rcu: Introduce hlist_nulls variant of hlist

hlist uses NULL value to finish a chain.

hlist_nulls variant use the low order bit set to 1 to signal an end-of-list marker.

This allows to store many different end markers, so that some RCU lockless
algos (used in TCP/UDP stack for example) can save some memory barriers in
fast paths.

Two new files are added :

include/linux/list_nulls.h
  - mimics hlist part of include/linux/list.h, derived to hlist_nulls variant

include/linux/rculist_nulls.h
  - mimics hlist part of include/linux/rculist.h, derived to hlist_nulls variant

   Only four helpers are declared for the moment :

     hlist_nulls_del_init_rcu(), hlist_nulls_del_rcu(),
     hlist_nulls_add_head_rcu() and hlist_nulls_for_each_entry_rcu()

prefetches() were removed, since an end of list is not anymore NULL value.
prefetches() could trigger useless (and possibly dangerous) memory transactions.

Example of use (extracted from __udp4_lib_lookup())

	struct sock *sk, *result;
        struct hlist_nulls_node *node;
        unsigned short hnum = ntohs(dport);
        unsigned int hash = udp_hashfn(net, hnum);
        struct udp_hslot *hslot = &udptable->hash[hash];
        int score, badness;

        rcu_read_lock();
begin:
        result = NULL;
        badness = -1;
        sk_nulls_for_each_rcu(sk, node, &hslot->head) {
                score = compute_score(sk, net, saddr, hnum, sport,
                                      daddr, dport, dif);
                if (score > badness) {
                        result = sk;
                        badness = score;
                }
        }
        /*
         * if the nulls value we got at the end of this lookup is
         * not the expected one, we must restart lookup.
         * We probably met an item that was moved to another chain.
         */
        if (get_nulls_value(node) != hash)
                goto begin;

        if (result) {
                if (unlikely(!atomic_inc_not_zero(&result->sk_refcnt)))
                        result = NULL;
                else if (unlikely(compute_score(result, net, saddr, hnum, sport,
                                  daddr, dport, dif) < badness)) {
                        sock_put(result);
                        goto begin;
                }
        }
        rcu_read_unlock();
        return result;

Signed-off-by: Eric Dumazet <dada1@cosmosbay.com>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 110 insertions, 0 deletions

diff --git a/include/linux/rculist_nulls.h b/include/linux/rculist_nulls.h
new file mode 100644
index 000000000000..f9ddd03961a8
--- /dev/null
+++ b/include/linux/rculist_nulls.h
@@ -0,0 +1,110 @@
+#ifndef _LINUX_RCULIST_NULLS_H
+#define _LINUX_RCULIST_NULLS_H
+
+#ifdef __KERNEL__
+
+/*
+ * RCU-protected list version
+ */
+#include <linux/list_nulls.h>
+#include <linux/rcupdate.h>
+
+/**
+ * hlist_nulls_del_init_rcu - deletes entry from hash list with re-initialization
+ * @n: the element to delete from the hash list.
+ *
+ * Note: hlist_nulls_unhashed() on the node return 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_nulls_add_head_rcu() or
+ * hlist_nulls_del_rcu(), running on this same list.  However, it is
+ * perfectly legal to run concurrently with the _rcu list-traversal
+ * primitives, such as hlist_nulls_for_each_entry_rcu().
+ */
+static inline void hlist_nulls_del_init_rcu(struct hlist_nulls_node *n)
+{
+        if (!hlist_nulls_unhashed(n)) {
+                __hlist_nulls_del(n);
+                n->pprev = NULL;
+        }
+}
+
+/**
+ * hlist_nulls_del_rcu - deletes entry from hash list without re-initialization
+ * @n: the element to delete from the hash list.
+ *
+ * Note: hlist_nulls_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_nulls_add_head_rcu()
+ * or hlist_nulls_del_rcu(), running on this same list.
+ * However, it is perfectly legal to run concurrently with
+ * the _rcu list-traversal primitives, such as
+ * hlist_nulls_for_each_entry().
+ */
+static inline void hlist_nulls_del_rcu(struct hlist_nulls_node *n)
+{
+        __hlist_nulls_del(n);
+        n->pprev = LIST_POISON2;
+}
+
+/**
+ * hlist_nulls_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_nulls,
+ * 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_nulls_add_head_rcu()
+ * or hlist_nulls_del_rcu(), running on this same list.
+ * However, it is perfectly legal to run concurrently with
+ * the _rcu list-traversal primitives, such as
+ * hlist_nulls_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_nulls_add_head_rcu(struct hlist_nulls_node *n,
+                                        struct hlist_nulls_head *h)
+{
+        struct hlist_nulls_node *first = h->first;
+
+        n->next = first;
+        n->pprev = &h->first;
+        rcu_assign_pointer(h->first, n);
+        if (!is_a_nulls(first))
+                first->pprev = &n->next;
+}
+/**
+ * hlist_nulls_for_each_entry_rcu - iterate over rcu list of given type
+ * @tpos:       the type * to use as a loop cursor.
+ * @pos:        the &struct hlist_nulls_node to use as a loop cursor.
+ * @head:       the head for your list.
+ * @member:     the name of the hlist_nulls_node within the struct.
+ *
+ */
+#define hlist_nulls_for_each_entry_rcu(tpos, pos, head, member) \
+        for (pos = rcu_dereference((head)->first);                       \
+                (!is_a_nulls(pos)) &&                   \
+                ({ tpos = hlist_nulls_entry(pos, typeof(*tpos), member); 1; }); \
+                pos = rcu_dereference(pos->next))
+
+#endif
+#endif