From 9fdfdcf17151e8326c4d18cc133abc6e58f47568 Mon Sep 17 00:00:00 2001 From: Dan Magenheimer Date: Thu, 26 May 2011 10:01:19 -0600 Subject: fs: add field to superblock to support cleancache This second patch of eight in this cleancache series adds a field to the generic superblock to squirrel away a pool identifier that is dynamically provided by cleancache-enabled filesystems at mount time to uniquely identify files and pages belonging to this mounted filesystem. Details and a FAQ can be found in Documentation/vm/cleancache.txt [v8: trivial merge conflict update] Signed-off-by: Dan Magenheimer Reviewed-by: Jeremy Fitzhardinge Reviewed-by: Konrad Rzeszutek Wilk Cc: Andrew Morton Cc: Al Viro Cc: Matthew Wilcox Cc: Nick Piggin Cc: Mel Gorman Cc: Rik Van Riel Cc: Jan Beulich Cc: Chris Mason Cc: Andreas Dilger Cc: Ted Ts'o Cc: Mark Fasheh Cc: Joel Becker Cc: Nitin Gupta --- include/linux/fs.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/linux/fs.h b/include/linux/fs.h index cdf9495df204..0169ed3f106e 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1429,6 +1429,11 @@ struct super_block { */ char __rcu *s_options; const struct dentry_operations *s_d_op; /* default d_op for dentries */ + + /* + * Saved pool identifier for cleancache (-1 means none) + */ + int cleancache_poolid; }; extern struct timespec current_fs_time(struct super_block *sb); -- cgit v1.2.3 From 077b1f83a69d94f2918630a882d74939baca0bce Mon Sep 17 00:00:00 2001 From: Dan Magenheimer Date: Thu, 26 May 2011 10:01:36 -0600 Subject: mm: cleancache core ops functions and config This third patch of eight in this cleancache series provides the core code for cleancache that interfaces between the hooks in VFS and individual filesystems and a cleancache backend. It also includes build and config patches. Two new files are added: mm/cleancache.c and include/linux/cleancache.h. Note that CONFIG_CLEANCACHE can default to on; in systems that do not provide a cleancache backend, all hooks devolve to a simple check of a global enable flag, so performance impact should be negligible but can be reduced to zero impact if config'ed off. However for this first commit, it defaults to off. Details and a FAQ can be found in Documentation/vm/cleancache.txt Credits: Cleancache_ops design derived from Jeremy Fitzhardinge design for tmem [v8: dan.magenheimer@oracle.com: fix exportfs call affecting btrfs] [v8: akpm@linux-foundation.org: use static inline function, not macro] [v7: dan.magenheimer@oracle.com: cleanup sysfs and remove cleancache prefix] [v6: JBeulich@novell.com: robustly handle buggy fs encode_fh actor definition] [v5: jeremy@goop.org: clean up global usage and static var names] [v5: jeremy@goop.org: simplify init hook and any future fs init changes] [v5: hch@infradead.org: cleaner non-global interface for ops registration] [v4: adilger@sun.com: interface must support exportfs FS's] [v4: hch@infradead.org: interface must support 64-bit FS on 32-bit kernel] [v3: akpm@linux-foundation.org: use one ops struct to avoid pointer hops] [v3: akpm@linux-foundation.org: document and ensure PageLocked reqts are met] [v3: ngupta@vflare.org: fix success/fail codes, change funcs to void] [v2: viro@ZenIV.linux.org.uk: use sane types] Signed-off-by: Dan Magenheimer Reviewed-by: Jeremy Fitzhardinge Reviewed-by: Konrad Rzeszutek Wilk Acked-by: Al Viro Acked-by: Andrew Morton Acked-by: Nitin Gupta Acked-by: Minchan Kim Acked-by: Andreas Dilger Acked-by: Jan Beulich Cc: Matthew Wilcox Cc: Nick Piggin Cc: Mel Gorman Cc: Rik Van Riel Cc: Chris Mason Cc: Ted Ts'o Cc: Mark Fasheh Cc: Joel Becker --- include/linux/cleancache.h | 122 +++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 122 insertions(+) create mode 100644 include/linux/cleancache.h (limited to 'include') diff --git a/include/linux/cleancache.h b/include/linux/cleancache.h new file mode 100644 index 000000000000..04ffb2e6c9d0 --- /dev/null +++ b/include/linux/cleancache.h @@ -0,0 +1,122 @@ +#ifndef _LINUX_CLEANCACHE_H +#define _LINUX_CLEANCACHE_H + +#include +#include +#include + +#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 +static inline bool cleancache_fs_enabled(struct page *page) +{ + return page->mapping->host->i_sb->cleancache_poolid >= 0; +} +static inline bool cleancache_fs_enabled_mapping(struct address_space *mapping) +{ + return 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 */ -- cgit v1.2.3 From 5bc20fc59706214d9591c11e1938a629d3538c12 Mon Sep 17 00:00:00 2001 From: Dan Magenheimer Date: Thu, 26 May 2011 10:02:21 -0600 Subject: xen: cleancache shim to Xen Transcendent Memory This patch provides a shim between the kernel-internal cleancache API (see Documentation/mm/cleancache.txt) and the Xen Transcendent Memory ABI (see http://oss.oracle.com/projects/tmem). Xen tmem provides "hypervisor RAM" as an ephemeral page-oriented pseudo-RAM store for cleancache pages, shared cleancache pages, and frontswap pages. Tmem provides enterprise-quality concurrency, full save/restore and live migration support, compression and deduplication. A presentation showing up to 8% faster performance and up to 52% reduction in sectors read on a kernel compile workload, despite aggressive in-kernel page reclamation ("self-ballooning") can be found at: http://oss.oracle.com/projects/tmem/dist/documentation/presentations/TranscendentMemoryXenSummit2010.pdf Signed-off-by: Dan Magenheimer Reviewed-by: Jeremy Fitzhardinge Cc: Konrad Rzeszutek Wilk Cc: Matthew Wilcox Cc: Nick Piggin Cc: Mel Gorman Cc: Rik Van Riel Cc: Jan Beulich Cc: Chris Mason Cc: Andreas Dilger Cc: Ted Ts'o Cc: Mark Fasheh Cc: Joel Becker Cc: Nitin Gupta --- include/xen/interface/xen.h | 22 ++++++++++++++++++++++ 1 file changed, 22 insertions(+) (limited to 'include') diff --git a/include/xen/interface/xen.h b/include/xen/interface/xen.h index b33257bc7e83..70213b4515eb 100644 --- a/include/xen/interface/xen.h +++ b/include/xen/interface/xen.h @@ -58,6 +58,7 @@ #define __HYPERVISOR_event_channel_op 32 #define __HYPERVISOR_physdev_op 33 #define __HYPERVISOR_hvm_op 34 +#define __HYPERVISOR_tmem_op 38 /* Architecture-specific hypercall definitions. */ #define __HYPERVISOR_arch_0 48 @@ -461,6 +462,27 @@ typedef uint8_t xen_domain_handle_t[16]; #define __mk_unsigned_long(x) x ## UL #define mk_unsigned_long(x) __mk_unsigned_long(x) +#define TMEM_SPEC_VERSION 1 + +struct tmem_op { + uint32_t cmd; + int32_t pool_id; + union { + struct { /* for cmd == TMEM_NEW_POOL */ + uint64_t uuid[2]; + uint32_t flags; + } new; + struct { + uint64_t oid[3]; + uint32_t index; + uint32_t tmem_offset; + uint32_t pfn_offset; + uint32_t len; + GUEST_HANDLE(void) gmfn; /* guest machine page frame */ + } gen; + } u; +}; + #else /* __ASSEMBLY__ */ /* In assembly code we cannot use C numeric constant suffixes. */ -- cgit v1.2.3