diff mbox series

mm/up: combine put_compound_head() and unpin_user_page()

Message ID 0-v1-6730d4ee0d32+40e6-gup_combine_put_jgg@nvidia.com (mailing list archive)
State New, archived
Headers show
Series mm/up: combine put_compound_head() and unpin_user_page() | expand

Commit Message

Jason Gunthorpe Dec. 9, 2020, 7:13 p.m. UTC
These functions accomplish the same thing but have different
implementations.

unpin_user_page() has a bug where it calls mod_node_page_state() after
calling put_page() which creates a risk that the page could have been
hot-uplugged from the system.

Fix this by using put_compound_head() as the only implementation.

__unpin_devmap_managed_user_page() and related can be deleted as well in
favour of the simpler, but slower, version in put_compound_head() that has
an extra atomic page_ref_sub, but always calls put_page() which internally
contains the special devmap code.

Move put_compound_head() to be directly after try_grab_compound_head() so
people can find it in future.

Fixes: 1970dc6f5226 ("mm/gup: /proc/vmstat: pin_user_pages (FOLL_PIN) reporting")
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
---
 mm/gup.c | 103 +++++++++++++------------------------------------------
 1 file changed, 23 insertions(+), 80 deletions(-)

With Matt's folio idea I'd next to go to make a
  put_folio(folio, refs)

Which would cleanly eliminate that extra atomic here without duplicating the
devmap special case.

This should also be called 'ungrab_compound_head' as we seem to be using the
word 'grab' to mean 'pin or get' depending on GUP flags.

Comments

John Hubbard Dec. 9, 2020, 8:57 p.m. UTC | #1
On 12/9/20 11:13 AM, Jason Gunthorpe wrote:
> These functions accomplish the same thing but have different
> implementations.
> 
> unpin_user_page() has a bug where it calls mod_node_page_state() after
> calling put_page() which creates a risk that the page could have been
> hot-uplugged from the system.
> 
> Fix this by using put_compound_head() as the only implementation.
> 
> __unpin_devmap_managed_user_page() and related can be deleted as well in
> favour of the simpler, but slower, version in put_compound_head() that has
> an extra atomic page_ref_sub, but always calls put_page() which internally
> contains the special devmap code.
> 
> Move put_compound_head() to be directly after try_grab_compound_head() so
> people can find it in future.
> 
> Fixes: 1970dc6f5226 ("mm/gup: /proc/vmstat: pin_user_pages (FOLL_PIN) reporting")
> Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
> ---
>   mm/gup.c | 103 +++++++++++++------------------------------------------
>   1 file changed, 23 insertions(+), 80 deletions(-)
> 

Reviewed-by: John Hubbard <jhubbard@nvidia.com>

With a couple of minor notes below:

> With Matt's folio idea I'd next to go to make a
>    put_folio(folio, refs)
> 
> Which would cleanly eliminate that extra atomic here without duplicating the
> devmap special case.
> 
> This should also be called 'ungrab_compound_head' as we seem to be using the
> word 'grab' to mean 'pin or get' depending on GUP flags.
> 
> diff --git a/mm/gup.c b/mm/gup.c
> index 98eb8e6d2609c3..7b33b7d4b324d7 100644
> --- a/mm/gup.c
> +++ b/mm/gup.c
> @@ -123,6 +123,28 @@ static __maybe_unused struct page *try_grab_compound_head(struct page *page,
>   	return NULL;
>   }
>   
> +static void put_compound_head(struct page *page, int refs, unsigned int flags)
> +{

It might be nice to rename "page" to "head", here.

While reading this I toyed with the idea of having this at the top:

	VM_BUG_ON_PAGE(compound_head(page) != page, page);

...but it's overkill in a static function with pretty clear call sites. So I
think it's just right as-is.


> +	if (flags & FOLL_PIN) {
> +		mod_node_page_state(page_pgdat(page), NR_FOLL_PIN_RELEASED,
> +				    refs);
> +
> +		if (hpage_pincount_available(page))
> +			hpage_pincount_sub(page, refs);
> +		else
> +			refs *= GUP_PIN_COUNTING_BIAS;
> +	}
> +
> +	VM_BUG_ON_PAGE(page_ref_count(page) < refs, page);
> +	/*
> +	 * Calling put_page() for each ref is unnecessarily slow. Only the last
> +	 * ref needs a put_page().
> +	 */
> +	if (refs > 1)
> +		page_ref_sub(page, refs - 1);
> +	put_page(page);
> +}
> +
>   /**
>    * try_grab_page() - elevate a page's refcount by a flag-dependent amount
>    *
> @@ -177,41 +199,6 @@ bool __must_check try_grab_page(struct page *page, unsigned int flags)
>   	return true;
>   }
>   
> -#ifdef CONFIG_DEV_PAGEMAP_OPS
> -static bool __unpin_devmap_managed_user_page(struct page *page)
> -{
> -	int count, refs = 1;
> -
> -	if (!page_is_devmap_managed(page))
> -		return false;
> -
> -	if (hpage_pincount_available(page))
> -		hpage_pincount_sub(page, 1);
> -	else
> -		refs = GUP_PIN_COUNTING_BIAS;
> -
> -	count = page_ref_sub_return(page, refs);
> -
> -	mod_node_page_state(page_pgdat(page), NR_FOLL_PIN_RELEASED, 1);
> -	/*
> -	 * devmap page refcounts are 1-based, rather than 0-based: if
> -	 * refcount is 1, then the page is free and the refcount is
> -	 * stable because nobody holds a reference on the page.
> -	 */
> -	if (count == 1)
> -		free_devmap_managed_page(page);
> -	else if (!count)
> -		__put_page(page);
> -
> -	return true;
> -}
> -#else
> -static bool __unpin_devmap_managed_user_page(struct page *page)
> -{
> -	return false;
> -}
> -#endif /* CONFIG_DEV_PAGEMAP_OPS */
> -

Wow, getting rid of that duplication is beautiful!

thanks,
Jason Gunthorpe Dec. 9, 2020, 9:03 p.m. UTC | #2
On Wed, Dec 09, 2020 at 12:57:38PM -0800, John Hubbard wrote:
> > diff --git a/mm/gup.c b/mm/gup.c
> > index 98eb8e6d2609c3..7b33b7d4b324d7 100644
> > +++ b/mm/gup.c
> > @@ -123,6 +123,28 @@ static __maybe_unused struct page *try_grab_compound_head(struct page *page,
> >   	return NULL;
> >   }
> > +static void put_compound_head(struct page *page, int refs, unsigned int flags)
> > +{
> 
> It might be nice to rename "page" to "head", here.
> 
> While reading this I toyed with the idea of having this at the top:
> 
> 	VM_BUG_ON_PAGE(compound_head(page) != page, page);
> 
> ...but it's overkill in a static function with pretty clear call sites. So I
> think it's just right as-is.

Matt's folio patches would take are of this, when that is available
all this becomes a lot better.

Thanks,
Jason
Ira Weiny Dec. 9, 2020, 11:21 p.m. UTC | #3
On Wed, Dec 09, 2020 at 03:13:57PM -0400, Jason Gunthorpe wrote:
> These functions accomplish the same thing but have different
> implementations.
> 
> unpin_user_page() has a bug where it calls mod_node_page_state() after
> calling put_page() which creates a risk that the page could have been
> hot-uplugged from the system.
> 
> Fix this by using put_compound_head() as the only implementation.
> 
> __unpin_devmap_managed_user_page() and related can be deleted as well in
> favour of the simpler, but slower, version in put_compound_head() that has
> an extra atomic page_ref_sub, but always calls put_page() which internally
> contains the special devmap code.
> 
> Move put_compound_head() to be directly after try_grab_compound_head() so
> people can find it in future.
> 
> Fixes: 1970dc6f5226 ("mm/gup: /proc/vmstat: pin_user_pages (FOLL_PIN) reporting")
> Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>

Reviewed-by: Ira Weiny <ira.weiny@intel.com>

> ---
>  mm/gup.c | 103 +++++++++++++------------------------------------------
>  1 file changed, 23 insertions(+), 80 deletions(-)
> 
> With Matt's folio idea I'd next to go to make a
>   put_folio(folio, refs)
> 
> Which would cleanly eliminate that extra atomic here without duplicating the
> devmap special case.
> 
> This should also be called 'ungrab_compound_head' as we seem to be using the
> word 'grab' to mean 'pin or get' depending on GUP flags.
> 
> diff --git a/mm/gup.c b/mm/gup.c
> index 98eb8e6d2609c3..7b33b7d4b324d7 100644
> --- a/mm/gup.c
> +++ b/mm/gup.c
> @@ -123,6 +123,28 @@ static __maybe_unused struct page *try_grab_compound_head(struct page *page,
>  	return NULL;
>  }
>  
> +static void put_compound_head(struct page *page, int refs, unsigned int flags)
> +{
> +	if (flags & FOLL_PIN) {
> +		mod_node_page_state(page_pgdat(page), NR_FOLL_PIN_RELEASED,
> +				    refs);
> +
> +		if (hpage_pincount_available(page))
> +			hpage_pincount_sub(page, refs);
> +		else
> +			refs *= GUP_PIN_COUNTING_BIAS;
> +	}
> +
> +	VM_BUG_ON_PAGE(page_ref_count(page) < refs, page);
> +	/*
> +	 * Calling put_page() for each ref is unnecessarily slow. Only the last
> +	 * ref needs a put_page().
> +	 */
> +	if (refs > 1)
> +		page_ref_sub(page, refs - 1);
> +	put_page(page);
> +}
> +
>  /**
>   * try_grab_page() - elevate a page's refcount by a flag-dependent amount
>   *
> @@ -177,41 +199,6 @@ bool __must_check try_grab_page(struct page *page, unsigned int flags)
>  	return true;
>  }
>  
> -#ifdef CONFIG_DEV_PAGEMAP_OPS
> -static bool __unpin_devmap_managed_user_page(struct page *page)
> -{
> -	int count, refs = 1;
> -
> -	if (!page_is_devmap_managed(page))
> -		return false;
> -
> -	if (hpage_pincount_available(page))
> -		hpage_pincount_sub(page, 1);
> -	else
> -		refs = GUP_PIN_COUNTING_BIAS;
> -
> -	count = page_ref_sub_return(page, refs);
> -
> -	mod_node_page_state(page_pgdat(page), NR_FOLL_PIN_RELEASED, 1);
> -	/*
> -	 * devmap page refcounts are 1-based, rather than 0-based: if
> -	 * refcount is 1, then the page is free and the refcount is
> -	 * stable because nobody holds a reference on the page.
> -	 */
> -	if (count == 1)
> -		free_devmap_managed_page(page);
> -	else if (!count)
> -		__put_page(page);
> -
> -	return true;
> -}
> -#else
> -static bool __unpin_devmap_managed_user_page(struct page *page)
> -{
> -	return false;
> -}
> -#endif /* CONFIG_DEV_PAGEMAP_OPS */
> -
>  /**
>   * unpin_user_page() - release a dma-pinned page
>   * @page:            pointer to page to be released
> @@ -223,28 +210,7 @@ static bool __unpin_devmap_managed_user_page(struct page *page)
>   */
>  void unpin_user_page(struct page *page)
>  {
> -	int refs = 1;
> -
> -	page = compound_head(page);
> -
> -	/*
> -	 * For devmap managed pages we need to catch refcount transition from
> -	 * GUP_PIN_COUNTING_BIAS to 1, when refcount reach one it means the
> -	 * page is free and we need to inform the device driver through
> -	 * callback. See include/linux/memremap.h and HMM for details.
> -	 */
> -	if (__unpin_devmap_managed_user_page(page))
> -		return;
> -
> -	if (hpage_pincount_available(page))
> -		hpage_pincount_sub(page, 1);
> -	else
> -		refs = GUP_PIN_COUNTING_BIAS;
> -
> -	if (page_ref_sub_and_test(page, refs))
> -		__put_page(page);
> -
> -	mod_node_page_state(page_pgdat(page), NR_FOLL_PIN_RELEASED, 1);
> +	put_compound_head(compound_head(page), 1, FOLL_PIN);
>  }
>  EXPORT_SYMBOL(unpin_user_page);
>  
> @@ -2062,29 +2028,6 @@ EXPORT_SYMBOL(get_user_pages_unlocked);
>   * This code is based heavily on the PowerPC implementation by Nick Piggin.
>   */
>  #ifdef CONFIG_HAVE_FAST_GUP
> -
> -static void put_compound_head(struct page *page, int refs, unsigned int flags)
> -{
> -	if (flags & FOLL_PIN) {
> -		mod_node_page_state(page_pgdat(page), NR_FOLL_PIN_RELEASED,
> -				    refs);
> -
> -		if (hpage_pincount_available(page))
> -			hpage_pincount_sub(page, refs);
> -		else
> -			refs *= GUP_PIN_COUNTING_BIAS;
> -	}
> -
> -	VM_BUG_ON_PAGE(page_ref_count(page) < refs, page);
> -	/*
> -	 * Calling put_page() for each ref is unnecessarily slow. Only the last
> -	 * ref needs a put_page().
> -	 */
> -	if (refs > 1)
> -		page_ref_sub(page, refs - 1);
> -	put_page(page);
> -}
> -
>  #ifdef CONFIG_GUP_GET_PTE_LOW_HIGH
>  
>  /*
> -- 
> 2.29.2
>
Jan Kara Dec. 10, 2020, 9:22 a.m. UTC | #4
On Wed 09-12-20 15:13:57, Jason Gunthorpe wrote:
> These functions accomplish the same thing but have different
> implementations.
> 
> unpin_user_page() has a bug where it calls mod_node_page_state() after
> calling put_page() which creates a risk that the page could have been
> hot-uplugged from the system.
> 
> Fix this by using put_compound_head() as the only implementation.
> 
> __unpin_devmap_managed_user_page() and related can be deleted as well in
> favour of the simpler, but slower, version in put_compound_head() that has
> an extra atomic page_ref_sub, but always calls put_page() which internally
> contains the special devmap code.
> 
> Move put_compound_head() to be directly after try_grab_compound_head() so
> people can find it in future.
> 
> Fixes: 1970dc6f5226 ("mm/gup: /proc/vmstat: pin_user_pages (FOLL_PIN) reporting")
> Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>

Nice cleanup. The patch looks good to me. You can add:

Reviewed-by: Jan Kara <jack@suse.cz>

								Honza

> ---
>  mm/gup.c | 103 +++++++++++++------------------------------------------
>  1 file changed, 23 insertions(+), 80 deletions(-)
> 
> With Matt's folio idea I'd next to go to make a
>   put_folio(folio, refs)
> 
> Which would cleanly eliminate that extra atomic here without duplicating the
> devmap special case.
> 
> This should also be called 'ungrab_compound_head' as we seem to be using the
> word 'grab' to mean 'pin or get' depending on GUP flags.
> 
> diff --git a/mm/gup.c b/mm/gup.c
> index 98eb8e6d2609c3..7b33b7d4b324d7 100644
> --- a/mm/gup.c
> +++ b/mm/gup.c
> @@ -123,6 +123,28 @@ static __maybe_unused struct page *try_grab_compound_head(struct page *page,
>  	return NULL;
>  }
>  
> +static void put_compound_head(struct page *page, int refs, unsigned int flags)
> +{
> +	if (flags & FOLL_PIN) {
> +		mod_node_page_state(page_pgdat(page), NR_FOLL_PIN_RELEASED,
> +				    refs);
> +
> +		if (hpage_pincount_available(page))
> +			hpage_pincount_sub(page, refs);
> +		else
> +			refs *= GUP_PIN_COUNTING_BIAS;
> +	}
> +
> +	VM_BUG_ON_PAGE(page_ref_count(page) < refs, page);
> +	/*
> +	 * Calling put_page() for each ref is unnecessarily slow. Only the last
> +	 * ref needs a put_page().
> +	 */
> +	if (refs > 1)
> +		page_ref_sub(page, refs - 1);
> +	put_page(page);
> +}
> +
>  /**
>   * try_grab_page() - elevate a page's refcount by a flag-dependent amount
>   *
> @@ -177,41 +199,6 @@ bool __must_check try_grab_page(struct page *page, unsigned int flags)
>  	return true;
>  }
>  
> -#ifdef CONFIG_DEV_PAGEMAP_OPS
> -static bool __unpin_devmap_managed_user_page(struct page *page)
> -{
> -	int count, refs = 1;
> -
> -	if (!page_is_devmap_managed(page))
> -		return false;
> -
> -	if (hpage_pincount_available(page))
> -		hpage_pincount_sub(page, 1);
> -	else
> -		refs = GUP_PIN_COUNTING_BIAS;
> -
> -	count = page_ref_sub_return(page, refs);
> -
> -	mod_node_page_state(page_pgdat(page), NR_FOLL_PIN_RELEASED, 1);
> -	/*
> -	 * devmap page refcounts are 1-based, rather than 0-based: if
> -	 * refcount is 1, then the page is free and the refcount is
> -	 * stable because nobody holds a reference on the page.
> -	 */
> -	if (count == 1)
> -		free_devmap_managed_page(page);
> -	else if (!count)
> -		__put_page(page);
> -
> -	return true;
> -}
> -#else
> -static bool __unpin_devmap_managed_user_page(struct page *page)
> -{
> -	return false;
> -}
> -#endif /* CONFIG_DEV_PAGEMAP_OPS */
> -
>  /**
>   * unpin_user_page() - release a dma-pinned page
>   * @page:            pointer to page to be released
> @@ -223,28 +210,7 @@ static bool __unpin_devmap_managed_user_page(struct page *page)
>   */
>  void unpin_user_page(struct page *page)
>  {
> -	int refs = 1;
> -
> -	page = compound_head(page);
> -
> -	/*
> -	 * For devmap managed pages we need to catch refcount transition from
> -	 * GUP_PIN_COUNTING_BIAS to 1, when refcount reach one it means the
> -	 * page is free and we need to inform the device driver through
> -	 * callback. See include/linux/memremap.h and HMM for details.
> -	 */
> -	if (__unpin_devmap_managed_user_page(page))
> -		return;
> -
> -	if (hpage_pincount_available(page))
> -		hpage_pincount_sub(page, 1);
> -	else
> -		refs = GUP_PIN_COUNTING_BIAS;
> -
> -	if (page_ref_sub_and_test(page, refs))
> -		__put_page(page);
> -
> -	mod_node_page_state(page_pgdat(page), NR_FOLL_PIN_RELEASED, 1);
> +	put_compound_head(compound_head(page), 1, FOLL_PIN);
>  }
>  EXPORT_SYMBOL(unpin_user_page);
>  
> @@ -2062,29 +2028,6 @@ EXPORT_SYMBOL(get_user_pages_unlocked);
>   * This code is based heavily on the PowerPC implementation by Nick Piggin.
>   */
>  #ifdef CONFIG_HAVE_FAST_GUP
> -
> -static void put_compound_head(struct page *page, int refs, unsigned int flags)
> -{
> -	if (flags & FOLL_PIN) {
> -		mod_node_page_state(page_pgdat(page), NR_FOLL_PIN_RELEASED,
> -				    refs);
> -
> -		if (hpage_pincount_available(page))
> -			hpage_pincount_sub(page, refs);
> -		else
> -			refs *= GUP_PIN_COUNTING_BIAS;
> -	}
> -
> -	VM_BUG_ON_PAGE(page_ref_count(page) < refs, page);
> -	/*
> -	 * Calling put_page() for each ref is unnecessarily slow. Only the last
> -	 * ref needs a put_page().
> -	 */
> -	if (refs > 1)
> -		page_ref_sub(page, refs - 1);
> -	put_page(page);
> -}
> -
>  #ifdef CONFIG_GUP_GET_PTE_LOW_HIGH
>  
>  /*
> -- 
> 2.29.2
>
diff mbox series

Patch

diff --git a/mm/gup.c b/mm/gup.c
index 98eb8e6d2609c3..7b33b7d4b324d7 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -123,6 +123,28 @@  static __maybe_unused struct page *try_grab_compound_head(struct page *page,
 	return NULL;
 }
 
+static void put_compound_head(struct page *page, int refs, unsigned int flags)
+{
+	if (flags & FOLL_PIN) {
+		mod_node_page_state(page_pgdat(page), NR_FOLL_PIN_RELEASED,
+				    refs);
+
+		if (hpage_pincount_available(page))
+			hpage_pincount_sub(page, refs);
+		else
+			refs *= GUP_PIN_COUNTING_BIAS;
+	}
+
+	VM_BUG_ON_PAGE(page_ref_count(page) < refs, page);
+	/*
+	 * Calling put_page() for each ref is unnecessarily slow. Only the last
+	 * ref needs a put_page().
+	 */
+	if (refs > 1)
+		page_ref_sub(page, refs - 1);
+	put_page(page);
+}
+
 /**
  * try_grab_page() - elevate a page's refcount by a flag-dependent amount
  *
@@ -177,41 +199,6 @@  bool __must_check try_grab_page(struct page *page, unsigned int flags)
 	return true;
 }
 
-#ifdef CONFIG_DEV_PAGEMAP_OPS
-static bool __unpin_devmap_managed_user_page(struct page *page)
-{
-	int count, refs = 1;
-
-	if (!page_is_devmap_managed(page))
-		return false;
-
-	if (hpage_pincount_available(page))
-		hpage_pincount_sub(page, 1);
-	else
-		refs = GUP_PIN_COUNTING_BIAS;
-
-	count = page_ref_sub_return(page, refs);
-
-	mod_node_page_state(page_pgdat(page), NR_FOLL_PIN_RELEASED, 1);
-	/*
-	 * devmap page refcounts are 1-based, rather than 0-based: if
-	 * refcount is 1, then the page is free and the refcount is
-	 * stable because nobody holds a reference on the page.
-	 */
-	if (count == 1)
-		free_devmap_managed_page(page);
-	else if (!count)
-		__put_page(page);
-
-	return true;
-}
-#else
-static bool __unpin_devmap_managed_user_page(struct page *page)
-{
-	return false;
-}
-#endif /* CONFIG_DEV_PAGEMAP_OPS */
-
 /**
  * unpin_user_page() - release a dma-pinned page
  * @page:            pointer to page to be released
@@ -223,28 +210,7 @@  static bool __unpin_devmap_managed_user_page(struct page *page)
  */
 void unpin_user_page(struct page *page)
 {
-	int refs = 1;
-
-	page = compound_head(page);
-
-	/*
-	 * For devmap managed pages we need to catch refcount transition from
-	 * GUP_PIN_COUNTING_BIAS to 1, when refcount reach one it means the
-	 * page is free and we need to inform the device driver through
-	 * callback. See include/linux/memremap.h and HMM for details.
-	 */
-	if (__unpin_devmap_managed_user_page(page))
-		return;
-
-	if (hpage_pincount_available(page))
-		hpage_pincount_sub(page, 1);
-	else
-		refs = GUP_PIN_COUNTING_BIAS;
-
-	if (page_ref_sub_and_test(page, refs))
-		__put_page(page);
-
-	mod_node_page_state(page_pgdat(page), NR_FOLL_PIN_RELEASED, 1);
+	put_compound_head(compound_head(page), 1, FOLL_PIN);
 }
 EXPORT_SYMBOL(unpin_user_page);
 
@@ -2062,29 +2028,6 @@  EXPORT_SYMBOL(get_user_pages_unlocked);
  * This code is based heavily on the PowerPC implementation by Nick Piggin.
  */
 #ifdef CONFIG_HAVE_FAST_GUP
-
-static void put_compound_head(struct page *page, int refs, unsigned int flags)
-{
-	if (flags & FOLL_PIN) {
-		mod_node_page_state(page_pgdat(page), NR_FOLL_PIN_RELEASED,
-				    refs);
-
-		if (hpage_pincount_available(page))
-			hpage_pincount_sub(page, refs);
-		else
-			refs *= GUP_PIN_COUNTING_BIAS;
-	}
-
-	VM_BUG_ON_PAGE(page_ref_count(page) < refs, page);
-	/*
-	 * Calling put_page() for each ref is unnecessarily slow. Only the last
-	 * ref needs a put_page().
-	 */
-	if (refs > 1)
-		page_ref_sub(page, refs - 1);
-	put_page(page);
-}
-
 #ifdef CONFIG_GUP_GET_PTE_LOW_HIGH
 
 /*