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@gmail.com: adapt to new remove_from_page_cache function]
Signed-off-by: Chris Mason <chris.mason@oracle.com>
Signed-off-by: Dan Magenheimer <dan.magenheimer@oracle.com>
Reviewed-by: Jeremy Fitzhardinge <jeremy@goop.org>
Reviewed-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Al Viro <viro@ZenIV.linux.org.uk>
Cc: Matthew Wilcox <matthew@wil.cx>
Cc: Nick Piggin <npiggin@kernel.dk>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Rik Van Riel <riel@redhat.com>
Cc: Jan Beulich <JBeulich@novell.com>
Cc: Andreas Dilger <adilger@sun.com>
Cc: Ted Ts'o <tytso@mit.edu>
Cc: Mark Fasheh <mfasheh@suse.com>
Cc: Joel Becker <joel.becker@oracle.com>
Cc: Nitin Gupta <ngupta@vflare.org>

diff --git a/fs/buffer.c b/fs/buffer.c
index a08bb8e..de05703 100644 (file)
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -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 *bdev)
        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);
 

diff --git a/fs/mpage.c b/fs/mpage.c
index 0afc809..fdfae9f 100644 (file)
--- a/fs/mpage.c
+++ b/fs/mpage.c
@@ -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, struct page *page, unsigned nr_pages,
                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?
         */

diff --git a/fs/super.c b/fs/super.c
index 8a06881..b383fa4 100644 (file)
--- a/fs/super.c
+++ b/fs/super.c
@@ -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(struct file_system_type *type)
                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 super_block *s)
 {
        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

diff --git a/mm/filemap.c b/mm/filemap.c
index c641edf..ec6fa2d 100644 (file)
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -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 page *page)
 {
        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--;

diff --git a/mm/truncate.c b/mm/truncate.c
index a956675..3a29a61 100644 (file)
--- a/mm/truncate.c
+++ b/mm/truncate.c
@@ -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, unsigned long offset)
 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 address_space *mapping,
        pgoff_t next;
        int i;
 
+       cleancache_flush_inode(mapping);
        if (mapping->nrpages == 0)
                return;
 
@@ -291,6 +294,7 @@ void truncate_inode_pages_range(struct address_space *mapping,
                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 address_space *mapping,
        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 address_space *mapping,
                mem_cgroup_uncharge_end();
                cond_resched();
        }
+       cleancache_flush_inode(mapping);
        return ret;
 }
 EXPORT_SYMBOL_GPL(invalidate_inode_pages2_range);