, I didn't notice this.
It looks like we should remove PTE_DEVMAP first and then add soft
dirty and uffd_wp.
Thanks,
Chunyan
>
> > endmenu # "Kernel features"
> >
> > menu "Boot options"
> > diff --git a/arch/riscv/include/asm/pgtable-bits.h b/arch/riscv/include/asm/pgtable-bits.h
> > index 5bcc73430829..c6d51fe9fc6f 100644
> > --- a/arch/riscv/include/asm/pgtable-bits.h
> > +++ b/arch/riscv/include/asm/pgtable-bits.h
> > @@ -26,6 +26,18 @@
> > #define _PAGE_DEVMAP 0
> > #endif /* CONFIG_ARCH_HAS_PTE_DEVMAP */
> >
> > +#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 089f3c9f56a3..d41507919ef2 100644
> > --- a/arch/riscv/include/asm/pgtable.h
> > +++ b/arch/riscv/include/asm/pgtable.h
> > @@ -428,7 +428,7 @@ 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)
> > @@ -461,6 +461,38 @@ static inline pte_t pte_mkhuge(pte_t pte)
> > return pte;
> > }
> >
> > +#ifdef CONFIG_HAVE_ARCH_SOFT_DIRTY
> > +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));
> > +}
> > +#endif /* CONFIG_HAVE_ARCH_SOFT_DIRTY */
> > +
> > #ifdef CONFIG_RISCV_ISA_SVNAPOT
> > #define pte_leaf_size(pte) (pte_napot(pte) ? \
> > napot_cont_size(napot_cont_order(pte)) :\
> > @@ -751,6 +783,40 @@ static inline pmd_t pmd_mkdevmap(pmd_t pmd)
> > return pte_pmd(pte_mkdevmap(pmd_pte(pmd)));
> > }
> >
> > +#ifdef CONFIG_HAVE_ARCH_SOFT_DIRTY
> > +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 */
> > +#endif /* CONFIG_HAVE_ARCH_SOFT_DIRTY */
> > +
> > static inline void set_pmd_at(struct mm_struct *mm, unsigned long addr,
> > pmd_t *pmdp, pmd_t pmd)
> > {
> > @@ -841,6 +907,7 @@ 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
More information about the linux-riscv
mailing list