[PATCHv2,1/9] mm: Introduce new vm_insert_range and vm_insert_range_buggy API

Commit Message

Souptick Joarder Jan. 31, 2019, 3:08 a.m. UTC

Previouly drivers have their own way of mapping range of
kernel pages/memory into user vma and this was done by
invoking vm_insert_page() within a loop.

As this pattern is common across different drivers, it can
be generalized by creating new functions and use it across
the drivers.

vm_insert_range() is the API which could be used to mapped
kernel memory/pages in drivers which has considered vm_pgoff

vm_insert_range_buggy() is the API which could be used to map
range of kernel memory/pages in drivers which has not considered
vm_pgoff. vm_pgoff is passed default as 0 for those drivers.

We _could_ then at a later "fix" these drivers which are using
vm_insert_range_buggy() to behave according to the normal vm_pgoff
offsetting simply by removing the _buggy suffix on the function
name and if that causes regressions, it gives us an easy way to revert.

Signed-off-by: Souptick Joarder <[e-mail]>
Suggested-by: Russell King <[e-mail]>
Suggested-by: Matthew Wilcox <[e-mail]>
---
 include/linux/mm.h |  4 +++
 mm/memory.c        | 81 ++++++++++++++++++++++++++++++++++++++++++++++++++++++
 mm/nommu.c         | 14 ++++++++++
 3 files changed, 99 insertions(+)

Comments

Mike Rapoport Jan. 31, 2019, 8:38 a.m. UTC | #1

On Thu, Jan 31, 2019 at 08:38:12AM +0530, Souptick Joarder wrote:
> Previouly drivers have their own way of mapping range of
> kernel pages/memory into user vma and this was done by
> invoking vm_insert_page() within a loop.
> 
> As this pattern is common across different drivers, it can
> be generalized by creating new functions and use it across
> the drivers.
> 
> vm_insert_range() is the API which could be used to mapped
> kernel memory/pages in drivers which has considered vm_pgoff
> 
> vm_insert_range_buggy() is the API which could be used to map
> range of kernel memory/pages in drivers which has not considered
> vm_pgoff. vm_pgoff is passed default as 0 for those drivers.
> 
> We _could_ then at a later "fix" these drivers which are using
> vm_insert_range_buggy() to behave according to the normal vm_pgoff
> offsetting simply by removing the _buggy suffix on the function
> name and if that causes regressions, it gives us an easy way to revert.
> 
> Signed-off-by: Souptick Joarder <[e-mail]>
> Suggested-by: Russell King <[e-mail]>
> Suggested-by: Matthew Wilcox <[e-mail]>
> ---
>  include/linux/mm.h |  4 +++
>  mm/memory.c        | 81 ++++++++++++++++++++++++++++++++++++++++++++++++++++++
>  mm/nommu.c         | 14 ++++++++++
>  3 files changed, 99 insertions(+)
> 
> diff --git a/include/linux/mm.h b/include/linux/mm.h
> index 80bb640..25752b0 100644
> --- a/include/linux/mm.h
> +++ b/include/linux/mm.h
> @@ -2565,6 +2565,10 @@ unsigned long change_prot_numa(struct vm_area_struct *vma,
>  int remap_pfn_range(struct vm_area_struct *, unsigned long addr,
>  			unsigned long pfn, unsigned long size, pgprot_t);
>  int vm_insert_page(struct vm_area_struct *, unsigned long addr, struct page *);
> +int vm_insert_range(struct vm_area_struct *vma, struct page **pages,
> +				unsigned long num);
> +int vm_insert_range_buggy(struct vm_area_struct *vma, struct page **pages,
> +				unsigned long num);
>  vm_fault_t vmf_insert_pfn(struct vm_area_struct *vma, unsigned long addr,
>  			unsigned long pfn);
>  vm_fault_t vmf_insert_pfn_prot(struct vm_area_struct *vma, unsigned long addr,
> diff --git a/mm/memory.c b/mm/memory.c
> index e11ca9d..0a4bf57 100644
> --- a/mm/memory.c
> +++ b/mm/memory.c
> @@ -1520,6 +1520,87 @@ int vm_insert_page(struct vm_area_struct *vma, unsigned long addr,
>  }
>  EXPORT_SYMBOL(vm_insert_page);
> 
> +/**
> + * __vm_insert_range - insert range of kernel pages into user vma
> + * @vma: user vma to map to
> + * @pages: pointer to array of source kernel pages
> + * @num: number of pages in page array
> + * @offset: user's requested vm_pgoff
> + *
> + * This allows drivers to insert range of kernel pages they've allocated
> + * into a user vma.
> + *
> + * If we fail to insert any page into the vma, the function will return
> + * immediately leaving any previously inserted pages present.  Callers
> + * from the mmap handler may immediately return the error as their caller
> + * will destroy the vma, removing any successfully inserted pages. Other
> + * callers should make their own arrangements for calling unmap_region().
> + *
> + * Context: Process context.
> + * Return: 0 on success and error code otherwise.
> + */
> +static int __vm_insert_range(struct vm_area_struct *vma, struct page **pages,
> +				unsigned long num, unsigned long offset)
> +{
> +	unsigned long count = vma_pages(vma);
> +	unsigned long uaddr = vma->vm_start;
> +	int ret, i;
> +
> +	/* Fail if the user requested offset is beyond the end of the object */
> +	if (offset > num)
> +		return -ENXIO;
> +
> +	/* Fail if the user requested size exceeds available object size */
> +	if (count > num - offset)
> +		return -ENXIO;
> +
> +	for (i = 0; i < count; i++) {
> +		ret = vm_insert_page(vma, uaddr, pages[offset + i]);
> +		if (ret < 0)
> +			return ret;
> +		uaddr += PAGE_SIZE;
> +	}
> +
> +	return 0;
> +}
> +
> +/**
> + * vm_insert_range - insert range of kernel pages starts with non zero offset
> + * @vma: user vma to map to
> + * @pages: pointer to array of source kernel pages
> + * @num: number of pages in page array
> + *
> + * Maps an object consisting of `num' `pages', catering for the user's
> + * requested vm_pgoff
> + *

The elaborate description you've added to __vm_insert_range() is better put
here, as this is the "public" function.

> + * Context: Process context. Called by mmap handlers.
> + * Return: 0 on success and error code otherwise.
> + */
> +int vm_insert_range(struct vm_area_struct *vma, struct page **pages,
> +				unsigned long num)
> +{
> +	return __vm_insert_range(vma, pages, num, vma->vm_pgoff);
> +}
> +EXPORT_SYMBOL(vm_insert_range);
> +
> +/**
> + * vm_insert_range_buggy - insert range of kernel pages starts with zero offset
> + * @vma: user vma to map to
> + * @pages: pointer to array of source kernel pages
> + * @num: number of pages in page array
> + *
> + * Maps a set of pages, always starting at page[0]

Here I'd add something like:

Similar to vm_insert_range(), except that it explicitly sets @vm_pgoff to
0. This function is intended for the drivers that did not consider
@vm_pgoff.

> vm_insert_range_buggy() is the API which could be used to map
> range of kernel memory/pages in drivers which has not considered
> vm_pgoff. vm_pgoff is passed default as 0 for those drivers.

> + *
> + * Context: Process context. Called by mmap handlers.
> + * Return: 0 on success and error code otherwise.
> + */
> +int vm_insert_range_buggy(struct vm_area_struct *vma, struct page **pages,
> +				unsigned long num)
> +{
> +	return __vm_insert_range(vma, pages, num, 0);
> +}
> +EXPORT_SYMBOL(vm_insert_range_buggy);
> +
>  static vm_fault_t insert_pfn(struct vm_area_struct *vma, unsigned long addr,
>  			pfn_t pfn, pgprot_t prot, bool mkwrite)
>  {
> diff --git a/mm/nommu.c b/mm/nommu.c
> index 749276b..21d101e 100644
> --- a/mm/nommu.c
> +++ b/mm/nommu.c
> @@ -473,6 +473,20 @@ int vm_insert_page(struct vm_area_struct *vma, unsigned long addr,
>  }
>  EXPORT_SYMBOL(vm_insert_page);
> 
> +int vm_insert_range(struct vm_area_struct *vma, struct page **pages,
> +			unsigned long num)
> +{
> +	return -EINVAL;
> +}
> +EXPORT_SYMBOL(vm_insert_range);
> +
> +int vm_insert_range_buggy(struct vm_area_struct *vma, struct page **pages,
> +				unsigned long num)
> +{
> +	return -EINVAL;
> +}
> +EXPORT_SYMBOL(vm_insert_range_buggy);
> +
>  /*
>   *  sys_brk() for the most part doesn't need the global kernel
>   *  lock, except when an application is doing something nasty
> -- 
> 1.9.1
>

Souptick Joarder Jan. 31, 2019, 10:13 a.m. UTC | #2

On Thu, Jan 31, 2019 at 2:09 PM Mike Rapoport <[e-mail]> wrote:
>
> On Thu, Jan 31, 2019 at 08:38:12AM +0530, Souptick Joarder wrote:
> > Previouly drivers have their own way of mapping range of
> > kernel pages/memory into user vma and this was done by
> > invoking vm_insert_page() within a loop.
> >
> > As this pattern is common across different drivers, it can
> > be generalized by creating new functions and use it across
> > the drivers.
> >
> > vm_insert_range() is the API which could be used to mapped
> > kernel memory/pages in drivers which has considered vm_pgoff
> >
> > vm_insert_range_buggy() is the API which could be used to map
> > range of kernel memory/pages in drivers which has not considered
> > vm_pgoff. vm_pgoff is passed default as 0 for those drivers.
> >
> > We _could_ then at a later "fix" these drivers which are using
> > vm_insert_range_buggy() to behave according to the normal vm_pgoff
> > offsetting simply by removing the _buggy suffix on the function
> > name and if that causes regressions, it gives us an easy way to revert.
> >
> > Signed-off-by: Souptick Joarder <[e-mail]>
> > Suggested-by: Russell King <[e-mail]>
> > Suggested-by: Matthew Wilcox <[e-mail]>
> > ---
> >  include/linux/mm.h |  4 +++
> >  mm/memory.c        | 81 ++++++++++++++++++++++++++++++++++++++++++++++++++++++
> >  mm/nommu.c         | 14 ++++++++++
> >  3 files changed, 99 insertions(+)
> >
> > diff --git a/include/linux/mm.h b/include/linux/mm.h
> > index 80bb640..25752b0 100644
> > --- a/include/linux/mm.h
> > +++ b/include/linux/mm.h
> > @@ -2565,6 +2565,10 @@ unsigned long change_prot_numa(struct vm_area_struct *vma,
> >  int remap_pfn_range(struct vm_area_struct *, unsigned long addr,
> >                       unsigned long pfn, unsigned long size, pgprot_t);
> >  int vm_insert_page(struct vm_area_struct *, unsigned long addr, struct page *);
> > +int vm_insert_range(struct vm_area_struct *vma, struct page **pages,
> > +                             unsigned long num);
> > +int vm_insert_range_buggy(struct vm_area_struct *vma, struct page **pages,
> > +                             unsigned long num);
> >  vm_fault_t vmf_insert_pfn(struct vm_area_struct *vma, unsigned long addr,
> >                       unsigned long pfn);
> >  vm_fault_t vmf_insert_pfn_prot(struct vm_area_struct *vma, unsigned long addr,
> > diff --git a/mm/memory.c b/mm/memory.c
> > index e11ca9d..0a4bf57 100644
> > --- a/mm/memory.c
> > +++ b/mm/memory.c
> > @@ -1520,6 +1520,87 @@ int vm_insert_page(struct vm_area_struct *vma, unsigned long addr,
> >  }
> >  EXPORT_SYMBOL(vm_insert_page);
> >
> > +/**
> > + * __vm_insert_range - insert range of kernel pages into user vma
> > + * @vma: user vma to map to
> > + * @pages: pointer to array of source kernel pages
> > + * @num: number of pages in page array
> > + * @offset: user's requested vm_pgoff
> > + *
> > + * This allows drivers to insert range of kernel pages they've allocated
> > + * into a user vma.
> > + *
> > + * If we fail to insert any page into the vma, the function will return
> > + * immediately leaving any previously inserted pages present.  Callers
> > + * from the mmap handler may immediately return the error as their caller
> > + * will destroy the vma, removing any successfully inserted pages. Other
> > + * callers should make their own arrangements for calling unmap_region().
> > + *
> > + * Context: Process context.
> > + * Return: 0 on success and error code otherwise.
> > + */
> > +static int __vm_insert_range(struct vm_area_struct *vma, struct page **pages,
> > +                             unsigned long num, unsigned long offset)
> > +{
> > +     unsigned long count = vma_pages(vma);
> > +     unsigned long uaddr = vma->vm_start;
> > +     int ret, i;
> > +
> > +     /* Fail if the user requested offset is beyond the end of the object */
> > +     if (offset > num)
> > +             return -ENXIO;
> > +
> > +     /* Fail if the user requested size exceeds available object size */
> > +     if (count > num - offset)
> > +             return -ENXIO;
> > +
> > +     for (i = 0; i < count; i++) {
> > +             ret = vm_insert_page(vma, uaddr, pages[offset + i]);
> > +             if (ret < 0)
> > +                     return ret;
> > +             uaddr += PAGE_SIZE;
> > +     }
> > +
> > +     return 0;
> > +}
> > +
> > +/**
> > + * vm_insert_range - insert range of kernel pages starts with non zero offset
> > + * @vma: user vma to map to
> > + * @pages: pointer to array of source kernel pages
> > + * @num: number of pages in page array
> > + *
> > + * Maps an object consisting of `num' `pages', catering for the user's
> > + * requested vm_pgoff
> > + *
>
> The elaborate description you've added to __vm_insert_range() is better put
> here, as this is the "public" function.

Ok, will add it in v3. Which means __vm_insert_range() still needs a short
description ?
>
> > + * Context: Process context. Called by mmap handlers.
> > + * Return: 0 on success and error code otherwise.
> > + */
> > +int vm_insert_range(struct vm_area_struct *vma, struct page **pages,
> > +                             unsigned long num)
> > +{
> > +     return __vm_insert_range(vma, pages, num, vma->vm_pgoff);
> > +}
> > +EXPORT_SYMBOL(vm_insert_range);
> > +
> > +/**
> > + * vm_insert_range_buggy - insert range of kernel pages starts with zero offset
> > + * @vma: user vma to map to
> > + * @pages: pointer to array of source kernel pages
> > + * @num: number of pages in page array
> > + *
> > + * Maps a set of pages, always starting at page[0]
>
> Here I'd add something like:
>
> Similar to vm_insert_range(), except that it explicitly sets @vm_pgoff to
> 0. This function is intended for the drivers that did not consider
> @vm_pgoff.

Ok.

>
> > vm_insert_range_buggy() is the API which could be used to map
> > range of kernel memory/pages in drivers which has not considered
> > vm_pgoff. vm_pgoff is passed default as 0 for those drivers.
>
> > + *
> > + * Context: Process context. Called by mmap handlers.
> > + * Return: 0 on success and error code otherwise.
> > + */
> > +int vm_insert_range_buggy(struct vm_area_struct *vma, struct page **pages,
> > +                             unsigned long num)
> > +{
> > +     return __vm_insert_range(vma, pages, num, 0);
> > +}
> > +EXPORT_SYMBOL(vm_insert_range_buggy);
> > +
> >  static vm_fault_t insert_pfn(struct vm_area_struct *vma, unsigned long addr,
> >                       pfn_t pfn, pgprot_t prot, bool mkwrite)
> >  {
> > diff --git a/mm/nommu.c b/mm/nommu.c
> > index 749276b..21d101e 100644
> > --- a/mm/nommu.c
> > +++ b/mm/nommu.c
> > @@ -473,6 +473,20 @@ int vm_insert_page(struct vm_area_struct *vma, unsigned long addr,
> >  }
> >  EXPORT_SYMBOL(vm_insert_page);
> >
> > +int vm_insert_range(struct vm_area_struct *vma, struct page **pages,
> > +                     unsigned long num)
> > +{
> > +     return -EINVAL;
> > +}
> > +EXPORT_SYMBOL(vm_insert_range);
> > +
> > +int vm_insert_range_buggy(struct vm_area_struct *vma, struct page **pages,
> > +                             unsigned long num)
> > +{
> > +     return -EINVAL;
> > +}
> > +EXPORT_SYMBOL(vm_insert_range_buggy);
> > +
> >  /*
> >   *  sys_brk() for the most part doesn't need the global kernel
> >   *  lock, except when an application is doing something nasty
> > --
> > 1.9.1
> >
>
> --
> Sincerely yours,
> Mike.
>

Mike Rapoport Jan. 31, 2019, 11:06 a.m. UTC | #3

On Thu, Jan 31, 2019 at 03:43:39PM +0530, Souptick Joarder wrote:
> On Thu, Jan 31, 2019 at 2:09 PM Mike Rapoport <[e-mail]> wrote:
> >
> > On Thu, Jan 31, 2019 at 08:38:12AM +0530, Souptick Joarder wrote:
> > > Previouly drivers have their own way of mapping range of
> > > kernel pages/memory into user vma and this was done by
> > > invoking vm_insert_page() within a loop.
> > >
> > > As this pattern is common across different drivers, it can
> > > be generalized by creating new functions and use it across
> > > the drivers.
> > >
> > > vm_insert_range() is the API which could be used to mapped
> > > kernel memory/pages in drivers which has considered vm_pgoff
> > >
> > > vm_insert_range_buggy() is the API which could be used to map
> > > range of kernel memory/pages in drivers which has not considered
> > > vm_pgoff. vm_pgoff is passed default as 0 for those drivers.
> > >
> > > We _could_ then at a later "fix" these drivers which are using
> > > vm_insert_range_buggy() to behave according to the normal vm_pgoff
> > > offsetting simply by removing the _buggy suffix on the function
> > > name and if that causes regressions, it gives us an easy way to revert.
> > >
> > > Signed-off-by: Souptick Joarder <[e-mail]>
> > > Suggested-by: Russell King <[e-mail]>
> > > Suggested-by: Matthew Wilcox <[e-mail]>
> > > ---
> > >  include/linux/mm.h |  4 +++
> > >  mm/memory.c        | 81 ++++++++++++++++++++++++++++++++++++++++++++++++++++++
> > >  mm/nommu.c         | 14 ++++++++++
> > >  3 files changed, 99 insertions(+)
> > >
> > > diff --git a/include/linux/mm.h b/include/linux/mm.h
> > > index 80bb640..25752b0 100644
> > > --- a/include/linux/mm.h
> > > +++ b/include/linux/mm.h
> > > @@ -2565,6 +2565,10 @@ unsigned long change_prot_numa(struct vm_area_struct *vma,
> > >  int remap_pfn_range(struct vm_area_struct *, unsigned long addr,
> > >                       unsigned long pfn, unsigned long size, pgprot_t);
> > >  int vm_insert_page(struct vm_area_struct *, unsigned long addr, struct page *);
> > > +int vm_insert_range(struct vm_area_struct *vma, struct page **pages,
> > > +                             unsigned long num);
> > > +int vm_insert_range_buggy(struct vm_area_struct *vma, struct page **pages,
> > > +                             unsigned long num);
> > >  vm_fault_t vmf_insert_pfn(struct vm_area_struct *vma, unsigned long addr,
> > >                       unsigned long pfn);
> > >  vm_fault_t vmf_insert_pfn_prot(struct vm_area_struct *vma, unsigned long addr,
> > > diff --git a/mm/memory.c b/mm/memory.c
> > > index e11ca9d..0a4bf57 100644
> > > --- a/mm/memory.c
> > > +++ b/mm/memory.c
> > > @@ -1520,6 +1520,87 @@ int vm_insert_page(struct vm_area_struct *vma, unsigned long addr,
> > >  }
> > >  EXPORT_SYMBOL(vm_insert_page);
> > >
> > > +/**
> > > + * __vm_insert_range - insert range of kernel pages into user vma
> > > + * @vma: user vma to map to
> > > + * @pages: pointer to array of source kernel pages
> > > + * @num: number of pages in page array
> > > + * @offset: user's requested vm_pgoff
> > > + *
> > > + * This allows drivers to insert range of kernel pages they've allocated
> > > + * into a user vma.
> > > + *
> > > + * If we fail to insert any page into the vma, the function will return
> > > + * immediately leaving any previously inserted pages present.  Callers
> > > + * from the mmap handler may immediately return the error as their caller
> > > + * will destroy the vma, removing any successfully inserted pages. Other
> > > + * callers should make their own arrangements for calling unmap_region().
> > > + *
> > > + * Context: Process context.
> > > + * Return: 0 on success and error code otherwise.
> > > + */
> > > +static int __vm_insert_range(struct vm_area_struct *vma, struct page **pages,
> > > +                             unsigned long num, unsigned long offset)
> > > +{
> > > +     unsigned long count = vma_pages(vma);
> > > +     unsigned long uaddr = vma->vm_start;
> > > +     int ret, i;
> > > +
> > > +     /* Fail if the user requested offset is beyond the end of the object */
> > > +     if (offset > num)
> > > +             return -ENXIO;
> > > +
> > > +     /* Fail if the user requested size exceeds available object size */
> > > +     if (count > num - offset)
> > > +             return -ENXIO;
> > > +
> > > +     for (i = 0; i < count; i++) {
> > > +             ret = vm_insert_page(vma, uaddr, pages[offset + i]);
> > > +             if (ret < 0)
> > > +                     return ret;
> > > +             uaddr += PAGE_SIZE;
> > > +     }
> > > +
> > > +     return 0;
> > > +}
> > > +
> > > +/**
> > > + * vm_insert_range - insert range of kernel pages starts with non zero offset
> > > + * @vma: user vma to map to
> > > + * @pages: pointer to array of source kernel pages
> > > + * @num: number of pages in page array
> > > + *
> > > + * Maps an object consisting of `num' `pages', catering for the user's
> > > + * requested vm_pgoff
> > > + *
> >
> > The elaborate description you've added to __vm_insert_range() is better put
> > here, as this is the "public" function.
> 
> Ok, will add it in v3. Which means __vm_insert_range() still needs a short
> description ?

It won't hurt ;-)

> >
> > > + * Context: Process context. Called by mmap handlers.
> > > + * Return: 0 on success and error code otherwise.
> > > + */
> > > +int vm_insert_range(struct vm_area_struct *vma, struct page **pages,
> > > +                             unsigned long num)
> > > +{
> > > +     return __vm_insert_range(vma, pages, num, vma->vm_pgoff);
> > > +}
> > > +EXPORT_SYMBOL(vm_insert_range);
> > > +
> > > +/**
> > > + * vm_insert_range_buggy - insert range of kernel pages starts with zero offset
> > > + * @vma: user vma to map to
> > > + * @pages: pointer to array of source kernel pages
> > > + * @num: number of pages in page array
> > > + *
> > > + * Maps a set of pages, always starting at page[0]
> >
> > Here I'd add something like:
> >
> > Similar to vm_insert_range(), except that it explicitly sets @vm_pgoff to
> > 0. This function is intended for the drivers that did not consider
> > @vm_pgoff.
> 
> Ok.
> 
> >
> > > vm_insert_range_buggy() is the API which could be used to map
> > > range of kernel memory/pages in drivers which has not considered
> > > vm_pgoff. vm_pgoff is passed default as 0 for those drivers.
> >
> > > + *
> > > + * Context: Process context. Called by mmap handlers.
> > > + * Return: 0 on success and error code otherwise.
> > > + */
> > > +int vm_insert_range_buggy(struct vm_area_struct *vma, struct page **pages,
> > > +                             unsigned long num)
> > > +{
> > > +     return __vm_insert_range(vma, pages, num, 0);
> > > +}
> > > +EXPORT_SYMBOL(vm_insert_range_buggy);
> > > +
> > >  static vm_fault_t insert_pfn(struct vm_area_struct *vma, unsigned long addr,
> > >                       pfn_t pfn, pgprot_t prot, bool mkwrite)
> > >  {
> > > diff --git a/mm/nommu.c b/mm/nommu.c
> > > index 749276b..21d101e 100644
> > > --- a/mm/nommu.c
> > > +++ b/mm/nommu.c
> > > @@ -473,6 +473,20 @@ int vm_insert_page(struct vm_area_struct *vma, unsigned long addr,
> > >  }
> > >  EXPORT_SYMBOL(vm_insert_page);
> > >
> > > +int vm_insert_range(struct vm_area_struct *vma, struct page **pages,
> > > +                     unsigned long num)
> > > +{
> > > +     return -EINVAL;
> > > +}
> > > +EXPORT_SYMBOL(vm_insert_range);
> > > +
> > > +int vm_insert_range_buggy(struct vm_area_struct *vma, struct page **pages,
> > > +                             unsigned long num)
> > > +{
> > > +     return -EINVAL;
> > > +}
> > > +EXPORT_SYMBOL(vm_insert_range_buggy);
> > > +
> > >  /*
> > >   *  sys_brk() for the most part doesn't need the global kernel
> > >   *  lock, except when an application is doing something nasty
> > > --
> > > 1.9.1
> > >
> >
> > --
> > Sincerely yours,
> > Mike.
> >
>

Heiko Stübner Jan. 31, 2019, 12:06 p.m. UTC | #4

Am Donnerstag, 31. Januar 2019, 04:08:12 CET schrieb Souptick Joarder:
> Previouly drivers have their own way of mapping range of
> kernel pages/memory into user vma and this was done by
> invoking vm_insert_page() within a loop.
> 
> As this pattern is common across different drivers, it can
> be generalized by creating new functions and use it across
> the drivers.
> 
> vm_insert_range() is the API which could be used to mapped
> kernel memory/pages in drivers which has considered vm_pgoff
> 
> vm_insert_range_buggy() is the API which could be used to map
> range of kernel memory/pages in drivers which has not considered
> vm_pgoff. vm_pgoff is passed default as 0 for those drivers.
> 
> We _could_ then at a later "fix" these drivers which are using
> vm_insert_range_buggy() to behave according to the normal vm_pgoff
> offsetting simply by removing the _buggy suffix on the function
> name and if that causes regressions, it gives us an easy way to revert.
> 
> Signed-off-by: Souptick Joarder <[e-mail]>
> Suggested-by: Russell King <[e-mail]>
> Suggested-by: Matthew Wilcox <[e-mail]>

hmm, I'm missing a changelog here between v1 and v2.
Nevertheless I managed to test v1 on Rockchip hardware
and display is still working, including talking to Lima via prime.

So if there aren't any big changes for v2, on Rockchip
Tested-by: Heiko Stuebner <[e-mail]>

Heiko

Souptick Joarder Jan. 31, 2019, 12:31 p.m. UTC | #5

On Thu, Jan 31, 2019 at 5:37 PM Heiko Stuebner <[e-mail]> wrote:
>
> Am Donnerstag, 31. Januar 2019, 04:08:12 CET schrieb Souptick Joarder:
> > Previouly drivers have their own way of mapping range of
> > kernel pages/memory into user vma and this was done by
> > invoking vm_insert_page() within a loop.
> >
> > As this pattern is common across different drivers, it can
> > be generalized by creating new functions and use it across
> > the drivers.
> >
> > vm_insert_range() is the API which could be used to mapped
> > kernel memory/pages in drivers which has considered vm_pgoff
> >
> > vm_insert_range_buggy() is the API which could be used to map
> > range of kernel memory/pages in drivers which has not considered
> > vm_pgoff. vm_pgoff is passed default as 0 for those drivers.
> >
> > We _could_ then at a later "fix" these drivers which are using
> > vm_insert_range_buggy() to behave according to the normal vm_pgoff
> > offsetting simply by removing the _buggy suffix on the function
> > name and if that causes regressions, it gives us an easy way to revert.
> >
> > Signed-off-by: Souptick Joarder <[e-mail]>
> > Suggested-by: Russell King <[e-mail]>
> > Suggested-by: Matthew Wilcox <[e-mail]>
>
> hmm, I'm missing a changelog here between v1 and v2.
> Nevertheless I managed to test v1 on Rockchip hardware
> and display is still working, including talking to Lima via prime.
>
> So if there aren't any big changes for v2, on Rockchip
> Tested-by: Heiko Stuebner <[e-mail]>

Change log is available in [0/9].
Patch [1/9] & [4/9] have no changes between v1 -> v2.

Heiko Stübner Jan. 31, 2019, 12:34 p.m. UTC | #6

Am Donnerstag, 31. Januar 2019, 13:31:52 CET schrieb Souptick Joarder:
> On Thu, Jan 31, 2019 at 5:37 PM Heiko Stuebner <[e-mail]> wrote:
> >
> > Am Donnerstag, 31. Januar 2019, 04:08:12 CET schrieb Souptick Joarder:
> > > Previouly drivers have their own way of mapping range of
> > > kernel pages/memory into user vma and this was done by
> > > invoking vm_insert_page() within a loop.
> > >
> > > As this pattern is common across different drivers, it can
> > > be generalized by creating new functions and use it across
> > > the drivers.
> > >
> > > vm_insert_range() is the API which could be used to mapped
> > > kernel memory/pages in drivers which has considered vm_pgoff
> > >
> > > vm_insert_range_buggy() is the API which could be used to map
> > > range of kernel memory/pages in drivers which has not considered
> > > vm_pgoff. vm_pgoff is passed default as 0 for those drivers.
> > >
> > > We _could_ then at a later "fix" these drivers which are using
> > > vm_insert_range_buggy() to behave according to the normal vm_pgoff
> > > offsetting simply by removing the _buggy suffix on the function
> > > name and if that causes regressions, it gives us an easy way to revert.
> > >
> > > Signed-off-by: Souptick Joarder <[e-mail]>
> > > Suggested-by: Russell King <[e-mail]>
> > > Suggested-by: Matthew Wilcox <[e-mail]>
> >
> > hmm, I'm missing a changelog here between v1 and v2.
> > Nevertheless I managed to test v1 on Rockchip hardware
> > and display is still working, including talking to Lima via prime.
> >
> > So if there aren't any big changes for v2, on Rockchip
> > Tested-by: Heiko Stuebner <[e-mail]>
> 
> Change log is available in [0/9].
> Patch [1/9] & [4/9] have no changes between v1 -> v2.

I never seem to get your cover-letters, so didn't see that, sorry.

But great that there weren't changes then :-)

Heiko

Souptick Joarder Feb. 1, 2019, 12:38 p.m. UTC | #7

On Thu, Jan 31, 2019 at 6:04 PM Heiko Stuebner <[e-mail]> wrote:
>
> Am Donnerstag, 31. Januar 2019, 13:31:52 CET schrieb Souptick Joarder:
> > On Thu, Jan 31, 2019 at 5:37 PM Heiko Stuebner <[e-mail]> wrote:
> > >
> > > Am Donnerstag, 31. Januar 2019, 04:08:12 CET schrieb Souptick Joarder:
> > > > Previouly drivers have their own way of mapping range of
> > > > kernel pages/memory into user vma and this was done by
> > > > invoking vm_insert_page() within a loop.
> > > >
> > > > As this pattern is common across different drivers, it can
> > > > be generalized by creating new functions and use it across
> > > > the drivers.
> > > >
> > > > vm_insert_range() is the API which could be used to mapped
> > > > kernel memory/pages in drivers which has considered vm_pgoff
> > > >
> > > > vm_insert_range_buggy() is the API which could be used to map
> > > > range of kernel memory/pages in drivers which has not considered
> > > > vm_pgoff. vm_pgoff is passed default as 0 for those drivers.
> > > >
> > > > We _could_ then at a later "fix" these drivers which are using
> > > > vm_insert_range_buggy() to behave according to the normal vm_pgoff
> > > > offsetting simply by removing the _buggy suffix on the function
> > > > name and if that causes regressions, it gives us an easy way to revert.
> > > >
> > > > Signed-off-by: Souptick Joarder <[e-mail]>
> > > > Suggested-by: Russell King <[e-mail]>
> > > > Suggested-by: Matthew Wilcox <[e-mail]>
> > >
> > > hmm, I'm missing a changelog here between v1 and v2.
> > > Nevertheless I managed to test v1 on Rockchip hardware
> > > and display is still working, including talking to Lima via prime.
> > >
> > > So if there aren't any big changes for v2, on Rockchip
> > > Tested-by: Heiko Stuebner <[e-mail]>
> >
> > Change log is available in [0/9].
> > Patch [1/9] & [4/9] have no changes between v1 -> v2.
>
> I never seem to get your cover-letters, so didn't see that, sorry.

I added you in sender list for all cover-letters but it didn't reach
your inbox :-)
Thanks for reviewing and validating the patch.

>
> But great that there weren't changes then :-)
>
> Heiko
>
>

Souptick Joarder Feb. 7, 2019, 3:49 p.m. UTC | #8

Hi Mike,

On Thu, Jan 31, 2019 at 2:09 PM Mike Rapoport <[e-mail]> wrote:
>
> On Thu, Jan 31, 2019 at 08:38:12AM +0530, Souptick Joarder wrote:
> > Previouly drivers have their own way of mapping range of
> > kernel pages/memory into user vma and this was done by
> > invoking vm_insert_page() within a loop.
> >
> > As this pattern is common across different drivers, it can
> > be generalized by creating new functions and use it across
> > the drivers.
> >
> > vm_insert_range() is the API which could be used to mapped
> > kernel memory/pages in drivers which has considered vm_pgoff
> >
> > vm_insert_range_buggy() is the API which could be used to map
> > range of kernel memory/pages in drivers which has not considered
> > vm_pgoff. vm_pgoff is passed default as 0 for those drivers.
> >
> > We _could_ then at a later "fix" these drivers which are using
> > vm_insert_range_buggy() to behave according to the normal vm_pgoff
> > offsetting simply by removing the _buggy suffix on the function
> > name and if that causes regressions, it gives us an easy way to revert.
> >
> > Signed-off-by: Souptick Joarder <[e-mail]>
> > Suggested-by: Russell King <[e-mail]>
> > Suggested-by: Matthew Wilcox <[e-mail]>
> > ---
> >  include/linux/mm.h |  4 +++
> >  mm/memory.c        | 81 ++++++++++++++++++++++++++++++++++++++++++++++++++++++
> >  mm/nommu.c         | 14 ++++++++++
> >  3 files changed, 99 insertions(+)
> >
> > diff --git a/include/linux/mm.h b/include/linux/mm.h
> > index 80bb640..25752b0 100644
> > --- a/include/linux/mm.h
> > +++ b/include/linux/mm.h
> > @@ -2565,6 +2565,10 @@ unsigned long change_prot_numa(struct vm_area_struct *vma,
> >  int remap_pfn_range(struct vm_area_struct *, unsigned long addr,
> >                       unsigned long pfn, unsigned long size, pgprot_t);
> >  int vm_insert_page(struct vm_area_struct *, unsigned long addr, struct page *);
> > +int vm_insert_range(struct vm_area_struct *vma, struct page **pages,
> > +                             unsigned long num);
> > +int vm_insert_range_buggy(struct vm_area_struct *vma, struct page **pages,
> > +                             unsigned long num);
> >  vm_fault_t vmf_insert_pfn(struct vm_area_struct *vma, unsigned long addr,
> >                       unsigned long pfn);
> >  vm_fault_t vmf_insert_pfn_prot(struct vm_area_struct *vma, unsigned long addr,
> > diff --git a/mm/memory.c b/mm/memory.c
> > index e11ca9d..0a4bf57 100644
> > --- a/mm/memory.c
> > +++ b/mm/memory.c
> > @@ -1520,6 +1520,87 @@ int vm_insert_page(struct vm_area_struct *vma, unsigned long addr,
> >  }
> >  EXPORT_SYMBOL(vm_insert_page);
> >
> > +/**
> > + * __vm_insert_range - insert range of kernel pages into user vma
> > + * @vma: user vma to map to
> > + * @pages: pointer to array of source kernel pages
> > + * @num: number of pages in page array
> > + * @offset: user's requested vm_pgoff
> > + *
> > + * This allows drivers to insert range of kernel pages they've allocated
> > + * into a user vma.
> > + *
> > + * If we fail to insert any page into the vma, the function will return
> > + * immediately leaving any previously inserted pages present.  Callers
> > + * from the mmap handler may immediately return the error as their caller
> > + * will destroy the vma, removing any successfully inserted pages. Other
> > + * callers should make their own arrangements for calling unmap_region().
> > + *
> > + * Context: Process context.
> > + * Return: 0 on success and error code otherwise.
> > + */
> > +static int __vm_insert_range(struct vm_area_struct *vma, struct page **pages,
> > +                             unsigned long num, unsigned long offset)
> > +{
> > +     unsigned long count = vma_pages(vma);
> > +     unsigned long uaddr = vma->vm_start;
> > +     int ret, i;
> > +
> > +     /* Fail if the user requested offset is beyond the end of the object */
> > +     if (offset > num)
> > +             return -ENXIO;
> > +
> > +     /* Fail if the user requested size exceeds available object size */
> > +     if (count > num - offset)
> > +             return -ENXIO;
> > +
> > +     for (i = 0; i < count; i++) {
> > +             ret = vm_insert_page(vma, uaddr, pages[offset + i]);
> > +             if (ret < 0)
> > +                     return ret;
> > +             uaddr += PAGE_SIZE;
> > +     }
> > +
> > +     return 0;
> > +}
> > +
> > +/**
> > + * vm_insert_range - insert range of kernel pages starts with non zero offset
> > + * @vma: user vma to map to
> > + * @pages: pointer to array of source kernel pages
> > + * @num: number of pages in page array
> > + *
> > + * Maps an object consisting of `num' `pages', catering for the user's
> > + * requested vm_pgoff
> > + *
>
> The elaborate description you've added to __vm_insert_range() is better put
> here, as this is the "public" function.
>
> > + * Context: Process context. Called by mmap handlers.
> > + * Return: 0 on success and error code otherwise.
> > + */
> > +int vm_insert_range(struct vm_area_struct *vma, struct page **pages,
> > +                             unsigned long num)
> > +{
> > +     return __vm_insert_range(vma, pages, num, vma->vm_pgoff);
> > +}
> > +EXPORT_SYMBOL(vm_insert_range);
> > +
> > +/**
> > + * vm_insert_range_buggy - insert range of kernel pages starts with zero offset
> > + * @vma: user vma to map to
> > + * @pages: pointer to array of source kernel pages
> > + * @num: number of pages in page array
> > + *
> > + * Maps a set of pages, always starting at page[0]
>
> Here I'd add something like:
>
> Similar to vm_insert_range(), except that it explicitly sets @vm_pgoff to
> 0. This function is intended for the drivers that did not consider
> @vm_pgoff.

Just thought to take opinion for documentation before placing it in v3.
Does it looks fine ?

+/**
+ * __vm_insert_range - insert range of kernel pages into user vma
+ * @vma: user vma to map to
+ * @pages: pointer to array of source kernel pages
+ * @num: number of pages in page array
+ * @offset: user's requested vm_pgoff
+ *
+ * This allow drivers to insert range of kernel pages into a user vma.
+ *
+ * Return: 0 on success and error code otherwise.
+ */
+static int __vm_insert_range(struct vm_area_struct *vma, struct page **pages,
+                               unsigned long num, unsigned long offset)


+/**
+ * vm_insert_range - insert range of kernel pages starts with non zero offset
+ * @vma: user vma to map to
+ * @pages: pointer to array of source kernel pages
+ * @num: number of pages in page array
+ *
+ * Maps an object consisting of `num' `pages', catering for the user's
+ * requested vm_pgoff
+ *
+ * If we fail to insert any page into the vma, the function will return
+ * immediately leaving any previously inserted pages present.  Callers
+ * from the mmap handler may immediately return the error as their caller
+ * will destroy the vma, removing any successfully inserted pages. Other
+ * callers should make their own arrangements for calling unmap_region().
+ *
+ * Context: Process context. Called by mmap handlers.
+ * Return: 0 on success and error code otherwise.
+ */
+int vm_insert_range(struct vm_area_struct *vma, struct page **pages,
+                               unsigned long num)


+/**
+ * vm_insert_range_buggy - insert range of kernel pages starts with zero offset
+ * @vma: user vma to map to
+ * @pages: pointer to array of source kernel pages
+ * @num: number of pages in page array
+ *
+ * Similar to vm_insert_range(), except that it explicitly sets @vm_pgoff to
+ * 0. This function is intended for the drivers that did not consider
+ * @vm_pgoff.
+ *
+ * Context: Process context. Called by mmap handlers.
+ * Return: 0 on success and error code otherwise.
+ */
+int vm_insert_range_buggy(struct vm_area_struct *vma, struct page **pages,
+                               unsigned long num)

Mike Rapoport Feb. 7, 2019, 3:57 p.m. UTC | #9

Hi Souptick,

On Thu, Feb 07, 2019 at 09:19:47PM +0530, Souptick Joarder wrote:
> Hi Mike,
> 
> Just thought to take opinion for documentation before placing it in v3.
> Does it looks fine ?
 
Overall looks good to me. Several minor points below.

> +/**
> + * __vm_insert_range - insert range of kernel pages into user vma
> + * @vma: user vma to map to
> + * @pages: pointer to array of source kernel pages
> + * @num: number of pages in page array
> + * @offset: user's requested vm_pgoff
> + *
> + * This allow drivers to insert range of kernel pages into a user vma.

          allows
> + *
> + * Return: 0 on success and error code otherwise.
> + */
> +static int __vm_insert_range(struct vm_area_struct *vma, struct page **pages,
> +                               unsigned long num, unsigned long offset)
> 
> 
> +/**
> + * vm_insert_range - insert range of kernel pages starts with non zero offset
> + * @vma: user vma to map to
> + * @pages: pointer to array of source kernel pages
> + * @num: number of pages in page array
> + *
> + * Maps an object consisting of `num' `pages', catering for the user's
                                   @num pages
> + * requested vm_pgoff
> + *
> + * If we fail to insert any page into the vma, the function will return
> + * immediately leaving any previously inserted pages present.  Callers
> + * from the mmap handler may immediately return the error as their caller
> + * will destroy the vma, removing any successfully inserted pages. Other
> + * callers should make their own arrangements for calling unmap_region().
> + *
> + * Context: Process context. Called by mmap handlers.
> + * Return: 0 on success and error code otherwise.
> + */
> +int vm_insert_range(struct vm_area_struct *vma, struct page **pages,
> +                               unsigned long num)
> 
> 
> +/**
> + * vm_insert_range_buggy - insert range of kernel pages starts with zero offset
> + * @vma: user vma to map to
> + * @pages: pointer to array of source kernel pages
> + * @num: number of pages in page array
> + *
> + * Similar to vm_insert_range(), except that it explicitly sets @vm_pgoff to

                                                                  the offset

> + * 0. This function is intended for the drivers that did not consider
> + * @vm_pgoff.
> + *
> + * Context: Process context. Called by mmap handlers.
> + * Return: 0 on success and error code otherwise.
> + */
> +int vm_insert_range_buggy(struct vm_area_struct *vma, struct page **pages,
> +                               unsigned long num)
>

Mike Rapoport Feb. 7, 2019, 4:04 p.m. UTC | #10

On Thu, Feb 07, 2019 at 09:37:08PM +0530, Souptick Joarder wrote:
> On Thu, Feb 7, 2019 at 9:27 PM Mike Rapoport <[e-mail]> wrote:
> >
> > Hi Souptick,
> >
> > On Thu, Feb 07, 2019 at 09:19:47PM +0530, Souptick Joarder wrote:
> > > Hi Mike,
> > >
> > > Just thought to take opinion for documentation before placing it in v3.
> > > Does it looks fine ?
> >
> > Overall looks good to me. Several minor points below.
> 
> Thanks Mike. Noted.
> Shall I consider it as *Reviewed-by:* with below changes ?
 
Yeah, sure.

> >
> > > +/**
> > > + * __vm_insert_range - insert range of kernel pages into user vma
> > > + * @vma: user vma to map to
> > > + * @pages: pointer to array of source kernel pages
> > > + * @num: number of pages in page array
> > > + * @offset: user's requested vm_pgoff
> > > + *
> > > + * This allow drivers to insert range of kernel pages into a user vma.
> >
> >           allows
> > > + *
> > > + * Return: 0 on success and error code otherwise.
> > > + */
> > > +static int __vm_insert_range(struct vm_area_struct *vma, struct page **pages,
> > > +                               unsigned long num, unsigned long offset)
> > >
> > >
> > > +/**
> > > + * vm_insert_range - insert range of kernel pages starts with non zero offset
> > > + * @vma: user vma to map to
> > > + * @pages: pointer to array of source kernel pages
> > > + * @num: number of pages in page array
> > > + *
> > > + * Maps an object consisting of `num' `pages', catering for the user's
> >                                    @num pages
> > > + * requested vm_pgoff
> > > + *
> > > + * If we fail to insert any page into the vma, the function will return
> > > + * immediately leaving any previously inserted pages present.  Callers
> > > + * from the mmap handler may immediately return the error as their caller
> > > + * will destroy the vma, removing any successfully inserted pages. Other
> > > + * callers should make their own arrangements for calling unmap_region().
> > > + *
> > > + * Context: Process context. Called by mmap handlers.
> > > + * Return: 0 on success and error code otherwise.
> > > + */
> > > +int vm_insert_range(struct vm_area_struct *vma, struct page **pages,
> > > +                               unsigned long num)
> > >
> > >
> > > +/**
> > > + * vm_insert_range_buggy - insert range of kernel pages starts with zero offset
> > > + * @vma: user vma to map to
> > > + * @pages: pointer to array of source kernel pages
> > > + * @num: number of pages in page array
> > > + *
> > > + * Similar to vm_insert_range(), except that it explicitly sets @vm_pgoff to
> >
> >                                                                   the offset
> >
> > > + * 0. This function is intended for the drivers that did not consider
> > > + * @vm_pgoff.
> > > + *
> > > + * Context: Process context. Called by mmap handlers.
> > > + * Return: 0 on success and error code otherwise.
> > > + */
> > > +int vm_insert_range_buggy(struct vm_area_struct *vma, struct page **pages,
> > > +                               unsigned long num)
> > >
> >
> > --
> > Sincerely yours,
> > Mike.
> >
>

Souptick Joarder Feb. 7, 2019, 4:07 p.m. UTC | #11

On Thu, Feb 7, 2019 at 9:27 PM Mike Rapoport <[e-mail]> wrote:
>
> Hi Souptick,
>
> On Thu, Feb 07, 2019 at 09:19:47PM +0530, Souptick Joarder wrote:
> > Hi Mike,
> >
> > Just thought to take opinion for documentation before placing it in v3.
> > Does it looks fine ?
>
> Overall looks good to me. Several minor points below.

Thanks Mike. Noted.
Shall I consider it as *Reviewed-by:* with below changes ?

>
> > +/**
> > + * __vm_insert_range - insert range of kernel pages into user vma
> > + * @vma: user vma to map to
> > + * @pages: pointer to array of source kernel pages
> > + * @num: number of pages in page array
> > + * @offset: user's requested vm_pgoff
> > + *
> > + * This allow drivers to insert range of kernel pages into a user vma.
>
>           allows
> > + *
> > + * Return: 0 on success and error code otherwise.
> > + */
> > +static int __vm_insert_range(struct vm_area_struct *vma, struct page **pages,
> > +                               unsigned long num, unsigned long offset)
> >
> >
> > +/**
> > + * vm_insert_range - insert range of kernel pages starts with non zero offset
> > + * @vma: user vma to map to
> > + * @pages: pointer to array of source kernel pages
> > + * @num: number of pages in page array
> > + *
> > + * Maps an object consisting of `num' `pages', catering for the user's
>                                    @num pages
> > + * requested vm_pgoff
> > + *
> > + * If we fail to insert any page into the vma, the function will return
> > + * immediately leaving any previously inserted pages present.  Callers
> > + * from the mmap handler may immediately return the error as their caller
> > + * will destroy the vma, removing any successfully inserted pages. Other
> > + * callers should make their own arrangements for calling unmap_region().
> > + *
> > + * Context: Process context. Called by mmap handlers.
> > + * Return: 0 on success and error code otherwise.
> > + */
> > +int vm_insert_range(struct vm_area_struct *vma, struct page **pages,
> > +                               unsigned long num)
> >
> >
> > +/**
> > + * vm_insert_range_buggy - insert range of kernel pages starts with zero offset
> > + * @vma: user vma to map to
> > + * @pages: pointer to array of source kernel pages
> > + * @num: number of pages in page array
> > + *
> > + * Similar to vm_insert_range(), except that it explicitly sets @vm_pgoff to
>
>                                                                   the offset
>
> > + * 0. This function is intended for the drivers that did not consider
> > + * @vm_pgoff.
> > + *
> > + * Context: Process context. Called by mmap handlers.
> > + * Return: 0 on success and error code otherwise.
> > + */
> > +int vm_insert_range_buggy(struct vm_area_struct *vma, struct page **pages,
> > +                               unsigned long num)
> >
>
> --
> Sincerely yours,
> Mike.
>

Matthew Wilcox (Oracle) Feb. 7, 2019, 4:47 p.m. UTC | #12

On Thu, Feb 07, 2019 at 09:19:47PM +0530, Souptick Joarder wrote:
> Just thought to take opinion for documentation before placing it in v3.
> Does it looks fine ?
> 
> +/**
> + * __vm_insert_range - insert range of kernel pages into user vma
> + * @vma: user vma to map to
> + * @pages: pointer to array of source kernel pages
> + * @num: number of pages in page array
> + * @offset: user's requested vm_pgoff
> + *
> + * This allow drivers to insert range of kernel pages into a user vma.
> + *
> + * Return: 0 on success and error code otherwise.
> + */
> +static int __vm_insert_range(struct vm_area_struct *vma, struct page **pages,
> +                               unsigned long num, unsigned long offset)

For static functions, I prefer to leave off the second '*', ie make it
formatted like a docbook comment, but not be processed like a docbook
comment.  That avoids cluttering the html with descriptions of internal
functions that people can't actually call.

> +/**
> + * vm_insert_range - insert range of kernel pages starts with non zero offset
> + * @vma: user vma to map to
> + * @pages: pointer to array of source kernel pages
> + * @num: number of pages in page array
> + *
> + * Maps an object consisting of `num' `pages', catering for the user's

Rather than using `num', you should use @num.

> + * requested vm_pgoff
> + *
> + * If we fail to insert any page into the vma, the function will return
> + * immediately leaving any previously inserted pages present.  Callers
> + * from the mmap handler may immediately return the error as their caller
> + * will destroy the vma, removing any successfully inserted pages. Other
> + * callers should make their own arrangements for calling unmap_region().
> + *
> + * Context: Process context. Called by mmap handlers.
> + * Return: 0 on success and error code otherwise.
> + */
> +int vm_insert_range(struct vm_area_struct *vma, struct page **pages,
> +                               unsigned long num)
> 
> 
> +/**
> + * vm_insert_range_buggy - insert range of kernel pages starts with zero offset
> + * @vma: user vma to map to
> + * @pages: pointer to array of source kernel pages
> + * @num: number of pages in page array
> + *
> + * Similar to vm_insert_range(), except that it explicitly sets @vm_pgoff to

But vm_pgoff isn't a parameter, so it's misleading to format it as such.

> + * 0. This function is intended for the drivers that did not consider
> + * @vm_pgoff.
> + *
> + * Context: Process context. Called by mmap handlers.
> + * Return: 0 on success and error code otherwise.
> + */
> +int vm_insert_range_buggy(struct vm_area_struct *vma, struct page **pages,
> +                               unsigned long num)

I don't think we should call it 'buggy'.  'zero' would make more sense
as a suffix.

Given how this interface has evolved, I'm no longer sure than
'vm_insert_range' makes sense as the name for it.  Is it perhaps
'vm_map_object' or 'vm_map_pages'?

Souptick Joarder Feb. 8, 2019, 5:22 a.m. UTC | #13

On Thu, Feb 7, 2019 at 10:17 PM Matthew Wilcox <[e-mail]> wrote:
>
> On Thu, Feb 07, 2019 at 09:19:47PM +0530, Souptick Joarder wrote:
> > Just thought to take opinion for documentation before placing it in v3.
> > Does it looks fine ?
> >
> > +/**
> > + * __vm_insert_range - insert range of kernel pages into user vma
> > + * @vma: user vma to map to
> > + * @pages: pointer to array of source kernel pages
> > + * @num: number of pages in page array
> > + * @offset: user's requested vm_pgoff
> > + *
> > + * This allow drivers to insert range of kernel pages into a user vma.
> > + *
> > + * Return: 0 on success and error code otherwise.
> > + */
> > +static int __vm_insert_range(struct vm_area_struct *vma, struct page **pages,
> > +                               unsigned long num, unsigned long offset)
>
> For static functions, I prefer to leave off the second '*', ie make it
> formatted like a docbook comment, but not be processed like a docbook
> comment.  That avoids cluttering the html with descriptions of internal
> functions that people can't actually call.
>
> > +/**
> > + * vm_insert_range - insert range of kernel pages starts with non zero offset
> > + * @vma: user vma to map to
> > + * @pages: pointer to array of source kernel pages
> > + * @num: number of pages in page array
> > + *
> > + * Maps an object consisting of `num' `pages', catering for the user's
>
> Rather than using `num', you should use @num.
>
> > + * requested vm_pgoff
> > + *
> > + * If we fail to insert any page into the vma, the function will return
> > + * immediately leaving any previously inserted pages present.  Callers
> > + * from the mmap handler may immediately return the error as their caller
> > + * will destroy the vma, removing any successfully inserted pages. Other
> > + * callers should make their own arrangements for calling unmap_region().
> > + *
> > + * Context: Process context. Called by mmap handlers.
> > + * Return: 0 on success and error code otherwise.
> > + */
> > +int vm_insert_range(struct vm_area_struct *vma, struct page **pages,
> > +                               unsigned long num)
> >
> >
> > +/**
> > + * vm_insert_range_buggy - insert range of kernel pages starts with zero offset
> > + * @vma: user vma to map to
> > + * @pages: pointer to array of source kernel pages
> > + * @num: number of pages in page array
> > + *
> > + * Similar to vm_insert_range(), except that it explicitly sets @vm_pgoff to
>
> But vm_pgoff isn't a parameter, so it's misleading to format it as such.
>
> > + * 0. This function is intended for the drivers that did not consider
> > + * @vm_pgoff.
> > + *
> > + * Context: Process context. Called by mmap handlers.
> > + * Return: 0 on success and error code otherwise.
> > + */
> > +int vm_insert_range_buggy(struct vm_area_struct *vma, struct page **pages,
> > +                               unsigned long num)
>
> I don't think we should call it 'buggy'.  'zero' would make more sense
> as a suffix.

suffix can be *zero or zero_offset* whichever suits better.

>
> Given how this interface has evolved, I'm no longer sure than
> 'vm_insert_range' makes sense as the name for it.  Is it perhaps
> 'vm_map_object' or 'vm_map_pages'?
>

I prefer vm_map_pages. Considering it, both the interface name can be changed
to *vm_insert_range -> vm_map_pages* and *vm_insert_range_buggy ->
vm_map_pages_{zero/zero_offset}.

As this is only change in interface name and rest of code remain same
shall I post it in v3 ( with additional change log mentioned about interface
name changed) ?

or,

It will be a new patch series ( with carry forward all the Reviewed-by
/ Tested-by on
vm_insert_range/ vm_insert_range_buggy ) ?

Souptick Joarder Feb. 11, 2019, 5:06 p.m. UTC | #14

On Fri, Feb 8, 2019 at 10:52 AM Souptick Joarder <[e-mail]> wrote:
>
> On Thu, Feb 7, 2019 at 10:17 PM Matthew Wilcox <[e-mail]> wrote:
> >
> > On Thu, Feb 07, 2019 at 09:19:47PM +0530, Souptick Joarder wrote:
> > > Just thought to take opinion for documentation before placing it in v3.
> > > Does it looks fine ?
> > >
> > > +/**
> > > + * __vm_insert_range - insert range of kernel pages into user vma
> > > + * @vma: user vma to map to
> > > + * @pages: pointer to array of source kernel pages
> > > + * @num: number of pages in page array
> > > + * @offset: user's requested vm_pgoff
> > > + *
> > > + * This allow drivers to insert range of kernel pages into a user vma.
> > > + *
> > > + * Return: 0 on success and error code otherwise.
> > > + */
> > > +static int __vm_insert_range(struct vm_area_struct *vma, struct page **pages,
> > > +                               unsigned long num, unsigned long offset)
> >
> > For static functions, I prefer to leave off the second '*', ie make it
> > formatted like a docbook comment, but not be processed like a docbook
> > comment.  That avoids cluttering the html with descriptions of internal
> > functions that people can't actually call.
> >
> > > +/**
> > > + * vm_insert_range - insert range of kernel pages starts with non zero offset
> > > + * @vma: user vma to map to
> > > + * @pages: pointer to array of source kernel pages
> > > + * @num: number of pages in page array
> > > + *
> > > + * Maps an object consisting of `num' `pages', catering for the user's
> >
> > Rather than using `num', you should use @num.
> >
> > > + * requested vm_pgoff
> > > + *
> > > + * If we fail to insert any page into the vma, the function will return
> > > + * immediately leaving any previously inserted pages present.  Callers
> > > + * from the mmap handler may immediately return the error as their caller
> > > + * will destroy the vma, removing any successfully inserted pages. Other
> > > + * callers should make their own arrangements for calling unmap_region().
> > > + *
> > > + * Context: Process context. Called by mmap handlers.
> > > + * Return: 0 on success and error code otherwise.
> > > + */
> > > +int vm_insert_range(struct vm_area_struct *vma, struct page **pages,
> > > +                               unsigned long num)
> > >
> > >
> > > +/**
> > > + * vm_insert_range_buggy - insert range of kernel pages starts with zero offset
> > > + * @vma: user vma to map to
> > > + * @pages: pointer to array of source kernel pages
> > > + * @num: number of pages in page array
> > > + *
> > > + * Similar to vm_insert_range(), except that it explicitly sets @vm_pgoff to
> >
> > But vm_pgoff isn't a parameter, so it's misleading to format it as such.
> >
> > > + * 0. This function is intended for the drivers that did not consider
> > > + * @vm_pgoff.
> > > + *
> > > + * Context: Process context. Called by mmap handlers.
> > > + * Return: 0 on success and error code otherwise.
> > > + */
> > > +int vm_insert_range_buggy(struct vm_area_struct *vma, struct page **pages,
> > > +                               unsigned long num)
> >
> > I don't think we should call it 'buggy'.  'zero' would make more sense
> > as a suffix.
>
> suffix can be *zero or zero_offset* whichever suits better.
>
> >
> > Given how this interface has evolved, I'm no longer sure than
> > 'vm_insert_range' makes sense as the name for it.  Is it perhaps
> > 'vm_map_object' or 'vm_map_pages'?
> >
>
> I prefer vm_map_pages. Considering it, both the interface name can be changed
> to *vm_insert_range -> vm_map_pages* and *vm_insert_range_buggy ->
> vm_map_pages_{zero/zero_offset}.
>
> As this is only change in interface name and rest of code remain same
> shall I post it in v3 ( with additional change log mentioned about interface
> name changed) ?
>
> or,
>
> It will be a new patch series ( with carry forward all the Reviewed-by
> / Tested-by on
> vm_insert_range/ vm_insert_range_buggy ) ?

Any suggestion on this minor query ?

Patch

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 80bb640..25752b0 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -2565,6 +2565,10 @@  unsigned long change_prot_numa(struct vm_area_struct *vma,
 int remap_pfn_range(struct vm_area_struct *, unsigned long addr,
 			unsigned long pfn, unsigned long size, pgprot_t);
 int vm_insert_page(struct vm_area_struct *, unsigned long addr, struct page *);
+int vm_insert_range(struct vm_area_struct *vma, struct page **pages,
+				unsigned long num);
+int vm_insert_range_buggy(struct vm_area_struct *vma, struct page **pages,
+				unsigned long num);
 vm_fault_t vmf_insert_pfn(struct vm_area_struct *vma, unsigned long addr,
 			unsigned long pfn);
 vm_fault_t vmf_insert_pfn_prot(struct vm_area_struct *vma, unsigned long addr,
diff --git a/mm/memory.c b/mm/memory.c
index e11ca9d..0a4bf57 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1520,6 +1520,87 @@  int vm_insert_page(struct vm_area_struct *vma, unsigned long addr,
 }
 EXPORT_SYMBOL(vm_insert_page);
 
+/**
+ * __vm_insert_range - insert range of kernel pages into user vma
+ * @vma: user vma to map to
+ * @pages: pointer to array of source kernel pages
+ * @num: number of pages in page array
+ * @offset: user's requested vm_pgoff
+ *
+ * This allows drivers to insert range of kernel pages they've allocated
+ * into a user vma.
+ *
+ * If we fail to insert any page into the vma, the function will return
+ * immediately leaving any previously inserted pages present.  Callers
+ * from the mmap handler may immediately return the error as their caller
+ * will destroy the vma, removing any successfully inserted pages. Other
+ * callers should make their own arrangements for calling unmap_region().
+ *
+ * Context: Process context.
+ * Return: 0 on success and error code otherwise.
+ */
+static int __vm_insert_range(struct vm_area_struct *vma, struct page **pages,
+				unsigned long num, unsigned long offset)
+{
+	unsigned long count = vma_pages(vma);
+	unsigned long uaddr = vma->vm_start;
+	int ret, i;
+
+	/* Fail if the user requested offset is beyond the end of the object */
+	if (offset > num)
+		return -ENXIO;
+
+	/* Fail if the user requested size exceeds available object size */
+	if (count > num - offset)
+		return -ENXIO;
+
+	for (i = 0; i < count; i++) {
+		ret = vm_insert_page(vma, uaddr, pages[offset + i]);
+		if (ret < 0)
+			return ret;
+		uaddr += PAGE_SIZE;
+	}
+
+	return 0;
+}
+
+/**
+ * vm_insert_range - insert range of kernel pages starts with non zero offset
+ * @vma: user vma to map to
+ * @pages: pointer to array of source kernel pages
+ * @num: number of pages in page array
+ *
+ * Maps an object consisting of `num' `pages', catering for the user's
+ * requested vm_pgoff
+ *
+ * Context: Process context. Called by mmap handlers.
+ * Return: 0 on success and error code otherwise.
+ */
+int vm_insert_range(struct vm_area_struct *vma, struct page **pages,
+				unsigned long num)
+{
+	return __vm_insert_range(vma, pages, num, vma->vm_pgoff);
+}
+EXPORT_SYMBOL(vm_insert_range);
+
+/**
+ * vm_insert_range_buggy - insert range of kernel pages starts with zero offset
+ * @vma: user vma to map to
+ * @pages: pointer to array of source kernel pages
+ * @num: number of pages in page array
+ *
+ * Maps a set of pages, always starting at page[0]
+ *
+ * Context: Process context. Called by mmap handlers.
+ * Return: 0 on success and error code otherwise.
+ */
+int vm_insert_range_buggy(struct vm_area_struct *vma, struct page **pages,
+				unsigned long num)
+{
+	return __vm_insert_range(vma, pages, num, 0);
+}
+EXPORT_SYMBOL(vm_insert_range_buggy);
+
 static vm_fault_t insert_pfn(struct vm_area_struct *vma, unsigned long addr,
 			pfn_t pfn, pgprot_t prot, bool mkwrite)
 {
diff --git a/mm/nommu.c b/mm/nommu.c
index 749276b..21d101e 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -473,6 +473,20 @@  int vm_insert_page(struct vm_area_struct *vma, unsigned long addr,
 }
 EXPORT_SYMBOL(vm_insert_page);
 
+int vm_insert_range(struct vm_area_struct *vma, struct page **pages,
+			unsigned long num)
+{
+	return -EINVAL;
+}
+EXPORT_SYMBOL(vm_insert_range);
+
+int vm_insert_range_buggy(struct vm_area_struct *vma, struct page **pages,
+				unsigned long num)
+{
+	return -EINVAL;
+}
+EXPORT_SYMBOL(vm_insert_range_buggy);
+
 /*
  *  sys_brk() for the most part doesn't need the global kernel
  *  lock, except when an application is doing something nasty