diff mbox series

[3/9] mm/readahead: Make page_cache_ra_unbounded take a readahead_control

Message ID 20200903140844.14194-4-willy@infradead.org (mailing list archive)
State New, archived
Headers show
Series Readahead patches for 5.9/5.10 | expand

Commit Message

Matthew Wilcox Sept. 3, 2020, 2:08 p.m. UTC
Define it in the callers instead of in page_cache_ra_unbounded().

Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
---
 fs/ext4/verity.c        |  4 ++--
 fs/f2fs/verity.c        |  4 ++--
 include/linux/pagemap.h |  5 ++---
 mm/readahead.c          | 30 ++++++++++++++----------------
 4 files changed, 20 insertions(+), 23 deletions(-)

Comments

Andrew Morton Sept. 3, 2020, 7:22 p.m. UTC | #1
On Thu,  3 Sep 2020 15:08:38 +0100 "Matthew Wilcox (Oracle)" <willy@infradead.org> wrote:

> Define it in the callers instead of in page_cache_ra_unbounded().
> 

The changelogs for patches 2-9 are explaining what the patches do, but
not why they do it, Presumably there's some grand scheme in mind, but
it isn't being revealed to the reader!
Matthew Wilcox Sept. 3, 2020, 7:33 p.m. UTC | #2
On Thu, Sep 03, 2020 at 12:22:18PM -0700, Andrew Morton wrote:
> On Thu,  3 Sep 2020 15:08:38 +0100 "Matthew Wilcox (Oracle)" <willy@infradead.org> wrote:
> 
> > Define it in the callers instead of in page_cache_ra_unbounded().
> > 
> 
> The changelogs for patches 2-9 are explaining what the patches do, but
> not why they do it, Presumably there's some grand scheme in mind, but
> it isn't being revealed to the reader!

Sorry!  For both pieces of infrastructure being build on top of this
patchset, we want the ractl to be available higher in the call-stack.

For David's work, he wants to add the 'critical page' to the ractl so that
he knows which page NEEDS to be brought in from storage, and which ones
are nice-to-have.  We might want something similar in block storage too.
It used to be simple -- the first page was the critical one, but then
mmap added fault-around and so for that usecase, the middle page is
the critical one.  Anyway, I don't have any code to show that yet,
we just know that the lowest point in the callchain where we have that
information is do_sync_mmap_readahead() and so the ractl needs to start
its life there.

For THP, I can show you the code that needs it.  It's actually the
apex patch to the series; the one which finally starts to allocate
THPs and present them to consenting filesystems:
http://git.infradead.org/users/willy/pagecache.git/commitdiff/798bcf30ab2eff278caad03a9edca74d2f8ae760

This doesn't need the ractl to be available as high in the stack as
David does, which is why he did the last few patches.
diff mbox series

Patch

diff --git a/fs/ext4/verity.c b/fs/ext4/verity.c
index bbd5e7e0632b..5b7ba8f71153 100644
--- a/fs/ext4/verity.c
+++ b/fs/ext4/verity.c
@@ -349,6 +349,7 @@  static struct page *ext4_read_merkle_tree_page(struct inode *inode,
 					       pgoff_t index,
 					       unsigned long num_ra_pages)
 {
+	DEFINE_READAHEAD(ractl, NULL, inode->i_mapping, index);
 	struct page *page;
 
 	index += ext4_verity_metadata_pos(inode) >> PAGE_SHIFT;
@@ -358,8 +359,7 @@  static struct page *ext4_read_merkle_tree_page(struct inode *inode,
 		if (page)
 			put_page(page);
 		else if (num_ra_pages > 1)
-			page_cache_readahead_unbounded(inode->i_mapping, NULL,
-					index, num_ra_pages, 0);
+			page_cache_ra_unbounded(&ractl, num_ra_pages, 0);
 		page = read_mapping_page(inode->i_mapping, index, NULL);
 	}
 	return page;
diff --git a/fs/f2fs/verity.c b/fs/f2fs/verity.c
index 9eb0dba851e8..054ec852b5ea 100644
--- a/fs/f2fs/verity.c
+++ b/fs/f2fs/verity.c
@@ -228,6 +228,7 @@  static struct page *f2fs_read_merkle_tree_page(struct inode *inode,
 					       pgoff_t index,
 					       unsigned long num_ra_pages)
 {
+	DEFINE_READAHEAD(ractl, NULL, inode->i_mapping, index);
 	struct page *page;
 
 	index += f2fs_verity_metadata_pos(inode) >> PAGE_SHIFT;
@@ -237,8 +238,7 @@  static struct page *f2fs_read_merkle_tree_page(struct inode *inode,
 		if (page)
 			put_page(page);
 		else if (num_ra_pages > 1)
-			page_cache_readahead_unbounded(inode->i_mapping, NULL,
-					index, num_ra_pages, 0);
+			page_cache_ra_unbounded(&ractl, num_ra_pages, 0);
 		page = read_mapping_page(inode->i_mapping, index, NULL);
 	}
 	return page;
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index 19bba4360436..2b613c369a2f 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -705,9 +705,8 @@  void page_cache_sync_readahead(struct address_space *, struct file_ra_state *,
 void page_cache_async_readahead(struct address_space *, struct file_ra_state *,
 		struct file *, struct page *, pgoff_t index,
 		unsigned long req_count);
-void page_cache_readahead_unbounded(struct address_space *, struct file *,
-		pgoff_t index, unsigned long nr_to_read,
-		unsigned long lookahead_count);
+void page_cache_ra_unbounded(struct readahead_control *,
+		unsigned long nr_to_read, unsigned long lookahead_count);
 
 /*
  * Like add_to_page_cache_locked, but used to add newly allocated pages:
diff --git a/mm/readahead.c b/mm/readahead.c
index 2126a2754e22..a444943781bb 100644
--- a/mm/readahead.c
+++ b/mm/readahead.c
@@ -158,10 +158,8 @@  static void read_pages(struct readahead_control *rac, struct list_head *pages,
 }
 
 /**
- * page_cache_readahead_unbounded - Start unchecked readahead.
- * @mapping: File address space.
- * @file: This instance of the open file; used for authentication.
- * @index: First page index to read.
+ * page_cache_ra_unbounded - Start unchecked readahead.
+ * @ractl: Readahead control.
  * @nr_to_read: The number of pages to read.
  * @lookahead_size: Where to start the next readahead.
  *
@@ -173,13 +171,13 @@  static void read_pages(struct readahead_control *rac, struct list_head *pages,
  * Context: File is referenced by caller.  Mutexes may be held by caller.
  * May sleep, but will not reenter filesystem to reclaim memory.
  */
-void page_cache_readahead_unbounded(struct address_space *mapping,
-		struct file *file, pgoff_t index, unsigned long nr_to_read,
-		unsigned long lookahead_size)
+void page_cache_ra_unbounded(struct readahead_control *ractl,
+		unsigned long nr_to_read, unsigned long lookahead_size)
 {
+	struct address_space *mapping = ractl->mapping;
+	unsigned long index = readahead_index(ractl);
 	LIST_HEAD(page_pool);
 	gfp_t gfp_mask = readahead_gfp_mask(mapping);
-	DEFINE_READAHEAD(rac, file, mapping, index);
 	unsigned long i;
 
 	/*
@@ -200,7 +198,7 @@  void page_cache_readahead_unbounded(struct address_space *mapping,
 	for (i = 0; i < nr_to_read; i++) {
 		struct page *page = xa_load(&mapping->i_pages, index + i);
 
-		BUG_ON(index + i != rac._index + rac._nr_pages);
+		BUG_ON(index + i != ractl->_index + ractl->_nr_pages);
 
 		if (page && !xa_is_value(page)) {
 			/*
@@ -211,7 +209,7 @@  void page_cache_readahead_unbounded(struct address_space *mapping,
 			 * have a stable reference to this page, and it's
 			 * not worth getting one just for that.
 			 */
-			read_pages(&rac, &page_pool, true);
+			read_pages(ractl, &page_pool, true);
 			continue;
 		}
 
@@ -224,12 +222,12 @@  void page_cache_readahead_unbounded(struct address_space *mapping,
 		} else if (add_to_page_cache_lru(page, mapping, index + i,
 					gfp_mask) < 0) {
 			put_page(page);
-			read_pages(&rac, &page_pool, true);
+			read_pages(ractl, &page_pool, true);
 			continue;
 		}
 		if (i == nr_to_read - lookahead_size)
 			SetPageReadahead(page);
-		rac._nr_pages++;
+		ractl->_nr_pages++;
 	}
 
 	/*
@@ -237,10 +235,10 @@  void page_cache_readahead_unbounded(struct address_space *mapping,
 	 * uptodate then the caller will launch readpage again, and
 	 * will then handle the error.
 	 */
-	read_pages(&rac, &page_pool, false);
+	read_pages(ractl, &page_pool, false);
 	memalloc_nofs_restore(nofs);
 }
-EXPORT_SYMBOL_GPL(page_cache_readahead_unbounded);
+EXPORT_SYMBOL_GPL(page_cache_ra_unbounded);
 
 /*
  * __do_page_cache_readahead() actually reads a chunk of disk.  It allocates
@@ -252,6 +250,7 @@  void __do_page_cache_readahead(struct address_space *mapping,
 		struct file *file, pgoff_t index, unsigned long nr_to_read,
 		unsigned long lookahead_size)
 {
+	DEFINE_READAHEAD(ractl, file, mapping, index);
 	struct inode *inode = mapping->host;
 	loff_t isize = i_size_read(inode);
 	pgoff_t end_index;	/* The last page we want to read */
@@ -266,8 +265,7 @@  void __do_page_cache_readahead(struct address_space *mapping,
 	if (nr_to_read > end_index - index)
 		nr_to_read = end_index - index + 1;
 
-	page_cache_readahead_unbounded(mapping, file, index, nr_to_read,
-			lookahead_size);
+	page_cache_ra_unbounded(&ractl, nr_to_read, lookahead_size);
 }
 
 /*