Merge branch 'rhash-cleanups'

NeilBrown says:

====================
A few rhashtables cleanups

2 patches fixes documentation
1 fixes a bit in rhashtable_walk_start()
1 improves rhashtable_walk stability.

All reviewed and Acked.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

2 files changed, 63 insertions, 26 deletions

diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h
index 1f8ad121eb43..4e1f535c2034 100644
--- a/include/linux/rhashtable.h
+++ b/include/linux/rhashtable.h
@@ -836,9 +836,8 @@ out:
  *
  * It is safe to call this function from atomic context.
  *
- * Will trigger an automatic deferred table resizing if the size grows
- * beyond the watermark indicated by grow_decision() which can be passed
- * to rhashtable_init().
+ * Will trigger an automatic deferred table resizing if residency in the
+ * table grows beyond 70%.
  */
 static inline int rhashtable_insert_fast(
 	struct rhashtable *ht, struct rhash_head *obj,
@@ -866,9 +865,8 @@ static inline int rhashtable_insert_fast(
  *
  * It is safe to call this function from atomic context.
  *
- * Will trigger an automatic deferred table resizing if the size grows
- * beyond the watermark indicated by grow_decision() which can be passed
- * to rhashtable_init().
+ * Will trigger an automatic deferred table resizing if residency in the
+ * table grows beyond 70%.
  */
 static inline int rhltable_insert_key(
 	struct rhltable *hlt, const void *key, struct rhlist_head *list,
@@ -890,9 +888,8 @@ static inline int rhltable_insert_key(
  *
  * It is safe to call this function from atomic context.
  *
- * Will trigger an automatic deferred table resizing if the size grows
- * beyond the watermark indicated by grow_decision() which can be passed
- * to rhashtable_init().
+ * Will trigger an automatic deferred table resizing if residency in the
+ * table grows beyond 70%.
  */
 static inline int rhltable_insert(
 	struct rhltable *hlt, struct rhlist_head *list,
@@ -922,9 +919,8 @@ static inline int rhltable_insert(
  *
  * It is safe to call this function from atomic context.
  *
- * Will trigger an automatic deferred table resizing if the size grows
- * beyond the watermark indicated by grow_decision() which can be passed
- * to rhashtable_init().
+ * Will trigger an automatic deferred table resizing if residency in the
+ * table grows beyond 70%.
  */
 static inline int rhashtable_lookup_insert_fast(
 	struct rhashtable *ht, struct rhash_head *obj,
@@ -981,9 +977,8 @@ static inline void *rhashtable_lookup_get_insert_fast(
  *
  * Lookups may occur in parallel with hashtable mutations and resizing.
  *
- * Will trigger an automatic deferred table resizing if the size grows
- * beyond the watermark indicated by grow_decision() which can be passed
- * to rhashtable_init().
+ * Will trigger an automatic deferred table resizing if residency in the
+ * table grows beyond 70%.
  *
  * Returns zero on success.
  */
@@ -1134,8 +1129,8 @@ static inline int __rhashtable_remove_fast(
  * walk the bucket chain upon removal. The removal operation is thus
  * considerable slow if the hash table is not correctly sized.
  *
- * Will automatically shrink the table via rhashtable_expand() if the
- * shrink_decision function specified at rhashtable_init() returns true.
+ * Will automatically shrink the table if permitted when residency drops
+ * below 30%.
  *
  * Returns zero on success, -ENOENT if the entry could not be found.
  */
@@ -1156,8 +1151,8 @@ static inline int rhashtable_remove_fast(
  * walk the bucket chain upon removal. The removal operation is thus
  * considerable slow if the hash table is not correctly sized.
  *
- * Will automatically shrink the table via rhashtable_expand() if the
- * shrink_decision function specified at rhashtable_init() returns true.
+ * Will automatically shrink the table if permitted when residency drops
+ * below 30%
  *
  * Returns zero on success, -ENOENT if the entry could not be found.
  */
@@ -1273,8 +1268,9 @@ static inline int rhashtable_walk_init(struct rhashtable *ht,
  * For a completely stable walk you should construct your own data
  * structure outside the hash table.
  *
- * This function may sleep so you must not call it from interrupt
- * context or with spin locks held.
+ * This function may be called from any process context, including
+ * non-preemptable context, but cannot be called from softirq or
+ * hardirq context.
  *
  * You must call rhashtable_walk_exit after this function returns.
  */
diff --git a/lib/rhashtable.c b/lib/rhashtable.c
index 2b2b79974b61..9427b5766134 100644
--- a/lib/rhashtable.c
+++ b/lib/rhashtable.c
@@ -668,8 +668,9 @@ EXPORT_SYMBOL_GPL(rhashtable_insert_slow);
  * For a completely stable walk you should construct your own data
  * structure outside the hash table.
  *
- * This function may sleep so you must not call it from interrupt
- * context or with spin locks held.
+ * This function may be called from any process context, including
+ * non-preemptable context, but cannot be called from softirq or
+ * hardirq context.
  *
  * You must call rhashtable_walk_exit after this function returns.
  */
@@ -726,6 +727,7 @@ int rhashtable_walk_start_check(struct rhashtable_iter *iter)
 	__acquires(RCU)
 {
 	struct rhashtable *ht = iter->ht;
+	bool rhlist = ht->rhlist;
 
 	rcu_read_lock();
 
@@ -734,11 +736,52 @@ int rhashtable_walk_start_check(struct rhashtable_iter *iter)
 		list_del(&iter->walker.list);
 	spin_unlock(&ht->lock);
 
-	if (!iter->walker.tbl && !iter->end_of_table) {
+	if (iter->end_of_table)
+		return 0;
+	if (!iter->walker.tbl) {
 		iter->walker.tbl = rht_dereference_rcu(ht->tbl, ht);
+		iter->slot = 0;
+		iter->skip = 0;
 		return -EAGAIN;
 	}
 
+	if (iter->p && !rhlist) {
+		/*
+		 * We need to validate that 'p' is still in the table, and
+		 * if so, update 'skip'
+		 */
+		struct rhash_head *p;
+		int skip = 0;
+		rht_for_each_rcu(p, iter->walker.tbl, iter->slot) {
+			skip++;
+			if (p == iter->p) {
+				iter->skip = skip;
+				goto found;
+			}
+		}
+		iter->p = NULL;
+	} else if (iter->p && rhlist) {
+		/* Need to validate that 'list' is still in the table, and
+		 * if so, update 'skip' and 'p'.
+		 */
+		struct rhash_head *p;
+		struct rhlist_head *list;
+		int skip = 0;
+		rht_for_each_rcu(p, iter->walker.tbl, iter->slot) {
+			for (list = container_of(p, struct rhlist_head, rhead);
+			     list;
+			     list = rcu_dereference(list->next)) {
+				skip++;
+				if (list == iter->list) {
+					iter->p = p;
+					skip = skip;
+					goto found;
+				}
+			}
+		}
+		iter->p = NULL;
+	}
+found:
 	return 0;
 }
 EXPORT_SYMBOL_GPL(rhashtable_walk_start_check);
@@ -914,8 +957,6 @@ void rhashtable_walk_stop(struct rhashtable_iter *iter)
 		iter->walker.tbl = NULL;
 	spin_unlock(&ht->lock);
 
-	iter->p = NULL;
-
 out:
 	rcu_read_unlock();
 }