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 <dan.magenheimer@oracle.com> Reviewed-by: Jeremy Fitzhardinge <jeremy@goop.org> Reviewed-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Al Viro <viro@ZenIV.linux.org.uk> Cc: Matthew Wilcox <matthew@wil.cx> Cc: Nick Piggin <npiggin@kernel.dk> Cc: Mel Gorman <mel@csn.ul.ie> Cc: Rik Van Riel <riel@redhat.com> Cc: Jan Beulich <JBeulich@novell.com> Cc: Chris Mason <chris.mason@oracle.com> Cc: Andreas Dilger <adilger@sun.com> Cc: Ted Ts'o <tytso@mit.edu> Cc: Mark Fasheh <mfasheh@suse.com> Cc: Joel Becker <joel.becker@oracle.com> Cc: Nitin Gupta <ngupta@vflare.org> --- 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 <dan.magenheimer@oracle.com> Reviewed-by: Jeremy Fitzhardinge <jeremy@goop.org> Reviewed-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> Acked-by: Al Viro <viro@ZenIV.linux.org.uk> Acked-by: Andrew Morton <akpm@linux-foundation.org> Acked-by: Nitin Gupta <ngupta@vflare.org> Acked-by: Minchan Kim <minchan.kim@gmail.com> Acked-by: Andreas Dilger <adilger@sun.com> Acked-by: Jan Beulich <JBeulich@novell.com> Cc: Matthew Wilcox <matthew@wil.cx> Cc: Nick Piggin <npiggin@kernel.dk> Cc: Mel Gorman <mel@csn.ul.ie> Cc: Rik Van Riel <riel@redhat.com> Cc: Chris Mason <chris.mason@oracle.com> Cc: Ted Ts'o <tytso@mit.edu> Cc: Mark Fasheh <mfasheh@suse.com> Cc: Joel Becker <joel.becker@oracle.com> --- 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 (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 <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 +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 <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) -- 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 <dan.magenheimer@oracle.com> Reviewed-by: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> Cc: Matthew Wilcox <matthew@wil.cx> Cc: Nick Piggin <npiggin@kernel.dk> Cc: Mel Gorman <mel@csn.ul.ie> Cc: Rik Van Riel <riel@redhat.com> Cc: Jan Beulich <JBeulich@novell.com> Cc: Chris Mason <chris.mason@oracle.com> Cc: Andreas Dilger <adilger@sun.com> Cc: Ted Ts'o <tytso@mit.edu> Cc: Mark Fasheh <mfasheh@suse.com> Cc: Joel Becker <joel.becker@oracle.com> Cc: Nitin Gupta <ngupta@vflare.org> --- 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 (limited to 'include') 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 <linux/kernel.h> +#include <linux/types.h> +#include <linux/init.h> +#include <linux/pagemap.h> +#include <linux/cleancache.h> + +#include <xen/xen.h> +#include <xen/interface/xen.h> +#include <asm/xen/hypercall.h> +#include <asm/xen/page.h> +#include <asm/xen/hypervisor.h> + +#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