From: Nick Piggin <npiggin@kernel.dk>
To: linux-fsdevel@vger.kernel.org
Cc: linux-kernel@vger.kernel.org
Subject: [PATCH 42/46] kernel: add bl_list
Date: Sat, 27 Nov 2010 20:45:12 +1100 [thread overview]
Message-ID: <574d900af0cf01be2ab929a4030ed4a3d2a2b1de.1290852960.git.npiggin@kernel.dk> (raw)
In-Reply-To: <cover.1290852958.git.npiggin@kernel.dk>
Introduce a type of hlist that can support the use of the lowest bit in the
hlist_head. This will be subsequently used to implement per-bucket bit spinlock
for inode and dentry hashes, and may be useful in other cases such as network
hashes.
Reviewed-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Signed-off-by: Nick Piggin <npiggin@kernel.dk>
---
include/linux/list_bl.h | 141 ++++++++++++++++++++++++++++++++++++++++++++
include/linux/rculist_bl.h | 128 ++++++++++++++++++++++++++++++++++++++++
2 files changed, 269 insertions(+), 0 deletions(-)
create mode 100644 include/linux/list_bl.h
create mode 100644 include/linux/rculist_bl.h
diff --git a/include/linux/list_bl.h b/include/linux/list_bl.h
new file mode 100644
index 0000000..c2034b9
--- /dev/null
+++ b/include/linux/list_bl.h
@@ -0,0 +1,141 @@
+#ifndef _LINUX_LIST_BL_H
+#define _LINUX_LIST_BL_H
+
+#include <linux/list.h>
+#include <linux/bit_spinlock.h>
+
+/*
+ * Special version of lists, where head of the list has a bit spinlock
+ * in the lowest bit. This is useful for scalable hash tables without
+ * increasing memory footprint overhead.
+ *
+ * For modification operations, the 0 bit of hlist_bl_head->first
+ * pointer must be set.
+ */
+
+#if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK)
+#define LIST_BL_LOCKMASK 1UL
+#else
+#define LIST_BL_LOCKMASK 0UL
+#endif
+
+#ifdef CONFIG_DEBUG_LIST
+#define LIST_BL_BUG_ON(x) BUG_ON(x)
+#else
+#define LIST_BL_BUG_ON(x)
+#endif
+
+
+struct hlist_bl_head {
+ struct hlist_bl_node *first;
+};
+
+struct hlist_bl_node {
+ struct hlist_bl_node *next, **pprev;
+};
+#define INIT_HLIST_BL_HEAD(ptr) \
+ ((ptr)->first = NULL)
+
+static inline void INIT_HLIST_BL_NODE(struct hlist_bl_node *h)
+{
+ h->next = NULL;
+ h->pprev = NULL;
+}
+
+#define hlist_bl_entry(ptr, type, member) container_of(ptr,type,member)
+
+static inline int hlist_bl_unhashed(const struct hlist_bl_node *h)
+{
+ return !h->pprev;
+}
+
+static inline struct hlist_bl_node *hlist_bl_first(struct hlist_bl_head *h)
+{
+ return (struct hlist_bl_node *)
+ ((unsigned long)h->first & ~LIST_BL_LOCKMASK);
+}
+
+static inline void hlist_bl_set_first(struct hlist_bl_head *h,
+ struct hlist_bl_node *n)
+{
+ LIST_BL_BUG_ON((unsigned long)n & LIST_BL_LOCKMASK);
+ LIST_BL_BUG_ON(!bit_spin_is_locked(0, (unsigned long *)&h->first));
+ h->first = (struct hlist_bl_node *)((unsigned long)n | LIST_BL_LOCKMASK);
+}
+
+static inline int hlist_bl_empty(const struct hlist_bl_head *h)
+{
+ return !((unsigned long)h->first & ~LIST_BL_LOCKMASK);
+}
+
+static inline void hlist_bl_add_head(struct hlist_bl_node *n,
+ struct hlist_bl_head *h)
+{
+ struct hlist_bl_node *first = hlist_bl_first(h);
+
+ n->next = first;
+ if (first)
+ first->pprev = &n->next;
+ n->pprev = &h->first;
+ hlist_bl_set_first(h, n);
+}
+
+static inline void __hlist_bl_del(struct hlist_bl_node *n)
+{
+ struct hlist_bl_node *next = n->next;
+ struct hlist_bl_node **pprev = n->pprev;
+
+ LIST_BL_BUG_ON((unsigned long)n & LIST_BL_LOCKMASK);
+
+ /* pprev may be `first`, so be careful not to lose the lock bit */
+ *pprev = (struct hlist_bl_node *)
+ ((unsigned long)next |
+ ((unsigned long)*pprev & LIST_BL_LOCKMASK));
+ if (next)
+ next->pprev = pprev;
+}
+
+static inline void hlist_bl_del(struct hlist_bl_node *n)
+{
+ __hlist_bl_del(n);
+ n->next = LIST_POISON1;
+ n->pprev = LIST_POISON2;
+}
+
+static inline void hlist_bl_del_init(struct hlist_bl_node *n)
+{
+ if (!hlist_bl_unhashed(n)) {
+ __hlist_bl_del(n);
+ INIT_HLIST_BL_NODE(n);
+ }
+}
+
+/**
+ * hlist_bl_for_each_entry - iterate over list of given type
+ * @tpos: the type * to use as a loop cursor.
+ * @pos: the &struct hlist_node to use as a loop cursor.
+ * @head: the head for your list.
+ * @member: the name of the hlist_node within the struct.
+ *
+ */
+#define hlist_bl_for_each_entry(tpos, pos, head, member) \
+ for (pos = hlist_bl_first(head); \
+ pos && \
+ ({ tpos = hlist_bl_entry(pos, typeof(*tpos), member); 1;}); \
+ pos = pos->next)
+
+/**
+ * hlist_bl_for_each_entry_safe - iterate over list of given type safe against removal of list entry
+ * @tpos: the type * to use as a loop cursor.
+ * @pos: the &struct hlist_node to use as a loop cursor.
+ * @n: another &struct hlist_node to use as temporary storage
+ * @head: the head for your list.
+ * @member: the name of the hlist_node within the struct.
+ */
+#define hlist_bl_for_each_entry_safe(tpos, pos, n, head, member) \
+ for (pos = hlist_bl_first(head); \
+ pos && ({ n = pos->next; 1; }) && \
+ ({ tpos = hlist_bl_entry(pos, typeof(*tpos), member); 1;}); \
+ pos = n)
+
+#endif
diff --git a/include/linux/rculist_bl.h b/include/linux/rculist_bl.h
new file mode 100644
index 0000000..cdfb54e
--- /dev/null
+++ b/include/linux/rculist_bl.h
@@ -0,0 +1,128 @@
+#ifndef _LINUX_RCULIST_BL_H
+#define _LINUX_RCULIST_BL_H
+
+/*
+ * RCU-protected bl list version. See include/linux/list_bl.h.
+ */
+#include <linux/list_bl.h>
+#include <linux/rcupdate.h>
+#include <linux/bit_spinlock.h>
+
+static inline void hlist_bl_set_first_rcu(struct hlist_bl_head *h,
+ struct hlist_bl_node *n)
+{
+ LIST_BL_BUG_ON((unsigned long)n & LIST_BL_LOCKMASK);
+ LIST_BL_BUG_ON(!bit_spin_is_locked(0, (unsigned long *)&h->first));
+ rcu_assign_pointer(h->first,
+ (struct hlist_bl_node *)((unsigned long)n | LIST_BL_LOCKMASK));
+}
+
+static inline struct hlist_bl_node *hlist_bl_first_rcu(struct hlist_bl_head *h)
+{
+ return (struct hlist_bl_node *)
+ ((unsigned long)rcu_dereference(h->first) & ~LIST_BL_LOCKMASK);
+}
+
+/**
+ * hlist_bl_del_init_rcu - deletes entry from hash list with re-initialization
+ * @n: the element to delete from the hash list.
+ *
+ * Note: hlist_bl_unhashed() on the node returns true after this. It is
+ * useful for RCU based read lockfree traversal if the writer side
+ * must know if the list entry is still hashed or already unhashed.
+ *
+ * In particular, it means that we can not poison the forward pointers
+ * that may still be used for walking the hash list and we can only
+ * zero the pprev pointer so list_unhashed() will return true after
+ * this.
+ *
+ * The caller must take whatever precautions are necessary (such as
+ * holding appropriate locks) to avoid racing with another
+ * list-mutation primitive, such as hlist_bl_add_head_rcu() or
+ * hlist_bl_del_rcu(), running on this same list. However, it is
+ * perfectly legal to run concurrently with the _rcu list-traversal
+ * primitives, such as hlist_bl_for_each_entry_rcu().
+ */
+static inline void hlist_bl_del_init_rcu(struct hlist_bl_node *n)
+{
+ if (!hlist_bl_unhashed(n)) {
+ __hlist_bl_del(n);
+ n->pprev = NULL;
+ }
+}
+
+/**
+ * hlist_bl_del_rcu - deletes entry from hash list without re-initialization
+ * @n: the element to delete from the hash list.
+ *
+ * Note: hlist_bl_unhashed() on entry does not return true after this,
+ * the entry is in an undefined state. It is useful for RCU based
+ * lockfree traversal.
+ *
+ * In particular, it means that we can not poison the forward
+ * pointers that may still be used for walking the hash list.
+ *
+ * The caller must take whatever precautions are necessary
+ * (such as holding appropriate locks) to avoid racing
+ * with another list-mutation primitive, such as hlist_bl_add_head_rcu()
+ * or hlist_bl_del_rcu(), running on this same list.
+ * However, it is perfectly legal to run concurrently with
+ * the _rcu list-traversal primitives, such as
+ * hlist_bl_for_each_entry().
+ */
+static inline void hlist_bl_del_rcu(struct hlist_bl_node *n)
+{
+ __hlist_bl_del(n);
+ n->pprev = LIST_POISON2;
+}
+
+/**
+ * hlist_bl_add_head_rcu
+ * @n: the element to add to the hash list.
+ * @h: the list to add to.
+ *
+ * Description:
+ * Adds the specified element to the specified hlist_bl,
+ * while permitting racing traversals.
+ *
+ * The caller must take whatever precautions are necessary
+ * (such as holding appropriate locks) to avoid racing
+ * with another list-mutation primitive, such as hlist_bl_add_head_rcu()
+ * or hlist_bl_del_rcu(), running on this same list.
+ * However, it is perfectly legal to run concurrently with
+ * the _rcu list-traversal primitives, such as
+ * hlist_bl_for_each_entry_rcu(), used to prevent memory-consistency
+ * problems on Alpha CPUs. Regardless of the type of CPU, the
+ * list-traversal primitive must be guarded by rcu_read_lock().
+ */
+static inline void hlist_bl_add_head_rcu(struct hlist_bl_node *n,
+ struct hlist_bl_head *h)
+{
+ struct hlist_bl_node *first;
+
+ /* don't need hlist_bl_first_rcu because we're under lock */
+ first = hlist_bl_first(h);
+
+ n->next = first;
+ if (first)
+ first->pprev = &n->next;
+ n->pprev = &h->first;
+
+ /* need _rcu because we can have concurrent lock free readers */
+ hlist_bl_set_first_rcu(h, n);
+}
+/**
+ * hlist_bl_for_each_entry_rcu - iterate over rcu list of given type
+ * @tpos: the type * to use as a loop cursor.
+ * @pos: the &struct hlist_bl_node to use as a loop cursor.
+ * @head: the head for your list.
+ * @member: the name of the hlist_bl_node within the struct.
+ *
+ */
+#define hlist_bl_for_each_entry_rcu(tpos, pos, head, member) \
+ for (pos = hlist_bl_first_rcu(head); \
+ pos && \
+ ({ tpos = hlist_bl_entry(pos, typeof(*tpos), member); 1; }); \
+ pos = rcu_dereference_raw(pos->next))
+
+#endif
--
1.7.1
next prev parent reply other threads:[~2010-11-27 10:28 UTC|newest]
Thread overview: 96+ messages / expand[flat|nested] mbox.gz Atom feed top
2010-11-27 10:15 [PATCH 00/46] rcu-walk and dcache scaling Nick Piggin
2010-11-27 9:44 ` [PATCH 02/46] fs: d_validate fixes Nick Piggin
2010-12-08 1:53 ` Dave Chinner
2010-12-08 6:59 ` Nick Piggin
2010-12-09 0:50 ` Dave Chinner
2010-12-09 4:50 ` Nick Piggin
2010-11-27 9:44 ` [PATCH 03/46] kernel: kmem_ptr_validate considered harmful Nick Piggin
2010-11-27 9:44 ` [PATCH 04/46] fs: dcache documentation cleanup Nick Piggin
2010-11-27 9:44 ` [PATCH 05/46] fs: change d_delete semantics Nick Piggin
2010-11-27 9:44 ` [PATCH 06/46] cifs: dont overwrite dentry name in d_revalidate Nick Piggin
2010-11-27 9:44 ` [PATCH 07/46] jfs: " Nick Piggin
2010-11-27 9:44 ` [PATCH 08/46] fs: change d_compare for rcu-walk Nick Piggin
2010-11-27 9:44 ` [PATCH 09/46] fs: change d_hash " Nick Piggin
2010-11-27 9:44 ` [PATCH 10/46] hostfs: simplify locking Nick Piggin
2010-11-27 9:44 ` [PATCH 11/46] fs: dcache scale hash Nick Piggin
2010-12-09 6:09 ` Dave Chinner
2010-12-09 6:28 ` Nick Piggin
2010-12-09 8:17 ` Dave Chinner
2010-12-09 12:53 ` Nick Piggin
2010-12-09 23:42 ` Dave Chinner
2010-12-10 2:35 ` Nick Piggin
2010-12-10 9:01 ` Dave Chinner
2010-12-13 4:48 ` Nick Piggin
2010-12-13 5:05 ` Nick Piggin
2010-11-27 9:44 ` [PATCH 12/46] fs: dcache scale lru Nick Piggin
2010-12-09 7:22 ` Dave Chinner
2010-12-09 12:34 ` Nick Piggin
2010-11-27 9:44 ` [PATCH 13/46] fs: dcache scale dentry refcount Nick Piggin
2010-11-27 9:44 ` [PATCH 14/46] fs: dcache scale d_unhashed Nick Piggin
2010-11-27 9:44 ` [PATCH 15/46] fs: dcache scale subdirs Nick Piggin
2010-11-27 9:44 ` [PATCH 16/46] fs: scale inode alias list Nick Piggin
2010-11-27 9:44 ` [PATCH 17/46] fs: Use rename lock and RCU for multi-step operations Nick Piggin
2011-01-18 22:32 ` Yehuda Sadeh Weinraub
2011-01-18 22:42 ` Nick Piggin
2011-01-19 22:27 ` Yehuda Sadeh Weinraub
2011-01-19 22:32 ` Nick Piggin
2011-01-25 22:10 ` Yehuda Sadeh Weinraub
2011-01-27 5:18 ` Nick Piggin
2011-02-07 18:52 ` Jim Schutt
2011-02-07 21:04 ` Yehuda Sadeh Weinraub
2011-02-07 21:31 ` Jim Schutt
2011-02-07 22:25 ` Jim Schutt
2011-02-14 17:57 ` Yehuda Sadeh Weinraub
2010-11-27 9:44 ` [PATCH 18/46] fs: increase d_name lock coverage Nick Piggin
2010-11-27 9:44 ` [PATCH 19/46] fs: dcache remove dcache_lock Nick Piggin
2010-11-27 9:44 ` [PATCH 20/46] fs: dcache avoid starvation in dcache multi-step operations Nick Piggin
2010-11-27 9:44 ` [PATCH 21/46] fs: dcache reduce dput locking Nick Piggin
2010-11-27 9:44 ` [PATCH 22/46] fs: dcache reduce locking in d_alloc Nick Piggin
2010-11-27 9:44 ` [PATCH 23/46] fs: dcache reduce dcache_inode_lock Nick Piggin
2010-11-27 9:44 ` [PATCH 24/46] fs: dcache rationalise dget variants Nick Piggin
2010-11-27 9:44 ` [PATCH 25/46] fs: dcache reduce d_parent locking Nick Piggin
2010-11-27 9:44 ` [PATCH 26/46] fs: dcache reduce prune_one_dentry locking Nick Piggin
2010-11-27 9:44 ` [PATCH 27/46] fs: reduce dcache_inode_lock width in lru scanning Nick Piggin
2010-11-27 9:44 ` [PATCH 28/46] fs: use RCU in shrink_dentry_list to reduce lock nesting Nick Piggin
2010-11-27 9:44 ` [PATCH 29/46] fs: consolidate dentry kill sequence Nick Piggin
2010-11-27 9:45 ` [PATCH 30/46] fs: icache RCU free inodes Nick Piggin
2010-11-27 9:45 ` [PATCH 31/46] fs: avoid inode RCU freeing for pseudo fs Nick Piggin
2010-11-27 9:45 ` [PATCH 32/46] kernel: optimise seqlock Nick Piggin
2010-11-27 9:45 ` [PATCH 33/46] fs: rcu-walk for path lookup Nick Piggin
2010-11-27 9:45 ` [PATCH 34/46] fs: fs_struct use seqlock Nick Piggin
2010-11-27 9:45 ` [PATCH 35/46] fs: dcache remove d_mounted Nick Piggin
2010-11-27 9:45 ` [PATCH 36/46] fs: dcache reduce branches in lookup path Nick Piggin
2010-11-27 9:45 ` [PATCH 37/46] fs: cache optimise dentry and inode for rcu-walk Nick Piggin
2010-11-27 9:45 ` [PATCH 38/46] fs: prefetch inode data in dcache lookup Nick Piggin
2010-11-27 9:45 ` [PATCH 39/46] fs: d_revalidate_rcu for rcu-walk Nick Piggin
2010-11-27 9:45 ` [PATCH 40/46] fs: provide rcu-walk aware permission i_ops Nick Piggin
2010-11-27 9:45 ` [PATCH 41/46] fs: provide simple rcu-walk ACL implementation Nick Piggin
2010-11-27 9:45 ` Nick Piggin [this message]
2010-11-27 9:45 ` [PATCH 43/46] bit_spinlock: add required includes Nick Piggin
2010-11-27 9:45 ` [PATCH 44/46] fs: dcache per-bucket dcache hash locking Nick Piggin
2010-11-27 9:45 ` [PATCH 45/46] fs: dcache per-inode inode alias locking Nick Piggin
2010-11-27 9:45 ` [PATCH 46/46] fs: improve scalability of pseudo filesystems Nick Piggin
2010-11-27 9:56 ` [PATCH 01/46] Revert "fs: use RCU read side protection in d_validate" Nick Piggin
2010-12-08 1:16 ` Dave Chinner
2010-12-08 9:38 ` Nick Piggin
2010-12-09 0:44 ` Dave Chinner
2010-12-09 4:38 ` Nick Piggin
2010-12-09 5:16 ` Nick Piggin
2010-11-27 15:04 ` [PATCH 00/46] rcu-walk and dcache scaling Anca Emanuel
2010-11-28 3:28 ` Nick Piggin
2010-11-28 6:24 ` Sedat Dilek
2010-12-01 18:03 ` David Miller
2010-12-03 16:55 ` Nick Piggin
2010-12-07 11:25 ` Dave Chinner
2010-12-07 15:24 ` Nick Piggin
2010-12-07 15:49 ` Peter Zijlstra
2010-12-07 15:59 ` Nick Piggin
2010-12-07 16:23 ` Peter Zijlstra
2010-12-08 3:28 ` Nick Piggin
2010-12-07 21:56 ` Dave Chinner
2010-12-08 1:47 ` Nick Piggin
2010-12-08 3:32 ` Dave Chinner
2010-12-08 4:28 ` Dave Chinner
2010-12-08 7:09 ` Nick Piggin
2010-12-10 20:32 ` Paul E. McKenney
2010-12-12 14:54 ` Paul E. McKenney
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=574d900af0cf01be2ab929a4030ed4a3d2a2b1de.1290852960.git.npiggin@kernel.dk \
--to=npiggin@kernel.dk \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox
all inboxes | Powered by JetHome®