diff mbox series

[v7,10/24] mm: Add readahead address space operation

Message ID 20200219210103.32400-11-willy@infradead.org (mailing list archive)
State New, archived
Headers show
Series Change readahead API | expand

Commit Message

Matthew Wilcox Feb. 19, 2020, 9 p.m. UTC
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>

This replaces ->readpages with a saner interface:
 - Return void instead of an ignored error code.
 - Page cache is already populated with locked pages when ->readahead
   is called.
 - New arguments can be passed to the implementation without changing
   all the filesystems that use a common helper function like
   mpage_readahead().

Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
---
 Documentation/filesystems/locking.rst |  6 +++++-
 Documentation/filesystems/vfs.rst     | 15 +++++++++++++++
 include/linux/fs.h                    |  2 ++
 include/linux/pagemap.h               | 18 ++++++++++++++++++
 mm/readahead.c                        | 12 ++++++++++--
 5 files changed, 50 insertions(+), 3 deletions(-)

Comments

Zi Yan Feb. 20, 2020, 3 p.m. UTC | #1
On 19 Feb 2020, at 16:00, Matthew Wilcox wrote:

> From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
>
> This replaces ->readpages with a saner interface:
>  - Return void instead of an ignored error code.
>  - Page cache is already populated with locked pages when ->readahead
>    is called.
>  - New arguments can be passed to the implementation without changing
>    all the filesystems that use a common helper function like
>    mpage_readahead().
>
> Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
> ---
>  Documentation/filesystems/locking.rst |  6 +++++-
>  Documentation/filesystems/vfs.rst     | 15 +++++++++++++++
>  include/linux/fs.h                    |  2 ++
>  include/linux/pagemap.h               | 18 ++++++++++++++++++
>  mm/readahead.c                        | 12 ++++++++++--
>  5 files changed, 50 insertions(+), 3 deletions(-)
>
> diff --git a/Documentation/filesystems/locking.rst b/Documentation/filesystems/locking.rst
> index 5057e4d9dcd1..0af2e0e11461 100644
> --- a/Documentation/filesystems/locking.rst
> +++ b/Documentation/filesystems/locking.rst
> @@ -239,6 +239,7 @@ prototypes::
>  	int (*readpage)(struct file *, struct page *);
>  	int (*writepages)(struct address_space *, struct writeback_control *);
>  	int (*set_page_dirty)(struct page *page);
> +	void (*readahead)(struct readahead_control *);
>  	int (*readpages)(struct file *filp, struct address_space *mapping,
>  			struct list_head *pages, unsigned nr_pages);
>  	int (*write_begin)(struct file *, struct address_space *mapping,
> @@ -271,7 +272,8 @@ writepage:		yes, unlocks (see below)
>  readpage:		yes, unlocks
>  writepages:
>  set_page_dirty		no
> -readpages:
> +readahead:		yes, unlocks
> +readpages:		no
>  write_begin:		locks the page		 exclusive
>  write_end:		yes, unlocks		 exclusive
>  bmap:
> @@ -295,6 +297,8 @@ the request handler (/dev/loop).
>  ->readpage() unlocks the page, either synchronously or via I/O
>  completion.
>
> +->readahead() unlocks the pages that I/O is attempted on like ->readpage().
> +
>  ->readpages() populates the pagecache with the passed pages and starts
>  I/O against them.  They come unlocked upon I/O completion.
>
> diff --git a/Documentation/filesystems/vfs.rst b/Documentation/filesystems/vfs.rst
> index 7d4d09dd5e6d..ed17771c212b 100644
> --- a/Documentation/filesystems/vfs.rst
> +++ b/Documentation/filesystems/vfs.rst
> @@ -706,6 +706,7 @@ cache in your filesystem.  The following members are defined:
>  		int (*readpage)(struct file *, struct page *);
>  		int (*writepages)(struct address_space *, struct writeback_control *);
>  		int (*set_page_dirty)(struct page *page);
> +		void (*readahead)(struct readahead_control *);
>  		int (*readpages)(struct file *filp, struct address_space *mapping,
>  				 struct list_head *pages, unsigned nr_pages);
>  		int (*write_begin)(struct file *, struct address_space *mapping,
> @@ -781,12 +782,26 @@ cache in your filesystem.  The following members are defined:
>  	If defined, it should set the PageDirty flag, and the
>  	PAGECACHE_TAG_DIRTY tag in the radix tree.
>
> +``readahead``
> +	Called by the VM to read pages associated with the address_space
> +	object.  The pages are consecutive in the page cache and are
> +	locked.  The implementation should decrement the page refcount
> +	after starting I/O on each page.  Usually the page will be
> +	unlocked by the I/O completion handler.  If the filesystem decides
> +	to stop attempting I/O before reaching the end of the readahead
> +	window, it can simply return.  The caller will decrement the page
> +	refcount and unlock the remaining pages for you.  Set PageUptodate
> +	if the I/O completes successfully.  Setting PageError on any page
> +	will be ignored; simply unlock the page if an I/O error occurs.
> +
>  ``readpages``
>  	called by the VM to read pages associated with the address_space
>  	object.  This is essentially just a vector version of readpage.
>  	Instead of just one page, several pages are requested.
>  	readpages is only used for read-ahead, so read errors are
>  	ignored.  If anything goes wrong, feel free to give up.
> +	This interface is deprecated and will be removed by the end of
> +	2020; implement readahead instead.
>
>  ``write_begin``
>  	Called by the generic buffered write code to ask the filesystem
> diff --git a/include/linux/fs.h b/include/linux/fs.h
> index 3cd4fe6b845e..d4e2d2964346 100644
> --- a/include/linux/fs.h
> +++ b/include/linux/fs.h
> @@ -292,6 +292,7 @@ enum positive_aop_returns {
>  struct page;
>  struct address_space;
>  struct writeback_control;
> +struct readahead_control;
>
>  /*
>   * Write life time hint values.
> @@ -375,6 +376,7 @@ struct address_space_operations {
>  	 */
>  	int (*readpages)(struct file *filp, struct address_space *mapping,
>  			struct list_head *pages, unsigned nr_pages);
> +	void (*readahead)(struct readahead_control *);
>
>  	int (*write_begin)(struct file *, struct address_space *mapping,
>  				loff_t pos, unsigned len, unsigned flags,
> diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
> index 4989d330fada..b3008605fd1b 100644
> --- a/include/linux/pagemap.h
> +++ b/include/linux/pagemap.h
> @@ -669,6 +669,24 @@ static inline struct page *readahead_page(struct readahead_control *rac)
>  	return page;
>  }
>
> +/* The byte offset into the file of this readahead block */
> +static inline loff_t readahead_pos(struct readahead_control *rac)
> +{
> +	return (loff_t)rac->_index * PAGE_SIZE;
> +}
> +
> +/* The number of bytes in this readahead block */
> +static inline loff_t readahead_length(struct readahead_control *rac)
> +{
> +	return (loff_t)rac->_nr_pages * PAGE_SIZE;
> +}
> +
> +/* The index of the first page in this readahead block */
> +static inline unsigned int readahead_index(struct readahead_control *rac)
> +{
> +	return rac->_index;
> +}

rac->_index is pgoff_t, so readahead_index() should return the same type, right?
BTW, pgoff_t is unsigned long.

> +
>  /* The number of pages in this readahead block */
>  static inline unsigned int readahead_count(struct readahead_control *rac)
>  {
> diff --git a/mm/readahead.c b/mm/readahead.c
> index aaa209559ba2..07cdfbf00f4b 100644
> --- a/mm/readahead.c
> +++ b/mm/readahead.c
> @@ -124,7 +124,14 @@ static void read_pages(struct readahead_control *rac, struct list_head *pages)
>
>  	blk_start_plug(&plug);
>
> -	if (aops->readpages) {
> +	if (aops->readahead) {
> +		aops->readahead(rac);
> +		/* Clean up the remaining pages */
> +		while ((page = readahead_page(rac))) {
> +			unlock_page(page);
> +			put_page(page);
> +		}
> +	} else if (aops->readpages) {
>  		aops->readpages(rac->file, rac->mapping, pages,
>  				readahead_count(rac));
>  		/* Clean up the remaining pages */
> @@ -234,7 +241,8 @@ void force_page_cache_readahead(struct address_space *mapping,
>  	struct file_ra_state *ra = &filp->f_ra;
>  	unsigned long max_pages;
>
> -	if (unlikely(!mapping->a_ops->readpage && !mapping->a_ops->readpages))
> +	if (unlikely(!mapping->a_ops->readpage && !mapping->a_ops->readpages &&
> +			!mapping->a_ops->readahead))
>  		return;
>
>  	/*
> -- 
> 2.25.0


--
Best Regards,
Yan Zi
Matthew Wilcox Feb. 20, 2020, 3:10 p.m. UTC | #2
On Thu, Feb 20, 2020 at 10:00:30AM -0500, Zi Yan wrote:
> > +/* The index of the first page in this readahead block */
> > +static inline unsigned int readahead_index(struct readahead_control *rac)
> > +{
> > +	return rac->_index;
> > +}
> 
> rac->_index is pgoff_t, so readahead_index() should return the same type, right?
> BTW, pgoff_t is unsigned long.

Oh my goodness!  Thank you for spotting that.  Fortunately, it's only
currently used by tracepoints, so it wasn't causing any trouble, but
that's a nasty landmine to leave lying around.  Fixed:

static inline pgoff_t readahead_index(struct readahead_control *rac)
John Hubbard Feb. 21, 2020, 4:30 a.m. UTC | #3
On 2/19/20 1:00 PM, Matthew Wilcox wrote:
> From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
> 
> This replaces ->readpages with a saner interface:
>  - Return void instead of an ignored error code.
>  - Page cache is already populated with locked pages when ->readahead
>    is called.
>  - New arguments can be passed to the implementation without changing
>    all the filesystems that use a common helper function like
>    mpage_readahead().
> 
> Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
> ---
>  Documentation/filesystems/locking.rst |  6 +++++-
>  Documentation/filesystems/vfs.rst     | 15 +++++++++++++++
>  include/linux/fs.h                    |  2 ++
>  include/linux/pagemap.h               | 18 ++++++++++++++++++
>  mm/readahead.c                        | 12 ++++++++++--
>  5 files changed, 50 insertions(+), 3 deletions(-)


This all looks correct to me, so: 

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


thanks,
Christoph Hellwig Feb. 24, 2020, 9:41 p.m. UTC | #4
Looks fine modulo the little data type issue:

Reviewed-by: Christoph Hellwig <hch@lst.de>
diff mbox series

Patch

diff --git a/Documentation/filesystems/locking.rst b/Documentation/filesystems/locking.rst
index 5057e4d9dcd1..0af2e0e11461 100644
--- a/Documentation/filesystems/locking.rst
+++ b/Documentation/filesystems/locking.rst
@@ -239,6 +239,7 @@  prototypes::
 	int (*readpage)(struct file *, struct page *);
 	int (*writepages)(struct address_space *, struct writeback_control *);
 	int (*set_page_dirty)(struct page *page);
+	void (*readahead)(struct readahead_control *);
 	int (*readpages)(struct file *filp, struct address_space *mapping,
 			struct list_head *pages, unsigned nr_pages);
 	int (*write_begin)(struct file *, struct address_space *mapping,
@@ -271,7 +272,8 @@  writepage:		yes, unlocks (see below)
 readpage:		yes, unlocks
 writepages:
 set_page_dirty		no
-readpages:
+readahead:		yes, unlocks
+readpages:		no
 write_begin:		locks the page		 exclusive
 write_end:		yes, unlocks		 exclusive
 bmap:
@@ -295,6 +297,8 @@  the request handler (/dev/loop).
 ->readpage() unlocks the page, either synchronously or via I/O
 completion.
 
+->readahead() unlocks the pages that I/O is attempted on like ->readpage().
+
 ->readpages() populates the pagecache with the passed pages and starts
 I/O against them.  They come unlocked upon I/O completion.
 
diff --git a/Documentation/filesystems/vfs.rst b/Documentation/filesystems/vfs.rst
index 7d4d09dd5e6d..ed17771c212b 100644
--- a/Documentation/filesystems/vfs.rst
+++ b/Documentation/filesystems/vfs.rst
@@ -706,6 +706,7 @@  cache in your filesystem.  The following members are defined:
 		int (*readpage)(struct file *, struct page *);
 		int (*writepages)(struct address_space *, struct writeback_control *);
 		int (*set_page_dirty)(struct page *page);
+		void (*readahead)(struct readahead_control *);
 		int (*readpages)(struct file *filp, struct address_space *mapping,
 				 struct list_head *pages, unsigned nr_pages);
 		int (*write_begin)(struct file *, struct address_space *mapping,
@@ -781,12 +782,26 @@  cache in your filesystem.  The following members are defined:
 	If defined, it should set the PageDirty flag, and the
 	PAGECACHE_TAG_DIRTY tag in the radix tree.
 
+``readahead``
+	Called by the VM to read pages associated with the address_space
+	object.  The pages are consecutive in the page cache and are
+	locked.  The implementation should decrement the page refcount
+	after starting I/O on each page.  Usually the page will be
+	unlocked by the I/O completion handler.  If the filesystem decides
+	to stop attempting I/O before reaching the end of the readahead
+	window, it can simply return.  The caller will decrement the page
+	refcount and unlock the remaining pages for you.  Set PageUptodate
+	if the I/O completes successfully.  Setting PageError on any page
+	will be ignored; simply unlock the page if an I/O error occurs.
+
 ``readpages``
 	called by the VM to read pages associated with the address_space
 	object.  This is essentially just a vector version of readpage.
 	Instead of just one page, several pages are requested.
 	readpages is only used for read-ahead, so read errors are
 	ignored.  If anything goes wrong, feel free to give up.
+	This interface is deprecated and will be removed by the end of
+	2020; implement readahead instead.
 
 ``write_begin``
 	Called by the generic buffered write code to ask the filesystem
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 3cd4fe6b845e..d4e2d2964346 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -292,6 +292,7 @@  enum positive_aop_returns {
 struct page;
 struct address_space;
 struct writeback_control;
+struct readahead_control;
 
 /*
  * Write life time hint values.
@@ -375,6 +376,7 @@  struct address_space_operations {
 	 */
 	int (*readpages)(struct file *filp, struct address_space *mapping,
 			struct list_head *pages, unsigned nr_pages);
+	void (*readahead)(struct readahead_control *);
 
 	int (*write_begin)(struct file *, struct address_space *mapping,
 				loff_t pos, unsigned len, unsigned flags,
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index 4989d330fada..b3008605fd1b 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -669,6 +669,24 @@  static inline struct page *readahead_page(struct readahead_control *rac)
 	return page;
 }
 
+/* The byte offset into the file of this readahead block */
+static inline loff_t readahead_pos(struct readahead_control *rac)
+{
+	return (loff_t)rac->_index * PAGE_SIZE;
+}
+
+/* The number of bytes in this readahead block */
+static inline loff_t readahead_length(struct readahead_control *rac)
+{
+	return (loff_t)rac->_nr_pages * PAGE_SIZE;
+}
+
+/* The index of the first page in this readahead block */
+static inline unsigned int readahead_index(struct readahead_control *rac)
+{
+	return rac->_index;
+}
+
 /* The number of pages in this readahead block */
 static inline unsigned int readahead_count(struct readahead_control *rac)
 {
diff --git a/mm/readahead.c b/mm/readahead.c
index aaa209559ba2..07cdfbf00f4b 100644
--- a/mm/readahead.c
+++ b/mm/readahead.c
@@ -124,7 +124,14 @@  static void read_pages(struct readahead_control *rac, struct list_head *pages)
 
 	blk_start_plug(&plug);
 
-	if (aops->readpages) {
+	if (aops->readahead) {
+		aops->readahead(rac);
+		/* Clean up the remaining pages */
+		while ((page = readahead_page(rac))) {
+			unlock_page(page);
+			put_page(page);
+		}
+	} else if (aops->readpages) {
 		aops->readpages(rac->file, rac->mapping, pages,
 				readahead_count(rac));
 		/* Clean up the remaining pages */
@@ -234,7 +241,8 @@  void force_page_cache_readahead(struct address_space *mapping,
 	struct file_ra_state *ra = &filp->f_ra;
 	unsigned long max_pages;
 
-	if (unlikely(!mapping->a_ops->readpage && !mapping->a_ops->readpages))
+	if (unlikely(!mapping->a_ops->readpage && !mapping->a_ops->readpages &&
+			!mapping->a_ops->readahead))
 		return;
 
 	/*