@@ -0,0 +1,118 @@
+#ifndef _LINUX_CLEANCACHE_H
+#define _LINUX_CLEANCACHE_H
+
+#include <linux/fs.h>
+#include <linux/exportfs.h>
+#include <linux/mm.h>
+
+#define CLEANCACHE_KEY_MAX 6
+
+/*
+ * cleancache requires every file with a page in cleancache to have a
+ * unique key unless/until the file is removed/truncated. For some
+ * filesystems, the inode number is unique, but for "modern" filesystems
+ * an exportable filehandle is required (see exportfs.h)
+ */
+struct cleancache_filekey {
+ union {
+ ino_t ino;
+ __u32 fh[CLEANCACHE_KEY_MAX];
+ u32 key[CLEANCACHE_KEY_MAX];
+ } u;
+};
+
+struct cleancache_ops {
+ int (*init_fs)(size_t);
+ int (*init_shared_fs)(char *uuid, size_t);
+ int (*get_page)(int, struct cleancache_filekey,
+ pgoff_t, struct page *);
+ void (*put_page)(int, struct cleancache_filekey,
+ pgoff_t, struct page *);
+ void (*flush_page)(int, struct cleancache_filekey, pgoff_t);
+ void (*flush_inode)(int, struct cleancache_filekey);
+ void (*flush_fs)(int);
+};
+
+extern struct cleancache_ops
+ cleancache_register_ops(struct cleancache_ops *ops);
+extern void __cleancache_init_fs(struct super_block *);
+extern void __cleancache_init_shared_fs(char *, struct super_block *);
+extern int __cleancache_get_page(struct page *);
+extern void __cleancache_put_page(struct page *);
+extern void __cleancache_flush_page(struct address_space *, struct page *);
+extern void __cleancache_flush_inode(struct address_space *);
+extern void __cleancache_flush_fs(struct super_block *);
+extern int cleancache_enabled;
+
+#ifdef CONFIG_CLEANCACHE
+#define cleancache_fs_enabled(_page) \
+ (_page->mapping->host->i_sb->cleancache_poolid >= 0)
+#define cleancache_fs_enabled_mapping(_mapping) \
+ (mapping->host->i_sb->cleancache_poolid >= 0)
+#else
+#define cleancache_enabled (0)
+#define cleancache_fs_enabled(_page) (0)
+#define cleancache_fs_enabled_mapping(_page) (0)
+#endif
+
+/*
+ * The shim layer provided by these inline functions allows the compiler
+ * to reduce all cleancache hooks to nothingness if CONFIG_CLEANCACHE
+ * is disabled, to a single global variable check if CONFIG_CLEANCACHE
+ * is enabled but no cleancache "backend" has dynamically enabled it,
+ * and, for the most frequent cleancache ops, to a single global variable
+ * check plus a superblock element comparison if CONFIG_CLEANCACHE is enabled
+ * and a cleancache backend has dynamically enabled cleancache, but the
+ * filesystem referenced by that cleancache op has not enabled cleancache.
+ * As a result, CONFIG_CLEANCACHE can be enabled by default with essentially
+ * no measurable performance impact.
+ */
+
+static inline void cleancache_init_fs(struct super_block *sb)
+{
+ if (cleancache_enabled)
+ __cleancache_init_fs(sb);
+}
+
+static inline void cleancache_init_shared_fs(char *uuid, struct super_block *sb)
+{
+ if (cleancache_enabled)
+ __cleancache_init_shared_fs(uuid, sb);
+}
+
+static inline int cleancache_get_page(struct page *page)
+{
+ int ret = -1;
+
+ if (cleancache_enabled && cleancache_fs_enabled(page))
+ ret = __cleancache_get_page(page);
+ return ret;
+}
+
+static inline void cleancache_put_page(struct page *page)
+{
+ if (cleancache_enabled && cleancache_fs_enabled(page))
+ __cleancache_put_page(page);
+}
+
+static inline void cleancache_flush_page(struct address_space *mapping,
+ struct page *page)
+{
+ /* careful... page->mapping is NULL sometimes when this is called */
+ if (cleancache_enabled && cleancache_fs_enabled_mapping(mapping))
+ __cleancache_flush_page(mapping, page);
+}
+
+static inline void cleancache_flush_inode(struct address_space *mapping)
+{
+ if (cleancache_enabled && cleancache_fs_enabled_mapping(mapping))
+ __cleancache_flush_inode(mapping);
+}
+
+static inline void cleancache_flush_fs(struct super_block *sb)
+{
+ if (cleancache_enabled)
+ __cleancache_flush_fs(sb);
+}
+
+#endif /* _LINUX_CLEANCACHE_H */
@@ -0,0 +1,258 @@
+/*
+ * 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 maxlen = CLEANCACHE_KEY_MAX;
+ struct super_block *sb = inode->i_sb;
+ struct dentry *d;
+
+ key->u.ino = inode->i_ino;
+ if (sb->s_export_op != NULL) {
+ fhfn = sb->s_export_op->encode_fh;
+ if (fhfn) {
+ d = list_first_entry(&inode->i_dentry,
+ struct dentry, d_alias);
+ (void)(*fhfn)(d, &key->u.fh[0], &maxlen, 0);
+ 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_ATTR_RO(_name) \
+ static struct kobj_attribute _name##_attr = __ATTR_RO(_name)
+
+static ssize_t cleancache_succ_gets_show(struct kobject *kobj,
+ struct kobj_attribute *attr, char *buf)
+{
+ return sprintf(buf, "%lu\n", cleancache_succ_gets);
+}
+CLEANCACHE_ATTR_RO(cleancache_succ_gets);
+
+static ssize_t cleancache_failed_gets_show(struct kobject *kobj,
+ struct kobj_attribute *attr, char *buf)
+{
+ return sprintf(buf, "%lu\n", cleancache_failed_gets);
+}
+CLEANCACHE_ATTR_RO(cleancache_failed_gets);
+
+static ssize_t cleancache_puts_show(struct kobject *kobj,
+ struct kobj_attribute *attr, char *buf)
+{
+ return sprintf(buf, "%lu\n", cleancache_puts);
+}
+CLEANCACHE_ATTR_RO(cleancache_puts);
+
+static ssize_t cleancache_flushes_show(struct kobject *kobj,
+ struct kobj_attribute *attr, char *buf)
+{
+ return sprintf(buf, "%lu\n", cleancache_flushes);
+}
+CLEANCACHE_ATTR_RO(cleancache_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)
@@ -301,3 +301,25 @@ config NOMMU_INITIAL_TRIM_EXCESS
of 1 says that all excess pages should be trimmed.
See Documentation/nommu-mmap.txt for more information.
+
+config CLEANCACHE
+ bool "Enable cleancache pseudo-RAM driver to cache clean pages"
+ default y
+ 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 put
+ it into a synchronous concurrency-safe page-oriented pseudo-RAM
+ device (such as Xen's Transcendent Memory, aka "tmem") which 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 pseudo-RAM device is available, 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
@@ -47,3 +47,4 @@ obj-$(CONFIG_MEMORY_FAILURE) += memory-f
obj-$(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