2010-04-07 06:14:15 +08:00
|
|
|
#ifndef _FS_CEPH_LIBCEPH_H
|
|
|
|
#define _FS_CEPH_LIBCEPH_H
|
|
|
|
|
2012-10-03 01:01:25 +08:00
|
|
|
#include <linux/ceph/ceph_debug.h>
|
2010-04-07 06:14:15 +08:00
|
|
|
|
|
|
|
#include <asm/unaligned.h>
|
|
|
|
#include <linux/backing-dev.h>
|
|
|
|
#include <linux/completion.h>
|
|
|
|
#include <linux/exportfs.h>
|
2011-11-24 09:12:59 +08:00
|
|
|
#include <linux/bug.h>
|
2010-04-07 06:14:15 +08:00
|
|
|
#include <linux/fs.h>
|
|
|
|
#include <linux/mempool.h>
|
|
|
|
#include <linux/pagemap.h>
|
|
|
|
#include <linux/wait.h>
|
|
|
|
#include <linux/writeback.h>
|
|
|
|
#include <linux/slab.h>
|
|
|
|
|
2012-10-03 01:01:25 +08:00
|
|
|
#include <linux/ceph/types.h>
|
|
|
|
#include <linux/ceph/messenger.h>
|
|
|
|
#include <linux/ceph/msgpool.h>
|
|
|
|
#include <linux/ceph/mon_client.h>
|
|
|
|
#include <linux/ceph/osd_client.h>
|
|
|
|
#include <linux/ceph/ceph_fs.h>
|
2010-04-07 06:14:15 +08:00
|
|
|
|
|
|
|
/*
|
|
|
|
* mount options
|
|
|
|
*/
|
|
|
|
#define CEPH_OPT_FSID (1<<0)
|
|
|
|
#define CEPH_OPT_NOSHARE (1<<1) /* don't share client with other sbs */
|
|
|
|
#define CEPH_OPT_MYIP (1<<2) /* specified my ip */
|
|
|
|
#define CEPH_OPT_NOCRC (1<<3) /* no data crc on writes */
|
2015-10-29 06:52:06 +08:00
|
|
|
#define CEPH_OPT_NOMSGAUTH (1<<4) /* don't require msg signing feat */
|
2015-01-23 19:11:25 +08:00
|
|
|
#define CEPH_OPT_TCP_NODELAY (1<<5) /* TCP_NODELAY on TCP sockets */
|
2015-10-29 06:52:06 +08:00
|
|
|
#define CEPH_OPT_NOMSGSIGN (1<<6) /* don't sign msgs */
|
2010-04-07 06:14:15 +08:00
|
|
|
|
2015-01-23 19:11:25 +08:00
|
|
|
#define CEPH_OPT_DEFAULT (CEPH_OPT_TCP_NODELAY)
|
2010-04-07 06:14:15 +08:00
|
|
|
|
|
|
|
#define ceph_set_opt(client, opt) \
|
|
|
|
(client)->options->flags |= CEPH_OPT_##opt;
|
|
|
|
#define ceph_test_opt(client, opt) \
|
|
|
|
(!!((client)->options->flags & CEPH_OPT_##opt))
|
|
|
|
|
|
|
|
struct ceph_options {
|
|
|
|
int flags;
|
|
|
|
struct ceph_fsid fsid;
|
|
|
|
struct ceph_entity_addr my_addr;
|
2015-05-15 17:02:17 +08:00
|
|
|
unsigned long mount_timeout; /* jiffies */
|
|
|
|
unsigned long osd_idle_ttl; /* jiffies */
|
|
|
|
unsigned long osd_keepalive_timeout; /* jiffies */
|
2010-04-07 06:14:15 +08:00
|
|
|
|
|
|
|
/*
|
|
|
|
* any type that can't be simply compared or doesn't need need
|
|
|
|
* to be compared should go beyond this point,
|
|
|
|
* ceph_compare_options() should be updated accordingly
|
|
|
|
*/
|
|
|
|
|
|
|
|
struct ceph_entity_addr *mon_addr; /* should be the first
|
|
|
|
pointer type of args */
|
|
|
|
int num_mon;
|
|
|
|
char *name;
|
2011-03-26 07:32:57 +08:00
|
|
|
struct ceph_crypto_key *key;
|
2010-04-07 06:14:15 +08:00
|
|
|
};
|
|
|
|
|
|
|
|
/*
|
|
|
|
* defaults
|
|
|
|
*/
|
2015-05-15 17:02:17 +08:00
|
|
|
#define CEPH_MOUNT_TIMEOUT_DEFAULT msecs_to_jiffies(60 * 1000)
|
|
|
|
#define CEPH_OSD_KEEPALIVE_DEFAULT msecs_to_jiffies(5 * 1000)
|
|
|
|
#define CEPH_OSD_IDLE_TTL_DEFAULT msecs_to_jiffies(60 * 1000)
|
2016-01-21 23:33:15 +08:00
|
|
|
|
2016-01-21 23:33:19 +08:00
|
|
|
#define CEPH_MONC_HUNT_INTERVAL msecs_to_jiffies(3 * 1000)
|
2016-01-21 23:33:15 +08:00
|
|
|
#define CEPH_MONC_PING_INTERVAL msecs_to_jiffies(10 * 1000)
|
|
|
|
#define CEPH_MONC_PING_TIMEOUT msecs_to_jiffies(30 * 1000)
|
2016-01-21 23:33:19 +08:00
|
|
|
#define CEPH_MONC_HUNT_BACKOFF 2
|
|
|
|
#define CEPH_MONC_HUNT_MAX_MULT 10
|
2010-04-07 06:14:15 +08:00
|
|
|
|
|
|
|
#define CEPH_MSG_MAX_FRONT_LEN (16*1024*1024)
|
2013-03-09 08:51:03 +08:00
|
|
|
#define CEPH_MSG_MAX_MIDDLE_LEN (16*1024*1024)
|
2010-04-07 06:14:15 +08:00
|
|
|
#define CEPH_MSG_MAX_DATA_LEN (16*1024*1024)
|
|
|
|
|
|
|
|
#define CEPH_AUTH_NAME_DEFAULT "guest"
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Delay telling the MDS we no longer want caps, in case we reopen
|
|
|
|
* the file. Delay a minimum amount of time, even if we send a cap
|
|
|
|
* message for some other reason. Otherwise, take the oppotunity to
|
|
|
|
* update the mds to avoid sending another message later.
|
|
|
|
*/
|
|
|
|
#define CEPH_CAPS_WANTED_DELAY_MIN_DEFAULT 5 /* cap release delay */
|
|
|
|
#define CEPH_CAPS_WANTED_DELAY_MAX_DEFAULT 60 /* cap release delay */
|
|
|
|
|
|
|
|
#define CEPH_CAP_RELEASE_SAFETY_DEFAULT (CEPH_CAPS_PER_RELEASE * 4)
|
|
|
|
|
|
|
|
/* mount state */
|
|
|
|
enum {
|
|
|
|
CEPH_MOUNT_MOUNTING,
|
|
|
|
CEPH_MOUNT_MOUNTED,
|
|
|
|
CEPH_MOUNT_UNMOUNTING,
|
|
|
|
CEPH_MOUNT_UNMOUNTED,
|
|
|
|
CEPH_MOUNT_SHUTDOWN,
|
|
|
|
};
|
|
|
|
|
2015-05-15 17:02:17 +08:00
|
|
|
static inline unsigned long ceph_timeout_jiffies(unsigned long timeout)
|
|
|
|
{
|
|
|
|
return timeout ?: MAX_SCHEDULE_TIMEOUT;
|
|
|
|
}
|
|
|
|
|
2010-04-07 06:14:15 +08:00
|
|
|
struct ceph_mds_client;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* per client state
|
|
|
|
*
|
|
|
|
* possibly shared by multiple mount points, if they are
|
|
|
|
* mounting the same ceph filesystem/cluster.
|
|
|
|
*/
|
|
|
|
struct ceph_client {
|
|
|
|
struct ceph_fsid fsid;
|
|
|
|
bool have_fsid;
|
|
|
|
|
|
|
|
void *private;
|
|
|
|
|
|
|
|
struct ceph_options *options;
|
|
|
|
|
|
|
|
struct mutex mount_mutex; /* serialize mount attempts */
|
|
|
|
wait_queue_head_t auth_wq;
|
|
|
|
int auth_err;
|
|
|
|
|
|
|
|
int (*extra_mon_dispatch)(struct ceph_client *, struct ceph_msg *);
|
|
|
|
|
2013-12-25 03:19:23 +08:00
|
|
|
u64 supported_features;
|
|
|
|
u64 required_features;
|
2010-04-07 06:14:15 +08:00
|
|
|
|
2012-05-27 12:26:43 +08:00
|
|
|
struct ceph_messenger msgr; /* messenger instance */
|
2010-04-07 06:14:15 +08:00
|
|
|
struct ceph_mon_client monc;
|
|
|
|
struct ceph_osd_client osdc;
|
|
|
|
|
|
|
|
#ifdef CONFIG_DEBUG_FS
|
|
|
|
struct dentry *debugfs_dir;
|
|
|
|
struct dentry *debugfs_monmap;
|
|
|
|
struct dentry *debugfs_osdmap;
|
2015-03-26 02:07:41 +08:00
|
|
|
struct dentry *debugfs_options;
|
2010-04-07 06:14:15 +08:00
|
|
|
#endif
|
|
|
|
};
|
|
|
|
|
2015-10-29 06:50:58 +08:00
|
|
|
#define from_msgr(ms) container_of(ms, struct ceph_client, msgr)
|
2010-04-07 06:14:15 +08:00
|
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
* snapshots
|
|
|
|
*/
|
|
|
|
|
|
|
|
/*
|
|
|
|
* A "snap context" is the set of existing snapshots when we
|
|
|
|
* write data. It is used by the OSD to guide its COW behavior.
|
|
|
|
*
|
|
|
|
* The ceph_snap_context is refcounted, and attached to each dirty
|
|
|
|
* page, indicating which context the dirty data belonged when it was
|
|
|
|
* dirtied.
|
|
|
|
*/
|
|
|
|
struct ceph_snap_context {
|
|
|
|
atomic_t nref;
|
|
|
|
u64 seq;
|
2012-07-14 09:35:11 +08:00
|
|
|
u32 num_snaps;
|
2010-04-07 06:14:15 +08:00
|
|
|
u64 snaps[];
|
|
|
|
};
|
|
|
|
|
2013-04-30 13:44:32 +08:00
|
|
|
extern struct ceph_snap_context *ceph_create_snap_context(u32 snap_count,
|
|
|
|
gfp_t gfp_flags);
|
|
|
|
extern struct ceph_snap_context *ceph_get_snap_context(
|
|
|
|
struct ceph_snap_context *sc);
|
|
|
|
extern void ceph_put_snap_context(struct ceph_snap_context *sc);
|
2010-04-07 06:14:15 +08:00
|
|
|
|
|
|
|
/*
|
|
|
|
* calculate the number of pages a given length and offset map onto,
|
|
|
|
* if we align the data.
|
|
|
|
*/
|
|
|
|
static inline int calc_pages_for(u64 off, u64 len)
|
|
|
|
{
|
mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros
PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} macros were introduced *long* time
ago with promise that one day it will be possible to implement page
cache with bigger chunks than PAGE_SIZE.
This promise never materialized. And unlikely will.
We have many places where PAGE_CACHE_SIZE assumed to be equal to
PAGE_SIZE. And it's constant source of confusion on whether
PAGE_CACHE_* or PAGE_* constant should be used in a particular case,
especially on the border between fs and mm.
Global switching to PAGE_CACHE_SIZE != PAGE_SIZE would cause to much
breakage to be doable.
Let's stop pretending that pages in page cache are special. They are
not.
The changes are pretty straight-forward:
- <foo> << (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>;
- <foo> >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>;
- PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} -> PAGE_{SIZE,SHIFT,MASK,ALIGN};
- page_cache_get() -> get_page();
- page_cache_release() -> put_page();
This patch contains automated changes generated with coccinelle using
script below. For some reason, coccinelle doesn't patch header files.
I've called spatch for them manually.
The only adjustment after coccinelle is revert of changes to
PAGE_CAHCE_ALIGN definition: we are going to drop it later.
There are few places in the code where coccinelle didn't reach. I'll
fix them manually in a separate patch. Comments and documentation also
will be addressed with the separate patch.
virtual patch
@@
expression E;
@@
- E << (PAGE_CACHE_SHIFT - PAGE_SHIFT)
+ E
@@
expression E;
@@
- E >> (PAGE_CACHE_SHIFT - PAGE_SHIFT)
+ E
@@
@@
- PAGE_CACHE_SHIFT
+ PAGE_SHIFT
@@
@@
- PAGE_CACHE_SIZE
+ PAGE_SIZE
@@
@@
- PAGE_CACHE_MASK
+ PAGE_MASK
@@
expression E;
@@
- PAGE_CACHE_ALIGN(E)
+ PAGE_ALIGN(E)
@@
expression E;
@@
- page_cache_get(E)
+ get_page(E)
@@
expression E;
@@
- page_cache_release(E)
+ put_page(E)
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-04-01 20:29:47 +08:00
|
|
|
return ((off+len+PAGE_SIZE-1) >> PAGE_SHIFT) -
|
|
|
|
(off >> PAGE_SHIFT);
|
2010-04-07 06:14:15 +08:00
|
|
|
}
|
|
|
|
|
2016-04-28 22:07:22 +08:00
|
|
|
/*
|
|
|
|
* These are not meant to be generic - an integer key is assumed.
|
|
|
|
*/
|
|
|
|
#define DEFINE_RB_INSDEL_FUNCS(name, type, keyfld, nodefld) \
|
|
|
|
static void insert_##name(struct rb_root *root, type *t) \
|
|
|
|
{ \
|
|
|
|
struct rb_node **n = &root->rb_node; \
|
|
|
|
struct rb_node *parent = NULL; \
|
|
|
|
\
|
|
|
|
BUG_ON(!RB_EMPTY_NODE(&t->nodefld)); \
|
|
|
|
\
|
|
|
|
while (*n) { \
|
|
|
|
type *cur = rb_entry(*n, type, nodefld); \
|
|
|
|
\
|
|
|
|
parent = *n; \
|
|
|
|
if (t->keyfld < cur->keyfld) \
|
|
|
|
n = &(*n)->rb_left; \
|
|
|
|
else if (t->keyfld > cur->keyfld) \
|
|
|
|
n = &(*n)->rb_right; \
|
|
|
|
else \
|
|
|
|
BUG(); \
|
|
|
|
} \
|
|
|
|
\
|
|
|
|
rb_link_node(&t->nodefld, parent, n); \
|
|
|
|
rb_insert_color(&t->nodefld, root); \
|
|
|
|
} \
|
|
|
|
static void erase_##name(struct rb_root *root, type *t) \
|
|
|
|
{ \
|
|
|
|
BUG_ON(RB_EMPTY_NODE(&t->nodefld)); \
|
|
|
|
rb_erase(&t->nodefld, root); \
|
|
|
|
RB_CLEAR_NODE(&t->nodefld); \
|
|
|
|
}
|
|
|
|
|
|
|
|
#define DEFINE_RB_LOOKUP_FUNC(name, type, keyfld, nodefld) \
|
|
|
|
static type *lookup_##name(struct rb_root *root, \
|
|
|
|
typeof(((type *)0)->keyfld) key) \
|
|
|
|
{ \
|
|
|
|
struct rb_node *n = root->rb_node; \
|
|
|
|
\
|
|
|
|
while (n) { \
|
|
|
|
type *cur = rb_entry(n, type, nodefld); \
|
|
|
|
\
|
|
|
|
if (key < cur->keyfld) \
|
|
|
|
n = n->rb_left; \
|
|
|
|
else if (key > cur->keyfld) \
|
|
|
|
n = n->rb_right; \
|
|
|
|
else \
|
|
|
|
return cur; \
|
|
|
|
} \
|
|
|
|
\
|
|
|
|
return NULL; \
|
|
|
|
}
|
|
|
|
|
|
|
|
#define DEFINE_RB_FUNCS(name, type, keyfld, nodefld) \
|
|
|
|
DEFINE_RB_INSDEL_FUNCS(name, type, keyfld, nodefld) \
|
|
|
|
DEFINE_RB_LOOKUP_FUNC(name, type, keyfld, nodefld)
|
|
|
|
|
2014-01-10 02:08:21 +08:00
|
|
|
extern struct kmem_cache *ceph_inode_cachep;
|
|
|
|
extern struct kmem_cache *ceph_cap_cachep;
|
2015-06-10 17:26:13 +08:00
|
|
|
extern struct kmem_cache *ceph_cap_flush_cachep;
|
2014-01-10 02:08:21 +08:00
|
|
|
extern struct kmem_cache *ceph_dentry_cachep;
|
|
|
|
extern struct kmem_cache *ceph_file_cachep;
|
|
|
|
|
2010-04-07 06:14:15 +08:00
|
|
|
/* ceph_common.c */
|
2013-01-31 01:13:33 +08:00
|
|
|
extern bool libceph_compatible(void *data);
|
|
|
|
|
2010-04-07 06:14:15 +08:00
|
|
|
extern const char *ceph_msg_type_name(int type);
|
|
|
|
extern int ceph_check_fsid(struct ceph_client *client, struct ceph_fsid *fsid);
|
2014-01-10 02:08:21 +08:00
|
|
|
extern void *ceph_kvmalloc(size_t size, gfp_t flags);
|
2010-04-07 06:14:15 +08:00
|
|
|
|
2012-01-25 00:08:36 +08:00
|
|
|
extern struct ceph_options *ceph_parse_options(char *options,
|
2010-04-07 06:14:15 +08:00
|
|
|
const char *dev_name, const char *dev_name_end,
|
|
|
|
int (*parse_extra_token)(char *c, void *private),
|
|
|
|
void *private);
|
2015-03-26 02:02:16 +08:00
|
|
|
int ceph_print_client_options(struct seq_file *m, struct ceph_client *client);
|
2010-04-07 06:14:15 +08:00
|
|
|
extern void ceph_destroy_options(struct ceph_options *opt);
|
|
|
|
extern int ceph_compare_options(struct ceph_options *new_opt,
|
|
|
|
struct ceph_client *client);
|
|
|
|
extern struct ceph_client *ceph_create_client(struct ceph_options *opt,
|
2011-08-10 00:41:59 +08:00
|
|
|
void *private,
|
2013-12-25 03:19:23 +08:00
|
|
|
u64 supported_features,
|
|
|
|
u64 required_features);
|
2010-04-07 06:14:15 +08:00
|
|
|
extern u64 ceph_client_id(struct ceph_client *client);
|
|
|
|
extern void ceph_destroy_client(struct ceph_client *client);
|
|
|
|
extern int __ceph_open_session(struct ceph_client *client,
|
|
|
|
unsigned long started);
|
|
|
|
extern int ceph_open_session(struct ceph_client *client);
|
|
|
|
|
|
|
|
/* pagevec.c */
|
|
|
|
extern void ceph_release_page_vector(struct page **pages, int num_pages);
|
|
|
|
|
2013-02-07 03:11:38 +08:00
|
|
|
extern struct page **ceph_get_direct_page_vector(const void __user *data,
|
2010-12-16 12:45:41 +08:00
|
|
|
int num_pages,
|
|
|
|
bool write_page);
|
|
|
|
extern void ceph_put_page_vector(struct page **pages, int num_pages,
|
|
|
|
bool dirty);
|
2010-04-07 06:14:15 +08:00
|
|
|
extern struct page **ceph_alloc_page_vector(int num_pages, gfp_t flags);
|
|
|
|
extern int ceph_copy_user_to_page_vector(struct page **pages,
|
2013-02-07 03:11:38 +08:00
|
|
|
const void __user *data,
|
2010-04-07 06:14:15 +08:00
|
|
|
loff_t off, size_t len);
|
2013-02-07 03:11:38 +08:00
|
|
|
extern void ceph_copy_to_page_vector(struct page **pages,
|
2013-02-07 03:11:38 +08:00
|
|
|
const void *data,
|
2010-04-07 06:14:15 +08:00
|
|
|
loff_t off, size_t len);
|
2013-02-07 03:11:38 +08:00
|
|
|
extern void ceph_copy_from_page_vector(struct page **pages,
|
2013-02-07 03:11:38 +08:00
|
|
|
void *data,
|
2010-04-07 06:14:15 +08:00
|
|
|
loff_t off, size_t len);
|
|
|
|
extern void ceph_zero_page_vector_range(int off, int len, struct page **pages);
|
|
|
|
|
|
|
|
|
|
|
|
#endif /* _FS_CEPH_SUPER_H */
|