[PATCH V8 4/8] mm/fs: add hooks to support cleancache

[Dan Magenheimer]

[PATCH V8 4/8] mm/fs: add hooks to support cleancache

This fourth patch of eight in this cleancache series provides the
core hooks in VFS for: initializing cleancache per filesystem;
capturing clean pages reclaimed by page cache; attempting to get
pages from cleancache before filesystem read; and ensuring coherency
between pagecache, disk, and cleancache.  Note that the placement
of these hooks was stable from 2.6.18 to 2.6.38; a minor semantic
change was required due to a patchset in 2.6.39.

All hooks become no-ops if CONFIG_CLEANCACHE is unset, or become
a check of a boolean global if CONFIG_CLEANCACHE is set but no
cleancache "backend" has claimed cleancache_ops.

Details and a FAQ can be found in Documentation/vm/cleancache.txt

[v8: minchan.kim@xxxxxxxxx: adapt to new remove_from_page_cache function]
Signed-off-by: Chris Mason <chris.mason@xxxxxxxxxx>
Signed-off-by: Dan Magenheimer <dan.magenheimer@xxxxxxxxxx>
Reviewed-by: Jeremy Fitzhardinge <jeremy@xxxxxxxx>
Reviewed-by: Konrad Rzeszutek Wilk <konrad.wilk@xxxxxxxxxx>
Cc: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
Cc: Al Viro <viro@xxxxxxxxxxxxxxxxxx>
Cc: Matthew Wilcox <matthew@xxxxxx>
Cc: Nick Piggin <npiggin@xxxxxxxxx>
Cc: Mel Gorman <mel@xxxxxxxxx>
Cc: Rik Van Riel <riel@xxxxxxxxxx>
Cc: Jan Beulich <JBeulich@xxxxxxxxxx>
Cc: Andreas Dilger <adilger@xxxxxxx>
Cc: Ted Ts'o <tytso@xxxxxxx>
Cc: Mark Fasheh <mfasheh@xxxxxxxx>
Cc: Joel Becker <joel.becker@xxxxxxxxxx>
Cc: Nitin Gupta <ngupta@xxxxxxxxxx>

---

Diffstat:
 fs/buffer.c                              |    5 +++++
 fs/mpage.c                               |    7 +++++++
 fs/super.c                               |    3 +++
 mm/filemap.c                             |   11 +++++++++++
 mm/truncate.c                            |    6 ++++++
 5 files changed, 32 insertions(+)

--- linux-2.6.39-rc3/fs/super.c	2011-04-11 18:21:51.000000000 -0600
+++ linux-2.6.39-rc3-cleancache/fs/super.c	2011-04-13 17:08:09.175853426 -0600
@@ -31,6 +31,7 @@
 #include <linux/mutex.h>
 #include <linux/backing-dev.h>
 #include <linux/rculist_bl.h>
+#include <linux/cleancache.h>
 #include "internal.h"
 
 
@@ -112,6 +113,7 @@ static struct super_block *alloc_super(s
 		s->s_maxbytes = MAX_NON_LFS;
 		s->s_op = &default_op;
 		s->s_time_gran = 1000000000;
+		s->cleancache_poolid = -1;
 	}
 out:
 	return s;
@@ -177,6 +179,7 @@ void deactivate_locked_super(struct supe
 {
 	struct file_system_type *fs = s->s_type;
 	if (atomic_dec_and_test(&s->s_active)) {
+		cleancache_flush_fs(s);
 		fs->kill_sb(s);
 		/*
 		 * We need to call rcu_barrier so all the delayed rcu free
--- linux-2.6.39-rc3/fs/buffer.c	2011-04-11 18:21:51.000000000 -0600
+++ linux-2.6.39-rc3-cleancache/fs/buffer.c	2011-04-13 17:07:24.700917174 -0600
@@ -41,6 +41,7 @@
 #include <linux/bitops.h>
 #include <linux/mpage.h>
 #include <linux/bit_spinlock.h>
+#include <linux/cleancache.h>
 
 static int fsync_buffers_list(spinlock_t *lock, struct list_head *list);
 
@@ -269,6 +270,10 @@ void invalidate_bdev(struct block_device
 	invalidate_bh_lrus();
 	lru_add_drain_all();	/* make sure all lru add caches are flushed */
 	invalidate_mapping_pages(mapping, 0, -1);
+	/* 99% of the time, we don't need to flush the cleancache on the bdev.
+	 * But, for the strange corners, lets be cautious
+	 */
+	cleancache_flush_inode(mapping);
 }
 EXPORT_SYMBOL(invalidate_bdev);
 
--- linux-2.6.39-rc3/fs/mpage.c	2011-04-11 18:21:51.000000000 -0600
+++ linux-2.6.39-rc3-cleancache/fs/mpage.c	2011-04-13 17:07:24.706913410 -0600
@@ -27,6 +27,7 @@
 #include <linux/writeback.h>
 #include <linux/backing-dev.h>
 #include <linux/pagevec.h>
+#include <linux/cleancache.h>
 
 /*
  * I/O completion handler for multipage BIOs.
@@ -271,6 +272,12 @@ do_mpage_readpage(struct bio *bio, struc
 		SetPageMappedToDisk(page);
 	}
 
+	if (fully_mapped && blocks_per_page == 1 && !PageUptodate(page) &&
+	    cleancache_get_page(page) == 0) {
+		SetPageUptodate(page);
+		goto confused;
+	}
+
 	/*
 	 * This page will go to BIO.  Do we need to send this BIO off first?
 	 */
--- linux-2.6.39-rc3/mm/filemap.c	2011-04-11 18:21:51.000000000 -0600
+++ linux-2.6.39-rc3-cleancache/mm/filemap.c	2011-04-13 17:09:46.367852002 -0600
@@ -34,6 +34,7 @@
 #include <linux/hardirq.h> /* for BUG_ON(!in_atomic()) only */
 #include <linux/memcontrol.h>
 #include <linux/mm_inline.h> /* for page_is_file_cache() */
+#include <linux/cleancache.h>
 #include "internal.h"
 
 /*
@@ -118,6 +119,16 @@ void __delete_from_page_cache(struct pag
 {
 	struct address_space *mapping = page->mapping;
 
+	/*
+	 * if we're uptodate, flush out into the cleancache, otherwise
+	 * invalidate any existing cleancache entries.  We can't leave
+	 * stale data around in the cleancache once our page is gone
+	 */
+	if (PageUptodate(page) && PageMappedToDisk(page))
+		cleancache_put_page(page);
+	else
+		cleancache_flush_page(mapping, page);
+
 	radix_tree_delete(&mapping->page_tree, page->index);
 	page->mapping = NULL;
 	mapping->nrpages--;
--- linux-2.6.39-rc3/mm/truncate.c	2011-04-11 18:21:51.000000000 -0600
+++ linux-2.6.39-rc3-cleancache/mm/truncate.c	2011-04-13 17:07:24.710911759 -0600
@@ -19,6 +19,7 @@
 #include <linux/task_io_accounting_ops.h>
 #include <linux/buffer_head.h>	/* grr. try_to_release_page,
 				   do_invalidatepage */
+#include <linux/cleancache.h>
 #include "internal.h"
 
 
@@ -51,6 +52,7 @@ void do_invalidatepage(struct page *page
 static inline void truncate_partial_page(struct page *page, unsigned partial)
 {
 	zero_user_segment(page, partial, PAGE_CACHE_SIZE);
+	cleancache_flush_page(page->mapping, page);
 	if (page_has_private(page))
 		do_invalidatepage(page, partial);
 }
@@ -214,6 +216,7 @@ void truncate_inode_pages_range(struct a
 	pgoff_t next;
 	int i;
 
+	cleancache_flush_inode(mapping);
 	if (mapping->nrpages == 0)
 		return;
 
@@ -291,6 +294,7 @@ void truncate_inode_pages_range(struct a
 		pagevec_release(&pvec);
 		mem_cgroup_uncharge_end();
 	}
+	cleancache_flush_inode(mapping);
 }
 EXPORT_SYMBOL(truncate_inode_pages_range);
 
@@ -440,6 +444,7 @@ int invalidate_inode_pages2_range(struct
 	int did_range_unmap = 0;
 	int wrapped = 0;
 
+	cleancache_flush_inode(mapping);
 	pagevec_init(&pvec, 0);
 	next = start;
 	while (next <= end && !wrapped &&
@@ -498,6 +503,7 @@ int invalidate_inode_pages2_range(struct
 		mem_cgroup_uncharge_end();
 		cond_resched();
 	}
+	cleancache_flush_inode(mapping);
 	return ret;
 }
 EXPORT_SYMBOL_GPL(invalidate_inode_pages2_range);
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/