summaryrefslogtreecommitdiff
path: root/mm
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2011-05-26 10:50:56 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2011-05-26 10:50:56 -0700
commitf8d613e2a665bf1be9628a3c3f9bafe7599b32c0 (patch)
tree98d4da8d0e1a5fb1d9064626b4b96d95ccf26375 /mm
parent8a0599dd2471f2a2e409498c08a0ab339057ad06 (diff)
parent5bc20fc59706214d9591c11e1938a629d3538c12 (diff)
Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/djm/tmem
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/djm/tmem: xen: cleancache shim to Xen Transcendent Memory ocfs2: add cleancache support ext4: add cleancache support btrfs: add cleancache support ext3: add cleancache support mm/fs: add hooks to support cleancache mm: cleancache core ops functions and config fs: add field to superblock to support cleancache mm/fs: cleancache documentation Fix up trivial conflict in fs/btrfs/extent_io.c due to includes
Diffstat (limited to 'mm')
-rw-r--r--mm/Kconfig23
-rw-r--r--mm/Makefile1
-rw-r--r--mm/cleancache.c244
-rw-r--r--mm/filemap.c11
-rw-r--r--mm/truncate.c6
5 files changed, 285 insertions, 0 deletions
diff --git a/mm/Kconfig b/mm/Kconfig
index e9c0c61f2ddd..8ca47a5ee9c8 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -347,3 +347,26 @@ config NEED_PER_CPU_KM
depends on !SMP
bool
default y
+
+config CLEANCACHE
+ bool "Enable cleancache driver to cache clean pages if tmem is present"
+ default n
+ help
+ Cleancache can be thought of as a page-granularity victim cache
+ for clean pages that the kernel's pageframe replacement algorithm
+ (PFRA) would like to keep around, but can't since there isn't enough
+ memory. So when the PFRA "evicts" a page, it first attempts to use
+ cleancacne code to put the data contained in that page into
+ "transcendent memory", memory that is not directly accessible or
+ addressable by the kernel and is of unknown and possibly
+ time-varying size. And when a cleancache-enabled
+ filesystem wishes to access a page in a file on disk, it first
+ checks cleancache to see if it already contains it; if it does,
+ the page is copied into the kernel and a disk access is avoided.
+ When a transcendent memory driver is available (such as zcache or
+ Xen transcendent memory), a significant I/O reduction
+ may be achieved. When none is available, all cleancache calls
+ are reduced to a single pointer-compare-against-NULL resulting
+ in a negligible performance hit.
+
+ If unsure, say Y to enable cleancache
diff --git a/mm/Makefile b/mm/Makefile
index 42a8326c3e3d..836e4163c1bf 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -49,3 +49,4 @@ obj-$(CONFIG_MEMORY_FAILURE) += memory-failure.o
obj-$(CONFIG_HWPOISON_INJECT) += hwpoison-inject.o
obj-$(CONFIG_DEBUG_KMEMLEAK) += kmemleak.o
obj-$(CONFIG_DEBUG_KMEMLEAK_TEST) += kmemleak-test.o
+obj-$(CONFIG_CLEANCACHE) += cleancache.o
diff --git a/mm/cleancache.c b/mm/cleancache.c
new file mode 100644
index 000000000000..bcaae4c2a770
--- /dev/null
+++ b/mm/cleancache.c
@@ -0,0 +1,244 @@
+/*
+ * Cleancache frontend
+ *
+ * This code provides the generic "frontend" layer to call a matching
+ * "backend" driver implementation of cleancache. See
+ * Documentation/vm/cleancache.txt for more information.
+ *
+ * Copyright (C) 2009-2010 Oracle Corp. All rights reserved.
+ * Author: Dan Magenheimer
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2.
+ */
+
+#include <linux/module.h>
+#include <linux/fs.h>
+#include <linux/exportfs.h>
+#include <linux/mm.h>
+#include <linux/cleancache.h>
+
+/*
+ * This global enablement flag may be read thousands of times per second
+ * by cleancache_get/put/flush even on systems where cleancache_ops
+ * is not claimed (e.g. cleancache is config'ed on but remains
+ * disabled), so is preferred to the slower alternative: a function
+ * call that checks a non-global.
+ */
+int cleancache_enabled;
+EXPORT_SYMBOL(cleancache_enabled);
+
+/*
+ * cleancache_ops is set by cleancache_ops_register to contain the pointers
+ * to the cleancache "backend" implementation functions.
+ */
+static struct cleancache_ops cleancache_ops;
+
+/* useful stats available in /sys/kernel/mm/cleancache */
+static unsigned long cleancache_succ_gets;
+static unsigned long cleancache_failed_gets;
+static unsigned long cleancache_puts;
+static unsigned long cleancache_flushes;
+
+/*
+ * register operations for cleancache, returning previous thus allowing
+ * detection of multiple backends and possible nesting
+ */
+struct cleancache_ops cleancache_register_ops(struct cleancache_ops *ops)
+{
+ struct cleancache_ops old = cleancache_ops;
+
+ cleancache_ops = *ops;
+ cleancache_enabled = 1;
+ return old;
+}
+EXPORT_SYMBOL(cleancache_register_ops);
+
+/* Called by a cleancache-enabled filesystem at time of mount */
+void __cleancache_init_fs(struct super_block *sb)
+{
+ sb->cleancache_poolid = (*cleancache_ops.init_fs)(PAGE_SIZE);
+}
+EXPORT_SYMBOL(__cleancache_init_fs);
+
+/* Called by a cleancache-enabled clustered filesystem at time of mount */
+void __cleancache_init_shared_fs(char *uuid, struct super_block *sb)
+{
+ sb->cleancache_poolid =
+ (*cleancache_ops.init_shared_fs)(uuid, PAGE_SIZE);
+}
+EXPORT_SYMBOL(__cleancache_init_shared_fs);
+
+/*
+ * If the filesystem uses exportable filehandles, use the filehandle as
+ * the key, else use the inode number.
+ */
+static int cleancache_get_key(struct inode *inode,
+ struct cleancache_filekey *key)
+{
+ int (*fhfn)(struct dentry *, __u32 *fh, int *, int);
+ int len = 0, maxlen = CLEANCACHE_KEY_MAX;
+ struct super_block *sb = inode->i_sb;
+
+ key->u.ino = inode->i_ino;
+ if (sb->s_export_op != NULL) {
+ fhfn = sb->s_export_op->encode_fh;
+ if (fhfn) {
+ struct dentry d;
+ d.d_inode = inode;
+ len = (*fhfn)(&d, &key->u.fh[0], &maxlen, 0);
+ if (len <= 0 || len == 255)
+ return -1;
+ if (maxlen > CLEANCACHE_KEY_MAX)
+ return -1;
+ }
+ }
+ return 0;
+}
+
+/*
+ * "Get" data from cleancache associated with the poolid/inode/index
+ * that were specified when the data was put to cleanache and, if
+ * successful, use it to fill the specified page with data and return 0.
+ * The pageframe is unchanged and returns -1 if the get fails.
+ * Page must be locked by caller.
+ */
+int __cleancache_get_page(struct page *page)
+{
+ int ret = -1;
+ int pool_id;
+ struct cleancache_filekey key = { .u.key = { 0 } };
+
+ VM_BUG_ON(!PageLocked(page));
+ pool_id = page->mapping->host->i_sb->cleancache_poolid;
+ if (pool_id < 0)
+ goto out;
+
+ if (cleancache_get_key(page->mapping->host, &key) < 0)
+ goto out;
+
+ ret = (*cleancache_ops.get_page)(pool_id, key, page->index, page);
+ if (ret == 0)
+ cleancache_succ_gets++;
+ else
+ cleancache_failed_gets++;
+out:
+ return ret;
+}
+EXPORT_SYMBOL(__cleancache_get_page);
+
+/*
+ * "Put" data from a page to cleancache and associate it with the
+ * (previously-obtained per-filesystem) poolid and the page's,
+ * inode and page index. Page must be locked. Note that a put_page
+ * always "succeeds", though a subsequent get_page may succeed or fail.
+ */
+void __cleancache_put_page(struct page *page)
+{
+ int pool_id;
+ struct cleancache_filekey key = { .u.key = { 0 } };
+
+ VM_BUG_ON(!PageLocked(page));
+ pool_id = page->mapping->host->i_sb->cleancache_poolid;
+ if (pool_id >= 0 &&
+ cleancache_get_key(page->mapping->host, &key) >= 0) {
+ (*cleancache_ops.put_page)(pool_id, key, page->index, page);
+ cleancache_puts++;
+ }
+}
+EXPORT_SYMBOL(__cleancache_put_page);
+
+/*
+ * Flush any data from cleancache associated with the poolid and the
+ * page's inode and page index so that a subsequent "get" will fail.
+ */
+void __cleancache_flush_page(struct address_space *mapping, struct page *page)
+{
+ /* careful... page->mapping is NULL sometimes when this is called */
+ int pool_id = mapping->host->i_sb->cleancache_poolid;
+ struct cleancache_filekey key = { .u.key = { 0 } };
+
+ if (pool_id >= 0) {
+ VM_BUG_ON(!PageLocked(page));
+ if (cleancache_get_key(mapping->host, &key) >= 0) {
+ (*cleancache_ops.flush_page)(pool_id, key, page->index);
+ cleancache_flushes++;
+ }
+ }
+}
+EXPORT_SYMBOL(__cleancache_flush_page);
+
+/*
+ * Flush all data from cleancache associated with the poolid and the
+ * mappings's inode so that all subsequent gets to this poolid/inode
+ * will fail.
+ */
+void __cleancache_flush_inode(struct address_space *mapping)
+{
+ int pool_id = mapping->host->i_sb->cleancache_poolid;
+ struct cleancache_filekey key = { .u.key = { 0 } };
+
+ if (pool_id >= 0 && cleancache_get_key(mapping->host, &key) >= 0)
+ (*cleancache_ops.flush_inode)(pool_id, key);
+}
+EXPORT_SYMBOL(__cleancache_flush_inode);
+
+/*
+ * Called by any cleancache-enabled filesystem at time of unmount;
+ * note that pool_id is surrendered and may be reutrned by a subsequent
+ * cleancache_init_fs or cleancache_init_shared_fs
+ */
+void __cleancache_flush_fs(struct super_block *sb)
+{
+ if (sb->cleancache_poolid >= 0) {
+ int old_poolid = sb->cleancache_poolid;
+ sb->cleancache_poolid = -1;
+ (*cleancache_ops.flush_fs)(old_poolid);
+ }
+}
+EXPORT_SYMBOL(__cleancache_flush_fs);
+
+#ifdef CONFIG_SYSFS
+
+/* see Documentation/ABI/xxx/sysfs-kernel-mm-cleancache */
+
+#define CLEANCACHE_SYSFS_RO(_name) \
+ static ssize_t cleancache_##_name##_show(struct kobject *kobj, \
+ struct kobj_attribute *attr, char *buf) \
+ { \
+ return sprintf(buf, "%lu\n", cleancache_##_name); \
+ } \
+ static struct kobj_attribute cleancache_##_name##_attr = { \
+ .attr = { .name = __stringify(_name), .mode = 0444 }, \
+ .show = cleancache_##_name##_show, \
+ }
+
+CLEANCACHE_SYSFS_RO(succ_gets);
+CLEANCACHE_SYSFS_RO(failed_gets);
+CLEANCACHE_SYSFS_RO(puts);
+CLEANCACHE_SYSFS_RO(flushes);
+
+static struct attribute *cleancache_attrs[] = {
+ &cleancache_succ_gets_attr.attr,
+ &cleancache_failed_gets_attr.attr,
+ &cleancache_puts_attr.attr,
+ &cleancache_flushes_attr.attr,
+ NULL,
+};
+
+static struct attribute_group cleancache_attr_group = {
+ .attrs = cleancache_attrs,
+ .name = "cleancache",
+};
+
+#endif /* CONFIG_SYSFS */
+
+static int __init init_cleancache(void)
+{
+#ifdef CONFIG_SYSFS
+ int err;
+
+ err = sysfs_create_group(mm_kobj, &cleancache_attr_group);
+#endif /* CONFIG_SYSFS */
+ return 0;
+}
+module_init(init_cleancache)
diff --git a/mm/filemap.c b/mm/filemap.c
index 68e782b3d3de..7455ccd8bda8 100644
--- 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 a95667529135..3a29a6180212 100644
--- 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);