OpenCloudOS-Kernel/include/linux/idr.h

167 lines
5.1 KiB
C
Raw Normal View History

/*
* include/linux/idr.h
*
* 2002-10-18 written by Jim Houston jim.houston@ccur.com
* Copyright (C) 2002 by Concurrent Computer Corporation
* Distributed under the GNU GPL license version 2.
*
* Small id to pointer translation service avoiding fixed sized
* tables.
*/
#ifndef __IDR_H__
#define __IDR_H__
#include <linux/types.h>
#include <linux/bitops.h>
#include <linux/init.h>
idr: change the idr structure After scalability problems have been detected when using the sysV ipcs, I have proposed to use an RCU based implementation of the IDR api instead (see threads http://lkml.org/lkml/2008/4/11/212 and http://lkml.org/lkml/2008/4/29/295). This resulted in many people asking to convert the idr API and make it rcu safe (because most of the code was duplicated and thus unmaintanable and unreviewable). So here is a first attempt. The important change wrt to the idr API itself is during idr removes: idr layers are freed after a grace period, instead of being moved to the free list. The important change wrt to ipcs, is that idr_find() can now be called locklessly inside a rcu read critical section. Here are the results I've got for the pmsg test sent by Manfred: 2.6.25-rc3-mm1 2.6.25-rc3-mm1+ 2.6.25-mm1 Patched 2.6.25-mm1 1 1168441 1064021 876000 947488 2 1094264 921059 1549592 1730685 3 2082520 1738165 1694370 2324880 4 2079929 1695521 404553 2400408 5 2898758 406566 391283 3246580 6 2921417 261275 263249 3752148 7 3308761 126056 191742 4243142 8 3329456 100129 141722 4275780 1st column: stock 2.6.25-rc3-mm1 2nd column: 2.6.25-rc3-mm1 + ipc patches (store ipcs into idrs) 3nd column: stock 2.6.25-mm1 4th column: 2.6.25-mm1 + this pacth series. This patch: Add an rcu_head to the idr_layer structure in order to free it after a grace period. Signed-off-by: Nadia Derbey <Nadia.Derbey@bull.net> Reviewed-by: "Paul E. McKenney" <paulmck@us.ibm.com> Cc: Manfred Spraul <manfred@colorfullife.com> Cc: Jim Houston <jim.houston@comcast.net> Cc: Pierre Peiffer <peifferp@gmail.com> Acked-by: Rik van Riel <riel@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-07-25 16:47:57 +08:00
#include <linux/rcupdate.h>
#if BITS_PER_LONG == 32
# define IDR_BITS 5
# define IDR_FULL 0xfffffffful
/* We can only use two of the bits in the top level because there is
only one possible bit in the top level (5 bits * 7 levels = 35
bits, but you only use 31 bits in the id). */
# define TOP_LEVEL_FULL (IDR_FULL >> 30)
#elif BITS_PER_LONG == 64
# define IDR_BITS 6
# define IDR_FULL 0xfffffffffffffffful
/* We can only use two of the bits in the top level because there is
only one possible bit in the top level (6 bits * 6 levels = 36
bits, but you only use 31 bits in the id). */
# define TOP_LEVEL_FULL (IDR_FULL >> 62)
#else
# error "BITS_PER_LONG is not 32 or 64"
#endif
#define IDR_SIZE (1 << IDR_BITS)
#define IDR_MASK ((1 << IDR_BITS)-1)
#define MAX_IDR_SHIFT (sizeof(int)*8 - 1)
#define MAX_IDR_BIT (1U << MAX_IDR_SHIFT)
#define MAX_IDR_MASK (MAX_IDR_BIT - 1)
/* Leave the possibility of an incomplete final layer */
#define MAX_IDR_LEVEL ((MAX_IDR_SHIFT + IDR_BITS - 1) / IDR_BITS)
/* Number of id_layer structs to leave in free list */
#define MAX_IDR_FREE (MAX_IDR_LEVEL * 2)
struct idr_layer {
unsigned long bitmap; /* A zero bit means "space here" */
struct idr_layer __rcu *ary[1<<IDR_BITS];
int count; /* When zero, we can release it */
int layer; /* distance from leaf */
idr: change the idr structure After scalability problems have been detected when using the sysV ipcs, I have proposed to use an RCU based implementation of the IDR api instead (see threads http://lkml.org/lkml/2008/4/11/212 and http://lkml.org/lkml/2008/4/29/295). This resulted in many people asking to convert the idr API and make it rcu safe (because most of the code was duplicated and thus unmaintanable and unreviewable). So here is a first attempt. The important change wrt to the idr API itself is during idr removes: idr layers are freed after a grace period, instead of being moved to the free list. The important change wrt to ipcs, is that idr_find() can now be called locklessly inside a rcu read critical section. Here are the results I've got for the pmsg test sent by Manfred: 2.6.25-rc3-mm1 2.6.25-rc3-mm1+ 2.6.25-mm1 Patched 2.6.25-mm1 1 1168441 1064021 876000 947488 2 1094264 921059 1549592 1730685 3 2082520 1738165 1694370 2324880 4 2079929 1695521 404553 2400408 5 2898758 406566 391283 3246580 6 2921417 261275 263249 3752148 7 3308761 126056 191742 4243142 8 3329456 100129 141722 4275780 1st column: stock 2.6.25-rc3-mm1 2nd column: 2.6.25-rc3-mm1 + ipc patches (store ipcs into idrs) 3nd column: stock 2.6.25-mm1 4th column: 2.6.25-mm1 + this pacth series. This patch: Add an rcu_head to the idr_layer structure in order to free it after a grace period. Signed-off-by: Nadia Derbey <Nadia.Derbey@bull.net> Reviewed-by: "Paul E. McKenney" <paulmck@us.ibm.com> Cc: Manfred Spraul <manfred@colorfullife.com> Cc: Jim Houston <jim.houston@comcast.net> Cc: Pierre Peiffer <peifferp@gmail.com> Acked-by: Rik van Riel <riel@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-07-25 16:47:57 +08:00
struct rcu_head rcu_head;
};
struct idr {
struct idr_layer __rcu *top;
struct idr_layer *id_free;
int layers; /* only valid without concurrent changes */
int id_free_cnt;
spinlock_t lock;
};
#define IDR_INIT(name) \
{ \
.top = NULL, \
.id_free = NULL, \
.layers = 0, \
.id_free_cnt = 0, \
.lock = __SPIN_LOCK_UNLOCKED(name.lock), \
}
#define DEFINE_IDR(name) struct idr name = IDR_INIT(name)
/* Actions to be taken after a call to _idr_sub_alloc */
#define IDR_NEED_TO_GROW -2
#define IDR_NOMORE_SPACE -3
#define _idr_rc_to_errno(rc) ((rc) == -1 ? -EAGAIN : -ENOSPC)
/**
* DOC: idr sync
* idr synchronization (stolen from radix-tree.h)
*
* idr_find() is able to be called locklessly, using RCU. The caller must
* ensure calls to this function are made within rcu_read_lock() regions.
* Other readers (lock-free or otherwise) and modifications may be running
* concurrently.
*
* It is still required that the caller manage the synchronization and
* lifetimes of the items. So if RCU lock-free lookups are used, typically
* this would mean that the items have their own locks, or are amenable to
* lock-free access; and that the items are freed by RCU (or only freed after
* having been deleted from the idr tree *and* a synchronize_rcu() grace
* period).
*/
/*
* This is what we export.
*/
void *idr_find(struct idr *idp, int id);
int idr_pre_get(struct idr *idp, gfp_t gfp_mask);
int idr_get_new(struct idr *idp, void *ptr, int *id);
int idr_get_new_above(struct idr *idp, void *ptr, int starting_id, int *id);
int idr_for_each(struct idr *idp,
int (*fn)(int id, void *p, void *data), void *data);
cgroup: CSS ID support Patch for Per-CSS(Cgroup Subsys State) ID and private hierarchy code. This patch attaches unique ID to each css and provides following. - css_lookup(subsys, id) returns pointer to struct cgroup_subysys_state of id. - css_get_next(subsys, id, rootid, depth, foundid) returns the next css under "root" by scanning When cgroup_subsys->use_id is set, an id for css is maintained. The cgroup framework only parepares - css_id of root css for subsys - id is automatically attached at creation of css. - id is *not* freed automatically. Because the cgroup framework don't know lifetime of cgroup_subsys_state. free_css_id() function is provided. This must be called by subsys. There are several reasons to develop this. - Saving space .... For example, memcg's swap_cgroup is array of pointers to cgroup. But it is not necessary to be very fast. By replacing pointers(8bytes per ent) to ID (2byes per ent), we can reduce much amount of memory usage. - Scanning without lock. CSS_ID provides "scan id under this ROOT" function. By this, scanning css under root can be written without locks. ex) do { rcu_read_lock(); next = cgroup_get_next(subsys, id, root, &found); /* check sanity of next here */ css_tryget(); rcu_read_unlock(); id = found + 1 } while(...) Characteristics: - Each css has unique ID under subsys. - Lifetime of ID is controlled by subsys. - css ID contains "ID" and "Depth in hierarchy" and stack of hierarchy - Allowed ID is 1-65535, ID 0 is UNUSED ID. Design Choices: - scan-by-ID v.s. scan-by-tree-walk. As /proc's pid scan does, scan-by-ID is robust when scanning is done by following kind of routine. scan -> rest a while(release a lock) -> conitunue from interrupted memcg's hierarchical reclaim does this. - When subsys->use_id is set, # of css in the system is limited to 65535. [bharata@linux.vnet.ibm.com: remove rcu_read_lock() from css_get_next()] Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Acked-by: Paul Menage <menage@google.com> Cc: Li Zefan <lizf@cn.fujitsu.com> Cc: Balbir Singh <balbir@in.ibm.com> Cc: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Signed-off-by: Bharata B Rao <bharata@linux.vnet.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-04-03 07:57:25 +08:00
void *idr_get_next(struct idr *idp, int *nextid);
void *idr_replace(struct idr *idp, void *ptr, int id);
void idr_remove(struct idr *idp, int id);
void idr_remove_all(struct idr *idp);
void idr_destroy(struct idr *idp);
void idr_init(struct idr *idp);
/*
* IDA - IDR based id allocator, use when translation from id to
* pointer isn't necessary.
*
* IDA_BITMAP_LONGS is calculated to be one less to accommodate
* ida_bitmap->nr_busy so that the whole struct fits in 128 bytes.
*/
#define IDA_CHUNK_SIZE 128 /* 128 bytes per chunk */
#define IDA_BITMAP_LONGS (IDA_CHUNK_SIZE / sizeof(long) - 1)
#define IDA_BITMAP_BITS (IDA_BITMAP_LONGS * sizeof(long) * 8)
struct ida_bitmap {
long nr_busy;
unsigned long bitmap[IDA_BITMAP_LONGS];
};
struct ida {
struct idr idr;
struct ida_bitmap *free_bitmap;
};
#define IDA_INIT(name) { .idr = IDR_INIT(name), .free_bitmap = NULL, }
#define DEFINE_IDA(name) struct ida name = IDA_INIT(name)
int ida_pre_get(struct ida *ida, gfp_t gfp_mask);
int ida_get_new_above(struct ida *ida, int starting_id, int *p_id);
int ida_get_new(struct ida *ida, int *p_id);
void ida_remove(struct ida *ida, int id);
void ida_destroy(struct ida *ida);
void ida_init(struct ida *ida);
int ida_simple_get(struct ida *ida, unsigned int start, unsigned int end,
gfp_t gfp_mask);
void ida_simple_remove(struct ida *ida, unsigned int id);
void __init idr_init_cache(void);
/**
* idr_for_each_entry - iterate over an idr's elements of a given type
* @idp: idr handle
* @entry: the type * to use as cursor
* @id: id entry's key
*/
#define idr_for_each_entry(idp, entry, id) \
for (id = 0, entry = (typeof(entry))idr_get_next((idp), &(id)); \
entry != NULL; \
++id, entry = (typeof(entry))idr_get_next((idp), &(id)))
#endif /* __IDR_H__ */