f0f1d32f93
Initial benchmarks show they're a net loss: $ for i in /sys/devices/system/cpu/cpu*/cpufreq/scaling_governor ; do echo performance > $i; done $ echo 4096 32000 64 128 > /proc/sys/kernel/sem $ ./sembench -t 2048 -w 1900 -o 0 Pre: run time 30 seconds 778936 worker burns per second run time 30 seconds 912190 worker burns per second run time 30 seconds 817506 worker burns per second run time 30 seconds 830870 worker burns per second run time 30 seconds 845056 worker burns per second Post: run time 30 seconds 905920 worker burns per second run time 30 seconds 849046 worker burns per second run time 30 seconds 886286 worker burns per second run time 30 seconds 822320 worker burns per second run time 30 seconds 900283 worker burns per second So about 4% faster. (!) cpu_relax() stalls the pipeline, therefore, when used in a tight loop it has the following benefits: - allows SMT siblings to have a go; - reduces pressure on the CPU interconnect. However, cmpxchg loops are unfair and thus have unbounded completion time, therefore we should avoid getting in such heavily contended situations where the above benefits make any difference. A typical cmpxchg loop should not go round more than a handfull of times at worst, therefore adding extra delays just slows things down. Since the llist primitives are new, there aren't any bad users yet, and we should avoid growing them. Heavily contended sites should generally be better off using the ticket locks for serialization since they provide bounded completion times (fifo-fair over the cpus). Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Huang Ying <ying.huang@intel.com> Cc: Andrew Morton <akpm@linux-foundation.org> Link: http://lkml.kernel.org/r/1315836358.26517.43.camel@twins Signed-off-by: Ingo Molnar <mingo@elte.hu>
181 lines
6.1 KiB
C
181 lines
6.1 KiB
C
#ifndef LLIST_H
|
|
#define LLIST_H
|
|
/*
|
|
* Lock-less NULL terminated single linked list
|
|
*
|
|
* If there are multiple producers and multiple consumers, llist_add
|
|
* can be used in producers and llist_del_all can be used in
|
|
* consumers. They can work simultaneously without lock. But
|
|
* llist_del_first can not be used here. Because llist_del_first
|
|
* depends on list->first->next does not changed if list->first is not
|
|
* changed during its operation, but llist_del_first, llist_add,
|
|
* llist_add (or llist_del_all, llist_add, llist_add) sequence in
|
|
* another consumer may violate that.
|
|
*
|
|
* If there are multiple producers and one consumer, llist_add can be
|
|
* used in producers and llist_del_all or llist_del_first can be used
|
|
* in the consumer.
|
|
*
|
|
* This can be summarized as follow:
|
|
*
|
|
* | add | del_first | del_all
|
|
* add | - | - | -
|
|
* del_first | | L | L
|
|
* del_all | | | -
|
|
*
|
|
* Where "-" stands for no lock is needed, while "L" stands for lock
|
|
* is needed.
|
|
*
|
|
* The list entries deleted via llist_del_all can be traversed with
|
|
* traversing function such as llist_for_each etc. But the list
|
|
* entries can not be traversed safely before deleted from the list.
|
|
* The order of deleted entries is from the newest to the oldest added
|
|
* one. If you want to traverse from the oldest to the newest, you
|
|
* must reverse the order by yourself before traversing.
|
|
*
|
|
* The basic atomic operation of this list is cmpxchg on long. On
|
|
* architectures that don't have NMI-safe cmpxchg implementation, the
|
|
* list can NOT be used in NMI handlers. So code that uses the list in
|
|
* an NMI handler should depend on CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG.
|
|
*
|
|
* Copyright 2010,2011 Intel Corp.
|
|
* Author: Huang Ying <ying.huang@intel.com>
|
|
*
|
|
* This program is free software; you can redistribute it and/or
|
|
* modify it under the terms of the GNU General Public License version
|
|
* 2 as published by the Free Software Foundation;
|
|
*
|
|
* This program is distributed in the hope that it will be useful,
|
|
* but WITHOUT ANY WARRANTY; without even the implied warranty of
|
|
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
|
* GNU General Public License for more details.
|
|
*
|
|
* You should have received a copy of the GNU General Public License
|
|
* along with this program; if not, write to the Free Software
|
|
* Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
|
|
*/
|
|
|
|
#include <linux/kernel.h>
|
|
#include <asm/system.h>
|
|
#include <asm/processor.h>
|
|
|
|
struct llist_head {
|
|
struct llist_node *first;
|
|
};
|
|
|
|
struct llist_node {
|
|
struct llist_node *next;
|
|
};
|
|
|
|
#define LLIST_HEAD_INIT(name) { NULL }
|
|
#define LLIST_HEAD(name) struct llist_head name = LLIST_HEAD_INIT(name)
|
|
|
|
/**
|
|
* init_llist_head - initialize lock-less list head
|
|
* @head: the head for your lock-less list
|
|
*/
|
|
static inline void init_llist_head(struct llist_head *list)
|
|
{
|
|
list->first = NULL;
|
|
}
|
|
|
|
/**
|
|
* llist_entry - get the struct of this entry
|
|
* @ptr: the &struct llist_node pointer.
|
|
* @type: the type of the struct this is embedded in.
|
|
* @member: the name of the llist_node within the struct.
|
|
*/
|
|
#define llist_entry(ptr, type, member) \
|
|
container_of(ptr, type, member)
|
|
|
|
/**
|
|
* llist_for_each - iterate over some deleted entries of a lock-less list
|
|
* @pos: the &struct llist_node to use as a loop cursor
|
|
* @node: the first entry of deleted list entries
|
|
*
|
|
* In general, some entries of the lock-less list can be traversed
|
|
* safely only after being deleted from list, so start with an entry
|
|
* instead of list head.
|
|
*
|
|
* If being used on entries deleted from lock-less list directly, the
|
|
* traverse order is from the newest to the oldest added entry. If
|
|
* you want to traverse from the oldest to the newest, you must
|
|
* reverse the order by yourself before traversing.
|
|
*/
|
|
#define llist_for_each(pos, node) \
|
|
for ((pos) = (node); pos; (pos) = (pos)->next)
|
|
|
|
/**
|
|
* llist_for_each_entry - iterate over some deleted entries of lock-less list of given type
|
|
* @pos: the type * to use as a loop cursor.
|
|
* @node: the fist entry of deleted list entries.
|
|
* @member: the name of the llist_node with the struct.
|
|
*
|
|
* In general, some entries of the lock-less list can be traversed
|
|
* safely only after being removed from list, so start with an entry
|
|
* instead of list head.
|
|
*
|
|
* If being used on entries deleted from lock-less list directly, the
|
|
* traverse order is from the newest to the oldest added entry. If
|
|
* you want to traverse from the oldest to the newest, you must
|
|
* reverse the order by yourself before traversing.
|
|
*/
|
|
#define llist_for_each_entry(pos, node, member) \
|
|
for ((pos) = llist_entry((node), typeof(*(pos)), member); \
|
|
&(pos)->member != NULL; \
|
|
(pos) = llist_entry((pos)->member.next, typeof(*(pos)), member))
|
|
|
|
/**
|
|
* llist_empty - tests whether a lock-less list is empty
|
|
* @head: the list to test
|
|
*
|
|
* Not guaranteed to be accurate or up to date. Just a quick way to
|
|
* test whether the list is empty without deleting something from the
|
|
* list.
|
|
*/
|
|
static inline bool llist_empty(const struct llist_head *head)
|
|
{
|
|
return ACCESS_ONCE(head->first) == NULL;
|
|
}
|
|
|
|
static inline struct llist_node *llist_next(struct llist_node *node)
|
|
{
|
|
return node->next;
|
|
}
|
|
|
|
/**
|
|
* llist_add - add a new entry
|
|
* @new: new entry to be added
|
|
* @head: the head for your lock-less list
|
|
*
|
|
* Return whether list is empty before adding.
|
|
*/
|
|
static inline bool llist_add(struct llist_node *new, struct llist_head *head)
|
|
{
|
|
struct llist_node *entry, *old_entry;
|
|
|
|
entry = head->first;
|
|
for (;;) {
|
|
old_entry = entry;
|
|
new->next = entry;
|
|
entry = cmpxchg(&head->first, old_entry, new);
|
|
if (entry == old_entry)
|
|
break;
|
|
}
|
|
|
|
return old_entry == NULL;
|
|
}
|
|
|
|
/**
|
|
* llist_del_all - delete all entries from lock-less list
|
|
* @head: the head of lock-less list to delete all entries
|
|
*
|
|
* If list is empty, return NULL, otherwise, delete all entries and
|
|
* return the pointer to the first entry. The order of entries
|
|
* deleted is from the newest to the oldest added one.
|
|
*/
|
|
static inline struct llist_node *llist_del_all(struct llist_head *head)
|
|
{
|
|
return xchg(&head->first, NULL);
|
|
}
|
|
#endif /* LLIST_H */
|