From 4fe4746ab694690af9f2ccb80184f5c575917c7f Mon Sep 17 00:00:00 2001 From: Dan Magenheimer Date: Thu, 26 May 2011 10:00:56 -0600 Subject: mm/fs: cleancache documentation This patchset introduces cleancache, an optional new feature exposed by the VFS layer that potentially dramatically increases page cache effectiveness for many workloads in many environments at a negligible cost. It does this by providing an interface to transcendent memory, which is memory/storage that is not otherwise visible to and/or directly addressable by the kernel. Instead of being discarded, hooks in the reclaim code "put" clean pages to cleancache. Filesystems that "opt-in" may "get" pages from cleancache that were previously put, but pages in cleancache are "ephemeral", meaning they may disappear at any time. And the size of cleancache is entirely dynamic and unknowable to the kernel. Filesystems currently supported by this patchset include ext3, ext4, btrfs, and ocfs2. Other filesystems (especially those built entirely on VFS) should be easy to add, but should first be thoroughly tested to ensure coherency. Details and a FAQ are provided in Documentation/vm/cleancache.txt This first patch of eight in this cleancache series only adds two new documentation files. [v8: minor documentation changes by author] [v3: akpm@linux-foundation.org: document sysfs API] [v3: hch@infradead.org: move detailed description to Documentation/vm] Signed-off-by: Dan Magenheimer Reviewed-by: Jeremy Fitzhardinge Reviewed-by: Konrad Rzeszutek Wilk Acked-by: Andrew Morton Acked-by: Randy Dunlap 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 --- .../ABI/testing/sysfs-kernel-mm-cleancache | 11 + Documentation/vm/cleancache.txt | 278 +++++++++++++++++++++ 2 files changed, 289 insertions(+) create mode 100644 Documentation/ABI/testing/sysfs-kernel-mm-cleancache create mode 100644 Documentation/vm/cleancache.txt diff --git a/Documentation/ABI/testing/sysfs-kernel-mm-cleancache b/Documentation/ABI/testing/sysfs-kernel-mm-cleancache new file mode 100644 index 000000000000..662ae646ea12 --- /dev/null +++ b/Documentation/ABI/testing/sysfs-kernel-mm-cleancache @@ -0,0 +1,11 @@ +What: /sys/kernel/mm/cleancache/ +Date: April 2011 +Contact: Dan Magenheimer +Description: + /sys/kernel/mm/cleancache/ contains a number of files which + record a count of various cleancache operations + (sum across all filesystems): + succ_gets + failed_gets + puts + flushes diff --git a/Documentation/vm/cleancache.txt b/Documentation/vm/cleancache.txt new file mode 100644 index 000000000000..36c367c73084 --- /dev/null +++ b/Documentation/vm/cleancache.txt @@ -0,0 +1,278 @@ +MOTIVATION + +Cleancache is a new optional feature provided by the VFS layer that +potentially dramatically increases page cache effectiveness for +many workloads in many environments at a negligible cost. + +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 cleancache 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. + +Later, 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 of data is copied into the kernel +and a disk access is avoided. + +Transcendent memory "drivers" for cleancache are currently implemented +in Xen (using hypervisor memory) and zcache (using in-kernel compressed +memory) and other implementations are in development. + +FAQs are included below. + +IMPLEMENTATION OVERVIEW + +A cleancache "backend" that provides transcendent memory registers itself +to the kernel's cleancache "frontend" by calling cleancache_register_ops, +passing a pointer to a cleancache_ops structure with funcs set appropriately. +Note that cleancache_register_ops returns the previous settings so that +chaining can be performed if desired. The functions provided must conform to +certain semantics as follows: + +Most important, cleancache is "ephemeral". Pages which are copied into +cleancache have an indefinite lifetime which is completely unknowable +by the kernel and so may or may not still be in cleancache at any later time. +Thus, as its name implies, cleancache is not suitable for dirty pages. +Cleancache has complete discretion over what pages to preserve and what +pages to discard and when. + +Mounting a cleancache-enabled filesystem should call "init_fs" to obtain a +pool id which, if positive, must be saved in the filesystem's superblock; +a negative return value indicates failure. A "put_page" will copy a +(presumably about-to-be-evicted) page into cleancache and associate it with +the pool id, a file key, and a page index into the file. (The combination +of a pool id, a file key, and an index is sometimes called a "handle".) +A "get_page" will copy the page, if found, from cleancache into kernel memory. +A "flush_page" will ensure the page no longer is present in cleancache; +a "flush_inode" will flush all pages associated with the specified file; +and, when a filesystem is unmounted, a "flush_fs" will flush all pages in +all files specified by the given pool id and also surrender the pool id. + +An "init_shared_fs", like init_fs, obtains a pool id but tells cleancache +to treat the pool as shared using a 128-bit UUID as a key. On systems +that may run multiple kernels (such as hard partitioned or virtualized +systems) that may share a clustered filesystem, and where cleancache +may be shared among those kernels, calls to init_shared_fs that specify the +same UUID will receive the same pool id, thus allowing the pages to +be shared. Note that any security requirements must be imposed outside +of the kernel (e.g. by "tools" that control cleancache). Or a +cleancache implementation can simply disable shared_init by always +returning a negative value. + +If a get_page is successful on a non-shared pool, the page is flushed (thus +making cleancache an "exclusive" cache). On a shared pool, the page +is NOT flushed on a successful get_page so that it remains accessible to +other sharers. The kernel is responsible for ensuring coherency between +cleancache (shared or not), the page cache, and the filesystem, using +cleancache flush operations as required. + +Note that cleancache must enforce put-put-get coherency and get-get +coherency. For the former, if two puts are made to the same handle but +with different data, say AAA by the first put and BBB by the second, a +subsequent get can never return the stale data (AAA). For get-get coherency, +if a get for a given handle fails, subsequent gets for that handle will +never succeed unless preceded by a successful put with that handle. + +Last, cleancache provides no SMP serialization guarantees; if two +different Linux threads are simultaneously putting and flushing a page +with the same handle, the results are indeterminate. Callers must +lock the page to ensure serial behavior. + +CLEANCACHE PERFORMANCE METRICS + +Cleancache monitoring is done by sysfs files in the +/sys/kernel/mm/cleancache directory. The effectiveness of cleancache +can be measured (across all filesystems) with: + +succ_gets - number of gets that were successful +failed_gets - number of gets that failed +puts - number of puts attempted (all "succeed") +flushes - number of flushes attempted + +A backend implementatation may provide additional metrics. + +FAQ + +1) Where's the value? (Andrew Morton) + +Cleancache provides a significant performance benefit to many workloads +in many environments with negligible overhead by improving the +effectiveness of the pagecache. Clean pagecache pages are +saved in transcendent memory (RAM that is otherwise not directly +addressable to the kernel); fetching those pages later avoids "refaults" +and thus disk reads. + +Cleancache (and its sister code "frontswap") provide interfaces for +this transcendent memory (aka "tmem"), which conceptually lies between +fast kernel-directly-addressable RAM and slower DMA/asynchronous devices. +Disallowing direct kernel or userland reads/writes to tmem +is ideal when data is transformed to a different form and size (such +as with compression) or secretly moved (as might be useful for write- +balancing for some RAM-like devices). Evicted page-cache pages (and +swap pages) are a great use for this kind of slower-than-RAM-but-much- +faster-than-disk transcendent memory, and the cleancache (and frontswap) +"page-object-oriented" specification provides a nice way to read and +write -- and indirectly "name" -- the pages. + +In the virtual case, the whole point of virtualization is to statistically +multiplex physical resources across the varying demands of multiple +virtual machines. This is really hard to do with RAM and efforts to +do it well with no kernel change have essentially failed (except in some +well-publicized special-case workloads). Cleancache -- and frontswap -- +with a fairly small impact on the kernel, provide a huge amount +of flexibility for more dynamic, flexible RAM multiplexing. +Specifically, the Xen Transcendent Memory backend allows otherwise +"fallow" hypervisor-owned RAM to not only be "time-shared" between multiple +virtual machines, but the pages can be compressed and deduplicated to +optimize RAM utilization. And when guest OS's are induced to surrender +underutilized RAM (e.g. with "self-ballooning"), page cache pages +are the first to go, and cleancache allows those pages to be +saved and reclaimed if overall host system memory conditions allow. + +And the identical interface used for cleancache can be used in +physical systems as well. The zcache driver acts as a memory-hungry +device that stores pages of data in a compressed state. And +the proposed "RAMster" driver shares RAM across multiple physical +systems. + +2) Why does cleancache have its sticky fingers so deep inside the + filesystems and VFS? (Andrew Morton and Christoph Hellwig) + +The core hooks for cleancache in VFS are in most cases a single line +and the minimum set are placed precisely where needed to maintain +coherency (via cleancache_flush operations) between cleancache, +the page cache, and disk. All hooks compile into nothingness if +cleancache is config'ed off and turn into a function-pointer- +compare-to-NULL if config'ed on but no backend claims the ops +functions, or to a compare-struct-element-to-negative if a +backend claims the ops functions but a filesystem doesn't enable +cleancache. + +Some filesystems are built entirely on top of VFS and the hooks +in VFS are sufficient, so don't require an "init_fs" hook; the +initial implementation of cleancache didn't provide this hook. +But for some filesystems (such as btrfs), the VFS hooks are +incomplete and one or more hooks in fs-specific code are required. +And for some other filesystems, such as tmpfs, cleancache may +be counterproductive. So it seemed prudent to require a filesystem +to "opt in" to use cleancache, which requires adding a hook in +each filesystem. Not all filesystems are supported by cleancache +only because they haven't been tested. The existing set should +be sufficient to validate the concept, the opt-in approach means +that untested filesystems are not affected, and the hooks in the +existing filesystems should make it very easy to add more +filesystems in the future. + +The total impact of the hooks to existing fs and mm files is only +about 40 lines added (not counting comments and blank lines). + +3) Why not make cleancache asynchronous and batched so it can + more easily interface with real devices with DMA instead + of copying each individual page? (Minchan Kim) + +The one-page-at-a-time copy semantics simplifies the implementation +on both the frontend and backend and also allows the backend to +do fancy things on-the-fly like page compression and +page deduplication. And since the data is "gone" (copied into/out +of the pageframe) before the cleancache get/put call returns, +a great deal of race conditions and potential coherency issues +are avoided. While the interface seems odd for a "real device" +or for real kernel-addressable RAM, it makes perfect sense for +transcendent memory. + +4) Why is non-shared cleancache "exclusive"? And where is the + page "flushed" after a "get"? (Minchan Kim) + +The main reason is to free up space in transcendent memory and +to avoid unnecessary cleancache_flush calls. If you want inclusive, +the page can be "put" immediately following the "get". If +put-after-get for inclusive becomes common, the interface could +be easily extended to add a "get_no_flush" call. + +The flush is done by the cleancache backend implementation. + +5) What's the performance impact? + +Performance analysis has been presented at OLS'09 and LCA'10. +Briefly, performance gains can be significant on most workloads, +especially when memory pressure is high (e.g. when RAM is +overcommitted in a virtual workload); and because the hooks are +invoked primarily in place of or in addition to a disk read/write, +overhead is negligible even in worst case workloads. Basically +cleancache replaces I/O with memory-copy-CPU-overhead; on older +single-core systems with slow memory-copy speeds, cleancache +has little value, but in newer multicore machines, especially +consolidated/virtualized machines, it has great value. + +6) How do I add cleancache support for filesystem X? (Boaz Harrash) + +Filesystems that are well-behaved and conform to certain +restrictions can utilize cleancache simply by making a call to +cleancache_init_fs at mount time. Unusual, misbehaving, or +poorly layered filesystems must either add additional hooks +and/or undergo extensive additional testing... or should just +not enable the optional cleancache. + +Some points for a filesystem to consider: + +- The FS should be block-device-based (e.g. a ram-based FS such + as tmpfs should not enable cleancache) +- To ensure coherency/correctness, the FS must ensure that all + file removal or truncation operations either go through VFS or + add hooks to do the equivalent cleancache "flush" operations +- To ensure coherency/correctness, either inode numbers must + be unique across the lifetime of the on-disk file OR the + FS must provide an "encode_fh" function. +- The FS must call the VFS superblock alloc and deactivate routines + or add hooks to do the equivalent cleancache calls done there. +- To maximize performance, all pages fetched from the FS should + go through the do_mpag_readpage routine or the FS should add + hooks to do the equivalent (cf. btrfs) +- Currently, the FS blocksize must be the same as PAGESIZE. This + is not an architectural restriction, but no backends currently + support anything different. +- A clustered FS should invoke the "shared_init_fs" cleancache + hook to get best performance for some backends. + +7) Why not use the KVA of the inode as the key? (Christoph Hellwig) + +If cleancache would use the inode virtual address instead of +inode/filehandle, the pool id could be eliminated. But, this +won't work because cleancache retains pagecache data pages +persistently even when the inode has been pruned from the +inode unused list, and only flushes the data page if the file +gets removed/truncated. So if cleancache used the inode kva, +there would be potential coherency issues if/when the inode +kva is reused for a different file. Alternately, if cleancache +flushed the pages when the inode kva was freed, much of the value +of cleancache would be lost because the cache of pages in cleanache +is potentially much larger than the kernel pagecache and is most +useful if the pages survive inode cache removal. + +8) Why is a global variable required? + +The cleancache_enabled flag is checked in all of the frequently-used +cleancache hooks. The alternative is a function call to check a static +variable. Since cleancache is enabled dynamically at runtime, systems +that don't enable cleancache would suffer thousands (possibly +tens-of-thousands) of unnecessary function calls per second. So the +global variable allows cleancache to be enabled by default at compile +time, but have insignificant performance impact when cleancache remains +disabled at runtime. + +9) Does cleanache work with KVM? + +The memory model of KVM is sufficiently different that a cleancache +backend may have less value for KVM. This remains to be tested, +especially in an overcommitted system. + +10) Does cleancache work in userspace? It sounds useful for + memory hungry caches like web browsers. (Jamie Lokier) + +No plans yet, though we agree it sounds useful, at least for +apps that bypass the page cache (e.g. O_DIRECT). + +Last updated: Dan Magenheimer, April 13 2011 -- cgit v1.2.3 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(+) 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 +++++++++++++++++++++++ mm/Kconfig | 23 +++++ mm/Makefile | 1 + mm/cleancache.c | 244 +++++++++++++++++++++++++++++++++++++++++++++ 4 files changed, 390 insertions(+) create mode 100644 include/linux/cleancache.h create mode 100644 mm/cleancache.c 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 */ 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 +#include +#include +#include +#include + +/* + * 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) -- cgit v1.2.3 From c515e1fd361c2a08a9c2eb139396ec30a4f477dc Mon Sep 17 00:00:00 2001 From: Dan Magenheimer Date: Thu, 26 May 2011 10:01:43 -0600 Subject: 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 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: Andreas Dilger Cc: Ted Ts'o Cc: Mark Fasheh Cc: Joel Becker Cc: Nitin Gupta --- 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(+) diff --git a/fs/buffer.c b/fs/buffer.c index a08bb8e61c6f..de05703b184b 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -41,6 +41,7 @@ #include #include #include +#include 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 0afc809e46e0..fdfae9fa98cd 100644 --- a/fs/mpage.c +++ b/fs/mpage.c @@ -27,6 +27,7 @@ #include #include #include +#include /* * 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 8a06881b1920..b383fa407740 100644 --- a/fs/super.c +++ b/fs/super.c @@ -31,6 +31,7 @@ #include #include #include +#include #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 c641edf553a9..ec6fa2d7e200 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -34,6 +34,7 @@ #include /* for BUG_ON(!in_atomic()) only */ #include #include /* for page_is_file_cache() */ +#include #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 #include /* grr. try_to_release_page, do_invalidatepage */ +#include #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); -- cgit v1.2.3 From d71bc6db5e48066bde78a480bb9e3057b3db1a3c Mon Sep 17 00:00:00 2001 From: Dan Magenheimer Date: Thu, 26 May 2011 10:01:49 -0600 Subject: ext3: add cleancache support This fifth patch of eight in this cleancache series "opts-in" cleancache for ext3. Filesystems must explicitly enable cleancache by calling cleancache_init_fs anytime an instance of the filesystem is mounted. For ext3, all other cleancache hooks are in the VFS layer including the matching cleancache_flush_fs hook which must be called on unmount. Details and a FAQ can be found in Documentation/vm/cleancache.txt [v6-v8: no changes] [v5: jeremy@goop.org: simplify init hook and any future fs init changes] Signed-off-by: Dan Magenheimer Reviewed-by: Jeremy Fitzhardinge Reviewed-by: Konrad Rzeszutek Wilk Acked-by: Andreas Dilger Cc: Ted Ts'o 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: Mark Fasheh Cc: Joel Becker Cc: Nitin Gupta --- fs/ext3/super.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/fs/ext3/super.c b/fs/ext3/super.c index 3c6a9e0eadc1..aad153ef6b78 100644 --- a/fs/ext3/super.c +++ b/fs/ext3/super.c @@ -36,6 +36,7 @@ #include #include #include +#include #include @@ -1367,6 +1368,7 @@ static int ext3_setup_super(struct super_block *sb, struct ext3_super_block *es, } else { ext3_msg(sb, KERN_INFO, "using internal journal"); } + cleancache_init_fs(sb); return res; } -- cgit v1.2.3 From 90a887c9a2e25bcb1fc658fad59dfbc6fb792734 Mon Sep 17 00:00:00 2001 From: Dan Magenheimer Date: Thu, 26 May 2011 10:01:56 -0600 Subject: btrfs: add cleancache support This sixth patch of eight in this cleancache series "opts-in" cleancache for btrfs. Filesystems must explicitly enable cleancache by calling cleancache_init_fs anytime an instance of the filesystem is mounted. Btrfs uses its own readpage which must be hooked, but all other cleancache hooks are in the VFS layer including the matching cleancache_flush_fs hook which must be called on unmount. Details and a FAQ can be found in Documentation/vm/cleancache.txt [v6-v8: no changes] [v5: jeremy@goop.org: simplify init hook and any future fs init changes] Signed-off-by: Dan Magenheimer Signed-off-by: Chris Mason 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: Andreas Dilger Cc: Ted Ts'o Cc: Mark Fasheh Cc: Joel Becker Cc: Nitin Gupta --- fs/btrfs/extent_io.c | 9 +++++++++ fs/btrfs/super.c | 2 ++ 2 files changed, 11 insertions(+) diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index ba41da59e31b..0cee46e01081 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -10,6 +10,7 @@ #include #include #include +#include #include "extent_io.h" #include "extent_map.h" #include "compat.h" @@ -2015,6 +2016,13 @@ static int __extent_read_full_page(struct extent_io_tree *tree, set_page_extent_mapped(page); + if (!PageUptodate(page)) { + if (cleancache_get_page(page) == 0) { + BUG_ON(blocksize != PAGE_SIZE); + goto out; + } + } + end = page_end; while (1) { lock_extent(tree, start, end, GFP_NOFS); @@ -2148,6 +2156,7 @@ static int __extent_read_full_page(struct extent_io_tree *tree, cur = cur + iosize; page_offset += iosize; } +out: if (!nr) { if (!PageError(page)) SetPageUptodate(page); diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index 0ac712efcdf2..be4ffa12f3ef 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -39,6 +39,7 @@ #include #include #include +#include #include "compat.h" #include "ctree.h" #include "disk-io.h" @@ -624,6 +625,7 @@ static int btrfs_fill_super(struct super_block *sb, sb->s_root = root_dentry; save_mount_options(sb, data); + cleancache_init_fs(sb); return 0; fail_close: -- cgit v1.2.3 From 7abc52c2ed169c65044d3a199879c8438ad82322 Mon Sep 17 00:00:00 2001 From: Dan Magenheimer Date: Thu, 26 May 2011 10:02:03 -0600 Subject: ext4: add cleancache support This seventh patch of eight in this cleancache series "opts-in" cleancache for ext4. Filesystems must explicitly enable cleancache by calling cleancache_init_fs anytime an instance of the filesystem is mounted. For ext4, all other cleancache hooks are in the VFS layer including the matching cleancache_flush_fs hook which must be called on unmount. Details and a FAQ can be found in Documentation/vm/cleancache.txt [v6-v8: no changes] [v5: jeremy@goop.org: simplify init hook and any future fs init changes] Signed-off-by: Dan Magenheimer Reviewed-by: Jeremy Fitzhardinge Reviewed-by: Konrad Rzeszutek Wilk Acked-by: Andreas Dilger Cc: Ted Ts'o 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: Mark Fasheh Cc: Joel Becker Cc: Nitin Gupta --- fs/ext4/super.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 8553dfb310af..51476477c818 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -38,6 +38,7 @@ #include #include #include +#include #include #include @@ -1932,6 +1933,7 @@ static int ext4_setup_super(struct super_block *sb, struct ext4_super_block *es, EXT4_INODES_PER_GROUP(sb), sbi->s_mount_opt, sbi->s_mount_opt2); + cleancache_init_fs(sb); return res; } -- cgit v1.2.3 From 1cfd8bd0f97ae3ad314151cd0fd70454d7b39699 Mon Sep 17 00:00:00 2001 From: Dan Magenheimer Date: Thu, 26 May 2011 10:02:08 -0600 Subject: ocfs2: add cleancache support This eighth patch of eight in this cleancache series "opts-in" cleancache for ocfs2. Clustered filesystems must explicitly enable cleancache by calling cleancache_init_shared_fs anytime an instance of the filesystem is mounted. Ocfs2 is currently the only user of the clustered filesystem interface but nevertheless, the cleancache hooks in the VFS layer are sufficient for ocfs2 including the matching cleancache_flush_fs hook which must be called on unmount. Details and a FAQ can be found in Documentation/vm/cleancache.txt [v8: trivial merge conflict update] [v5: jeremy@goop.org: simplify init hook and any future fs init changes] Signed-off-by: Dan Magenheimer Signed-off-by: Joel Becker Reviewed-by: Jeremy Fitzhardinge Reviewed-by: Konrad Rzeszutek Wilk Cc: Mark Fasheh 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 Tso Cc: Nitin Gupta --- fs/ocfs2/super.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c index 5a521c748859..4129fb671d71 100644 --- a/fs/ocfs2/super.c +++ b/fs/ocfs2/super.c @@ -41,6 +41,7 @@ #include #include #include +#include #define CREATE_TRACE_POINTS #include "ocfs2_trace.h" @@ -2352,6 +2353,7 @@ static int ocfs2_initialize_super(struct super_block *sb, mlog_errno(status); goto bail; } + cleancache_init_shared_fs((char *)&uuid_net_key, sb); bail: return status; -- 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 --- arch/x86/include/asm/xen/hypercall.h | 7 + drivers/xen/Makefile | 1 + drivers/xen/tmem.c | 264 +++++++++++++++++++++++++++++++++++ include/xen/interface/xen.h | 22 +++ 4 files changed, 294 insertions(+) create mode 100644 drivers/xen/tmem.c diff --git a/arch/x86/include/asm/xen/hypercall.h b/arch/x86/include/asm/xen/hypercall.h index 8508bfe52296..d240ea950519 100644 --- a/arch/x86/include/asm/xen/hypercall.h +++ b/arch/x86/include/asm/xen/hypercall.h @@ -447,6 +447,13 @@ HYPERVISOR_hvm_op(int op, void *arg) return _hypercall2(unsigned long, hvm_op, op, arg); } +static inline int +HYPERVISOR_tmem_op( + struct tmem_op *op) +{ + return _hypercall1(int, tmem_op, op); +} + static inline void MULTI_fpu_taskswitch(struct multicall_entry *mcl, int set) { diff --git a/drivers/xen/Makefile b/drivers/xen/Makefile index f420f1ff7f13..7aa6804173ab 100644 --- a/drivers/xen/Makefile +++ b/drivers/xen/Makefile @@ -1,5 +1,6 @@ obj-y += grant-table.o features.o events.o manage.o balloon.o obj-y += xenbus/ +obj-y += tmem.o nostackp := $(call cc-option, -fno-stack-protector) CFLAGS_features.o := $(nostackp) diff --git a/drivers/xen/tmem.c b/drivers/xen/tmem.c new file mode 100644 index 000000000000..816a44959ef0 --- /dev/null +++ b/drivers/xen/tmem.c @@ -0,0 +1,264 @@ +/* + * Xen implementation for transcendent memory (tmem) + * + * Copyright (C) 2009-2010 Oracle Corp. All rights reserved. + * Author: Dan Magenheimer + */ + +#include +#include +#include +#include +#include + +#include +#include +#include +#include +#include + +#define TMEM_CONTROL 0 +#define TMEM_NEW_POOL 1 +#define TMEM_DESTROY_POOL 2 +#define TMEM_NEW_PAGE 3 +#define TMEM_PUT_PAGE 4 +#define TMEM_GET_PAGE 5 +#define TMEM_FLUSH_PAGE 6 +#define TMEM_FLUSH_OBJECT 7 +#define TMEM_READ 8 +#define TMEM_WRITE 9 +#define TMEM_XCHG 10 + +/* Bits for HYPERVISOR_tmem_op(TMEM_NEW_POOL) */ +#define TMEM_POOL_PERSIST 1 +#define TMEM_POOL_SHARED 2 +#define TMEM_POOL_PAGESIZE_SHIFT 4 +#define TMEM_VERSION_SHIFT 24 + + +struct tmem_pool_uuid { + u64 uuid_lo; + u64 uuid_hi; +}; + +struct tmem_oid { + u64 oid[3]; +}; + +#define TMEM_POOL_PRIVATE_UUID { 0, 0 } + +/* flags for tmem_ops.new_pool */ +#define TMEM_POOL_PERSIST 1 +#define TMEM_POOL_SHARED 2 + +/* xen tmem foundation ops/hypercalls */ + +static inline int xen_tmem_op(u32 tmem_cmd, u32 tmem_pool, struct tmem_oid oid, + u32 index, unsigned long gmfn, u32 tmem_offset, u32 pfn_offset, u32 len) +{ + struct tmem_op op; + int rc = 0; + + op.cmd = tmem_cmd; + op.pool_id = tmem_pool; + op.u.gen.oid[0] = oid.oid[0]; + op.u.gen.oid[1] = oid.oid[1]; + op.u.gen.oid[2] = oid.oid[2]; + op.u.gen.index = index; + op.u.gen.tmem_offset = tmem_offset; + op.u.gen.pfn_offset = pfn_offset; + op.u.gen.len = len; + set_xen_guest_handle(op.u.gen.gmfn, (void *)gmfn); + rc = HYPERVISOR_tmem_op(&op); + return rc; +} + +static int xen_tmem_new_pool(struct tmem_pool_uuid uuid, + u32 flags, unsigned long pagesize) +{ + struct tmem_op op; + int rc = 0, pageshift; + + for (pageshift = 0; pagesize != 1; pageshift++) + pagesize >>= 1; + flags |= (pageshift - 12) << TMEM_POOL_PAGESIZE_SHIFT; + flags |= TMEM_SPEC_VERSION << TMEM_VERSION_SHIFT; + op.cmd = TMEM_NEW_POOL; + op.u.new.uuid[0] = uuid.uuid_lo; + op.u.new.uuid[1] = uuid.uuid_hi; + op.u.new.flags = flags; + rc = HYPERVISOR_tmem_op(&op); + return rc; +} + +/* xen generic tmem ops */ + +static int xen_tmem_put_page(u32 pool_id, struct tmem_oid oid, + u32 index, unsigned long pfn) +{ + unsigned long gmfn = xen_pv_domain() ? pfn_to_mfn(pfn) : pfn; + + return xen_tmem_op(TMEM_PUT_PAGE, pool_id, oid, index, + gmfn, 0, 0, 0); +} + +static int xen_tmem_get_page(u32 pool_id, struct tmem_oid oid, + u32 index, unsigned long pfn) +{ + unsigned long gmfn = xen_pv_domain() ? pfn_to_mfn(pfn) : pfn; + + return xen_tmem_op(TMEM_GET_PAGE, pool_id, oid, index, + gmfn, 0, 0, 0); +} + +static int xen_tmem_flush_page(u32 pool_id, struct tmem_oid oid, u32 index) +{ + return xen_tmem_op(TMEM_FLUSH_PAGE, pool_id, oid, index, + 0, 0, 0, 0); +} + +static int xen_tmem_flush_object(u32 pool_id, struct tmem_oid oid) +{ + return xen_tmem_op(TMEM_FLUSH_OBJECT, pool_id, oid, 0, 0, 0, 0, 0); +} + +static int xen_tmem_destroy_pool(u32 pool_id) +{ + struct tmem_oid oid = { { 0 } }; + + return xen_tmem_op(TMEM_DESTROY_POOL, pool_id, oid, 0, 0, 0, 0, 0); +} + +int tmem_enabled; + +static int __init enable_tmem(char *s) +{ + tmem_enabled = 1; + return 1; +} + +__setup("tmem", enable_tmem); + +/* cleancache ops */ + +static void tmem_cleancache_put_page(int pool, struct cleancache_filekey key, + pgoff_t index, struct page *page) +{ + u32 ind = (u32) index; + struct tmem_oid oid = *(struct tmem_oid *)&key; + unsigned long pfn = page_to_pfn(page); + + if (pool < 0) + return; + if (ind != index) + return; + mb(); /* ensure page is quiescent; tmem may address it with an alias */ + (void)xen_tmem_put_page((u32)pool, oid, ind, pfn); +} + +static int tmem_cleancache_get_page(int pool, struct cleancache_filekey key, + pgoff_t index, struct page *page) +{ + u32 ind = (u32) index; + struct tmem_oid oid = *(struct tmem_oid *)&key; + unsigned long pfn = page_to_pfn(page); + int ret; + + /* translate return values to linux semantics */ + if (pool < 0) + return -1; + if (ind != index) + return -1; + ret = xen_tmem_get_page((u32)pool, oid, ind, pfn); + if (ret == 1) + return 0; + else + return -1; +} + +static void tmem_cleancache_flush_page(int pool, struct cleancache_filekey key, + pgoff_t index) +{ + u32 ind = (u32) index; + struct tmem_oid oid = *(struct tmem_oid *)&key; + + if (pool < 0) + return; + if (ind != index) + return; + (void)xen_tmem_flush_page((u32)pool, oid, ind); +} + +static void tmem_cleancache_flush_inode(int pool, struct cleancache_filekey key) +{ + struct tmem_oid oid = *(struct tmem_oid *)&key; + + if (pool < 0) + return; + (void)xen_tmem_flush_object((u32)pool, oid); +} + +static void tmem_cleancache_flush_fs(int pool) +{ + if (pool < 0) + return; + (void)xen_tmem_destroy_pool((u32)pool); +} + +static int tmem_cleancache_init_fs(size_t pagesize) +{ + struct tmem_pool_uuid uuid_private = TMEM_POOL_PRIVATE_UUID; + + return xen_tmem_new_pool(uuid_private, 0, pagesize); +} + +static int tmem_cleancache_init_shared_fs(char *uuid, size_t pagesize) +{ + struct tmem_pool_uuid shared_uuid; + + shared_uuid.uuid_lo = *(u64 *)uuid; + shared_uuid.uuid_hi = *(u64 *)(&uuid[8]); + return xen_tmem_new_pool(shared_uuid, TMEM_POOL_SHARED, pagesize); +} + +static int use_cleancache = 1; + +static int __init no_cleancache(char *s) +{ + use_cleancache = 0; + return 1; +} + +__setup("nocleancache", no_cleancache); + +static struct cleancache_ops tmem_cleancache_ops = { + .put_page = tmem_cleancache_put_page, + .get_page = tmem_cleancache_get_page, + .flush_page = tmem_cleancache_flush_page, + .flush_inode = tmem_cleancache_flush_inode, + .flush_fs = tmem_cleancache_flush_fs, + .init_shared_fs = tmem_cleancache_init_shared_fs, + .init_fs = tmem_cleancache_init_fs +}; + +static int __init xen_tmem_init(void) +{ + struct cleancache_ops old_ops; + + if (!xen_domain()) + return 0; +#ifdef CONFIG_CLEANCACHE + BUG_ON(sizeof(struct cleancache_filekey) != sizeof(struct tmem_oid)); + if (tmem_enabled && use_cleancache) { + char *s = ""; + old_ops = cleancache_register_ops(&tmem_cleancache_ops); + if (old_ops.init_fs != NULL) + s = " (WARNING: cleancache_ops overridden)"; + printk(KERN_INFO "cleancache enabled, RAM provided by " + "Xen Transcendent Memory%s\n", s); + } +#endif + return 0; +} + +module_init(xen_tmem_init) 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