[RESEND PATCH V4 3/3] riscv: mm: Add uffd write-protect support

[Jinjie Ruan]

On 2024/8/30 9:11, Chunyan Zhang wrote:
> Reuse PTE bit(9) to do uffd-wp tracking and make it mutually exclusive
> with soft-dirty and DEVMAP which all use this PTE bit.
> 
> Additionally for tracking the uffd-wp state as a PTE swap bit,
> we use swap entry pte bit(4) which is also used by swap
> soft-dirty tracking.
> 
> Signed-off-by: Chunyan Zhang <zhangchunyan at iscas.ac.cn>

Hi, I have submitted a similar patch below before rebased on commit
216e04bf1e4d ("riscv: mm: Add support for ZONE_DEVICE")
has been removed:

https://lore.kernel.org/all/20240730095325.3540198-1-ruanjinjie@huawei.com/

> ---
>  arch/riscv/Kconfig                    |  7 +++
>  arch/riscv/include/asm/pgtable-bits.h | 13 ++++++
>  arch/riscv/include/asm/pgtable.h      | 66 ++++++++++++++++++++++++++-
>  3 files changed, 85 insertions(+), 1 deletion(-)
> 
> diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
> index f1460fc01cd4..aa595a5ed4b8 100644
> --- a/arch/riscv/Kconfig
> +++ b/arch/riscv/Kconfig
> @@ -971,6 +971,13 @@ config RISCV_HAS_SOFT_DIRTY
>  	help
>  	  The PTE bit(9) is used for soft-dirty tracking.
>  
> +config RISCV_HAS_USERFAULTFD_WP
> +	bool "userfaultfd write protection"
> +	select HAVE_ARCH_USERFAULTFD_WP
> +	depends on USERFAULTFD
> +	help
> +	  The PTE bit(9) is used for userfaultfd write-protected
> +	  tracking.
>  endchoice
>  
>  endmenu # "Kernel features"
> diff --git a/arch/riscv/include/asm/pgtable-bits.h b/arch/riscv/include/asm/pgtable-bits.h
> index c6d51fe9fc6f..7de16141c049 100644
> --- a/arch/riscv/include/asm/pgtable-bits.h
> +++ b/arch/riscv/include/asm/pgtable-bits.h
> @@ -38,6 +38,19 @@
>  #define _PAGE_SWP_SOFT_DIRTY	0
>  #endif /* CONFIG_MEM_SOFT_DIRTY */
>  
> +#ifdef CONFIG_HAVE_ARCH_USERFAULTFD_WP
> +/*
> + * CONFIG_HAVE_ARCH_USERFAULTFD_WP is mutually exclusive with
> + * HAVE_ARCH_SOFT_DIRTY so we can use the same bit for uffd-wp
> + * and soft-dirty tracking.
> + */
> +#define _PAGE_UFFD_WP		(1 << 9) /* RSW: 0x2 for uffd-wp tracking */
> +#define _PAGE_SWP_UFFD_WP	_PAGE_USER
> +#else
> +#define _PAGE_UFFD_WP		0
> +#define _PAGE_SWP_UFFD_WP	0
> +#endif
> +
>  #define _PAGE_TABLE     _PAGE_PRESENT
>  
>  /*
> diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h
> index d41507919ef2..6ce4c9ba862a 100644
> --- a/arch/riscv/include/asm/pgtable.h
> +++ b/arch/riscv/include/asm/pgtable.h
> @@ -417,6 +417,38 @@ static inline pte_t pte_wrprotect(pte_t pte)
>  	return __pte(pte_val(pte) & ~(_PAGE_WRITE));
>  }
>  
> +#ifdef CONFIG_HAVE_ARCH_USERFAULTFD_WP
> +static inline int pte_uffd_wp(pte_t pte)
> +{
> +	return pte_val(pte) & _PAGE_UFFD_WP;
> +}
> +
> +static inline pte_t pte_mkuffd_wp(pte_t pte)
> +{
> +	return pte_wrprotect(__pte(pte_val(pte) | _PAGE_UFFD_WP));
> +}
> +
> +static inline pte_t pte_clear_uffd_wp(pte_t pte)
> +{
> +	return __pte(pte_val(pte) & ~(_PAGE_UFFD_WP));
> +}
> +
> +static inline int pte_swp_uffd_wp(pte_t pte)
> +{
> +	return pte_val(pte) & _PAGE_SWP_UFFD_WP;
> +}
> +
> +static inline pte_t pte_swp_mkuffd_wp(pte_t pte)
> +{
> +	return pte_wrprotect(__pte(pte_val(pte) | _PAGE_SWP_UFFD_WP));
> +}
> +
> +static inline pte_t pte_swp_clear_uffd_wp(pte_t pte)
> +{
> +	return __pte(pte_val(pte) & ~(_PAGE_SWP_UFFD_WP));
> +}
> +#endif /* CONFIG_HAVE_ARCH_USERFAULTFD_WP */
> +
>  /* static inline pte_t pte_mkread(pte_t pte) */
>  
>  static inline pte_t pte_mkwrite_novma(pte_t pte)
> @@ -783,6 +815,38 @@ static inline pmd_t pmd_mkdevmap(pmd_t pmd)
>  	return pte_pmd(pte_mkdevmap(pmd_pte(pmd)));
>  }
>  
> +#ifdef CONFIG_HAVE_ARCH_USERFAULTFD_WP
> +static inline int pmd_uffd_wp(pmd_t pmd)
> +{
> +	return pte_uffd_wp(pmd_pte(pmd));
> +}
> +
> +static inline pmd_t pmd_mkuffd_wp(pmd_t pmd)
> +{
> +	return pte_pmd(pte_mkuffd_wp(pmd_pte(pmd)));
> +}
> +
> +static inline pmd_t pmd_clear_uffd_wp(pmd_t pmd)
> +{
> +	return pte_pmd(pte_clear_uffd_wp(pmd_pte(pmd)));
> +}
> +
> +static inline int pmd_swp_uffd_wp(pmd_t pmd)
> +{
> +	return pte_swp_uffd_wp(pmd_pte(pmd));
> +}
> +
> +static inline pmd_t pmd_swp_mkuffd_wp(pmd_t pmd)
> +{
> +	return pte_pmd(pte_swp_mkuffd_wp(pmd_pte(pmd)));
> +}
> +
> +static inline pmd_t pmd_swp_clear_uffd_wp(pmd_t pmd)
> +{
> +	return pte_pmd(pte_swp_clear_uffd_wp(pmd_pte(pmd)));
> +}
> +#endif /* CONFIG_HAVE_ARCH_USERFAULTFD_WP */
> +
>  #ifdef CONFIG_HAVE_ARCH_SOFT_DIRTY
>  static inline int pmd_soft_dirty(pmd_t pmd)
>  {
> @@ -907,7 +971,7 @@ 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	       4:	_PAGE_SWP_SOFT_DIRTY or _PAGE_SWP_UFFD_WP
>   *	bit            5:	_PAGE_PROT_NONE (zero)
>   *	bit            6:	exclusive marker
>   *	bits      7 to 11:	swap type