[RFC,v2,12/19] mm/gup: Prep put_user_pages() to take an vaddr_pin struct

Commit Message

Ira Weiny Aug. 9, 2019, 10:58 p.m. UTC

From: Ira Weiny <[e-mail]>

Once callers start to use vaddr_pin the put_user_pages calls will need
to have access to this data coming in.  Prep put_user_pages() for this
data.

Signed-off-by: Ira Weiny <[e-mail]>
---
 include/linux/mm.h |  20 +-------
 mm/gup.c           | 122 ++++++++++++++++++++++++++++++++-------------
 2 files changed, 88 insertions(+), 54 deletions(-)

Comments

John Hubbard Aug. 10, 2019, 12:30 a.m. UTC | #1

On 8/9/19 3:58 PM, [e-mail] wrote:
> From: Ira Weiny <[e-mail]>
> 
> Once callers start to use vaddr_pin the put_user_pages calls will need
> to have access to this data coming in.  Prep put_user_pages() for this
> data.
> 
> Signed-off-by: Ira Weiny <[e-mail]>
> ---
>  include/linux/mm.h |  20 +-------
>  mm/gup.c           | 122 ++++++++++++++++++++++++++++++++-------------
>  2 files changed, 88 insertions(+), 54 deletions(-)
> 
> diff --git a/include/linux/mm.h b/include/linux/mm.h
> index befe150d17be..9d37cafbef9a 100644
> --- a/include/linux/mm.h
> +++ b/include/linux/mm.h
> @@ -1064,25 +1064,7 @@ static inline void put_page(struct page *page)
>  		__put_page(page);
>  }
>  
> -/**
> - * put_user_page() - release a gup-pinned page
> - * @page:            pointer to page to be released
> - *
> - * Pages that were pinned via get_user_pages*() must be released via
> - * either put_user_page(), or one of the put_user_pages*() routines
> - * below. This is so that eventually, pages that are pinned via
> - * get_user_pages*() can be separately tracked and uniquely handled. In
> - * particular, interactions with RDMA and filesystems need special
> - * handling.
> - *
> - * put_user_page() and put_page() are not interchangeable, despite this early
> - * implementation that makes them look the same. put_user_page() calls must
> - * be perfectly matched up with get_user_page() calls.
> - */
> -static inline void put_user_page(struct page *page)
> -{
> -	put_page(page);
> -}
> +void put_user_page(struct page *page);
>  
>  void put_user_pages_dirty_lock(struct page **pages, unsigned long npages,
>  			       bool make_dirty);
> diff --git a/mm/gup.c b/mm/gup.c
> index a7a9d2f5278c..10cfd30ff668 100644
> --- a/mm/gup.c
> +++ b/mm/gup.c
> @@ -24,30 +24,41 @@
>  
>  #include "internal.h"
>  
> -/**
> - * put_user_pages_dirty_lock() - release and optionally dirty gup-pinned pages
> - * @pages:  array of pages to be maybe marked dirty, and definitely released.

A couple comments from our circular review chain: some fellow with the same
last name as you, recommended wording it like this:

      @pages:  array of pages to be put

> - * @npages: number of pages in the @pages array.
> - * @make_dirty: whether to mark the pages dirty
> - *
> - * "gup-pinned page" refers to a page that has had one of the get_user_pages()
> - * variants called on that page.
> - *
> - * For each page in the @pages array, make that page (or its head page, if a
> - * compound page) dirty, if @make_dirty is true, and if the page was previously
> - * listed as clean. In any case, releases all pages using put_user_page(),
> - * possibly via put_user_pages(), for the non-dirty case.
> - *
> - * Please see the put_user_page() documentation for details.
> - *
> - * set_page_dirty_lock() is used internally. If instead, set_page_dirty() is
> - * required, then the caller should a) verify that this is really correct,
> - * because _lock() is usually required, and b) hand code it:
> - * set_page_dirty_lock(), put_user_page().
> - *
> - */
> -void put_user_pages_dirty_lock(struct page **pages, unsigned long npages,
> -			       bool make_dirty)
> +static void __put_user_page(struct vaddr_pin *vaddr_pin, struct page *page)
> +{
> +	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 (put_devmap_managed_page(page))
> +		return;
> +
> +	if (put_page_testzero(page))
> +		__put_page(page);
> +}
> +
> +static void __put_user_pages(struct vaddr_pin *vaddr_pin, struct page **pages,
> +			     unsigned long npages)
> +{
> +	unsigned long index;
> +
> +	/*
> +	 * TODO: this can be optimized for huge pages: if a series of pages is
> +	 * physically contiguous and part of the same compound page, then a
> +	 * single operation to the head page should suffice.
> +	 */

As discussed in the other review thread (""), let's just delete that comment,
as long as you're moving things around.


> +	for (index = 0; index < npages; index++)
> +		__put_user_page(vaddr_pin, pages[index]);
> +}
> +
> +static void __put_user_pages_dirty_lock(struct vaddr_pin *vaddr_pin,
> +					struct page **pages,
> +					unsigned long npages,
> +					bool make_dirty)

Elsewhere in this series, we pass vaddr_pin at the end of the arg list.
Here we pass it at the beginning, and it caused a minor jar when reading it.
Obviously just bike shedding at this point, though. Either way. :)

>  {
>  	unsigned long index;
>  
> @@ -58,7 +69,7 @@ void put_user_pages_dirty_lock(struct page **pages, unsigned long npages,
>  	 */
>  
>  	if (!make_dirty) {
> -		put_user_pages(pages, npages);
> +		__put_user_pages(vaddr_pin, pages, npages);
>  		return;
>  	}
>  
> @@ -86,9 +97,58 @@ void put_user_pages_dirty_lock(struct page **pages, unsigned long npages,
>  		 */
>  		if (!PageDirty(page))
>  			set_page_dirty_lock(page);
> -		put_user_page(page);
> +		__put_user_page(vaddr_pin, page);
>  	}
>  }
> +
> +/**
> + * put_user_page() - release a gup-pinned page
> + * @page:            pointer to page to be released
> + *
> + * Pages that were pinned via get_user_pages*() must be released via
> + * either put_user_page(), or one of the put_user_pages*() routines
> + * below. This is so that eventually, pages that are pinned via
> + * get_user_pages*() can be separately tracked and uniquely handled. In
> + * particular, interactions with RDMA and filesystems need special
> + * handling.
> + *
> + * put_user_page() and put_page() are not interchangeable, despite this early
> + * implementation that makes them look the same. put_user_page() calls must
> + * be perfectly matched up with get_user_page() calls.
> + */
> +void put_user_page(struct page *page)
> +{
> +	__put_user_page(NULL, page);
> +}
> +EXPORT_SYMBOL(put_user_page);
> +
> +/**
> + * put_user_pages_dirty_lock() - release and optionally dirty gup-pinned pages
> + * @pages:  array of pages to be maybe marked dirty, and definitely released.

Same here:

      @pages:  array of pages to be put

> + * @npages: number of pages in the @pages array.
> + * @make_dirty: whether to mark the pages dirty
> + *
> + * "gup-pinned page" refers to a page that has had one of the get_user_pages()
> + * variants called on that page.
> + *
> + * For each page in the @pages array, make that page (or its head page, if a
> + * compound page) dirty, if @make_dirty is true, and if the page was previously
> + * listed as clean. In any case, releases all pages using put_user_page(),
> + * possibly via put_user_pages(), for the non-dirty case.
> + *
> + * Please see the put_user_page() documentation for details.
> + *
> + * set_page_dirty_lock() is used internally. If instead, set_page_dirty() is
> + * required, then the caller should a) verify that this is really correct,
> + * because _lock() is usually required, and b) hand code it:
> + * set_page_dirty_lock(), put_user_page().
> + *
> + */
> +void put_user_pages_dirty_lock(struct page **pages, unsigned long npages,
> +			       bool make_dirty)
> +{
> +	__put_user_pages_dirty_lock(NULL, pages, npages, make_dirty);
> +}
>  EXPORT_SYMBOL(put_user_pages_dirty_lock);
>  
>  /**
> @@ -102,15 +162,7 @@ EXPORT_SYMBOL(put_user_pages_dirty_lock);
>   */
>  void put_user_pages(struct page **pages, unsigned long npages)
>  {
> -	unsigned long index;
> -
> -	/*
> -	 * TODO: this can be optimized for huge pages: if a series of pages is
> -	 * physically contiguous and part of the same compound page, then a
> -	 * single operation to the head page should suffice.
> -	 */
> -	for (index = 0; index < npages; index++)
> -		put_user_page(pages[index]);
> +	__put_user_pages(NULL, pages, npages);
>  }
>  EXPORT_SYMBOL(put_user_pages);
>  
> 

This all looks pretty good, so regardless of the outcome of the minor
points above,
   
    Reviewed-by: John Hubbard <[e-mail]>


thanks,

Ira Weiny Aug. 12, 2019, 8:46 p.m. UTC | #2

On Fri, Aug 09, 2019 at 05:30:00PM -0700, John Hubbard wrote:
> On 8/9/19 3:58 PM, [e-mail] wrote:
> > From: Ira Weiny <[e-mail]>
> > 
> > Once callers start to use vaddr_pin the put_user_pages calls will need
> > to have access to this data coming in.  Prep put_user_pages() for this
> > data.
> > 
> > Signed-off-by: Ira Weiny <[e-mail]>

[snip]

> > diff --git a/mm/gup.c b/mm/gup.c
> > index a7a9d2f5278c..10cfd30ff668 100644
> > --- a/mm/gup.c
> > +++ b/mm/gup.c
> > @@ -24,30 +24,41 @@
> >  
> >  #include "internal.h"
> >  
> > -/**
> > - * put_user_pages_dirty_lock() - release and optionally dirty gup-pinned pages
> > - * @pages:  array of pages to be maybe marked dirty, and definitely released.
> 
> A couple comments from our circular review chain: some fellow with the same
> last name as you, recommended wording it like this:
> 
>       @pages:  array of pages to be put

Sure, see below...

> 
> > - * @npages: number of pages in the @pages array.
> > - * @make_dirty: whether to mark the pages dirty
> > - *
> > - * "gup-pinned page" refers to a page that has had one of the get_user_pages()
> > - * variants called on that page.
> > - *
> > - * For each page in the @pages array, make that page (or its head page, if a
> > - * compound page) dirty, if @make_dirty is true, and if the page was previously
> > - * listed as clean. In any case, releases all pages using put_user_page(),
> > - * possibly via put_user_pages(), for the non-dirty case.
> > - *
> > - * Please see the put_user_page() documentation for details.
> > - *
> > - * set_page_dirty_lock() is used internally. If instead, set_page_dirty() is
> > - * required, then the caller should a) verify that this is really correct,
> > - * because _lock() is usually required, and b) hand code it:
> > - * set_page_dirty_lock(), put_user_page().
> > - *
> > - */
> > -void put_user_pages_dirty_lock(struct page **pages, unsigned long npages,
> > -			       bool make_dirty)
> > +static void __put_user_page(struct vaddr_pin *vaddr_pin, struct page *page)
> > +{
> > +	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 (put_devmap_managed_page(page))
> > +		return;
> > +
> > +	if (put_page_testzero(page))
> > +		__put_page(page);
> > +}
> > +
> > +static void __put_user_pages(struct vaddr_pin *vaddr_pin, struct page **pages,
> > +			     unsigned long npages)
> > +{
> > +	unsigned long index;
> > +
> > +	/*
> > +	 * TODO: this can be optimized for huge pages: if a series of pages is
> > +	 * physically contiguous and part of the same compound page, then a
> > +	 * single operation to the head page should suffice.
> > +	 */
> 
> As discussed in the other review thread (""), let's just delete that comment,
> as long as you're moving things around.

Done.

> 
> 
> > +	for (index = 0; index < npages; index++)
> > +		__put_user_page(vaddr_pin, pages[index]);
> > +}
> > +
> > +static void __put_user_pages_dirty_lock(struct vaddr_pin *vaddr_pin,
> > +					struct page **pages,
> > +					unsigned long npages,
> > +					bool make_dirty)
> 
> Elsewhere in this series, we pass vaddr_pin at the end of the arg list.
> Here we pass it at the beginning, and it caused a minor jar when reading it.
> Obviously just bike shedding at this point, though. Either way. :)

Yea I guess that is odd...  I changed it.  Not a big deal.

> 
> >  {
> >  	unsigned long index;
> >  
> > @@ -58,7 +69,7 @@ void put_user_pages_dirty_lock(struct page **pages, unsigned long npages,
> >  	 */
> >  
> >  	if (!make_dirty) {
> > -		put_user_pages(pages, npages);
> > +		__put_user_pages(vaddr_pin, pages, npages);
> >  		return;
> >  	}
> >  
> > @@ -86,9 +97,58 @@ void put_user_pages_dirty_lock(struct page **pages, unsigned long npages,
> >  		 */
> >  		if (!PageDirty(page))
> >  			set_page_dirty_lock(page);
> > -		put_user_page(page);
> > +		__put_user_page(vaddr_pin, page);
> >  	}
> >  }
> > +
> > +/**
> > + * put_user_page() - release a gup-pinned page
> > + * @page:            pointer to page to be released
> > + *
> > + * Pages that were pinned via get_user_pages*() must be released via
> > + * either put_user_page(), or one of the put_user_pages*() routines
> > + * below. This is so that eventually, pages that are pinned via
> > + * get_user_pages*() can be separately tracked and uniquely handled. In
> > + * particular, interactions with RDMA and filesystems need special
> > + * handling.
> > + *
> > + * put_user_page() and put_page() are not interchangeable, despite this early
> > + * implementation that makes them look the same. put_user_page() calls must
> > + * be perfectly matched up with get_user_page() calls.
> > + */
> > +void put_user_page(struct page *page)
> > +{
> > +	__put_user_page(NULL, page);
> > +}
> > +EXPORT_SYMBOL(put_user_page);
> > +
> > +/**
> > + * put_user_pages_dirty_lock() - release and optionally dirty gup-pinned pages
> > + * @pages:  array of pages to be maybe marked dirty, and definitely released.
> 
> Same here:
> 
>       @pages:  array of pages to be put

Actually here is the only place.  Above was removing the text to be put here...

Done -- I'll made a lead in patch because this was just copied text.

> 
> > + * @npages: number of pages in the @pages array.
> > + * @make_dirty: whether to mark the pages dirty
> > + *
> > + * "gup-pinned page" refers to a page that has had one of the get_user_pages()
> > + * variants called on that page.
> > + *
> > + * For each page in the @pages array, make that page (or its head page, if a
> > + * compound page) dirty, if @make_dirty is true, and if the page was previously
> > + * listed as clean. In any case, releases all pages using put_user_page(),
> > + * possibly via put_user_pages(), for the non-dirty case.
> > + *
> > + * Please see the put_user_page() documentation for details.
> > + *
> > + * set_page_dirty_lock() is used internally. If instead, set_page_dirty() is
> > + * required, then the caller should a) verify that this is really correct,
> > + * because _lock() is usually required, and b) hand code it:
> > + * set_page_dirty_lock(), put_user_page().
> > + *
> > + */
> > +void put_user_pages_dirty_lock(struct page **pages, unsigned long npages,
> > +			       bool make_dirty)
> > +{
> > +	__put_user_pages_dirty_lock(NULL, pages, npages, make_dirty);
> > +}
> >  EXPORT_SYMBOL(put_user_pages_dirty_lock);
> >  
> >  /**
> > @@ -102,15 +162,7 @@ EXPORT_SYMBOL(put_user_pages_dirty_lock);
> >   */
> >  void put_user_pages(struct page **pages, unsigned long npages)
> >  {
> > -	unsigned long index;
> > -
> > -	/*
> > -	 * TODO: this can be optimized for huge pages: if a series of pages is
> > -	 * physically contiguous and part of the same compound page, then a
> > -	 * single operation to the head page should suffice.
> > -	 */
> > -	for (index = 0; index < npages; index++)
> > -		put_user_page(pages[index]);
> > +	__put_user_pages(NULL, pages, npages);
> >  }
> >  EXPORT_SYMBOL(put_user_pages);
> >  
> > 
> 
> This all looks pretty good, so regardless of the outcome of the minor
> points above,
>    
>     Reviewed-by: John Hubbard <[e-mail]>

Thanks,
Ira

> 
> 
> thanks,
> -- 
> John Hubbard
> NVIDIA

Patch

diff --git a/include/linux/mm.h b/include/linux/mm.h
index befe150d17be..9d37cafbef9a 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1064,25 +1064,7 @@  static inline void put_page(struct page *page)
 		__put_page(page);
 }
 
-/**
- * put_user_page() - release a gup-pinned page
- * @page:            pointer to page to be released
- *
- * Pages that were pinned via get_user_pages*() must be released via
- * either put_user_page(), or one of the put_user_pages*() routines
- * below. This is so that eventually, pages that are pinned via
- * get_user_pages*() can be separately tracked and uniquely handled. In
- * particular, interactions with RDMA and filesystems need special
- * handling.
- *
- * put_user_page() and put_page() are not interchangeable, despite this early
- * implementation that makes them look the same. put_user_page() calls must
- * be perfectly matched up with get_user_page() calls.
- */
-static inline void put_user_page(struct page *page)
-{
-	put_page(page);
-}
+void put_user_page(struct page *page);
 
 void put_user_pages_dirty_lock(struct page **pages, unsigned long npages,
 			       bool make_dirty);
diff --git a/mm/gup.c b/mm/gup.c
index a7a9d2f5278c..10cfd30ff668 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -24,30 +24,41 @@ 
 
 #include "internal.h"
 
-/**
- * put_user_pages_dirty_lock() - release and optionally dirty gup-pinned pages
- * @pages:  array of pages to be maybe marked dirty, and definitely released.
- * @npages: number of pages in the @pages array.
- * @make_dirty: whether to mark the pages dirty
- *
- * "gup-pinned page" refers to a page that has had one of the get_user_pages()
- * variants called on that page.
- *
- * For each page in the @pages array, make that page (or its head page, if a
- * compound page) dirty, if @make_dirty is true, and if the page was previously
- * listed as clean. In any case, releases all pages using put_user_page(),
- * possibly via put_user_pages(), for the non-dirty case.
- *
- * Please see the put_user_page() documentation for details.
- *
- * set_page_dirty_lock() is used internally. If instead, set_page_dirty() is
- * required, then the caller should a) verify that this is really correct,
- * because _lock() is usually required, and b) hand code it:
- * set_page_dirty_lock(), put_user_page().
- *
- */
-void put_user_pages_dirty_lock(struct page **pages, unsigned long npages,
-			       bool make_dirty)
+static void __put_user_page(struct vaddr_pin *vaddr_pin, struct page *page)
+{
+	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 (put_devmap_managed_page(page))
+		return;
+
+	if (put_page_testzero(page))
+		__put_page(page);
+}
+
+static void __put_user_pages(struct vaddr_pin *vaddr_pin, struct page **pages,
+			     unsigned long npages)
+{
+	unsigned long index;
+
+	/*
+	 * TODO: this can be optimized for huge pages: if a series of pages is
+	 * physically contiguous and part of the same compound page, then a
+	 * single operation to the head page should suffice.
+	 */
+	for (index = 0; index < npages; index++)
+		__put_user_page(vaddr_pin, pages[index]);
+}
+
+static void __put_user_pages_dirty_lock(struct vaddr_pin *vaddr_pin,
+					struct page **pages,
+					unsigned long npages,
+					bool make_dirty)
 {
 	unsigned long index;
 
@@ -58,7 +69,7 @@  void put_user_pages_dirty_lock(struct page **pages, unsigned long npages,
 	 */
 
 	if (!make_dirty) {
-		put_user_pages(pages, npages);
+		__put_user_pages(vaddr_pin, pages, npages);
 		return;
 	}
 
@@ -86,9 +97,58 @@  void put_user_pages_dirty_lock(struct page **pages, unsigned long npages,
 		 */
 		if (!PageDirty(page))
 			set_page_dirty_lock(page);
-		put_user_page(page);
+		__put_user_page(vaddr_pin, page);
 	}
 }
+
+/**
+ * put_user_page() - release a gup-pinned page
+ * @page:            pointer to page to be released
+ *
+ * Pages that were pinned via get_user_pages*() must be released via
+ * either put_user_page(), or one of the put_user_pages*() routines
+ * below. This is so that eventually, pages that are pinned via
+ * get_user_pages*() can be separately tracked and uniquely handled. In
+ * particular, interactions with RDMA and filesystems need special
+ * handling.
+ *
+ * put_user_page() and put_page() are not interchangeable, despite this early
+ * implementation that makes them look the same. put_user_page() calls must
+ * be perfectly matched up with get_user_page() calls.
+ */
+void put_user_page(struct page *page)
+{
+	__put_user_page(NULL, page);
+}
+EXPORT_SYMBOL(put_user_page);
+
+/**
+ * put_user_pages_dirty_lock() - release and optionally dirty gup-pinned pages
+ * @pages:  array of pages to be maybe marked dirty, and definitely released.
+ * @npages: number of pages in the @pages array.
+ * @make_dirty: whether to mark the pages dirty
+ *
+ * "gup-pinned page" refers to a page that has had one of the get_user_pages()
+ * variants called on that page.
+ *
+ * For each page in the @pages array, make that page (or its head page, if a
+ * compound page) dirty, if @make_dirty is true, and if the page was previously
+ * listed as clean. In any case, releases all pages using put_user_page(),
+ * possibly via put_user_pages(), for the non-dirty case.
+ *
+ * Please see the put_user_page() documentation for details.
+ *
+ * set_page_dirty_lock() is used internally. If instead, set_page_dirty() is
+ * required, then the caller should a) verify that this is really correct,
+ * because _lock() is usually required, and b) hand code it:
+ * set_page_dirty_lock(), put_user_page().
+ *
+ */
+void put_user_pages_dirty_lock(struct page **pages, unsigned long npages,
+			       bool make_dirty)
+{
+	__put_user_pages_dirty_lock(NULL, pages, npages, make_dirty);
+}
 EXPORT_SYMBOL(put_user_pages_dirty_lock);
 
 /**
@@ -102,15 +162,7 @@  EXPORT_SYMBOL(put_user_pages_dirty_lock);
  */
 void put_user_pages(struct page **pages, unsigned long npages)
 {
-	unsigned long index;
-
-	/*
-	 * TODO: this can be optimized for huge pages: if a series of pages is
-	 * physically contiguous and part of the same compound page, then a
-	 * single operation to the head page should suffice.
-	 */
-	for (index = 0; index < npages; index++)
-		put_user_page(pages[index]);
+	__put_user_pages(NULL, pages, npages);
 }
 EXPORT_SYMBOL(put_user_pages);