* Huang Ying (ying.huang@xxxxxxxxx) wrote:
> Cmpxchg is used to implement adding new entry to the list, deleting
> all entries from the list, deleting first entry of the list and some
> other operations.
>
> Because this is a single list, so the tail can not be accessed in O(1).
>
> 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 handler. So code uses the list in NMI
> handler should depend on CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG.
>
> Signed-off-by: Huang Ying <ying.huang@xxxxxxxxx>
> Reviewed-by: Andi Kleen <ak@xxxxxxxxxxxxxxx>
> Cc: Mathieu Desnoyers <mathieu.desnoyers@xxxxxxxxxxxx>
Reviewed-by: Mathieu Desnoyers <mathieu.desnoyers@xxxxxxxxxxxx>
Thanks,
Mathieu
> Cc: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
> ---
> include/linux/llist.h | 126 ++++++++++++++++++++++++++++++++++++++++++++++++
> lib/Kconfig | 3 +
> lib/Makefile | 2
> lib/llist.c | 129 ++++++++++++++++++++++++++++++++++++++++++++++++++
> 4 files changed, 260 insertions(+)
> create mode 100644 include/linux/llist.h
> create mode 100644 lib/llist.c
>
> --- /dev/null
> +++ b/include/linux/llist.h
> @@ -0,0 +1,126 @@
> +#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 handler. So code uses the list in NMI
> + * handler should depend on CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG.
> + */
> +
> +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 int llist_empty(const struct llist_head *head)
> +{
> + return ACCESS_ONCE(head->first) == NULL;
> +}
> +
> +void llist_add(struct llist_node *new, struct llist_head *head);
> +void llist_add_batch(struct llist_node *new_first, struct llist_node *new_last,
> + struct llist_head *head);
> +struct llist_node *llist_del_first(struct llist_head *head);
> +struct llist_node *llist_del_all(struct llist_head *head);
> +#endif /* LLIST_H */
> --- a/lib/Kconfig
> +++ b/lib/Kconfig
> @@ -272,4 +272,7 @@ config AVERAGE
>
> If unsure, say N.
>
> +config LLIST
> + bool
> +
> endmenu
> --- a/lib/Makefile
> +++ b/lib/Makefile
> @@ -115,6 +115,8 @@ obj-$(CONFIG_AVERAGE) += average.o
>
> obj-$(CONFIG_CPU_RMAP) += cpu_rmap.o
>
> +obj-$(CONFIG_LLIST) += llist.o
> +
> hostprogs-y := gen_crc32table
> clean-files := crc32table.h
>
> --- /dev/null
> +++ b/lib/llist.c
> @@ -0,0 +1,129 @@
> +/*
> + * Lock-less NULL terminated single linked list
> + *
> + * 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 handler. So code uses the list in NMI
> + * handler should depend on CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG.
> + *
> + * Copyright 2010,2011 Intel Corp.
> + * Author: Huang Ying <ying.huang@xxxxxxxxx>
> + *
> + * 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 <linux/module.h>
> +#include <linux/interrupt.h>
> +#include <linux/llist.h>
> +
> +#include <asm/system.h>
> +
> +/**
> + * llist_add - add a new entry
> + * @new: new entry to be added
> + * @head: the head for your lock-less list
> + */
> +void llist_add(struct llist_node *new, struct llist_head *head)
> +{
> + struct llist_node *entry, *old_entry;
> +
> +#ifndef CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG
> + BUG_ON(in_nmi());
> +#endif
> +
> + entry = head->first;
> + do {
> + old_entry = entry;
> + new->next = entry;
> + cpu_relax();
> + } while ((entry = cmpxchg(&head->first, old_entry, new)) != old_entry);
> +}
> +EXPORT_SYMBOL_GPL(llist_add);
> +
> +/**
> + * llist_add_batch - add several linked entries in batch
> + * @new_first: first entry in batch to be added
> + * @new_last: last entry in batch to be added
> + * @head: the head for your lock-less list
> + */
> +void llist_add_batch(struct llist_node *new_first, struct llist_node *new_last,
> + struct llist_head *head)
> +{
> + struct llist_node *entry, *old_entry;
> +
> +#ifndef CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG
> + BUG_ON(in_nmi());
> +#endif
> +
> + entry = head->first;
> + do {
> + old_entry = entry;
> + new_last->next = entry;
> + cpu_relax();
> + } while ((entry = cmpxchg(&head->first, old_entry, new_first)) != old_entry);
> +}
> +EXPORT_SYMBOL_GPL(llist_add_batch);
> +
> +/**
> + * llist_del_first - delete the first entry of lock-less list
> + * @head: the head for your lock-less list
> + *
> + * If list is empty, return NULL, otherwise, return the first entry
> + * deleted, this is the newest added one.
> + *
> + * Only one llist_del_first user can be used simultaneously with
> + * multiple llist_add users without lock. Because otherwise
> + * llist_del_first, llist_add, llist_add (or llist_del_all, llist_add,
> + * llist_add) sequence in another user may change @head->first->next,
> + * but keep @head->first. If multiple consumers are needed, please
> + * use llist_del_all or use lock between consumers.
> + */
> +struct llist_node *llist_del_first(struct llist_head *head)
> +{
> + struct llist_node *entry, *old_entry, *next;
> +
> +#ifndef CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG
> + BUG_ON(in_nmi());
> +#endif
> +
> + entry = head->first;
> + do {
> + if (entry == NULL)
> + return NULL;
> + old_entry = entry;
> + next = entry->next;
> + cpu_relax();
> + } while ((entry = cmpxchg(&head->first, old_entry, next)) != old_entry);
> +
> + return entry;
> +}
> +EXPORT_SYMBOL_GPL(llist_del_first);
> +
> +/**
> + * 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.
> + */
> +struct llist_node *llist_del_all(struct llist_head *head)
> +{
> +#ifndef CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG
> + BUG_ON(in_nmi());
> +#endif
> +
> + return xchg(&head->first, NULL);
> +}
> +EXPORT_SYMBOL_GPL(llist_del_all);
--
Mathieu Desnoyers
Operating System Efficiency R&D Consultant
EfficiOS Inc.
http://www.efficios.com
--
To unsubscribe from this list: send the line "unsubscribe linux-acpi" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
