OpenCloudOS-Kernel/include/linux/idr.h

187 lines
5.5 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>
/*
* We want shallower trees and thus more bits covered at each layer. 8
* bits gives us large enough first layer for most use cases and maximum
* tree depth of 4. Each idr_layer is slightly larger than 2k on 64bit and
* 1k on 32bit.
*/
#define IDR_BITS 8
#define IDR_SIZE (1 << IDR_BITS)
#define IDR_MASK ((1 << IDR_BITS)-1)
struct idr_layer {
int prefix; /* the ID prefix of this idr_layer */
int layer; /* distance from leaf */
struct idr_layer __rcu *ary[1<<IDR_BITS];
int count; /* When zero, we can release it */
union {
/* A zero bit means "space here" */
DECLARE_BITMAP(bitmap, IDR_SIZE);
struct rcu_head rcu_head;
};
};
struct idr {
struct idr_layer __rcu *hint; /* the last layer allocated from */
struct idr_layer __rcu *top;
int layers; /* only valid w/o concurrent changes */
idr: introduce idr_alloc_cyclic() As Tejun points out, there are several users of the IDR facility that attempt to use it in a cyclic fashion. These users are likely to see -ENOSPC errors after the counter wraps one or more times however. This patchset adds a new idr_alloc_cyclic routine and converts several of these users to it. Many of these users are in obscure parts of the kernel, and I don't have a good way to test some of them. The change is pretty straightforward though, so hopefully it won't be an issue. There is one other cyclic user of idr_alloc that I didn't touch in ipc/util.c. That one is doing some strange stuff that I didn't quite understand, but it looks like it should probably be converted later somehow. This patch: Thus spake Tejun Heo: Ooh, BTW, the cyclic allocation is broken. It's prone to -ENOSPC after the first wraparound. There are several cyclic users in the kernel and I think it probably would be best to implement cyclic support in idr. This patch does that by adding new idr_alloc_cyclic function that such users in the kernel can use. With this, there's no need for a caller to keep track of the last value used as that's now tracked internally. This should prevent the ENOSPC problems that can hit when the "last allocated" counter exceeds INT_MAX. Later patches will convert existing cyclic users to the new interface. Signed-off-by: Jeff Layton <jlayton@redhat.com> Reviewed-by: Tejun Heo <tj@kernel.org> Cc: "David S. Miller" <davem@davemloft.net> Cc: "J. Bruce Fields" <bfields@fieldses.org> Cc: Eric Paris <eparis@parisplace.org> Cc: Jack Morgenstein <jackm@dev.mellanox.co.il> Cc: John McCutchan <john@johnmccutchan.com> Cc: Neil Horman <nhorman@tuxdriver.com> Cc: Or Gerlitz <ogerlitz@mellanox.com> Cc: Robert Love <rlove@rlove.org> Cc: Roland Dreier <roland@purestorage.com> Cc: Sridhar Samudrala <sri@us.ibm.com> Cc: Steve Wise <swise@opengridcomputing.com> Cc: Tom Tucker <tom@opengridcomputing.com> Cc: Vlad Yasevich <vyasevich@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-04-30 07:21:16 +08:00
int cur; /* current pos for cyclic allocation */
spinlock_t lock;
int id_free_cnt;
struct idr_layer *id_free;
};
#define IDR_INIT(name) \
{ \
.lock = __SPIN_LOCK_UNLOCKED(name.lock), \
}
#define DEFINE_IDR(name) struct idr name = IDR_INIT(name)
/**
* 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_slowpath(struct idr *idp, int id);
idr: implement idr_preload[_end]() and idr_alloc() The current idr interface is very cumbersome. * For all allocations, two function calls - idr_pre_get() and idr_get_new*() - should be made. * idr_pre_get() doesn't guarantee that the following idr_get_new*() will not fail from memory shortage. If idr_get_new*() returns -EAGAIN, the caller is expected to retry pre_get and allocation. * idr_get_new*() can't enforce upper limit. Upper limit can only be enforced by allocating and then freeing if above limit. * idr_layer buffer is unnecessarily per-idr. Each idr ends up keeping around MAX_IDR_FREE idr_layers. The memory consumed per idr is under two pages but it makes it difficult to make idr_layer larger. This patch implements the following new set of allocation functions. * idr_preload[_end]() - Similar to radix preload but doesn't fail. The first idr_alloc() inside preload section can be treated as if it were called with @gfp_mask used for idr_preload(). * idr_alloc() - Allocate an ID w/ lower and upper limits. Takes @gfp_flags and can be used w/o preloading. When used inside preloaded section, the allocation mask of preloading can be assumed. If idr_alloc() can be called from a context which allows sufficiently relaxed @gfp_mask, it can be used by itself. If, for example, idr_alloc() is called inside spinlock protected region, preloading can be used like the following. idr_preload(GFP_KERNEL); spin_lock(lock); id = idr_alloc(idr, ptr, start, end, GFP_NOWAIT); spin_unlock(lock); idr_preload_end(); if (id < 0) error; which is much simpler and less error-prone than idr_pre_get and idr_get_new*() loop. The new interface uses per-pcu idr_layer buffer and thus the number of idr's in the system doesn't affect the amount of memory used for preloading. idr_layer_alloc() is introduced to handle idr_layer allocations for both old and new ID allocation paths. This is a bit hairy now but the new interface is expected to replace the old and the internal implementation eventually will become simpler. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Rusty Russell <rusty@rustcorp.com.au> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-02-28 09:03:55 +08:00
void idr_preload(gfp_t gfp_mask);
int idr_alloc(struct idr *idp, void *ptr, int start, int end, gfp_t gfp_mask);
idr: introduce idr_alloc_cyclic() As Tejun points out, there are several users of the IDR facility that attempt to use it in a cyclic fashion. These users are likely to see -ENOSPC errors after the counter wraps one or more times however. This patchset adds a new idr_alloc_cyclic routine and converts several of these users to it. Many of these users are in obscure parts of the kernel, and I don't have a good way to test some of them. The change is pretty straightforward though, so hopefully it won't be an issue. There is one other cyclic user of idr_alloc that I didn't touch in ipc/util.c. That one is doing some strange stuff that I didn't quite understand, but it looks like it should probably be converted later somehow. This patch: Thus spake Tejun Heo: Ooh, BTW, the cyclic allocation is broken. It's prone to -ENOSPC after the first wraparound. There are several cyclic users in the kernel and I think it probably would be best to implement cyclic support in idr. This patch does that by adding new idr_alloc_cyclic function that such users in the kernel can use. With this, there's no need for a caller to keep track of the last value used as that's now tracked internally. This should prevent the ENOSPC problems that can hit when the "last allocated" counter exceeds INT_MAX. Later patches will convert existing cyclic users to the new interface. Signed-off-by: Jeff Layton <jlayton@redhat.com> Reviewed-by: Tejun Heo <tj@kernel.org> Cc: "David S. Miller" <davem@davemloft.net> Cc: "J. Bruce Fields" <bfields@fieldses.org> Cc: Eric Paris <eparis@parisplace.org> Cc: Jack Morgenstein <jackm@dev.mellanox.co.il> Cc: John McCutchan <john@johnmccutchan.com> Cc: Neil Horman <nhorman@tuxdriver.com> Cc: Or Gerlitz <ogerlitz@mellanox.com> Cc: Robert Love <rlove@rlove.org> Cc: Roland Dreier <roland@purestorage.com> Cc: Sridhar Samudrala <sri@us.ibm.com> Cc: Steve Wise <swise@opengridcomputing.com> Cc: Tom Tucker <tom@opengridcomputing.com> Cc: Vlad Yasevich <vyasevich@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-04-30 07:21:16 +08:00
int idr_alloc_cyclic(struct idr *idr, void *ptr, int start, int end, gfp_t gfp_mask);
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_destroy(struct idr *idp);
void idr_init(struct idr *idp);
bool idr_is_empty(struct idr *idp);
idr: implement idr_preload[_end]() and idr_alloc() The current idr interface is very cumbersome. * For all allocations, two function calls - idr_pre_get() and idr_get_new*() - should be made. * idr_pre_get() doesn't guarantee that the following idr_get_new*() will not fail from memory shortage. If idr_get_new*() returns -EAGAIN, the caller is expected to retry pre_get and allocation. * idr_get_new*() can't enforce upper limit. Upper limit can only be enforced by allocating and then freeing if above limit. * idr_layer buffer is unnecessarily per-idr. Each idr ends up keeping around MAX_IDR_FREE idr_layers. The memory consumed per idr is under two pages but it makes it difficult to make idr_layer larger. This patch implements the following new set of allocation functions. * idr_preload[_end]() - Similar to radix preload but doesn't fail. The first idr_alloc() inside preload section can be treated as if it were called with @gfp_mask used for idr_preload(). * idr_alloc() - Allocate an ID w/ lower and upper limits. Takes @gfp_flags and can be used w/o preloading. When used inside preloaded section, the allocation mask of preloading can be assumed. If idr_alloc() can be called from a context which allows sufficiently relaxed @gfp_mask, it can be used by itself. If, for example, idr_alloc() is called inside spinlock protected region, preloading can be used like the following. idr_preload(GFP_KERNEL); spin_lock(lock); id = idr_alloc(idr, ptr, start, end, GFP_NOWAIT); spin_unlock(lock); idr_preload_end(); if (id < 0) error; which is much simpler and less error-prone than idr_pre_get and idr_get_new*() loop. The new interface uses per-pcu idr_layer buffer and thus the number of idr's in the system doesn't affect the amount of memory used for preloading. idr_layer_alloc() is introduced to handle idr_layer allocations for both old and new ID allocation paths. This is a bit hairy now but the new interface is expected to replace the old and the internal implementation eventually will become simpler. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Rusty Russell <rusty@rustcorp.com.au> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-02-28 09:03:55 +08:00
/**
* idr_preload_end - end preload section started with idr_preload()
*
* Each idr_preload() should be matched with an invocation of this
* function. See idr_preload() for details.
*/
static inline void idr_preload_end(void)
{
preempt_enable();
}
/**
* idr_find - return pointer for given id
* @idr: idr handle
* @id: lookup key
*
* Return the pointer given the id it has been registered with. A %NULL
* return indicates that @id is not valid or you passed %NULL in
* idr_get_new().
*
* This function can be called under rcu_read_lock(), given that the leaf
* pointers lifetimes are correctly managed.
*/
static inline void *idr_find(struct idr *idr, int id)
{
struct idr_layer *hint = rcu_dereference_raw(idr->hint);
if (hint && (id & ~IDR_MASK) == hint->prefix)
return rcu_dereference_raw(hint->ary[id & IDR_MASK]);
return idr_find_slowpath(idr, id);
}
/**
* 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
*
* @entry and @id do not need to be initialized before the loop, and
* after normal terminatinon @entry is left with the value NULL. This
* is convenient for a "not found" value.
*/
#define idr_for_each_entry(idp, entry, id) \
for (id = 0; ((entry) = idr_get_next(idp, &(id))) != NULL; ++id)
/*
* 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).idr), .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);
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);
/**
* ida_get_new - allocate new ID
* @ida: idr handle
* @p_id: pointer to the allocated handle
*
* Simple wrapper around ida_get_new_above() w/ @starting_id of zero.
*/
static inline int ida_get_new(struct ida *ida, int *p_id)
{
return ida_get_new_above(ida, 0, p_id);
}
void __init idr_init_cache(void);
#endif /* __IDR_H__ */