* [PATCH 1/5] mm: cleancache: lazy initialization to allow tmem backends to build/run as modules
2012-10-31 15:07 [PATCH 0/5] enable all tmem backends to be built and loaded as modules Dan Magenheimer
@ 2012-10-31 15:07 ` Dan Magenheimer
2012-11-02 18:29 ` Konrad Rzeszutek Wilk
2012-10-31 15:07 ` [PATCH 2/5] mm: frontswap: " Dan Magenheimer
` (3 subsequent siblings)
4 siblings, 1 reply; 15+ messages in thread
From: Dan Magenheimer @ 2012-10-31 15:07 UTC (permalink / raw)
To: devel, linux-kernel, gregkh, linux-mm, ngupta, konrad.wilk,
sjenning, minchan, dan.magenheimer, fschmaus, andor.damm, ilendir,
akpm, mgorman
With the goal of allowing tmem backends (zcache, ramster, Xen tmem) to be
built/loaded as modules rather than built-in and enabled by a boot parameter,
this patch provides "lazy initialization", allowing backends to register to
cleancache even after filesystems were mounted. Calls to init_fs and
init_shared_fs are remembered as fake poolids but no real tmem_pools created.
On backend registration the fake poolids are mapped to real poolids and
respective tmem_pools.
Signed-off-by: Stefan Hengelein <ilendir@googlemail.com>
Signed-off-by: Florian Schmaus <fschmaus@gmail.com>
Signed-off-by: Andor Daam <andor.daam@googlemail.com>
Signed-off-by: Dan Magenheimer <dan.magenheimer@oracle.com>
---
include/linux/cleancache.h | 1 +
mm/cleancache.c | 157 +++++++++++++++++++++++++++++++++++++++-----
2 files changed, 141 insertions(+), 17 deletions(-)
diff --git a/include/linux/cleancache.h b/include/linux/cleancache.h
index 42e55de..f7e32f0 100644
--- a/include/linux/cleancache.h
+++ b/include/linux/cleancache.h
@@ -37,6 +37,7 @@ 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 *);
+#define CLEANCACHE_HAS_LAZY_INIT
extern int __cleancache_get_page(struct page *);
extern void __cleancache_put_page(struct page *);
extern void __cleancache_invalidate_page(struct address_space *, struct page *);
diff --git a/mm/cleancache.c b/mm/cleancache.c
index 32e6f41..29430b7 100644
--- a/mm/cleancache.c
+++ b/mm/cleancache.c
@@ -45,15 +45,42 @@ static u64 cleancache_puts;
static u64 cleancache_invalidates;
/*
+ * When no backend is registered all calls to init_fs and init_shard_fs
+ * are registered and fake poolids are given to the respective
+ * super block but no tmem_pools are created. When a backend
+ * registers with cleancache the previous calls to init_fs and
+ * init_shared_fs are executed to create tmem_pools and set the
+ * respective poolids. While no backend is registered all "puts",
+ * "gets" and "flushes" are ignored or fail.
+ */
+#define MAX_INITIALIZABLE_FS 32
+#define FAKE_FS_POOLID_OFFSET 1000
+#define FAKE_SHARED_FS_POOLID_OFFSET 2000
+static int fs_poolid_map[MAX_INITIALIZABLE_FS];
+static int shared_fs_poolid_map[MAX_INITIALIZABLE_FS];
+static char *uuids[MAX_INITIALIZABLE_FS];
+static int backend_registered;
+
+/*
* 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;
+ int i;
cleancache_ops = *ops;
- cleancache_enabled = 1;
+
+ backend_registered = 1;
+ for (i = 0; i < MAX_INITIALIZABLE_FS; i++) {
+ if (fs_poolid_map[i] == -1)
+ fs_poolid_map[i] = (*cleancache_ops.init_fs)(PAGE_SIZE);
+ if (shared_fs_poolid_map[i] == -1)
+ shared_fs_poolid_map[i] =
+ (*cleancache_ops.init_shared_fs)
+ (uuids[i], PAGE_SIZE);
+ }
return old;
}
EXPORT_SYMBOL(cleancache_register_ops);
@@ -61,15 +88,42 @@ 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);
+ int i;
+
+ for (i = 0; i < MAX_INITIALIZABLE_FS; i++) {
+ if (fs_poolid_map[i] == -2) {
+ sb->cleancache_poolid =
+ i + FAKE_FS_POOLID_OFFSET;
+ if (backend_registered)
+ fs_poolid_map[i] =
+ (*cleancache_ops.init_fs)(PAGE_SIZE);
+ else
+ fs_poolid_map[i] = -1;
+ break;
+ }
+ }
}
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);
+ int i;
+
+ for (i = 0; i < MAX_INITIALIZABLE_FS; i++) {
+ if (shared_fs_poolid_map[i] == -2) {
+ sb->cleancache_poolid =
+ i + FAKE_SHARED_FS_POOLID_OFFSET;
+ uuids[i] = uuid;
+ if (backend_registered)
+ shared_fs_poolid_map[i] =
+ (*cleancache_ops.init_shared_fs)
+ (uuid, PAGE_SIZE);
+ else
+ shared_fs_poolid_map[i] = -1;
+ break;
+ }
+ }
}
EXPORT_SYMBOL(__cleancache_init_shared_fs);
@@ -99,6 +153,19 @@ static int cleancache_get_key(struct inode *inode,
}
/*
+ * Returns a pool_id that is associated with a given fake poolid.
+ */
+static int get_poolid_from_fake(int fake_pool_id)
+{
+ if (fake_pool_id >= FAKE_SHARED_FS_POOLID_OFFSET)
+ return shared_fs_poolid_map[fake_pool_id -
+ FAKE_SHARED_FS_POOLID_OFFSET];
+ else if (fake_pool_id >= FAKE_FS_POOLID_OFFSET)
+ return fs_poolid_map[fake_pool_id - FAKE_FS_POOLID_OFFSET];
+ return -1;
+}
+
+/*
* "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.
@@ -109,17 +176,26 @@ int __cleancache_get_page(struct page *page)
{
int ret = -1;
int pool_id;
+ int fake_pool_id;
struct cleancache_filekey key = { .u.key = { 0 } };
+ if (!backend_registered) {
+ cleancache_failed_gets++;
+ goto out;
+ }
+
VM_BUG_ON(!PageLocked(page));
- pool_id = page->mapping->host->i_sb->cleancache_poolid;
- if (pool_id < 0)
+ fake_pool_id = page->mapping->host->i_sb->cleancache_poolid;
+ if (fake_pool_id < 0)
goto out;
+ pool_id = get_poolid_from_fake(fake_pool_id);
if (cleancache_get_key(page->mapping->host, &key) < 0)
goto out;
- ret = (*cleancache_ops.get_page)(pool_id, key, page->index, page);
+ if (pool_id >= 0)
+ ret = (*cleancache_ops.get_page)(pool_id,
+ key, page->index, page);
if (ret == 0)
cleancache_succ_gets++;
else
@@ -138,12 +214,23 @@ EXPORT_SYMBOL(__cleancache_get_page);
void __cleancache_put_page(struct page *page)
{
int pool_id;
+ int fake_pool_id;
struct cleancache_filekey key = { .u.key = { 0 } };
+ if (!backend_registered) {
+ cleancache_puts++;
+ return;
+ }
+
VM_BUG_ON(!PageLocked(page));
- pool_id = page->mapping->host->i_sb->cleancache_poolid;
+ fake_pool_id = page->mapping->host->i_sb->cleancache_poolid;
+ if (fake_pool_id < 0)
+ return;
+
+ pool_id = get_poolid_from_fake(fake_pool_id);
+
if (pool_id >= 0 &&
- cleancache_get_key(page->mapping->host, &key) >= 0) {
+ cleancache_get_key(page->mapping->host, &key) >= 0) {
(*cleancache_ops.put_page)(pool_id, key, page->index, page);
cleancache_puts++;
}
@@ -158,14 +245,22 @@ void __cleancache_invalidate_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;
+ int pool_id;
+ int fake_pool_id = mapping->host->i_sb->cleancache_poolid;
struct cleancache_filekey key = { .u.key = { 0 } };
- if (pool_id >= 0) {
+ if (!backend_registered)
+ return;
+
+ if (fake_pool_id >= 0) {
+ pool_id = get_poolid_from_fake(fake_pool_id);
+ if (pool_id < 0)
+ return;
+
VM_BUG_ON(!PageLocked(page));
if (cleancache_get_key(mapping->host, &key) >= 0) {
(*cleancache_ops.invalidate_page)(pool_id,
- key, page->index);
+ key, page->index);
cleancache_invalidates++;
}
}
@@ -179,9 +274,18 @@ EXPORT_SYMBOL(__cleancache_invalidate_page);
*/
void __cleancache_invalidate_inode(struct address_space *mapping)
{
- int pool_id = mapping->host->i_sb->cleancache_poolid;
+ int pool_id;
+ int fake_pool_id = mapping->host->i_sb->cleancache_poolid;
struct cleancache_filekey key = { .u.key = { 0 } };
+ if (!backend_registered)
+ return;
+
+ if (fake_pool_id < 0)
+ return;
+
+ pool_id = get_poolid_from_fake(fake_pool_id);
+
if (pool_id >= 0 && cleancache_get_key(mapping->host, &key) >= 0)
(*cleancache_ops.invalidate_inode)(pool_id, key);
}
@@ -194,16 +298,30 @@ EXPORT_SYMBOL(__cleancache_invalidate_inode);
*/
void __cleancache_invalidate_fs(struct super_block *sb)
{
- if (sb->cleancache_poolid >= 0) {
- int old_poolid = sb->cleancache_poolid;
- sb->cleancache_poolid = -1;
- (*cleancache_ops.invalidate_fs)(old_poolid);
+ int index;
+ int fake_pool_id = sb->cleancache_poolid;
+ int old_poolid = fake_pool_id;
+
+ if (fake_pool_id >= FAKE_SHARED_FS_POOLID_OFFSET) {
+ index = fake_pool_id - FAKE_SHARED_FS_POOLID_OFFSET;
+ old_poolid = shared_fs_poolid_map[index];
+ shared_fs_poolid_map[index] = -2;
+ uuids[index] = NULL;
+ } else if (fake_pool_id >= FAKE_FS_POOLID_OFFSET) {
+ index = fake_pool_id - FAKE_FS_POOLID_OFFSET;
+ old_poolid = fs_poolid_map[index];
+ fs_poolid_map[index] = -2;
}
+ sb->cleancache_poolid = -1;
+ if (backend_registered)
+ (*cleancache_ops.invalidate_fs)(old_poolid);
}
EXPORT_SYMBOL(__cleancache_invalidate_fs);
static int __init init_cleancache(void)
{
+ int i;
+
#ifdef CONFIG_DEBUG_FS
struct dentry *root = debugfs_create_dir("cleancache", NULL);
if (root == NULL)
@@ -215,6 +333,11 @@ static int __init init_cleancache(void)
debugfs_create_u64("invalidates", S_IRUGO,
root, &cleancache_invalidates);
#endif
+ for (i = 0; i < MAX_INITIALIZABLE_FS; i++) {
+ fs_poolid_map[i] = -2;
+ shared_fs_poolid_map[i] = -2;
+ }
+ cleancache_enabled = 1;
return 0;
}
module_init(init_cleancache)
--
1.7.1
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply related [flat|nested] 15+ messages in thread* Re: [PATCH 1/5] mm: cleancache: lazy initialization to allow tmem backends to build/run as modules
2012-10-31 15:07 ` [PATCH 1/5] mm: cleancache: lazy initialization to allow tmem backends to build/run " Dan Magenheimer
@ 2012-11-02 18:29 ` Konrad Rzeszutek Wilk
0 siblings, 0 replies; 15+ messages in thread
From: Konrad Rzeszutek Wilk @ 2012-11-02 18:29 UTC (permalink / raw)
To: Dan Magenheimer
Cc: devel, linux-kernel, gregkh, linux-mm, ngupta, sjenning, minchan,
fschmaus, andor.damm, ilendir, akpm, mgorman
On Wed, Oct 31, 2012 at 08:07:50AM -0700, Dan Magenheimer wrote:
> With the goal of allowing tmem backends (zcache, ramster, Xen tmem) to be
> built/loaded as modules rather than built-in and enabled by a boot parameter,
> this patch provides "lazy initialization", allowing backends to register to
> cleancache even after filesystems were mounted. Calls to init_fs and
> init_shared_fs are remembered as fake poolids but no real tmem_pools created.
> On backend registration the fake poolids are mapped to real poolids and
> respective tmem_pools.
>
> Signed-off-by: Stefan Hengelein <ilendir@googlemail.com>
> Signed-off-by: Florian Schmaus <fschmaus@gmail.com>
> Signed-off-by: Andor Daam <andor.daam@googlemail.com>
> Signed-off-by: Dan Magenheimer <dan.magenheimer@oracle.com>
> ---
> include/linux/cleancache.h | 1 +
> mm/cleancache.c | 157 +++++++++++++++++++++++++++++++++++++++-----
> 2 files changed, 141 insertions(+), 17 deletions(-)
>
> diff --git a/include/linux/cleancache.h b/include/linux/cleancache.h
> index 42e55de..f7e32f0 100644
> --- a/include/linux/cleancache.h
> +++ b/include/linux/cleancache.h
> @@ -37,6 +37,7 @@ 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 *);
> +#define CLEANCACHE_HAS_LAZY_INIT
> extern int __cleancache_get_page(struct page *);
> extern void __cleancache_put_page(struct page *);
> extern void __cleancache_invalidate_page(struct address_space *, struct page *);
> diff --git a/mm/cleancache.c b/mm/cleancache.c
> index 32e6f41..29430b7 100644
> --- a/mm/cleancache.c
> +++ b/mm/cleancache.c
> @@ -45,15 +45,42 @@ static u64 cleancache_puts;
> static u64 cleancache_invalidates;
>
> /*
> + * When no backend is registered all calls to init_fs and init_shard_fs
> + * are registered and fake poolids are given to the respective
> + * super block but no tmem_pools are created. When a backend
> + * registers with cleancache the previous calls to init_fs and
> + * init_shared_fs are executed to create tmem_pools and set the
> + * respective poolids. While no backend is registered all "puts",
> + * "gets" and "flushes" are ignored or fail.
> + */
> +#define MAX_INITIALIZABLE_FS 32
> +#define FAKE_FS_POOLID_OFFSET 1000
> +#define FAKE_SHARED_FS_POOLID_OFFSET 2000
> +static int fs_poolid_map[MAX_INITIALIZABLE_FS];
> +static int shared_fs_poolid_map[MAX_INITIALIZABLE_FS];
> +static char *uuids[MAX_INITIALIZABLE_FS];
> +static int backend_registered;
Those could use some #define's and bool, so please see attached
patch which does this.
^ permalink raw reply [flat|nested] 15+ messages in thread
* [PATCH 2/5] mm: frontswap: lazy initialization to allow tmem backends to build/run as modules
2012-10-31 15:07 [PATCH 0/5] enable all tmem backends to be built and loaded as modules Dan Magenheimer
2012-10-31 15:07 ` [PATCH 1/5] mm: cleancache: lazy initialization to allow tmem backends to build/run " Dan Magenheimer
@ 2012-10-31 15:07 ` Dan Magenheimer
2012-10-31 17:05 ` Seth Jennings
2012-10-31 15:07 ` [PATCH 3/5] staging: zcache2+ramster: enable zcache2 to be built/loaded as a module Dan Magenheimer
` (2 subsequent siblings)
4 siblings, 1 reply; 15+ messages in thread
From: Dan Magenheimer @ 2012-10-31 15:07 UTC (permalink / raw)
To: devel, linux-kernel, gregkh, linux-mm, ngupta, konrad.wilk,
sjenning, minchan, dan.magenheimer, fschmaus, andor.damm, ilendir,
akpm, mgorman
With the goal of allowing tmem backends (zcache, ramster, Xen tmem) to be
built/loaded as modules rather than built-in and enabled by a boot parameter,
this patch provides "lazy initialization", allowing backends to register to
frontswap even after swapon was run. Before a backend registers all calls
to init are recorded and the creation of tmem_pools delayed until a backend
registers or until a frontswap put is attempted.
Signed-off-by: Stefan Hengelein <ilendir@googlemail.com>
Signed-off-by: Florian Schmaus <fschmaus@gmail.com>
Signed-off-by: Andor Daam <andor.daam@googlemail.com>
Signed-off-by: Dan Magenheimer <dan.magenheimer@oracle.com>
---
include/linux/frontswap.h | 1 +
mm/frontswap.c | 70 +++++++++++++++++++++++++++++++++++++++-----
2 files changed, 63 insertions(+), 8 deletions(-)
diff --git a/include/linux/frontswap.h b/include/linux/frontswap.h
index 3044254..ef6ada6 100644
--- a/include/linux/frontswap.h
+++ b/include/linux/frontswap.h
@@ -23,6 +23,7 @@ extern void frontswap_writethrough(bool);
extern void frontswap_tmem_exclusive_gets(bool);
extern void __frontswap_init(unsigned type);
+#define FRONTSWAP_HAS_LAZY_INIT
extern int __frontswap_store(struct page *page);
extern int __frontswap_load(struct page *page);
extern void __frontswap_invalidate_page(unsigned, pgoff_t);
diff --git a/mm/frontswap.c b/mm/frontswap.c
index 2890e67..523a19b 100644
--- a/mm/frontswap.c
+++ b/mm/frontswap.c
@@ -80,6 +80,19 @@ static inline void inc_frontswap_succ_stores(void) { }
static inline void inc_frontswap_failed_stores(void) { }
static inline void inc_frontswap_invalidates(void) { }
#endif
+
+/*
+ * When no backend is registered all calls to init are registered and
+ * remembered but fail to create tmem_pools. When a backend registers with
+ * frontswap the previous calls to init are executed to create tmem_pools
+ * and set the respective poolids.
+ * While no backend is registered all "puts", "gets" and "flushes" are
+ * ignored or fail.
+ */
+#define MAX_INITIALIZABLE_SD 32
+static int sds[MAX_INITIALIZABLE_SD];
+static int backend_registered;
+
/*
* Register operations for frontswap, returning previous thus allowing
* detection of multiple backends and possible nesting.
@@ -87,9 +100,16 @@ static inline void inc_frontswap_invalidates(void) { }
struct frontswap_ops frontswap_register_ops(struct frontswap_ops *ops)
{
struct frontswap_ops old = frontswap_ops;
+ int i;
frontswap_ops = *ops;
frontswap_enabled = true;
+
+ backend_registered = 1;
+ for (i = 0; i < MAX_INITIALIZABLE_SD; i++) {
+ if (sds[i] != -1)
+ (*frontswap_ops.init)(sds[i]);
+ }
return old;
}
EXPORT_SYMBOL(frontswap_register_ops);
@@ -122,7 +142,10 @@ void __frontswap_init(unsigned type)
BUG_ON(sis == NULL);
if (sis->frontswap_map == NULL)
return;
- frontswap_ops.init(type);
+ if (backend_registered) {
+ (*frontswap_ops.init)(type);
+ sds[type] = type;
+ }
}
EXPORT_SYMBOL(__frontswap_init);
@@ -147,10 +170,20 @@ int __frontswap_store(struct page *page)
struct swap_info_struct *sis = swap_info[type];
pgoff_t offset = swp_offset(entry);
+ if (!backend_registered) {
+ inc_frontswap_failed_stores();
+ return ret;
+ }
+
BUG_ON(!PageLocked(page));
BUG_ON(sis == NULL);
if (frontswap_test(sis, offset))
dup = 1;
+ if (type < MAX_INITIALIZABLE_SD && sds[type] == -1) {
+ /* lazy init call to handle post-boot insmod backends*/
+ (*frontswap_ops.init)(type);
+ sds[type] = type;
+ }
ret = frontswap_ops.store(type, offset, page);
if (ret == 0) {
frontswap_set(sis, offset);
@@ -186,6 +219,9 @@ int __frontswap_load(struct page *page)
struct swap_info_struct *sis = swap_info[type];
pgoff_t offset = swp_offset(entry);
+ if (!backend_registered)
+ return ret;
+
BUG_ON(!PageLocked(page));
BUG_ON(sis == NULL);
if (frontswap_test(sis, offset))
@@ -209,6 +245,9 @@ void __frontswap_invalidate_page(unsigned type, pgoff_t offset)
{
struct swap_info_struct *sis = swap_info[type];
+ if (!backend_registered)
+ return;
+
BUG_ON(sis == NULL);
if (frontswap_test(sis, offset)) {
frontswap_ops.invalidate_page(type, offset);
@@ -225,13 +264,23 @@ EXPORT_SYMBOL(__frontswap_invalidate_page);
void __frontswap_invalidate_area(unsigned type)
{
struct swap_info_struct *sis = swap_info[type];
-
- BUG_ON(sis == NULL);
- if (sis->frontswap_map == NULL)
- return;
- frontswap_ops.invalidate_area(type);
- atomic_set(&sis->frontswap_pages, 0);
- memset(sis->frontswap_map, 0, sis->max / sizeof(long));
+ int i;
+
+ if (backend_registered) {
+ BUG_ON(sis == NULL);
+ if (sis->frontswap_map == NULL)
+ return;
+ (*frontswap_ops.invalidate_area)(type);
+ atomic_set(&sis->frontswap_pages, 0);
+ memset(sis->frontswap_map, 0, sis->max / sizeof(long));
+ } else {
+ for (i = 0; i < MAX_INITIALIZABLE_SD; i++) {
+ if (sds[i] == type) {
+ sds[i] = -1;
+ break;
+ }
+ }
+ }
}
EXPORT_SYMBOL(__frontswap_invalidate_area);
@@ -353,6 +402,7 @@ EXPORT_SYMBOL(frontswap_curr_pages);
static int __init init_frontswap(void)
{
+ int i;
#ifdef CONFIG_DEBUG_FS
struct dentry *root = debugfs_create_dir("frontswap", NULL);
if (root == NULL)
@@ -364,6 +414,10 @@ static int __init init_frontswap(void)
debugfs_create_u64("invalidates", S_IRUGO,
root, &frontswap_invalidates);
#endif
+ for (i = 0; i < MAX_INITIALIZABLE_SD; i++)
+ sds[i] = -1;
+
+ frontswap_enabled = 1;
return 0;
}
--
1.7.1
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply related [flat|nested] 15+ messages in thread* Re: [PATCH 2/5] mm: frontswap: lazy initialization to allow tmem backends to build/run as modules
2012-10-31 15:07 ` [PATCH 2/5] mm: frontswap: " Dan Magenheimer
@ 2012-10-31 17:05 ` Seth Jennings
2012-10-31 21:42 ` Cesar Eduardo Barros
` (2 more replies)
0 siblings, 3 replies; 15+ messages in thread
From: Seth Jennings @ 2012-10-31 17:05 UTC (permalink / raw)
To: Dan Magenheimer
Cc: devel, linux-kernel, gregkh, linux-mm, ngupta, konrad.wilk,
minchan, fschmaus, andor.daam, ilendir, akpm, mgorman
On 10/31/2012 10:07 AM, Dan Magenheimer wrote:
> With the goal of allowing tmem backends (zcache, ramster, Xen tmem) to be
> built/loaded as modules rather than built-in and enabled by a boot parameter,
> this patch provides "lazy initialization", allowing backends to register to
> frontswap even after swapon was run. Before a backend registers all calls
> to init are recorded and the creation of tmem_pools delayed until a backend
> registers or until a frontswap put is attempted.
>
> Signed-off-by: Stefan Hengelein <ilendir@googlemail.com>
> Signed-off-by: Florian Schmaus <fschmaus@gmail.com>
> Signed-off-by: Andor Daam <andor.daam@googlemail.com>
> Signed-off-by: Dan Magenheimer <dan.magenheimer@oracle.com>
> ---
> include/linux/frontswap.h | 1 +
> mm/frontswap.c | 70 +++++++++++++++++++++++++++++++++++++++-----
> 2 files changed, 63 insertions(+), 8 deletions(-)
>
> diff --git a/include/linux/frontswap.h b/include/linux/frontswap.h
> index 3044254..ef6ada6 100644
> --- a/include/linux/frontswap.h
> +++ b/include/linux/frontswap.h
> @@ -23,6 +23,7 @@ extern void frontswap_writethrough(bool);
> extern void frontswap_tmem_exclusive_gets(bool);
>
> extern void __frontswap_init(unsigned type);
> +#define FRONTSWAP_HAS_LAZY_INIT
> extern int __frontswap_store(struct page *page);
> extern int __frontswap_load(struct page *page);
> extern void __frontswap_invalidate_page(unsigned, pgoff_t);
> diff --git a/mm/frontswap.c b/mm/frontswap.c
> index 2890e67..523a19b 100644
> --- a/mm/frontswap.c
> +++ b/mm/frontswap.c
> @@ -80,6 +80,19 @@ static inline void inc_frontswap_succ_stores(void) { }
> static inline void inc_frontswap_failed_stores(void) { }
> static inline void inc_frontswap_invalidates(void) { }
> #endif
> +
> +/*
> + * When no backend is registered all calls to init are registered and
> + * remembered but fail to create tmem_pools. When a backend registers with
> + * frontswap the previous calls to init are executed to create tmem_pools
> + * and set the respective poolids.
> + * While no backend is registered all "puts", "gets" and "flushes" are
> + * ignored or fail.
> + */
> +#define MAX_INITIALIZABLE_SD 32
MAX_INITIALIZABLE_SD should just be MAX_SWAPFILES
> +static int sds[MAX_INITIALIZABLE_SD];
Rather than store and array of enabled types indexed by type, why not
an array of booleans indexed by type. Or a bitfield if you really
want to save space.
> +static int backend_registered;
(backend_registered) is equivalent to checking (frontswap_ops != NULL)
right?
> +
> /*
> * Register operations for frontswap, returning previous thus allowing
> * detection of multiple backends and possible nesting.
> @@ -87,9 +100,16 @@ static inline void inc_frontswap_invalidates(void) { }
> struct frontswap_ops frontswap_register_ops(struct frontswap_ops *ops)
> {
> struct frontswap_ops old = frontswap_ops;
> + int i;
>
> frontswap_ops = *ops;
> frontswap_enabled = true;
> +
> + backend_registered = 1;
> + for (i = 0; i < MAX_INITIALIZABLE_SD; i++) {
> + if (sds[i] != -1)
> + (*frontswap_ops.init)(sds[i]);
> + }
> return old;
> }
> EXPORT_SYMBOL(frontswap_register_ops);
> @@ -122,7 +142,10 @@ void __frontswap_init(unsigned type)
> BUG_ON(sis == NULL);
> if (sis->frontswap_map == NULL)
> return;
> - frontswap_ops.init(type);
> + if (backend_registered) {
> + (*frontswap_ops.init)(type);
> + sds[type] = type;
This is weird, storing the type in an array indexed by type. Hence my
suggestion above about an array of booleans or a bitfield.
> + }
> }
> EXPORT_SYMBOL(__frontswap_init);
>
> @@ -147,10 +170,20 @@ int __frontswap_store(struct page *page)
> struct swap_info_struct *sis = swap_info[type];
> pgoff_t offset = swp_offset(entry);
>
> + if (!backend_registered) {
> + inc_frontswap_failed_stores();
> + return ret;
> + }
> +
> BUG_ON(!PageLocked(page));
> BUG_ON(sis == NULL);
> if (frontswap_test(sis, offset))
> dup = 1;
> + if (type < MAX_INITIALIZABLE_SD && sds[type] == -1) {
> + /* lazy init call to handle post-boot insmod backends*/
> + (*frontswap_ops.init)(type);
> + sds[type] = type;
> + }
> ret = frontswap_ops.store(type, offset, page);
> if (ret == 0) {
> frontswap_set(sis, offset);
> @@ -186,6 +219,9 @@ int __frontswap_load(struct page *page)
> struct swap_info_struct *sis = swap_info[type];
> pgoff_t offset = swp_offset(entry);
>
> + if (!backend_registered)
> + return ret;
> +
> BUG_ON(!PageLocked(page));
> BUG_ON(sis == NULL);
> if (frontswap_test(sis, offset))
> @@ -209,6 +245,9 @@ void __frontswap_invalidate_page(unsigned type, pgoff_t offset)
> {
> struct swap_info_struct *sis = swap_info[type];
>
> + if (!backend_registered)
> + return;
> +
> BUG_ON(sis == NULL);
> if (frontswap_test(sis, offset)) {
> frontswap_ops.invalidate_page(type, offset);
> @@ -225,13 +264,23 @@ EXPORT_SYMBOL(__frontswap_invalidate_page);
> void __frontswap_invalidate_area(unsigned type)
> {
> struct swap_info_struct *sis = swap_info[type];
> -
> - BUG_ON(sis == NULL);
> - if (sis->frontswap_map == NULL)
> - return;
> - frontswap_ops.invalidate_area(type);
> - atomic_set(&sis->frontswap_pages, 0);
> - memset(sis->frontswap_map, 0, sis->max / sizeof(long));
> + int i;
> +
> + if (backend_registered) {
> + BUG_ON(sis == NULL);
> + if (sis->frontswap_map == NULL)
> + return;
> + (*frontswap_ops.invalidate_area)(type);
> + atomic_set(&sis->frontswap_pages, 0);
> + memset(sis->frontswap_map, 0, sis->max / sizeof(long));
> + } else {
> + for (i = 0; i < MAX_INITIALIZABLE_SD; i++) {
> + if (sds[i] == type) {
Additional weirdness with sds. It seems this whole for loop could
just be reduced to:
sds[type] = -1;
> + sds[i] = -1;
> + break;
> + }
> + }
> + }
> }
> EXPORT_SYMBOL(__frontswap_invalidate_area);
>
> @@ -353,6 +402,7 @@ EXPORT_SYMBOL(frontswap_curr_pages);
>
> static int __init init_frontswap(void)
> {
> + int i;
> #ifdef CONFIG_DEBUG_FS
> struct dentry *root = debugfs_create_dir("frontswap", NULL);
> if (root == NULL)
> @@ -364,6 +414,10 @@ static int __init init_frontswap(void)
> debugfs_create_u64("invalidates", S_IRUGO,
> root, &frontswap_invalidates);
> #endif
> + for (i = 0; i < MAX_INITIALIZABLE_SD; i++)
> + sds[i] = -1;
> +
> + frontswap_enabled = 1;
If frontswap_enabled is going to be on all the time, then what point
does it serve? By extension, can all of the static inline wrappers in
frontswap.h be done away with?
--
Seth
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply [flat|nested] 15+ messages in thread* Re: [PATCH 2/5] mm: frontswap: lazy initialization to allow tmem backends to build/run as modules
2012-10-31 17:05 ` Seth Jennings
@ 2012-10-31 21:42 ` Cesar Eduardo Barros
2012-11-01 15:30 ` Dan Magenheimer
2012-11-02 18:27 ` Konrad Rzeszutek Wilk
2 siblings, 0 replies; 15+ messages in thread
From: Cesar Eduardo Barros @ 2012-10-31 21:42 UTC (permalink / raw)
To: Seth Jennings
Cc: Dan Magenheimer, devel, linux-kernel, gregkh, linux-mm, ngupta,
konrad.wilk, minchan, fschmaus, andor.daam, ilendir, akpm,
mgorman
Em 31-10-2012 15:05, Seth Jennings escreveu:
> On 10/31/2012 10:07 AM, Dan Magenheimer wrote:
>> +#define MAX_INITIALIZABLE_SD 32
>
> MAX_INITIALIZABLE_SD should just be MAX_SWAPFILES
>
>> +static int sds[MAX_INITIALIZABLE_SD];
>
> Rather than store and array of enabled types indexed by type, why not
> an array of booleans indexed by type. Or a bitfield if you really
> want to save space.
Since it is indexed by swap_info_struct's type, and frontswap already
pokes directly inside the swap_info_structs, it would be even cleaner to
use a boolean field within the swap_info_struct.
And if you are using a field within the swap_info_struct, you could
overload the already existing frontswap_map field, which should only
have any use if you have a frontswap module already loaded. That is,
move the vzalloc of the frontswap_map to within frontswap's init
function, and call it outside the swapfile_lock/swapon_mutex. This also
has the advantage of not allocating the frontswap_map when it is not
going to be used.
--
Cesar Eduardo Barros
cesarb@cesarb.net
cesar.barros@gmail.com
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply [flat|nested] 15+ messages in thread
* RE: [PATCH 2/5] mm: frontswap: lazy initialization to allow tmem backends to build/run as modules
2012-10-31 17:05 ` Seth Jennings
2012-10-31 21:42 ` Cesar Eduardo Barros
@ 2012-11-01 15:30 ` Dan Magenheimer
2012-11-02 18:24 ` Konrad Rzeszutek Wilk
2012-11-02 18:27 ` Konrad Rzeszutek Wilk
2 siblings, 1 reply; 15+ messages in thread
From: Dan Magenheimer @ 2012-11-01 15:30 UTC (permalink / raw)
To: Seth Jennings
Cc: devel, linux-kernel, gregkh, linux-mm, ngupta, Konrad Wilk,
minchan, fschmaus, andor.daam, ilendir, akpm, mgorman
> From: Seth Jennings [mailto:sjenning@linux.vnet.ibm.com]
> Subject: Re: [PATCH 2/5] mm: frontswap: lazy initialization to allow tmem backends to build/run as
> modules
>
> > static int __init init_frontswap(void)
> > {
> > + int i;
> > #ifdef CONFIG_DEBUG_FS
> > struct dentry *root = debugfs_create_dir("frontswap", NULL);
> > if (root == NULL)
> > @@ -364,6 +414,10 @@ static int __init init_frontswap(void)
> > debugfs_create_u64("invalidates", S_IRUGO,
> > root, &frontswap_invalidates);
> > #endif
> > + for (i = 0; i < MAX_INITIALIZABLE_SD; i++)
> > + sds[i] = -1;
> > +
> > + frontswap_enabled = 1;
>
> If frontswap_enabled is going to be on all the time, then what point
> does it serve? By extension, can all of the static inline wrappers in
> frontswap.h be done away with?
The intent of frontswap_enabled and cleancache_enabled was
to avoid the overhead of a function call at the point where
each frontswap/cleancache "hooks" is placed, using a global
variable check instead. I'm not sure if this minor
performance tuning effort is worth preserving: If not,
I agree frontswap_enabled and the static inline wrappers (as
well as their cleancache brethren) could be done away with **;
if worth preserving, then I think frontswap_enabled could
be set in the init method instead but the check for enabled
in the frontswap init method and the cleancache init_fs
method would need to be removed else lazy initialization
wouldn't work.
Dan
** Note to anyone that tries this: There is a subtle but
clever hack in the wrappers suggested by Jeremy Fitzhardinge
that disables the wrappers at compile-time as well as
runtime. IOW, make sure you test-compile both with
CONFIG_{CLEANCACHE|FRONTSWAP} _and_ with them unconfig'd.
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply [flat|nested] 15+ messages in thread* Re: [PATCH 2/5] mm: frontswap: lazy initialization to allow tmem backends to build/run as modules
2012-11-01 15:30 ` Dan Magenheimer
@ 2012-11-02 18:24 ` Konrad Rzeszutek Wilk
0 siblings, 0 replies; 15+ messages in thread
From: Konrad Rzeszutek Wilk @ 2012-11-02 18:24 UTC (permalink / raw)
To: Dan Magenheimer
Cc: Seth Jennings, devel, linux-kernel, gregkh, linux-mm, ngupta,
minchan, fschmaus, andor.daam, ilendir, akpm, mgorman
> > > + frontswap_enabled = 1;
> >
> > If frontswap_enabled is going to be on all the time, then what point
> > does it serve? By extension, can all of the static inline wrappers in
> > frontswap.h be done away with?
Hm, or the frontswap_enabled can be converted to a "frontswap_flag"
which has:
#define FRONTSWAP_ON (1<<1)
#define FRONTSWAP_BACKEND_ON (1<<2)
or so? And then we can see if we can squash the 'backend_registerd'
and 'frontswap_enabled' together.
>
> The intent of frontswap_enabled and cleancache_enabled was
> to avoid the overhead of a function call at the point where
> each frontswap/cleancache "hooks" is placed, using a global
> variable check instead. I'm not sure if this minor
> performance tuning effort is worth preserving: If not,
> I agree frontswap_enabled and the static inline wrappers (as
> well as their cleancache brethren) could be done away with **;
> if worth preserving, then I think frontswap_enabled could
> be set in the init method instead but the check for enabled
> in the frontswap init method and the cleancache init_fs
> method would need to be removed else lazy initialization
> wouldn't work.
Either way, that should be a seperate patch.
>
> Dan
>
> ** Note to anyone that tries this: There is a subtle but
> clever hack in the wrappers suggested by Jeremy Fitzhardinge
> that disables the wrappers at compile-time as well as
> runtime. IOW, make sure you test-compile both with
> CONFIG_{CLEANCACHE|FRONTSWAP} _and_ with them unconfig'd.
>
> --
> To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at http://vger.kernel.org/majordomo-info.html
> Please read the FAQ at http://www.tux.org/lkml/
>
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply [flat|nested] 15+ messages in thread
* Re: [PATCH 2/5] mm: frontswap: lazy initialization to allow tmem backends to build/run as modules
2012-10-31 17:05 ` Seth Jennings
2012-10-31 21:42 ` Cesar Eduardo Barros
2012-11-01 15:30 ` Dan Magenheimer
@ 2012-11-02 18:27 ` Konrad Rzeszutek Wilk
2012-11-03 1:21 ` Bob Liu
2 siblings, 1 reply; 15+ messages in thread
From: Konrad Rzeszutek Wilk @ 2012-11-02 18:27 UTC (permalink / raw)
To: Seth Jennings
Cc: Dan Magenheimer, devel, linux-kernel, gregkh, linux-mm, ngupta,
minchan, fschmaus, andor.daam, ilendir, akpm, mgorman
On Wed, Oct 31, 2012 at 12:05:32PM -0500, Seth Jennings wrote:
> On 10/31/2012 10:07 AM, Dan Magenheimer wrote:
> > With the goal of allowing tmem backends (zcache, ramster, Xen tmem) to be
> > built/loaded as modules rather than built-in and enabled by a boot parameter,
> > this patch provides "lazy initialization", allowing backends to register to
> > frontswap even after swapon was run. Before a backend registers all calls
> > to init are recorded and the creation of tmem_pools delayed until a backend
> > registers or until a frontswap put is attempted.
> >
> > Signed-off-by: Stefan Hengelein <ilendir@googlemail.com>
> > Signed-off-by: Florian Schmaus <fschmaus@gmail.com>
> > Signed-off-by: Andor Daam <andor.daam@googlemail.com>
> > Signed-off-by: Dan Magenheimer <dan.magenheimer@oracle.com>
> > ---
> > include/linux/frontswap.h | 1 +
> > mm/frontswap.c | 70 +++++++++++++++++++++++++++++++++++++++-----
> > 2 files changed, 63 insertions(+), 8 deletions(-)
> >
> > diff --git a/include/linux/frontswap.h b/include/linux/frontswap.h
> > index 3044254..ef6ada6 100644
> > --- a/include/linux/frontswap.h
> > +++ b/include/linux/frontswap.h
> > @@ -23,6 +23,7 @@ extern void frontswap_writethrough(bool);
> > extern void frontswap_tmem_exclusive_gets(bool);
> >
> > extern void __frontswap_init(unsigned type);
> > +#define FRONTSWAP_HAS_LAZY_INIT
> > extern int __frontswap_store(struct page *page);
> > extern int __frontswap_load(struct page *page);
> > extern void __frontswap_invalidate_page(unsigned, pgoff_t);
> > diff --git a/mm/frontswap.c b/mm/frontswap.c
> > index 2890e67..523a19b 100644
> > --- a/mm/frontswap.c
> > +++ b/mm/frontswap.c
> > @@ -80,6 +80,19 @@ static inline void inc_frontswap_succ_stores(void) { }
> > static inline void inc_frontswap_failed_stores(void) { }
> > static inline void inc_frontswap_invalidates(void) { }
> > #endif
> > +
> > +/*
> > + * When no backend is registered all calls to init are registered and
> > + * remembered but fail to create tmem_pools. When a backend registers with
> > + * frontswap the previous calls to init are executed to create tmem_pools
> > + * and set the respective poolids.
> > + * While no backend is registered all "puts", "gets" and "flushes" are
> > + * ignored or fail.
> > + */
> > +#define MAX_INITIALIZABLE_SD 32
>
> MAX_INITIALIZABLE_SD should just be MAX_SWAPFILES
>
> > +static int sds[MAX_INITIALIZABLE_SD];
>
> Rather than store and array of enabled types indexed by type, why not
> an array of booleans indexed by type. Or a bitfield if you really
> want to save space.
>
> > +static int backend_registered;
>
> (backend_registered) is equivalent to checking (frontswap_ops != NULL)
> right?
>
> > +
> > /*
> > * Register operations for frontswap, returning previous thus allowing
> > * detection of multiple backends and possible nesting.
> > @@ -87,9 +100,16 @@ static inline void inc_frontswap_invalidates(void) { }
> > struct frontswap_ops frontswap_register_ops(struct frontswap_ops *ops)
> > {
> > struct frontswap_ops old = frontswap_ops;
> > + int i;
> >
> > frontswap_ops = *ops;
> > frontswap_enabled = true;
> > +
> > + backend_registered = 1;
> > + for (i = 0; i < MAX_INITIALIZABLE_SD; i++) {
> > + if (sds[i] != -1)
> > + (*frontswap_ops.init)(sds[i]);
> > + }
> > return old;
> > }
> > EXPORT_SYMBOL(frontswap_register_ops);
> > @@ -122,7 +142,10 @@ void __frontswap_init(unsigned type)
> > BUG_ON(sis == NULL);
> > if (sis->frontswap_map == NULL)
> > return;
> > - frontswap_ops.init(type);
> > + if (backend_registered) {
> > + (*frontswap_ops.init)(type);
> > + sds[type] = type;
>
> This is weird, storing the type in an array indexed by type. Hence my
> suggestion above about an array of booleans or a bitfield.
>
> > + }
> > }
> > EXPORT_SYMBOL(__frontswap_init);
> >
> > @@ -147,10 +170,20 @@ int __frontswap_store(struct page *page)
> > struct swap_info_struct *sis = swap_info[type];
> > pgoff_t offset = swp_offset(entry);
> >
> > + if (!backend_registered) {
> > + inc_frontswap_failed_stores();
> > + return ret;
> > + }
> > +
> > BUG_ON(!PageLocked(page));
> > BUG_ON(sis == NULL);
> > if (frontswap_test(sis, offset))
> > dup = 1;
> > + if (type < MAX_INITIALIZABLE_SD && sds[type] == -1) {
> > + /* lazy init call to handle post-boot insmod backends*/
> > + (*frontswap_ops.init)(type);
> > + sds[type] = type;
> > + }
> > ret = frontswap_ops.store(type, offset, page);
> > if (ret == 0) {
> > frontswap_set(sis, offset);
> > @@ -186,6 +219,9 @@ int __frontswap_load(struct page *page)
> > struct swap_info_struct *sis = swap_info[type];
> > pgoff_t offset = swp_offset(entry);
> >
> > + if (!backend_registered)
> > + return ret;
> > +
> > BUG_ON(!PageLocked(page));
> > BUG_ON(sis == NULL);
> > if (frontswap_test(sis, offset))
> > @@ -209,6 +245,9 @@ void __frontswap_invalidate_page(unsigned type, pgoff_t offset)
> > {
> > struct swap_info_struct *sis = swap_info[type];
> >
> > + if (!backend_registered)
> > + return;
> > +
> > BUG_ON(sis == NULL);
> > if (frontswap_test(sis, offset)) {
> > frontswap_ops.invalidate_page(type, offset);
> > @@ -225,13 +264,23 @@ EXPORT_SYMBOL(__frontswap_invalidate_page);
> > void __frontswap_invalidate_area(unsigned type)
> > {
> > struct swap_info_struct *sis = swap_info[type];
> > -
> > - BUG_ON(sis == NULL);
> > - if (sis->frontswap_map == NULL)
> > - return;
> > - frontswap_ops.invalidate_area(type);
> > - atomic_set(&sis->frontswap_pages, 0);
> > - memset(sis->frontswap_map, 0, sis->max / sizeof(long));
> > + int i;
> > +
> > + if (backend_registered) {
> > + BUG_ON(sis == NULL);
> > + if (sis->frontswap_map == NULL)
> > + return;
> > + (*frontswap_ops.invalidate_area)(type);
> > + atomic_set(&sis->frontswap_pages, 0);
> > + memset(sis->frontswap_map, 0, sis->max / sizeof(long));
> > + } else {
> > + for (i = 0; i < MAX_INITIALIZABLE_SD; i++) {
> > + if (sds[i] == type) {
>
> Additional weirdness with sds. It seems this whole for loop could
> just be reduced to:
>
> sds[type] = -1;
How does this look? (I hadn't actually tested it, but did compile test
it)
^ permalink raw reply [flat|nested] 15+ messages in thread* Re: [PATCH 2/5] mm: frontswap: lazy initialization to allow tmem backends to build/run as modules
2012-11-02 18:27 ` Konrad Rzeszutek Wilk
@ 2012-11-03 1:21 ` Bob Liu
2012-11-14 16:25 ` Konrad Rzeszutek Wilk
0 siblings, 1 reply; 15+ messages in thread
From: Bob Liu @ 2012-11-03 1:21 UTC (permalink / raw)
To: Konrad Rzeszutek Wilk
Cc: Seth Jennings, Dan Magenheimer, devel, linux-kernel, gregkh,
linux-mm, ngupta, minchan, fschmaus, andor.daam, ilendir, akpm,
mgorman
On Sat, Nov 3, 2012 at 2:27 AM, Konrad Rzeszutek Wilk
<konrad.wilk@oracle.com> wrote:
> On Wed, Oct 31, 2012 at 12:05:32PM -0500, Seth Jennings wrote:
>> On 10/31/2012 10:07 AM, Dan Magenheimer wrote:
>> > With the goal of allowing tmem backends (zcache, ramster, Xen tmem) to be
>> > built/loaded as modules rather than built-in and enabled by a boot parameter,
>> > this patch provides "lazy initialization", allowing backends to register to
>> > frontswap even after swapon was run. Before a backend registers all calls
>> > to init are recorded and the creation of tmem_pools delayed until a backend
>> > registers or until a frontswap put is attempted.
>> >
>> > Signed-off-by: Stefan Hengelein <ilendir@googlemail.com>
>> > Signed-off-by: Florian Schmaus <fschmaus@gmail.com>
>> > Signed-off-by: Andor Daam <andor.daam@googlemail.com>
>> > Signed-off-by: Dan Magenheimer <dan.magenheimer@oracle.com>
>> > ---
>> > include/linux/frontswap.h | 1 +
>> > mm/frontswap.c | 70 +++++++++++++++++++++++++++++++++++++++-----
>> > 2 files changed, 63 insertions(+), 8 deletions(-)
>> >
>> > diff --git a/include/linux/frontswap.h b/include/linux/frontswap.h
>> > index 3044254..ef6ada6 100644
>> > --- a/include/linux/frontswap.h
>> > +++ b/include/linux/frontswap.h
>> > @@ -23,6 +23,7 @@ extern void frontswap_writethrough(bool);
>> > extern void frontswap_tmem_exclusive_gets(bool);
>> >
>> > extern void __frontswap_init(unsigned type);
>> > +#define FRONTSWAP_HAS_LAZY_INIT
>> > extern int __frontswap_store(struct page *page);
>> > extern int __frontswap_load(struct page *page);
>> > extern void __frontswap_invalidate_page(unsigned, pgoff_t);
>> > diff --git a/mm/frontswap.c b/mm/frontswap.c
>> > index 2890e67..523a19b 100644
>> > --- a/mm/frontswap.c
>> > +++ b/mm/frontswap.c
>> > @@ -80,6 +80,19 @@ static inline void inc_frontswap_succ_stores(void) { }
>> > static inline void inc_frontswap_failed_stores(void) { }
>> > static inline void inc_frontswap_invalidates(void) { }
>> > #endif
>> > +
>> > +/*
>> > + * When no backend is registered all calls to init are registered and
>> > + * remembered but fail to create tmem_pools. When a backend registers with
>> > + * frontswap the previous calls to init are executed to create tmem_pools
>> > + * and set the respective poolids.
>> > + * While no backend is registered all "puts", "gets" and "flushes" are
>> > + * ignored or fail.
>> > + */
>> > +#define MAX_INITIALIZABLE_SD 32
>>
>> MAX_INITIALIZABLE_SD should just be MAX_SWAPFILES
>>
>> > +static int sds[MAX_INITIALIZABLE_SD];
>>
>> Rather than store and array of enabled types indexed by type, why not
>> an array of booleans indexed by type. Or a bitfield if you really
>> want to save space.
>>
>> > +static int backend_registered;
>>
>> (backend_registered) is equivalent to checking (frontswap_ops != NULL)
>> right?
>>
>> > +
>> > /*
>> > * Register operations for frontswap, returning previous thus allowing
>> > * detection of multiple backends and possible nesting.
>> > @@ -87,9 +100,16 @@ static inline void inc_frontswap_invalidates(void) { }
>> > struct frontswap_ops frontswap_register_ops(struct frontswap_ops *ops)
>> > {
>> > struct frontswap_ops old = frontswap_ops;
>> > + int i;
>> >
>> > frontswap_ops = *ops;
>> > frontswap_enabled = true;
>> > +
>> > + backend_registered = 1;
>> > + for (i = 0; i < MAX_INITIALIZABLE_SD; i++) {
>> > + if (sds[i] != -1)
>> > + (*frontswap_ops.init)(sds[i]);
>> > + }
>> > return old;
>> > }
>> > EXPORT_SYMBOL(frontswap_register_ops);
>> > @@ -122,7 +142,10 @@ void __frontswap_init(unsigned type)
>> > BUG_ON(sis == NULL);
>> > if (sis->frontswap_map == NULL)
>> > return;
>> > - frontswap_ops.init(type);
>> > + if (backend_registered) {
>> > + (*frontswap_ops.init)(type);
>> > + sds[type] = type;
>>
>> This is weird, storing the type in an array indexed by type. Hence my
>> suggestion above about an array of booleans or a bitfield.
>>
>> > + }
>> > }
>> > EXPORT_SYMBOL(__frontswap_init);
>> >
>> > @@ -147,10 +170,20 @@ int __frontswap_store(struct page *page)
>> > struct swap_info_struct *sis = swap_info[type];
>> > pgoff_t offset = swp_offset(entry);
>> >
>> > + if (!backend_registered) {
>> > + inc_frontswap_failed_stores();
>> > + return ret;
>> > + }
>> > +
>> > BUG_ON(!PageLocked(page));
>> > BUG_ON(sis == NULL);
>> > if (frontswap_test(sis, offset))
>> > dup = 1;
>> > + if (type < MAX_INITIALIZABLE_SD && sds[type] == -1) {
>> > + /* lazy init call to handle post-boot insmod backends*/
>> > + (*frontswap_ops.init)(type);
>> > + sds[type] = type;
>> > + }
>> > ret = frontswap_ops.store(type, offset, page);
>> > if (ret == 0) {
>> > frontswap_set(sis, offset);
>> > @@ -186,6 +219,9 @@ int __frontswap_load(struct page *page)
>> > struct swap_info_struct *sis = swap_info[type];
>> > pgoff_t offset = swp_offset(entry);
>> >
>> > + if (!backend_registered)
>> > + return ret;
>> > +
>> > BUG_ON(!PageLocked(page));
>> > BUG_ON(sis == NULL);
>> > if (frontswap_test(sis, offset))
>> > @@ -209,6 +245,9 @@ void __frontswap_invalidate_page(unsigned type, pgoff_t offset)
>> > {
>> > struct swap_info_struct *sis = swap_info[type];
>> >
>> > + if (!backend_registered)
>> > + return;
>> > +
>> > BUG_ON(sis == NULL);
>> > if (frontswap_test(sis, offset)) {
>> > frontswap_ops.invalidate_page(type, offset);
>> > @@ -225,13 +264,23 @@ EXPORT_SYMBOL(__frontswap_invalidate_page);
>> > void __frontswap_invalidate_area(unsigned type)
>> > {
>> > struct swap_info_struct *sis = swap_info[type];
>> > -
>> > - BUG_ON(sis == NULL);
>> > - if (sis->frontswap_map == NULL)
>> > - return;
>> > - frontswap_ops.invalidate_area(type);
>> > - atomic_set(&sis->frontswap_pages, 0);
>> > - memset(sis->frontswap_map, 0, sis->max / sizeof(long));
>> > + int i;
>> > +
>> > + if (backend_registered) {
>> > + BUG_ON(sis == NULL);
>> > + if (sis->frontswap_map == NULL)
>> > + return;
>> > + (*frontswap_ops.invalidate_area)(type);
>> > + atomic_set(&sis->frontswap_pages, 0);
>> > + memset(sis->frontswap_map, 0, sis->max / sizeof(long));
>> > + } else {
>> > + for (i = 0; i < MAX_INITIALIZABLE_SD; i++) {
>> > + if (sds[i] == type) {
>>
>> Additional weirdness with sds. It seems this whole for loop could
>> just be reduced to:
>>
>> sds[type] = -1;
>
>
> How does this look? (I hadn't actually tested it, but did compile test
> it)
>
> From f545530e9ef2b0623ab9e78d490595e3b7eaa3fa Mon Sep 17 00:00:00 2001
> From: Dan Magenheimer <dan.magenheimer@oracle.com>
> Date: Wed, 31 Oct 2012 08:07:51 -0700
> Subject: [PATCH 2/2] mm: frontswap: lazy initialization to allow tmem
> backends to build/run as modules
>
> With the goal of allowing tmem backends (zcache, ramster, Xen tmem) to be
> built/loaded as modules rather than built-in and enabled by a boot parameter,
> this patch provides "lazy initialization", allowing backends to register to
> frontswap even after swapon was run. Before a backend registers all calls
> to init are recorded and the creation of tmem_pools delayed until a backend
> registers or until a frontswap put is attempted.
>
> Signed-off-by: Stefan Hengelein <ilendir@googlemail.com>
> Signed-off-by: Florian Schmaus <fschmaus@gmail.com>
> Signed-off-by: Andor Daam <andor.daam@googlemail.com>
> Signed-off-by: Dan Magenheimer <dan.magenheimer@oracle.com>
> [v1: Fixes per Seth Jennings suggestions]
> Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
> ---
> include/linux/frontswap.h | 1 +
> mm/frontswap.c | 59 +++++++++++++++++++++++++++++++++++++++++------
> 2 files changed, 53 insertions(+), 7 deletions(-)
>
> diff --git a/include/linux/frontswap.h b/include/linux/frontswap.h
> index 3044254..ef6ada6 100644
> --- a/include/linux/frontswap.h
> +++ b/include/linux/frontswap.h
> @@ -23,6 +23,7 @@ extern void frontswap_writethrough(bool);
> extern void frontswap_tmem_exclusive_gets(bool);
>
> extern void __frontswap_init(unsigned type);
> +#define FRONTSWAP_HAS_LAZY_INIT
> extern int __frontswap_store(struct page *page);
> extern int __frontswap_load(struct page *page);
> extern void __frontswap_invalidate_page(unsigned, pgoff_t);
> diff --git a/mm/frontswap.c b/mm/frontswap.c
> index 2890e67..4e04549 100644
> --- a/mm/frontswap.c
> +++ b/mm/frontswap.c
> @@ -80,6 +80,18 @@ static inline void inc_frontswap_succ_stores(void) { }
> static inline void inc_frontswap_failed_stores(void) { }
> static inline void inc_frontswap_invalidates(void) { }
> #endif
> +
> +/*
> + * When no backend is registered all calls to init are registered and
> + * remembered but fail to create tmem_pools. When a backend registers with
> + * frontswap the previous calls to init are executed to create tmem_pools
> + * and set the respective poolids.
> + * While no backend is registered all "puts", "gets" and "flushes" are
> + * ignored or fail.
> + */
> +static DECLARE_BITMAP(sds, MAX_SWAPFILES);
> +static bool backend_registered __read_mostly;
> +
Yes, i also prefer to use bitmap and resue MAX_SWAPFILES.
> /*
> * Register operations for frontswap, returning previous thus allowing
> * detection of multiple backends and possible nesting.
> @@ -87,9 +99,16 @@ static inline void inc_frontswap_invalidates(void) { }
> struct frontswap_ops frontswap_register_ops(struct frontswap_ops *ops)
> {
> struct frontswap_ops old = frontswap_ops;
> + int i;
>
> frontswap_ops = *ops;
> frontswap_enabled = true;
> +
> + backend_registered = true;
> + for (i = 0; i < MAX_SWAPFILES; i++) {
> + if (test_bit(i, sds))
> + (*frontswap_ops.init)(sds[i]);
> + }
> return old;
> }
> EXPORT_SYMBOL(frontswap_register_ops);
> @@ -122,7 +141,10 @@ void __frontswap_init(unsigned type)
> BUG_ON(sis == NULL);
> if (sis->frontswap_map == NULL)
> return;
> - frontswap_ops.init(type);
> + if (backend_registered) {
> + (*frontswap_ops.init)(type);
> + set_bit(type, sds);
> + }
> }
What about set bit if backend not registered and clear bit when invalidate.
I think that looks more directly.
Like:
+ if (backend_registered) {
+ BUG_ON(sis == NULL);
+ if (sis->frontswap_map == NULL)
+ return;
+ frontswap_ops.init(type);
+ }
+ else {
+ BUG_ON(type > MAX_SWAPFILES);
+ set_bit(type, sds);
+ }
> EXPORT_SYMBOL(__frontswap_init);
>
> @@ -147,10 +169,20 @@ int __frontswap_store(struct page *page)
> struct swap_info_struct *sis = swap_info[type];
> pgoff_t offset = swp_offset(entry);
>
> + if (!backend_registered) {
> + inc_frontswap_failed_stores();
> + return ret;
> + }
> +
> BUG_ON(!PageLocked(page));
> BUG_ON(sis == NULL);
> if (frontswap_test(sis, offset))
> dup = 1;
> + if (type < MAX_SWAPFILES && !test_bit(type, sds)) {
> + /* lazy init call to handle post-boot insmod backends*/
> + (*frontswap_ops.init)(type);
> + set_bit(type, sds);
> + }
Then rm this.
> ret = frontswap_ops.store(type, offset, page);
> if (ret == 0) {
> frontswap_set(sis, offset);
> @@ -186,6 +218,9 @@ int __frontswap_load(struct page *page)
> struct swap_info_struct *sis = swap_info[type];
> pgoff_t offset = swp_offset(entry);
>
> + if (!backend_registered)
> + return ret;
> +
> BUG_ON(!PageLocked(page));
> BUG_ON(sis == NULL);
> if (frontswap_test(sis, offset))
> @@ -209,6 +244,9 @@ void __frontswap_invalidate_page(unsigned type, pgoff_t offset)
> {
> struct swap_info_struct *sis = swap_info[type];
>
> + if (!backend_registered)
> + return;
> +
I'm not sure whether __frontswap_invalidate_page() will be called if
backend not registered.
> BUG_ON(sis == NULL);
> if (frontswap_test(sis, offset)) {
> frontswap_ops.invalidate_page(type, offset);
> @@ -226,12 +264,16 @@ void __frontswap_invalidate_area(unsigned type)
> {
> struct swap_info_struct *sis = swap_info[type];
>
> - BUG_ON(sis == NULL);
> - if (sis->frontswap_map == NULL)
> - return;
> - frontswap_ops.invalidate_area(type);
> - atomic_set(&sis->frontswap_pages, 0);
> - memset(sis->frontswap_map, 0, sis->max / sizeof(long));
> + if (backend_registered) {
> + BUG_ON(sis == NULL);
> + if (sis->frontswap_map == NULL)
> + return;
> + (*frontswap_ops.invalidate_area)(type);
> + atomic_set(&sis->frontswap_pages, 0);
> + memset(sis->frontswap_map, 0, sis->max / sizeof(long));
> + } else {
> + bitmap_zero(sds, MAX_SWAPFILES);
Use clear_bit(type, sds) here;
> + }
> }
> EXPORT_SYMBOL(__frontswap_invalidate_area);
>
> @@ -364,6 +406,9 @@ static int __init init_frontswap(void)
> debugfs_create_u64("invalidates", S_IRUGO,
> root, &frontswap_invalidates);
> #endif
> + bitmap_zero(sds, MAX_SWAPFILES);
> +
> + frontswap_enabled = 1;
We'd better init backend_registered = false also.
> return 0;
> }
>
> --
> 1.7.11.7
>
> --
> To unsubscribe, send a message with 'unsubscribe linux-mm' in
> the body to majordomo@kvack.org. For more info on Linux MM,
> see: http://www.linux-mm.org/ .
> Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
--
Thanks,
--Bob
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply [flat|nested] 15+ messages in thread* Re: [PATCH 2/5] mm: frontswap: lazy initialization to allow tmem backends to build/run as modules
2012-11-03 1:21 ` Bob Liu
@ 2012-11-14 16:25 ` Konrad Rzeszutek Wilk
0 siblings, 0 replies; 15+ messages in thread
From: Konrad Rzeszutek Wilk @ 2012-11-14 16:25 UTC (permalink / raw)
To: Bob Liu
Cc: Seth Jennings, Dan Magenheimer, devel, linux-kernel, gregkh,
linux-mm, ngupta, minchan, fschmaus, andor.daam, ilendir, akpm,
mgorman
> On Sat, Nov 3, 2012 at 2:27 AM, Konrad Rzeszutek Wilk
> <konrad.wilk@oracle.com> wrote:
> > On Wed, Oct 31, 2012 at 12:05:32PM -0500, Seth Jennings wrote:
> >> On 10/31/2012 10:07 AM, Dan Magenheimer wrote:
> >> > With the goal of allowing tmem backends (zcache, ramster, Xen tmem) to be
> >> > built/loaded as modules rather than built-in and enabled by a boot parameter,
> >> > this patch provides "lazy initialization", allowing backends to register to
> >> > frontswap even after swapon was run. Before a backend registers all calls
> >> > to init are recorded and the creation of tmem_pools delayed until a backend
> >> > registers or until a frontswap put is attempted.
> >> >
> >> > Signed-off-by: Stefan Hengelein <ilendir@googlemail.com>
> >> > Signed-off-by: Florian Schmaus <fschmaus@gmail.com>
> >> > Signed-off-by: Andor Daam <andor.daam@googlemail.com>
> >> > Signed-off-by: Dan Magenheimer <dan.magenheimer@oracle.com>
> >> > ---
> >> > include/linux/frontswap.h | 1 +
> >> > mm/frontswap.c | 70 +++++++++++++++++++++++++++++++++++++++-----
> >> > 2 files changed, 63 insertions(+), 8 deletions(-)
> >> >
> >> > diff --git a/include/linux/frontswap.h b/include/linux/frontswap.h
> >> > index 3044254..ef6ada6 100644
> >> > --- a/include/linux/frontswap.h
> >> > +++ b/include/linux/frontswap.h
> >> > @@ -23,6 +23,7 @@ extern void frontswap_writethrough(bool);
> >> > extern void frontswap_tmem_exclusive_gets(bool);
> >> >
> >> > extern void __frontswap_init(unsigned type);
> >> > +#define FRONTSWAP_HAS_LAZY_INIT
> >> > extern int __frontswap_store(struct page *page);
> >> > extern int __frontswap_load(struct page *page);
> >> > extern void __frontswap_invalidate_page(unsigned, pgoff_t);
> >> > diff --git a/mm/frontswap.c b/mm/frontswap.c
> >> > index 2890e67..523a19b 100644
> >> > --- a/mm/frontswap.c
> >> > +++ b/mm/frontswap.c
> >> > @@ -80,6 +80,19 @@ static inline void inc_frontswap_succ_stores(void) { }
> >> > static inline void inc_frontswap_failed_stores(void) { }
> >> > static inline void inc_frontswap_invalidates(void) { }
> >> > #endif
> >> > +
> >> > +/*
> >> > + * When no backend is registered all calls to init are registered and
> >> > + * remembered but fail to create tmem_pools. When a backend registers with
> >> > + * frontswap the previous calls to init are executed to create tmem_pools
> >> > + * and set the respective poolids.
> >> > + * While no backend is registered all "puts", "gets" and "flushes" are
> >> > + * ignored or fail.
> >> > + */
> >> > +#define MAX_INITIALIZABLE_SD 32
> >>
> >> MAX_INITIALIZABLE_SD should just be MAX_SWAPFILES
> >>
> >> > +static int sds[MAX_INITIALIZABLE_SD];
> >>
> >> Rather than store and array of enabled types indexed by type, why not
> >> an array of booleans indexed by type. Or a bitfield if you really
> >> want to save space.
> >>
> >> > +static int backend_registered;
> >>
> >> (backend_registered) is equivalent to checking (frontswap_ops != NULL)
> >> right?
Kind of. frontswap_ops is not a pointer though so it would be more of
a frontswap_ops != dummy. Lets make another patch that makes this a
pointer and then rip out the backend_registered.
.. snip..
> > if (sis->frontswap_map == NULL)
> > return;
> > - frontswap_ops.init(type);
> > + if (backend_registered) {
> > + (*frontswap_ops.init)(type);
> > + set_bit(type, sds);
> > + }
> > }
>
> What about set bit if backend not registered and clear bit when invalidate.
> I think that looks more directly.
> Like:
> + if (backend_registered) {
> + BUG_ON(sis == NULL);
> + if (sis->frontswap_map == NULL)
> + return;
> + frontswap_ops.init(type);
> + }
> + else {
> + BUG_ON(type > MAX_SWAPFILES);
> + set_bit(type, sds);
> + }
Good idea.
>
>
> > EXPORT_SYMBOL(__frontswap_init);
> >
> > @@ -147,10 +169,20 @@ int __frontswap_store(struct page *page)
> > struct swap_info_struct *sis = swap_info[type];
> > pgoff_t offset = swp_offset(entry);
> >
> > + if (!backend_registered) {
> > + inc_frontswap_failed_stores();
> > + return ret;
> > + }
> > +
> > BUG_ON(!PageLocked(page));
> > BUG_ON(sis == NULL);
> > if (frontswap_test(sis, offset))
> > dup = 1;
> > + if (type < MAX_SWAPFILES && !test_bit(type, sds)) {
> > + /* lazy init call to handle post-boot insmod backends*/
> > + (*frontswap_ops.init)(type);
> > + set_bit(type, sds);
> > + }
>
> Then rm this.
Right, b/c the frontswap_init takes care of initializing the backend.
And this does not get called _until_ backend_registered is set.
So we have to be extra careful to set backend_registered _after_
all the frontswap.init have been called.
>
> > ret = frontswap_ops.store(type, offset, page);
> > if (ret == 0) {
> > frontswap_set(sis, offset);
> > @@ -186,6 +218,9 @@ int __frontswap_load(struct page *page)
> > struct swap_info_struct *sis = swap_info[type];
> > pgoff_t offset = swp_offset(entry);
> >
> > + if (!backend_registered)
> > + return ret;
> > +
> > BUG_ON(!PageLocked(page));
> > BUG_ON(sis == NULL);
> > if (frontswap_test(sis, offset))
> > @@ -209,6 +244,9 @@ void __frontswap_invalidate_page(unsigned type, pgoff_t offset)
> > {
> > struct swap_info_struct *sis = swap_info[type];
> >
> > + if (!backend_registered)
> > + return;
> > +
>
> I'm not sure whether __frontswap_invalidate_page() will be called if
> backend not registered.
Yes.
User could do:
swapon /dev/sda3
swapoff /dev/sda3
modprobe zcache
>
> > BUG_ON(sis == NULL);
> > if (frontswap_test(sis, offset)) {
> > frontswap_ops.invalidate_page(type, offset);
> > @@ -226,12 +264,16 @@ void __frontswap_invalidate_area(unsigned type)
> > {
> > struct swap_info_struct *sis = swap_info[type];
> >
> > - BUG_ON(sis == NULL);
> > - if (sis->frontswap_map == NULL)
> > - return;
> > - frontswap_ops.invalidate_area(type);
> > - atomic_set(&sis->frontswap_pages, 0);
> > - memset(sis->frontswap_map, 0, sis->max / sizeof(long));
> > + if (backend_registered) {
> > + BUG_ON(sis == NULL);
> > + if (sis->frontswap_map == NULL)
> > + return;
> > + (*frontswap_ops.invalidate_area)(type);
> > + atomic_set(&sis->frontswap_pages, 0);
> > + memset(sis->frontswap_map, 0, sis->max / sizeof(long));
> > + } else {
> > + bitmap_zero(sds, MAX_SWAPFILES);
>
> Use clear_bit(type, sds) here;
Yikes. Yes. It actually could be unconditional too
>
> > + }
> > }
> > EXPORT_SYMBOL(__frontswap_invalidate_area);
> >
> > @@ -364,6 +406,9 @@ static int __init init_frontswap(void)
> > debugfs_create_u64("invalidates", S_IRUGO,
> > root, &frontswap_invalidates);
> > #endif
> > + bitmap_zero(sds, MAX_SWAPFILES);
> > +
> > + frontswap_enabled = 1;
>
> We'd better init backend_registered = false also.
I think we are OK. The .bss is set to zero so that means
backend_registered is by default zero.
The end result would look like this (I had not compiled tested it yet):
^ permalink raw reply [flat|nested] 15+ messages in thread
* [PATCH 3/5] staging: zcache2+ramster: enable zcache2 to be built/loaded as a module
2012-10-31 15:07 [PATCH 0/5] enable all tmem backends to be built and loaded as modules Dan Magenheimer
2012-10-31 15:07 ` [PATCH 1/5] mm: cleancache: lazy initialization to allow tmem backends to build/run " Dan Magenheimer
2012-10-31 15:07 ` [PATCH 2/5] mm: frontswap: " Dan Magenheimer
@ 2012-10-31 15:07 ` Dan Magenheimer
2012-11-02 18:39 ` Konrad Rzeszutek Wilk
2012-10-31 15:07 ` [PATCH 4/5] staging: zcache2+ramster: enable ramster " Dan Magenheimer
2012-10-31 15:07 ` [PATCH 5/5] xen: tmem: enable Xen tmem shim " Dan Magenheimer
4 siblings, 1 reply; 15+ messages in thread
From: Dan Magenheimer @ 2012-10-31 15:07 UTC (permalink / raw)
To: devel, linux-kernel, gregkh, linux-mm, ngupta, konrad.wilk,
sjenning, minchan, dan.magenheimer, fschmaus, andor.damm, ilendir,
akpm, mgorman
Allow zcache2 to be built/loaded as a module. Note runtime dependency
disallows loading if cleancache/frontswap lazy initialization patches
are not present. Zsmalloc support has not yet been merged into zcache2
but, once merged, could now easily be selected via a module_param.
If built-in (not built as a module), the original mechanism of enabling via
a kernel boot parameter is retained, but this should be considered deprecated.
Note that module unload is explicitly not yet supported.
Signed-off-by: Dan Magenheimer <dan.magenheimer@oracle.com>
---
drivers/staging/ramster/Kconfig | 6 ++--
drivers/staging/ramster/Makefile | 11 +++---
drivers/staging/ramster/tmem.c | 6 +++-
drivers/staging/ramster/tmem.h | 8 ++--
drivers/staging/ramster/zcache-main.c | 61 ++++++++++++++++++++++++++++++--
drivers/staging/ramster/zcache.h | 2 +-
6 files changed, 76 insertions(+), 18 deletions(-)
diff --git a/drivers/staging/ramster/Kconfig b/drivers/staging/ramster/Kconfig
index 843c541..fd3e767 100644
--- a/drivers/staging/ramster/Kconfig
+++ b/drivers/staging/ramster/Kconfig
@@ -1,5 +1,5 @@
config ZCACHE2
- bool "Dynamic compression of swap pages and clean pagecache pages"
+ tristate "Dynamic compression of swap pages and clean pagecache pages"
depends on CRYPTO=y && SWAP=y && CLEANCACHE && FRONTSWAP && !ZCACHE
select CRYPTO_LZO
default n
@@ -16,8 +16,8 @@ config ZCACHE2
version of ramster.
config RAMSTER
- bool "Cross-machine RAM capacity sharing, aka peer-to-peer tmem"
- depends on CONFIGFS_FS=y && SYSFS=y && !HIGHMEM && ZCACHE2=y
+ tristate "Cross-machine RAM capacity sharing, aka peer-to-peer tmem"
+ depends on CONFIGFS_FS && SYSFS && !HIGHMEM && ZCACHE2
# must ensure struct page is 8-byte aligned
select HAVE_ALIGNED_STRUCT_PAGE if !64_BIT
default n
diff --git a/drivers/staging/ramster/Makefile b/drivers/staging/ramster/Makefile
index 2d8b9d0..fcb25cb 100644
--- a/drivers/staging/ramster/Makefile
+++ b/drivers/staging/ramster/Makefile
@@ -1,6 +1,7 @@
zcache-y := zcache-main.o tmem.o zbud.o
-zcache-$(CONFIG_RAMSTER) += ramster/ramster.o ramster/r2net.o
-zcache-$(CONFIG_RAMSTER) += ramster/nodemanager.o ramster/tcp.o
-zcache-$(CONFIG_RAMSTER) += ramster/heartbeat.o ramster/masklog.o
-
-obj-$(CONFIG_ZCACHE2) += zcache.o
+ifneq (,$(filter $(CONFIG_RAMSTER),y m))
+zcache-y += ramster/ramster.o ramster/r2net.o
+zcache-y += ramster/nodemanager.o ramster/tcp.o
+zcache-y += ramster/heartbeat.o ramster/masklog.o
+endif
+obj-$(CONFIG_MODULES) += zcache.o
diff --git a/drivers/staging/ramster/tmem.c b/drivers/staging/ramster/tmem.c
index a2b7e03..d7e51e4 100644
--- a/drivers/staging/ramster/tmem.c
+++ b/drivers/staging/ramster/tmem.c
@@ -35,7 +35,8 @@
#include <linux/list.h>
#include <linux/spinlock.h>
#include <linux/atomic.h>
-#ifdef CONFIG_RAMSTER
+#include <linux/export.h>
+#if defined(CONFIG_RAMSTER) || defined(CONFIG_RAMSTER_MODULE)
#include <linux/delay.h>
#endif
@@ -641,6 +642,7 @@ void *tmem_localify_get_pampd(struct tmem_pool *pool, struct tmem_oid *oidp,
/* note, hashbucket remains locked */
return pampd;
}
+EXPORT_SYMBOL_GPL(tmem_localify_get_pampd);
void tmem_localify_finish(struct tmem_obj *obj, uint32_t index,
void *pampd, void *saved_hb, bool delete)
@@ -658,6 +660,7 @@ void tmem_localify_finish(struct tmem_obj *obj, uint32_t index,
}
spin_unlock(&hb->lock);
}
+EXPORT_SYMBOL_GPL(tmem_localify_finish);
/*
* For ramster only. Helper function to support asynchronous tmem_get.
@@ -719,6 +722,7 @@ out:
spin_unlock(&hb->lock);
return ret;
}
+EXPORT_SYMBOL_GPL(tmem_replace);
#endif
/*
diff --git a/drivers/staging/ramster/tmem.h b/drivers/staging/ramster/tmem.h
index adbe5a8..d128ce2 100644
--- a/drivers/staging/ramster/tmem.h
+++ b/drivers/staging/ramster/tmem.h
@@ -126,7 +126,7 @@ static inline unsigned tmem_oid_hash(struct tmem_oid *oidp)
TMEM_HASH_BUCKET_BITS);
}
-#ifdef CONFIG_RAMSTER
+#if defined(CONFIG_RAMSTER) || defined(CONFIG_RAMSTER_MODULE)
struct tmem_xhandle {
uint8_t client_id;
uint8_t xh_data_cksum;
@@ -171,7 +171,7 @@ struct tmem_obj {
unsigned int objnode_tree_height;
unsigned long objnode_count;
long pampd_count;
-#ifdef CONFIG_RAMSTER
+#if defined(CONFIG_RAMSTER) || defined(CONFIG_RAMSTER_MODULE)
/*
* for current design of ramster, all pages belonging to
* an object reside on the same remotenode and extra is
@@ -215,7 +215,7 @@ struct tmem_pamops {
uint32_t);
void (*free)(void *, struct tmem_pool *,
struct tmem_oid *, uint32_t, bool);
-#ifdef CONFIG_RAMSTER
+#if defined(CONFIG_RAMSTER) || defined(CONFIG_RAMSTER_MODULE)
void (*new_obj)(struct tmem_obj *);
void (*free_obj)(struct tmem_pool *, struct tmem_obj *, bool);
void *(*repatriate_preload)(void *, struct tmem_pool *,
@@ -247,7 +247,7 @@ extern int tmem_flush_page(struct tmem_pool *, struct tmem_oid *,
extern int tmem_flush_object(struct tmem_pool *, struct tmem_oid *);
extern int tmem_destroy_pool(struct tmem_pool *);
extern void tmem_new_pool(struct tmem_pool *, uint32_t);
-#ifdef CONFIG_RAMSTER
+#if defined(CONFIG_RAMSTER) || defined(CONFIG_RAMSTER_MODULE)
extern int tmem_replace(struct tmem_pool *, struct tmem_oid *, uint32_t index,
void *);
extern void *tmem_localify_get_pampd(struct tmem_pool *, struct tmem_oid *,
diff --git a/drivers/staging/ramster/zcache-main.c b/drivers/staging/ramster/zcache-main.c
index a09dd5c..956d16d 100644
--- a/drivers/staging/ramster/zcache-main.c
+++ b/drivers/staging/ramster/zcache-main.c
@@ -31,8 +31,10 @@
#include "ramster.h"
#ifdef CONFIG_RAMSTER
static int ramster_enabled;
+static int disable_frontswap_selfshrink;
#else
#define ramster_enabled 0
+#define disable_frontswap_selfshrink 0
#endif
#ifndef __PG_WAS_ACTIVE
@@ -68,8 +70,12 @@ static char *namestr __read_mostly = "zcache";
MODULE_LICENSE("GPL");
/* crypto API for zcache */
+#ifdef CONFIG_ZCACHE2_MODULE
+static char *zcache_comp_name = "lzo";
+#else
#define ZCACHE_COMP_NAME_SZ CRYPTO_MAX_ALG_NAME
static char zcache_comp_name[ZCACHE_COMP_NAME_SZ] __read_mostly;
+#endif
static struct crypto_comp * __percpu *zcache_comp_pcpu_tfms __read_mostly;
enum comp_op {
@@ -1346,7 +1352,7 @@ static int zcache_local_new_pool(uint32_t flags)
int zcache_autocreate_pool(unsigned int cli_id, unsigned int pool_id, bool eph)
{
struct tmem_pool *pool;
- struct zcache_client *cli;
+ struct zcache_client *cli = NULL;
uint32_t flags = eph ? 0 : TMEM_POOL_PERSIST;
int ret = -1;
@@ -1640,6 +1646,7 @@ struct frontswap_ops zcache_frontswap_register_ops(void)
* OR NOTHING HAPPENS!
*/
+#ifndef CONFIG_ZCACHE2_MODULE
static int __init enable_zcache(char *s)
{
zcache_enabled = 1;
@@ -1706,18 +1713,27 @@ static int __init enable_zcache_compressor(char *s)
return 1;
}
__setup("zcache=", enable_zcache_compressor);
+#endif
-static int __init zcache_comp_init(void)
+static int zcache_comp_init(void)
{
int ret = 0;
/* check crypto algorithm */
+#ifdef CONFIG_ZCACHE2_MODULE
+ ret = crypto_has_comp(zcache_comp_name, 0, 0);
+ if (!ret) {
+ ret = -1;
+ goto out;
+ }
+#else
if (*zcache_comp_name != '\0') {
ret = crypto_has_comp(zcache_comp_name, 0, 0);
if (!ret)
pr_info("zcache: %s not supported\n",
zcache_comp_name);
+ goto out;
}
if (!ret)
strcpy(zcache_comp_name, "lzo");
@@ -1726,6 +1742,7 @@ static int __init zcache_comp_init(void)
ret = 1;
goto out;
}
+#endif
pr_info("zcache: using %s compressor\n", zcache_comp_name);
/* alloc percpu transforms */
@@ -1737,10 +1754,27 @@ out:
return ret;
}
-static int __init zcache_init(void)
+static int zcache_init(void)
{
int ret = 0;
+#ifdef CONFIG_ZCACHE2_MODULE
+#if defined(CONFIG_FRONTSWAP) && !defined(FRONTSWAP_HAS_LAZY_INIT)
+ /* This ifdef can be removed when frontswap lazy init is merged */
+ if (!disable_frontswap) {
+ pr_err("zcache module requires frontswap lazy init\n");
+ return -EINVAL;
+ }
+#endif
+#if defined(CONFIG_CLEANCACHE) && !defined(CLEANCACHE_HAS_LAZY_INIT)
+ /* This ifdef can be removed when cleancache lazy init is merged */
+ if (!disable_cleancache) {
+ pr_err("zcache module requires cleancache lazy init\n");
+ return -EINVAL;
+ }
+#endif
+ zcache_enabled = 1;
+#endif
if (ramster_enabled) {
namestr = "ramster";
ramster_register_pamops(&zcache_pamops);
@@ -1812,9 +1846,28 @@ static int __init zcache_init(void)
}
if (ramster_enabled)
ramster_init(!disable_cleancache, !disable_frontswap,
- frontswap_has_exclusive_gets);
+ frontswap_has_exclusive_gets,
+ !disable_frontswap_selfshrink);
out:
return ret;
}
+#ifdef CONFIG_ZCACHE2_MODULE
+#ifdef CONFIG_RAMSTER
+module_param(ramster_enabled, int, S_IRUGO);
+module_param(disable_frontswap_selfshrink, int, S_IRUGO);
+#endif
+module_param(disable_cleancache, int, S_IRUGO);
+module_param(disable_frontswap, int, S_IRUGO);
+#ifdef FRONTSWAP_HAS_EXCLUSIVE_GETS
+module_param(frontswap_has_exclusive_gets, bool, S_IRUGO);
+#endif
+module_param(disable_frontswap_ignore_nonactive, int, S_IRUGO);
+module_param(zcache_comp_name, charp, S_IRUGO);
+module_init(zcache_init);
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Dan Magenheimer <dan.magenheimer@oracle.com>");
+MODULE_DESCRIPTION("In-kernel compression of cleancache/frontswap pages");
+#else
late_initcall(zcache_init);
+#endif
diff --git a/drivers/staging/ramster/zcache.h b/drivers/staging/ramster/zcache.h
index 81722b3..8491200 100644
--- a/drivers/staging/ramster/zcache.h
+++ b/drivers/staging/ramster/zcache.h
@@ -39,7 +39,7 @@ extern int zcache_flush_page(int, int, struct tmem_oid *, uint32_t);
extern int zcache_flush_object(int, int, struct tmem_oid *);
extern void zcache_decompress_to_page(char *, unsigned int, struct page *);
-#ifdef CONFIG_RAMSTER
+#if defined(CONFIG_RAMSTER) || defined(CONFIG_RAMSTER_MODULE)
extern void *zcache_pampd_create(char *, unsigned int, bool, int,
struct tmem_handle *);
int zcache_autocreate_pool(unsigned int cli_id, unsigned int pool_id, bool eph);
--
1.7.1
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply related [flat|nested] 15+ messages in thread* Re: [PATCH 3/5] staging: zcache2+ramster: enable zcache2 to be built/loaded as a module
2012-10-31 15:07 ` [PATCH 3/5] staging: zcache2+ramster: enable zcache2 to be built/loaded as a module Dan Magenheimer
@ 2012-11-02 18:39 ` Konrad Rzeszutek Wilk
0 siblings, 0 replies; 15+ messages in thread
From: Konrad Rzeszutek Wilk @ 2012-11-02 18:39 UTC (permalink / raw)
To: Dan Magenheimer
Cc: devel, linux-kernel, gregkh, linux-mm, ngupta, sjenning, minchan,
fschmaus, andor.damm, ilendir, akpm, mgorman
On Wed, Oct 31, 2012 at 08:07:52AM -0700, Dan Magenheimer wrote:
> Allow zcache2 to be built/loaded as a module. Note runtime dependency
> disallows loading if cleancache/frontswap lazy initialization patches
> are not present. Zsmalloc support has not yet been merged into zcache2
> but, once merged, could now easily be selected via a module_param.
>
> If built-in (not built as a module), the original mechanism of enabling via
> a kernel boot parameter is retained, but this should be considered deprecated.
>
> Note that module unload is explicitly not yet supported.
I had an issue putting it on v3.7-rc3 with the Kconfig. Not sure why
as it looks exactly the same.
The patch looks good, however..
> @@ -1812,9 +1846,28 @@ static int __init zcache_init(void)
> }
> if (ramster_enabled)
> ramster_init(!disable_cleancache, !disable_frontswap,
> - frontswap_has_exclusive_gets);
> + frontswap_has_exclusive_gets,
> + !disable_frontswap_selfshrink);
> out:
> return ret;
> }
.. ramster_init change is in the next patch. So it looks like the
patch order is a bit mismatched.
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply [flat|nested] 15+ messages in thread
* [PATCH 4/5] staging: zcache2+ramster: enable ramster to be built/loaded as a module
2012-10-31 15:07 [PATCH 0/5] enable all tmem backends to be built and loaded as modules Dan Magenheimer
` (2 preceding siblings ...)
2012-10-31 15:07 ` [PATCH 3/5] staging: zcache2+ramster: enable zcache2 to be built/loaded as a module Dan Magenheimer
@ 2012-10-31 15:07 ` Dan Magenheimer
2012-10-31 15:07 ` [PATCH 5/5] xen: tmem: enable Xen tmem shim " Dan Magenheimer
4 siblings, 0 replies; 15+ messages in thread
From: Dan Magenheimer @ 2012-10-31 15:07 UTC (permalink / raw)
To: devel, linux-kernel, gregkh, linux-mm, ngupta, konrad.wilk,
sjenning, minchan, dan.magenheimer, fschmaus, andor.damm, ilendir,
akpm, mgorman
Enable module support for ramster. Note runtime dependency disallows
loading if cleancache/frontswap lazy initialization patches are not
present.
If built-in (not built as a module), the original mechanism of enabling via
a kernel boot parameter is retained, but this should be considered deprecated.
Note that module unload is explicitly not yet supported.
Signed-off-by: Dan Magenheimer <dan.magenheimer@oracle.com>
---
drivers/staging/ramster/ramster.h | 6 +++-
drivers/staging/ramster/ramster/nodemanager.c | 9 +++---
drivers/staging/ramster/ramster/ramster.c | 29 ++++++++++++++++---
drivers/staging/ramster/ramster/ramster.h | 2 +-
.../staging/ramster/ramster/ramster_nodemanager.h | 2 +
5 files changed, 37 insertions(+), 11 deletions(-)
diff --git a/drivers/staging/ramster/ramster.h b/drivers/staging/ramster/ramster.h
index 1b71aea..e1f91d5 100644
--- a/drivers/staging/ramster/ramster.h
+++ b/drivers/staging/ramster/ramster.h
@@ -11,10 +11,14 @@
#ifndef _ZCACHE_RAMSTER_H_
#define _ZCACHE_RAMSTER_H_
+#ifdef CONFIG_RAMSTER_MODULE
+#define CONFIG_RAMSTER
+#endif
+
#ifdef CONFIG_RAMSTER
#include "ramster/ramster.h"
#else
-static inline void ramster_init(bool x, bool y, bool z)
+static inline void ramster_init(bool x, bool y, bool z, bool w)
{
}
diff --git a/drivers/staging/ramster/ramster/nodemanager.c b/drivers/staging/ramster/ramster/nodemanager.c
index c0f4815..2cfe933 100644
--- a/drivers/staging/ramster/ramster/nodemanager.c
+++ b/drivers/staging/ramster/ramster/nodemanager.c
@@ -949,7 +949,7 @@ static void __exit exit_r2nm(void)
r2hb_exit();
}
-static int __init init_r2nm(void)
+int r2nm_init(void)
{
int ret = -1;
@@ -986,10 +986,11 @@ out_r2hb:
out:
return ret;
}
+EXPORT_SYMBOL_GPL(r2nm_init);
MODULE_AUTHOR("Oracle");
MODULE_LICENSE("GPL");
-/* module_init(init_r2nm) */
-late_initcall(init_r2nm);
-/* module_exit(exit_r2nm) */
+#ifndef CONFIG_RAMSTER_MODULE
+late_initcall(r2nm_init);
+#endif
diff --git a/drivers/staging/ramster/ramster/ramster.c b/drivers/staging/ramster/ramster/ramster.c
index c06709f..491ec70 100644
--- a/drivers/staging/ramster/ramster/ramster.c
+++ b/drivers/staging/ramster/ramster/ramster.c
@@ -92,7 +92,7 @@ static unsigned long ramster_remote_page_flushes_failed;
#include <linux/debugfs.h>
#define zdfs debugfs_create_size_t
#define zdfs64 debugfs_create_u64
-static int __init ramster_debugfs_init(void)
+static int ramster_debugfs_init(void)
{
struct dentry *root = debugfs_create_dir("ramster", NULL);
if (root == NULL)
@@ -191,6 +191,7 @@ int ramster_do_preload_flnode(struct tmem_pool *pool)
kmem_cache_free(ramster_flnode_cache, flnode);
return ret;
}
+EXPORT_SYMBOL_GPL(ramster_do_preload_flnode);
/*
* Called by the message handler after a (still compressed) page has been
@@ -458,6 +459,7 @@ void *ramster_pampd_free(void *pampd, struct tmem_pool *pool,
}
return local_pampd;
}
+EXPORT_SYMBOL_GPL(ramster_pampd_free);
void ramster_count_foreign_pages(bool eph, int count)
{
@@ -489,6 +491,7 @@ void ramster_count_foreign_pages(bool eph, int count)
ramster_foreign_pers_pages = c;
}
}
+EXPORT_SYMBOL_GPL(ramster_count_foreign_pages);
/*
* For now, just push over a few pages every few seconds to
@@ -674,7 +677,7 @@ requeue:
ramster_remotify_queue_delayed_work(HZ);
}
-void __init ramster_remotify_init(void)
+void ramster_remotify_init(void)
{
unsigned long n = 60UL;
ramster_remotify_workqueue =
@@ -849,8 +852,10 @@ static bool frontswap_selfshrinking __read_mostly;
static void selfshrink_process(struct work_struct *work);
static DECLARE_DELAYED_WORK(selfshrink_worker, selfshrink_process);
+#ifndef CONFIG_RAMSTER_MODULE
/* Enable/disable with kernel boot option. */
static bool use_frontswap_selfshrink __initdata = true;
+#endif
/*
* The default values for the following parameters were deemed reasonable
@@ -905,6 +910,7 @@ static void frontswap_selfshrink(void)
frontswap_shrink(tgt_frontswap_pages);
}
+#ifndef CONFIG_RAMSTER_MODULE
static int __init ramster_nofrontswap_selfshrink_setup(char *s)
{
use_frontswap_selfshrink = false;
@@ -912,6 +918,7 @@ static int __init ramster_nofrontswap_selfshrink_setup(char *s)
}
__setup("noselfshrink", ramster_nofrontswap_selfshrink_setup);
+#endif
static void selfshrink_process(struct work_struct *work)
{
@@ -930,6 +937,7 @@ void ramster_cpu_up(int cpu)
per_cpu(ramster_remoteputmem1, cpu) = p1;
per_cpu(ramster_remoteputmem2, cpu) = p2;
}
+EXPORT_SYMBOL_GPL(ramster_cpu_up);
void ramster_cpu_down(int cpu)
{
@@ -945,6 +953,7 @@ void ramster_cpu_down(int cpu)
kp->flnode = NULL;
}
}
+EXPORT_SYMBOL_GPL(ramster_cpu_down);
void ramster_register_pamops(struct tmem_pamops *pamops)
{
@@ -955,9 +964,11 @@ void ramster_register_pamops(struct tmem_pamops *pamops)
pamops->repatriate = ramster_pampd_repatriate;
pamops->repatriate_preload = ramster_pampd_repatriate_preload;
}
+EXPORT_SYMBOL_GPL(ramster_register_pamops);
-void __init ramster_init(bool cleancache, bool frontswap,
- bool frontswap_exclusive_gets)
+void ramster_init(bool cleancache, bool frontswap,
+ bool frontswap_exclusive_gets,
+ bool frontswap_selfshrink)
{
int ret = 0;
@@ -972,10 +983,17 @@ void __init ramster_init(bool cleancache, bool frontswap,
if (ret)
pr_err("ramster: can't create sysfs for ramster\n");
(void)r2net_register_handlers();
+#ifdef CONFIG_RAMSTER_MODULE
+ ret = r2nm_init();
+ if (ret)
+ pr_err("ramster: can't init r2net\n");
+ frontswap_selfshrinking = frontswap_selfshrink;
+#else
+ frontswap_selfshrinking = use_frontswap_selfshrink;
+#endif
INIT_LIST_HEAD(&ramster_rem_op_list);
ramster_flnode_cache = kmem_cache_create("ramster_flnode",
sizeof(struct flushlist_node), 0, 0, NULL);
- frontswap_selfshrinking = use_frontswap_selfshrink;
if (frontswap_selfshrinking) {
pr_info("ramster: Initializing frontswap selfshrink driver.\n");
schedule_delayed_work(&selfshrink_worker,
@@ -983,3 +1001,4 @@ void __init ramster_init(bool cleancache, bool frontswap,
}
ramster_remotify_init();
}
+EXPORT_SYMBOL_GPL(ramster_init);
diff --git a/drivers/staging/ramster/ramster/ramster.h b/drivers/staging/ramster/ramster/ramster.h
index 12ae56f..6d41a7a 100644
--- a/drivers/staging/ramster/ramster/ramster.h
+++ b/drivers/staging/ramster/ramster/ramster.h
@@ -147,7 +147,7 @@ extern int r2net_register_handlers(void);
extern int r2net_remote_target_node_set(int);
extern int ramster_remotify_pageframe(bool);
-extern void ramster_init(bool, bool, bool);
+extern void ramster_init(bool, bool, bool, bool);
extern void ramster_register_pamops(struct tmem_pamops *);
extern int ramster_localify(int, struct tmem_oid *oidp, uint32_t, char *,
unsigned int, void *);
diff --git a/drivers/staging/ramster/ramster/ramster_nodemanager.h b/drivers/staging/ramster/ramster/ramster_nodemanager.h
index 49f879d..dbaae34 100644
--- a/drivers/staging/ramster/ramster/ramster_nodemanager.h
+++ b/drivers/staging/ramster/ramster/ramster_nodemanager.h
@@ -36,4 +36,6 @@
/* host name, group name, cluster name all 64 bytes */
#define R2NM_MAX_NAME_LEN 64 /* __NEW_UTS_LEN */
+extern int r2nm_init(void);
+
#endif /* _RAMSTER_NODEMANAGER_H */
--
1.7.1
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply related [flat|nested] 15+ messages in thread* [PATCH 5/5] xen: tmem: enable Xen tmem shim to be built/loaded as a module
2012-10-31 15:07 [PATCH 0/5] enable all tmem backends to be built and loaded as modules Dan Magenheimer
` (3 preceding siblings ...)
2012-10-31 15:07 ` [PATCH 4/5] staging: zcache2+ramster: enable ramster " Dan Magenheimer
@ 2012-10-31 15:07 ` Dan Magenheimer
4 siblings, 0 replies; 15+ messages in thread
From: Dan Magenheimer @ 2012-10-31 15:07 UTC (permalink / raw)
To: devel, linux-kernel, gregkh, linux-mm, ngupta, konrad.wilk,
sjenning, minchan, dan.magenheimer, fschmaus, andor.damm, ilendir,
akpm, mgorman
Allow Xen tmem shim to be built/loaded as a module. Xen self-ballooning
and frontswap-selfshrinking are now also "lazily" initialized when the
Xen tmem shim is loaded as a module, unless explicitly disabled
by module parameters.
Note runtime dependency disallows loading if cleancache/frontswap lazy
initialization patches are not present.
If built-in (not built as a module), the original mechanism of enabling via
a kernel boot parameter is retained, but this should be considered deprecated.
Note that module unload is explicitly not yet supported.
Signed-off-by: Dan Magenheimer <dan.magenheimer@oracle.com>
---
drivers/xen/Kconfig | 4 +-
drivers/xen/tmem.c | 56 +++++++++++++++++++++++++++++++++--------
drivers/xen/xen-selfballoon.c | 13 +++++----
include/xen/tmem.h | 8 ++++++
4 files changed, 62 insertions(+), 19 deletions(-)
diff --git a/drivers/xen/Kconfig b/drivers/xen/Kconfig
index d4dffcd..68dd78f 100644
--- a/drivers/xen/Kconfig
+++ b/drivers/xen/Kconfig
@@ -144,8 +144,8 @@ config SWIOTLB_XEN
select SWIOTLB
config XEN_TMEM
- bool
- default y if (CLEANCACHE || FRONTSWAP)
+ tristate
+ default m if (CLEANCACHE || FRONTSWAP)
help
Shim to interface in-kernel Transcendent Memory hooks
(e.g. cleancache and frontswap) to Xen tmem hypercalls.
diff --git a/drivers/xen/tmem.c b/drivers/xen/tmem.c
index 144564e..8ba0a3f 100644
--- a/drivers/xen/tmem.c
+++ b/drivers/xen/tmem.c
@@ -5,6 +5,7 @@
* Author: Dan Magenheimer
*/
+#include <linux/module.h>
#include <linux/kernel.h>
#include <linux/types.h>
#include <linux/init.h>
@@ -128,6 +129,7 @@ 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);
}
+#ifndef CONFIG_XEN_TMEM_MODULE
bool __read_mostly tmem_enabled = false;
static int __init enable_tmem(char *s)
@@ -136,6 +138,7 @@ static int __init enable_tmem(char *s)
return 1;
}
__setup("tmem", enable_tmem);
+#endif
#ifdef CONFIG_CLEANCACHE
static int xen_tmem_destroy_pool(u32 pool_id)
@@ -227,16 +230,21 @@ static int tmem_cleancache_init_shared_fs(char *uuid, size_t pagesize)
return xen_tmem_new_pool(shared_uuid, TMEM_POOL_SHARED, pagesize);
}
-static bool __initdata use_cleancache = true;
-
+static bool disable_cleancache __read_mostly;
+static bool disable_selfballooning __read_mostly;
+#ifdef CONFIG_XEN_TMEM_MODULE
+module_param(disable_cleancache, bool, S_IRUGO);
+module_param(disable_selfballooning, bool, S_IRUGO);
+#else
static int __init no_cleancache(char *s)
{
- use_cleancache = false;
+ disable_cleancache = true;
return 1;
}
__setup("nocleancache", no_cleancache);
+#endif
-static struct cleancache_ops __initdata tmem_cleancache_ops = {
+static struct cleancache_ops tmem_cleancache_ops = {
.put_page = tmem_cleancache_put_page,
.get_page = tmem_cleancache_get_page,
.invalidate_page = tmem_cleancache_flush_page,
@@ -353,16 +361,21 @@ static void tmem_frontswap_init(unsigned ignored)
xen_tmem_new_pool(private, TMEM_POOL_PERSIST, PAGE_SIZE);
}
-static bool __initdata use_frontswap = true;
-
+static bool disable_frontswap __read_mostly;
+static bool disable_frontswap_selfshrinking __read_mostly;
+#ifdef CONFIG_XEN_TMEM_MODULE
+module_param(disable_frontswap, bool, S_IRUGO);
+module_param(disable_frontswap_selfshrinking, bool, S_IRUGO);
+#else
static int __init no_frontswap(char *s)
{
- use_frontswap = false;
+ disable_frontswap = true;
return 1;
}
__setup("nofrontswap", no_frontswap);
+#endif
-static struct frontswap_ops __initdata tmem_frontswap_ops = {
+static struct frontswap_ops tmem_frontswap_ops = {
.store = tmem_frontswap_store,
.load = tmem_frontswap_load,
.invalidate_page = tmem_frontswap_flush_page,
@@ -371,12 +384,19 @@ static struct frontswap_ops __initdata tmem_frontswap_ops = {
};
#endif
-static int __init xen_tmem_init(void)
+static int xen_tmem_init(void)
{
if (!xen_domain())
return 0;
#ifdef CONFIG_FRONTSWAP
- if (tmem_enabled && use_frontswap) {
+#if defined(CONFIG_XEN_TMEM_MODULE) && !defined(FRONTSWAP_HAS_LAZY_INIT)
+ /* This ifdef can be removed when frontswap lazy init is merged */
+ if (!disable_frontswap) {
+ pr_err("Xen tmem module requires frontswap lazy init\n");
+ return -EINVAL;
+ }
+#endif
+ if (tmem_enabled && !disable_frontswap) {
char *s = "";
struct frontswap_ops old_ops =
frontswap_register_ops(&tmem_frontswap_ops);
@@ -389,8 +409,15 @@ static int __init xen_tmem_init(void)
}
#endif
#ifdef CONFIG_CLEANCACHE
+#if defined(CONFIG_XEN_TMEM_MODULE) && !defined(CLEANCACHE_HAS_LAZY_INIT)
+ /* This ifdef can be removed when cleancache lazy init is merged */
+ if (!disable_cleancache) {
+ pr_err("Xen tmem module requires cleancache lazy init\n");
+ return -EINVAL;
+ }
+#endif
BUG_ON(sizeof(struct cleancache_filekey) != sizeof(struct tmem_oid));
- if (tmem_enabled && use_cleancache) {
+ if (tmem_enabled && !disable_cleancache) {
char *s = "";
struct cleancache_ops old_ops =
cleancache_register_ops(&tmem_cleancache_ops);
@@ -400,7 +427,14 @@ static int __init xen_tmem_init(void)
"Xen Transcendent Memory%s\n", s);
}
#endif
+#ifdef CONFIG_XEN_SELFBALLOONING
+ xen_selfballoon_init(!disable_selfballooning,
+ !disable_frontswap_selfshrinking);
+#endif
return 0;
}
module_init(xen_tmem_init)
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Dan Magenheimer <dan.magenheimer@oracle.com>");
+MODULE_DESCRIPTION("Shim to Xen transcendent memory");
diff --git a/drivers/xen/xen-selfballoon.c b/drivers/xen/xen-selfballoon.c
index 7d041cb..f4808aa 100644
--- a/drivers/xen/xen-selfballoon.c
+++ b/drivers/xen/xen-selfballoon.c
@@ -121,7 +121,7 @@ static DECLARE_DELAYED_WORK(selfballoon_worker, selfballoon_process);
static bool frontswap_selfshrinking __read_mostly;
/* Enable/disable with kernel boot option. */
-static bool use_frontswap_selfshrink __initdata = true;
+static bool use_frontswap_selfshrink = true;
/*
* The default values for the following parameters were deemed reasonable
@@ -185,7 +185,7 @@ static int __init xen_nofrontswap_selfshrink_setup(char *s)
__setup("noselfshrink", xen_nofrontswap_selfshrink_setup);
/* Disable with kernel boot option. */
-static bool use_selfballooning __initdata = true;
+static bool use_selfballooning = true;
static int __init xen_noselfballooning_setup(char *s)
{
@@ -196,7 +196,7 @@ static int __init xen_noselfballooning_setup(char *s)
__setup("noselfballooning", xen_noselfballooning_setup);
#else /* !CONFIG_FRONTSWAP */
/* Enable with kernel boot option. */
-static bool use_selfballooning __initdata = false;
+static bool use_selfballooning;
static int __init xen_selfballooning_setup(char *s)
{
@@ -537,7 +537,7 @@ int register_xen_selfballooning(struct device *dev)
}
EXPORT_SYMBOL(register_xen_selfballooning);
-static int __init xen_selfballoon_init(void)
+int xen_selfballoon_init(bool use_selfballooning, bool use_frontswap_selfshrink)
{
bool enable = false;
@@ -571,7 +571,8 @@ static int __init xen_selfballoon_init(void)
return 0;
}
+EXPORT_SYMBOL(xen_selfballoon_init);
+#ifndef CONFIG_XEN_TMEM_MODULE
subsys_initcall(xen_selfballoon_init);
-
-MODULE_LICENSE("GPL");
+#endif
diff --git a/include/xen/tmem.h b/include/xen/tmem.h
index 591550a..f94bdd1 100644
--- a/include/xen/tmem.h
+++ b/include/xen/tmem.h
@@ -3,7 +3,15 @@
#include <linux/types.h>
+#ifdef CONFIG_XEN_TMEM_MODULE
+#define tmem_enabled 1
+#else
/* defined in drivers/xen/tmem.c */
extern bool tmem_enabled;
+#endif
+
+#ifdef CONFIG_XEN_SELFBALLOONING
+extern int xen_selfballoon_init(bool, bool);
+#endif
#endif /* _XEN_TMEM_H */
--
1.7.1
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply related [flat|nested] 15+ messages in thread