diff mbox series

ext4/xfs: add page refcount helper

Message ID 20201006230930.3908-1-rcampbell@nvidia.com (mailing list archive)
State New, archived
Headers show
Series ext4/xfs: add page refcount helper | expand

Commit Message

Ralph Campbell Oct. 6, 2020, 11:09 p.m. UTC
There are several places where ZONE_DEVICE struct pages assume a reference
count == 1 means the page is idle and free. Instead of open coding this,
add a helper function to hide this detail.

Signed-off-by: Ralph Campbell <rcampbell@nvidia.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---

I'm resending this as a separate patch since I think it is ready to
merge. Originally, this was part of an RFC and is unchanged from v3:
https://lore.kernel.org/linux-mm/20201001181715.17416-1-rcampbell@nvidia.com

It applies cleanly to linux-5.9.0-rc7-mm1 but doesn't really
depend on anything, just simple merge conflicts when applied to
other trees.
I'll let the various maintainers decide which tree and when to merge.
It isn't urgent since it is a clean up patch.

 fs/dax.c            |  4 ++--
 fs/ext4/inode.c     |  5 +----
 fs/xfs/xfs_file.c   |  4 +---
 include/linux/dax.h | 10 ++++++++++
 4 files changed, 14 insertions(+), 9 deletions(-)

Comments

Dan Williams Oct. 7, 2020, 2:40 a.m. UTC | #1
On Tue, Oct 6, 2020 at 4:09 PM Ralph Campbell <rcampbell@nvidia.com> wrote:
>
> There are several places where ZONE_DEVICE struct pages assume a reference
> count == 1 means the page is idle and free. Instead of open coding this,
> add a helper function to hide this detail.
>
> Signed-off-by: Ralph Campbell <rcampbell@nvidia.com>
> Reviewed-by: Christoph Hellwig <hch@lst.de>
> ---
>
> I'm resending this as a separate patch since I think it is ready to
> merge. Originally, this was part of an RFC and is unchanged from v3:
> https://lore.kernel.org/linux-mm/20201001181715.17416-1-rcampbell@nvidia.com
>
> It applies cleanly to linux-5.9.0-rc7-mm1 but doesn't really
> depend on anything, just simple merge conflicts when applied to
> other trees.
> I'll let the various maintainers decide which tree and when to merge.
> It isn't urgent since it is a clean up patch.

Thanks Ralph, it looks good to me. Jan, or Ted care to ack? I don't
have much else pending for dax at the moment as Andrew is carrying my
dax updates for this cycle. Andrew please take this into -mm if you
get a chance. Otherwise I'll cycle back to it when some other dax
updates arrive in my queue.
Jan Kara Oct. 7, 2020, 8:25 a.m. UTC | #2
On Tue 06-10-20 16:09:30, Ralph Campbell wrote:
> There are several places where ZONE_DEVICE struct pages assume a reference
> count == 1 means the page is idle and free. Instead of open coding this,
> add a helper function to hide this detail.
> 
> Signed-off-by: Ralph Campbell <rcampbell@nvidia.com>
> Reviewed-by: Christoph Hellwig <hch@lst.de>

Looks as sane direction but if we are going to abstract checks when
ZONE_DEVICE page is idle, we should also update e.g.
mm/swap.c:put_devmap_managed_page() or
mm/gup.c:__unpin_devmap_managed_user_page() (there may be more places like
this but I found at least these two...). Maybe Dan has more thoughts about
this.

								Honza

> diff --git a/fs/dax.c b/fs/dax.c
> index 5b47834f2e1b..85c63f735909 100644
> --- a/fs/dax.c
> +++ b/fs/dax.c
> @@ -358,7 +358,7 @@ static void dax_disassociate_entry(void *entry, struct address_space *mapping,
>  	for_each_mapped_pfn(entry, pfn) {
>  		struct page *page = pfn_to_page(pfn);
>  
> -		WARN_ON_ONCE(trunc && page_ref_count(page) > 1);
> +		WARN_ON_ONCE(trunc && !dax_layout_is_idle_page(page));
>  		WARN_ON_ONCE(page->mapping && page->mapping != mapping);
>  		page->mapping = NULL;
>  		page->index = 0;
> @@ -372,7 +372,7 @@ static struct page *dax_busy_page(void *entry)
>  	for_each_mapped_pfn(entry, pfn) {
>  		struct page *page = pfn_to_page(pfn);
>  
> -		if (page_ref_count(page) > 1)
> +		if (!dax_layout_is_idle_page(page))
>  			return page;
>  	}
>  	return NULL;
> diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
> index 771ed8b1fadb..132620cbfa13 100644
> --- a/fs/ext4/inode.c
> +++ b/fs/ext4/inode.c
> @@ -3937,10 +3937,7 @@ int ext4_break_layouts(struct inode *inode)
>  		if (!page)
>  			return 0;
>  
> -		error = ___wait_var_event(&page->_refcount,
> -				atomic_read(&page->_refcount) == 1,
> -				TASK_INTERRUPTIBLE, 0, 0,
> -				ext4_wait_dax_page(ei));
> +		error = dax_wait_page(ei, page, ext4_wait_dax_page);
>  	} while (error == 0);
>  
>  	return error;
> diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
> index 3d1b95124744..a5304aaeaa3a 100644
> --- a/fs/xfs/xfs_file.c
> +++ b/fs/xfs/xfs_file.c
> @@ -749,9 +749,7 @@ xfs_break_dax_layouts(
>  		return 0;
>  
>  	*retry = true;
> -	return ___wait_var_event(&page->_refcount,
> -			atomic_read(&page->_refcount) == 1, TASK_INTERRUPTIBLE,
> -			0, 0, xfs_wait_dax_page(inode));
> +	return dax_wait_page(inode, page, xfs_wait_dax_page);
>  }
>  
>  int
> diff --git a/include/linux/dax.h b/include/linux/dax.h
> index b52f084aa643..8909a91cd381 100644
> --- a/include/linux/dax.h
> +++ b/include/linux/dax.h
> @@ -243,6 +243,16 @@ static inline bool dax_mapping(struct address_space *mapping)
>  	return mapping->host && IS_DAX(mapping->host);
>  }
>  
> +static inline bool dax_layout_is_idle_page(struct page *page)
> +{
> +	return page_ref_count(page) == 1;
> +}
> +
> +#define dax_wait_page(_inode, _page, _wait_cb)				\
> +	___wait_var_event(&(_page)->_refcount,				\
> +		dax_layout_is_idle_page(_page),				\
> +		TASK_INTERRUPTIBLE, 0, 0, _wait_cb(_inode))
> +
>  #ifdef CONFIG_DEV_DAX_HMEM_DEVICES
>  void hmem_register_device(int target_nid, struct resource *r);
>  #else
> -- 
> 2.20.1
>
Theodore Ts'o Oct. 7, 2020, 2:41 p.m. UTC | #3
On Tue, Oct 06, 2020 at 07:40:05PM -0700, Dan Williams wrote:
> On Tue, Oct 6, 2020 at 4:09 PM Ralph Campbell <rcampbell@nvidia.com> wrote:
> >
> > There are several places where ZONE_DEVICE struct pages assume a reference
> > count == 1 means the page is idle and free. Instead of open coding this,
> > add a helper function to hide this detail.
> >
> > Signed-off-by: Ralph Campbell <rcampbell@nvidia.com>
> > Reviewed-by: Christoph Hellwig <hch@lst.de>
> > ---
> >
> > I'm resending this as a separate patch since I think it is ready to
> > merge. Originally, this was part of an RFC and is unchanged from v3:
> > https://lore.kernel.org/linux-mm/20201001181715.17416-1-rcampbell@nvidia.com
> >
> > It applies cleanly to linux-5.9.0-rc7-mm1 but doesn't really
> > depend on anything, just simple merge conflicts when applied to
> > other trees.
> > I'll let the various maintainers decide which tree and when to merge.
> > It isn't urgent since it is a clean up patch.
> 
> Thanks Ralph, it looks good to me. Jan, or Ted care to ack? I don't
> have much else pending for dax at the moment as Andrew is carrying my
> dax updates for this cycle. Andrew please take this into -mm if you
> get a chance. Otherwise I'll cycle back to it when some other dax
> updates arrive in my queue.

Acked-by: Theodore Ts'o <tytso@mit.edu> # for fs/ext4/inode.c
Darrick J. Wong Oct. 7, 2020, 3:36 p.m. UTC | #4
On Tue, Oct 06, 2020 at 04:09:30PM -0700, Ralph Campbell wrote:
> There are several places where ZONE_DEVICE struct pages assume a reference
> count == 1 means the page is idle and free. Instead of open coding this,
> add a helper function to hide this detail.
> 
> Signed-off-by: Ralph Campbell <rcampbell@nvidia.com>
> Reviewed-by: Christoph Hellwig <hch@lst.de>
> ---
> 
> I'm resending this as a separate patch since I think it is ready to
> merge. Originally, this was part of an RFC and is unchanged from v3:
> https://lore.kernel.org/linux-mm/20201001181715.17416-1-rcampbell@nvidia.com
> 
> It applies cleanly to linux-5.9.0-rc7-mm1 but doesn't really
> depend on anything, just simple merge conflicts when applied to
> other trees.
> I'll let the various maintainers decide which tree and when to merge.
> It isn't urgent since it is a clean up patch.
> 
>  fs/dax.c            |  4 ++--
>  fs/ext4/inode.c     |  5 +----
>  fs/xfs/xfs_file.c   |  4 +---
>  include/linux/dax.h | 10 ++++++++++
>  4 files changed, 14 insertions(+), 9 deletions(-)
> 
> diff --git a/fs/dax.c b/fs/dax.c
> index 5b47834f2e1b..85c63f735909 100644
> --- a/fs/dax.c
> +++ b/fs/dax.c
> @@ -358,7 +358,7 @@ static void dax_disassociate_entry(void *entry, struct address_space *mapping,
>  	for_each_mapped_pfn(entry, pfn) {
>  		struct page *page = pfn_to_page(pfn);
>  
> -		WARN_ON_ONCE(trunc && page_ref_count(page) > 1);
> +		WARN_ON_ONCE(trunc && !dax_layout_is_idle_page(page));
>  		WARN_ON_ONCE(page->mapping && page->mapping != mapping);
>  		page->mapping = NULL;
>  		page->index = 0;
> @@ -372,7 +372,7 @@ static struct page *dax_busy_page(void *entry)
>  	for_each_mapped_pfn(entry, pfn) {
>  		struct page *page = pfn_to_page(pfn);
>  
> -		if (page_ref_count(page) > 1)
> +		if (!dax_layout_is_idle_page(page))
>  			return page;
>  	}
>  	return NULL;
> diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
> index 771ed8b1fadb..132620cbfa13 100644
> --- a/fs/ext4/inode.c
> +++ b/fs/ext4/inode.c
> @@ -3937,10 +3937,7 @@ int ext4_break_layouts(struct inode *inode)
>  		if (!page)
>  			return 0;
>  
> -		error = ___wait_var_event(&page->_refcount,
> -				atomic_read(&page->_refcount) == 1,
> -				TASK_INTERRUPTIBLE, 0, 0,
> -				ext4_wait_dax_page(ei));
> +		error = dax_wait_page(ei, page, ext4_wait_dax_page);
>  	} while (error == 0);
>  
>  	return error;
> diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
> index 3d1b95124744..a5304aaeaa3a 100644
> --- a/fs/xfs/xfs_file.c
> +++ b/fs/xfs/xfs_file.c
> @@ -749,9 +749,7 @@ xfs_break_dax_layouts(
>  		return 0;
>  
>  	*retry = true;
> -	return ___wait_var_event(&page->_refcount,
> -			atomic_read(&page->_refcount) == 1, TASK_INTERRUPTIBLE,
> -			0, 0, xfs_wait_dax_page(inode));
> +	return dax_wait_page(inode, page, xfs_wait_dax_page);

I don't mind this open-coded soup getting cleaned up into a macro,
though my general opinion is that if the mm/dax developers are ok with
this then:

Acked-by: Darrick J. Wong <darrick.wong@oracle.com>

--D

>  }
>  
>  int
> diff --git a/include/linux/dax.h b/include/linux/dax.h
> index b52f084aa643..8909a91cd381 100644
> --- a/include/linux/dax.h
> +++ b/include/linux/dax.h
> @@ -243,6 +243,16 @@ static inline bool dax_mapping(struct address_space *mapping)
>  	return mapping->host && IS_DAX(mapping->host);
>  }
>  
> +static inline bool dax_layout_is_idle_page(struct page *page)
> +{
> +	return page_ref_count(page) == 1;
> +}
> +
> +#define dax_wait_page(_inode, _page, _wait_cb)				\
> +	___wait_var_event(&(_page)->_refcount,				\
> +		dax_layout_is_idle_page(_page),				\
> +		TASK_INTERRUPTIBLE, 0, 0, _wait_cb(_inode))
> +
>  #ifdef CONFIG_DEV_DAX_HMEM_DEVICES
>  void hmem_register_device(int target_nid, struct resource *r);
>  #else
> -- 
> 2.20.1
>
Ralph Campbell Oct. 7, 2020, 6:12 p.m. UTC | #5
On 10/7/20 1:25 AM, Jan Kara wrote:
> On Tue 06-10-20 16:09:30, Ralph Campbell wrote:
>> There are several places where ZONE_DEVICE struct pages assume a reference
>> count == 1 means the page is idle and free. Instead of open coding this,
>> add a helper function to hide this detail.
>>
>> Signed-off-by: Ralph Campbell <rcampbell@nvidia.com>
>> Reviewed-by: Christoph Hellwig <hch@lst.de>
> 
> Looks as sane direction but if we are going to abstract checks when
> ZONE_DEVICE page is idle, we should also update e.g.
> mm/swap.c:put_devmap_managed_page() or
> mm/gup.c:__unpin_devmap_managed_user_page() (there may be more places like
> this but I found at least these two...). Maybe Dan has more thoughts about
> this.
> 
> 								Honza

I think this is a good point but I would like to make that a follow on
patch rather than add to this one.
Dan Williams Oct. 7, 2020, 9:59 p.m. UTC | #6
On Wed, Oct 7, 2020 at 1:25 AM Jan Kara <jack@suse.cz> wrote:
>
> On Tue 06-10-20 16:09:30, Ralph Campbell wrote:
> > There are several places where ZONE_DEVICE struct pages assume a reference
> > count == 1 means the page is idle and free. Instead of open coding this,
> > add a helper function to hide this detail.
> >
> > Signed-off-by: Ralph Campbell <rcampbell@nvidia.com>
> > Reviewed-by: Christoph Hellwig <hch@lst.de>
>
> Looks as sane direction but if we are going to abstract checks when
> ZONE_DEVICE page is idle, we should also update e.g.
> mm/swap.c:put_devmap_managed_page() or
> mm/gup.c:__unpin_devmap_managed_user_page() (there may be more places like
> this but I found at least these two...). Maybe Dan has more thoughts about
> this.

Yes, but I think that cleanup comes once the idle page count is
unified to be 0 across typical and ZONE_DEVICE pages. Then
free_devmap_managed_page() can be moved internal to __put_page(). For
this patch it's just hiding the "idle == 1" assumption from
dax-filesystems.
diff mbox series

Patch

diff --git a/fs/dax.c b/fs/dax.c
index 5b47834f2e1b..85c63f735909 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -358,7 +358,7 @@  static void dax_disassociate_entry(void *entry, struct address_space *mapping,
 	for_each_mapped_pfn(entry, pfn) {
 		struct page *page = pfn_to_page(pfn);
 
-		WARN_ON_ONCE(trunc && page_ref_count(page) > 1);
+		WARN_ON_ONCE(trunc && !dax_layout_is_idle_page(page));
 		WARN_ON_ONCE(page->mapping && page->mapping != mapping);
 		page->mapping = NULL;
 		page->index = 0;
@@ -372,7 +372,7 @@  static struct page *dax_busy_page(void *entry)
 	for_each_mapped_pfn(entry, pfn) {
 		struct page *page = pfn_to_page(pfn);
 
-		if (page_ref_count(page) > 1)
+		if (!dax_layout_is_idle_page(page))
 			return page;
 	}
 	return NULL;
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 771ed8b1fadb..132620cbfa13 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -3937,10 +3937,7 @@  int ext4_break_layouts(struct inode *inode)
 		if (!page)
 			return 0;
 
-		error = ___wait_var_event(&page->_refcount,
-				atomic_read(&page->_refcount) == 1,
-				TASK_INTERRUPTIBLE, 0, 0,
-				ext4_wait_dax_page(ei));
+		error = dax_wait_page(ei, page, ext4_wait_dax_page);
 	} while (error == 0);
 
 	return error;
diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index 3d1b95124744..a5304aaeaa3a 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -749,9 +749,7 @@  xfs_break_dax_layouts(
 		return 0;
 
 	*retry = true;
-	return ___wait_var_event(&page->_refcount,
-			atomic_read(&page->_refcount) == 1, TASK_INTERRUPTIBLE,
-			0, 0, xfs_wait_dax_page(inode));
+	return dax_wait_page(inode, page, xfs_wait_dax_page);
 }
 
 int
diff --git a/include/linux/dax.h b/include/linux/dax.h
index b52f084aa643..8909a91cd381 100644
--- a/include/linux/dax.h
+++ b/include/linux/dax.h
@@ -243,6 +243,16 @@  static inline bool dax_mapping(struct address_space *mapping)
 	return mapping->host && IS_DAX(mapping->host);
 }
 
+static inline bool dax_layout_is_idle_page(struct page *page)
+{
+	return page_ref_count(page) == 1;
+}
+
+#define dax_wait_page(_inode, _page, _wait_cb)				\
+	___wait_var_event(&(_page)->_refcount,				\
+		dax_layout_is_idle_page(_page),				\
+		TASK_INTERRUPTIBLE, 0, 0, _wait_cb(_inode))
+
 #ifdef CONFIG_DEV_DAX_HMEM_DEVICES
 void hmem_register_device(int target_nid, struct resource *r);
 #else