Re: [PATCH v2 02/11] mm: convert track_pfn_insert() to pfnmap_setup_cachemode*()

["Liam R. Howlett" <Liam.Howlett@oracle.com>]

* David Hildenbrand <david@redhat.com> [250512 08:34]:
> ... by factoring it out from track_pfn_remap() into
> pfnmap_setup_cachemode() and provide pfnmap_setup_cachemode_pfn() as
> a replacement for track_pfn_insert().
> 
> For PMDs/PUDs, we keep checking a single pfn only. Add some documentation,
> and also document why it is valid to not check the whole pfn range.
> 
> We'll reuse pfnmap_setup_cachemode() from core MM next.
> 
> Acked-by: Ingo Molnar <mingo@kernel.org> # x86 bits
> Signed-off-by: David Hildenbrand <david@redhat.com>

Reviewed-by: Liam R. Howlett <Liam.Howlett@oracle.com>

> ---
>  arch/x86/mm/pat/memtype.c | 24 ++++++------------
>  include/linux/pgtable.h   | 52 +++++++++++++++++++++++++++++++++------
>  mm/huge_memory.c          |  5 ++--
>  mm/memory.c               |  4 +--
>  4 files changed, 57 insertions(+), 28 deletions(-)
> 
> diff --git a/arch/x86/mm/pat/memtype.c b/arch/x86/mm/pat/memtype.c
> index edec5859651d6..fa78facc6f633 100644
> --- a/arch/x86/mm/pat/memtype.c
> +++ b/arch/x86/mm/pat/memtype.c
> @@ -1031,7 +1031,6 @@ int track_pfn_remap(struct vm_area_struct *vma, pgprot_t *prot,
>  		    unsigned long pfn, unsigned long addr, unsigned long size)
>  {
>  	resource_size_t paddr = (resource_size_t)pfn << PAGE_SHIFT;
> -	enum page_cache_mode pcm;
>  
>  	/* reserve the whole chunk starting from paddr */
>  	if (!vma || (addr == vma->vm_start
> @@ -1044,13 +1043,17 @@ int track_pfn_remap(struct vm_area_struct *vma, pgprot_t *prot,
>  		return ret;
>  	}
>  
> +	return pfnmap_setup_cachemode(pfn, size, prot);
> +}
> +
> +int pfnmap_setup_cachemode(unsigned long pfn, unsigned long size, pgprot_t *prot)
> +{
> +	resource_size_t paddr = (resource_size_t)pfn << PAGE_SHIFT;
> +	enum page_cache_mode pcm;
> +
>  	if (!pat_enabled())
>  		return 0;
>  
> -	/*
> -	 * For anything smaller than the vma size we set prot based on the
> -	 * lookup.
> -	 */
>  	pcm = lookup_memtype(paddr);
>  
>  	/* Check memtype for the remaining pages */
> @@ -1065,17 +1068,6 @@ int track_pfn_remap(struct vm_area_struct *vma, pgprot_t *prot,
>  	return 0;
>  }
>  
> -void track_pfn_insert(struct vm_area_struct *vma, pgprot_t *prot, pfn_t pfn)
> -{
> -	enum page_cache_mode pcm;
> -
> -	if (!pat_enabled())
> -		return;
> -
> -	pcm = lookup_memtype(pfn_t_to_phys(pfn));
> -	pgprot_set_cachemode(prot, pcm);
> -}
> -
>  /*
>   * untrack_pfn is called while unmapping a pfnmap for a region.
>   * untrack can be called for a specific region indicated by pfn and size or
> diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h
> index f1e890b604609..be1745839871c 100644
> --- a/include/linux/pgtable.h
> +++ b/include/linux/pgtable.h
> @@ -1496,13 +1496,10 @@ static inline int track_pfn_remap(struct vm_area_struct *vma, pgprot_t *prot,
>  	return 0;
>  }
>  
> -/*
> - * track_pfn_insert is called when a _new_ single pfn is established
> - * by vmf_insert_pfn().
> - */
> -static inline void track_pfn_insert(struct vm_area_struct *vma, pgprot_t *prot,
> -				    pfn_t pfn)
> +static inline int pfnmap_setup_cachemode(unsigned long pfn, unsigned long size,
> +		pgprot_t *prot)
>  {
> +	return 0;
>  }
>  
>  /*
> @@ -1552,8 +1549,32 @@ static inline void untrack_pfn_clear(struct vm_area_struct *vma)
>  extern int track_pfn_remap(struct vm_area_struct *vma, pgprot_t *prot,
>  			   unsigned long pfn, unsigned long addr,
>  			   unsigned long size);
> -extern void track_pfn_insert(struct vm_area_struct *vma, pgprot_t *prot,
> -			     pfn_t pfn);
> +
> +/**
> + * pfnmap_setup_cachemode - setup the cachemode in the pgprot for a pfn range
> + * @pfn: the start of the pfn range
> + * @size: the size of the pfn range in bytes
> + * @prot: the pgprot to modify
> + *
> + * Lookup the cachemode for the pfn range starting at @pfn with the size
> + * @size and store it in @prot, leaving other data in @prot unchanged.
> + *
> + * This allows for a hardware implementation to have fine-grained control of
> + * memory cache behavior at page level granularity. Without a hardware
> + * implementation, this function does nothing.
> + *
> + * Currently there is only one implementation for this - x86 Page Attribute
> + * Table (PAT). See Documentation/arch/x86/pat.rst for more details.
> + *
> + * This function can fail if the pfn range spans pfns that require differing
> + * cachemodes. If the pfn range was previously verified to have a single
> + * cachemode, it is sufficient to query only a single pfn. The assumption is
> + * that this is the case for drivers using the vmf_insert_pfn*() interface.
> + *
> + * Returns 0 on success and -EINVAL on error.
> + */
> +int pfnmap_setup_cachemode(unsigned long pfn, unsigned long size,
> +		pgprot_t *prot);
>  extern int track_pfn_copy(struct vm_area_struct *dst_vma,
>  		struct vm_area_struct *src_vma, unsigned long *pfn);
>  extern void untrack_pfn_copy(struct vm_area_struct *dst_vma,
> @@ -1563,6 +1584,21 @@ extern void untrack_pfn(struct vm_area_struct *vma, unsigned long pfn,
>  extern void untrack_pfn_clear(struct vm_area_struct *vma);
>  #endif
>  
> +/**
> + * pfnmap_setup_cachemode_pfn - setup the cachemode in the pgprot for a pfn
> + * @pfn: the pfn
> + * @prot: the pgprot to modify
> + *
> + * Lookup the cachemode for @pfn and store it in @prot, leaving other
> + * data in @prot unchanged.
> + *
> + * See pfnmap_setup_cachemode() for details.
> + */
> +static inline void pfnmap_setup_cachemode_pfn(unsigned long pfn, pgprot_t *prot)
> +{
> +	pfnmap_setup_cachemode(pfn, PAGE_SIZE, prot);
> +}
> +
>  #ifdef CONFIG_MMU
>  #ifdef __HAVE_COLOR_ZERO_PAGE
>  static inline int is_zero_pfn(unsigned long pfn)
> diff --git a/mm/huge_memory.c b/mm/huge_memory.c
> index 2780a12b25f01..d3e66136e41a3 100644
> --- a/mm/huge_memory.c
> +++ b/mm/huge_memory.c
> @@ -1455,7 +1455,8 @@ vm_fault_t vmf_insert_pfn_pmd(struct vm_fault *vmf, pfn_t pfn, bool write)
>  			return VM_FAULT_OOM;
>  	}
>  
> -	track_pfn_insert(vma, &pgprot, pfn);
> +	pfnmap_setup_cachemode_pfn(pfn_t_to_pfn(pfn), &pgprot);
> +
>  	ptl = pmd_lock(vma->vm_mm, vmf->pmd);
>  	error = insert_pfn_pmd(vma, addr, vmf->pmd, pfn, pgprot, write,
>  			pgtable);
> @@ -1577,7 +1578,7 @@ vm_fault_t vmf_insert_pfn_pud(struct vm_fault *vmf, pfn_t pfn, bool write)
>  	if (addr < vma->vm_start || addr >= vma->vm_end)
>  		return VM_FAULT_SIGBUS;
>  
> -	track_pfn_insert(vma, &pgprot, pfn);
> +	pfnmap_setup_cachemode_pfn(pfn_t_to_pfn(pfn), &pgprot);
>  
>  	ptl = pud_lock(vma->vm_mm, vmf->pud);
>  	insert_pfn_pud(vma, addr, vmf->pud, pfn, write);
> diff --git a/mm/memory.c b/mm/memory.c
> index 99af83434e7c5..064fc55d8eab9 100644
> --- a/mm/memory.c
> +++ b/mm/memory.c
> @@ -2564,7 +2564,7 @@ vm_fault_t vmf_insert_pfn_prot(struct vm_area_struct *vma, unsigned long addr,
>  	if (!pfn_modify_allowed(pfn, pgprot))
>  		return VM_FAULT_SIGBUS;
>  
> -	track_pfn_insert(vma, &pgprot, __pfn_to_pfn_t(pfn, PFN_DEV));
> +	pfnmap_setup_cachemode_pfn(pfn, &pgprot);
>  
>  	return insert_pfn(vma, addr, __pfn_to_pfn_t(pfn, PFN_DEV), pgprot,
>  			false);
> @@ -2627,7 +2627,7 @@ static vm_fault_t __vm_insert_mixed(struct vm_area_struct *vma,
>  	if (addr < vma->vm_start || addr >= vma->vm_end)
>  		return VM_FAULT_SIGBUS;
>  
> -	track_pfn_insert(vma, &pgprot, pfn);
> +	pfnmap_setup_cachemode_pfn(pfn_t_to_pfn(pfn), &pgprot);
>  
>  	if (!pfn_modify_allowed(pfn_t_to_pfn(pfn), pgprot))
>  		return VM_FAULT_SIGBUS;
> -- 
> 2.49.0
>