[PATCH] rhashtable: detect when object movement between tables might have invalidated a lookup

[NeilBrown]

Some users of rhashtables might need to move an object from one table
to another -  this appears to be the reason for the incomplete usage
of NULLS markers.

To support these, we store a unique NULLS_MARKER at the end of
each chain, and when a search fails to find a match, we check
if the NULLS marker found was the expected one.  If not, the search
may not have examined all objects in the target bucket, so it is
repeated.

The unique NULLS_MARKER is derived from the address of the
head of the chain.  As this cannot be derived at load-time the
static rhnull in rht_bucket_nested() needs to be initialised
at run time.

Any caller of a lookup function must still be prepared for the
possibility that the object returned is in a different table - it
might have been there for some time.

Note that this does NOT provide support for other uses of
NULLS_MARKERs such as allocating with SLAB_TYPESAFE_BY_RCU or changing
the key of an object and re-inserting it in the same table.
These could only be done safely if new objects were inserted
at the *start* of a hash chain, and that is not currently the case.

Acked-by: Herbert Xu <herbert@xxxxxxxxxxxxxxxxxxx>
Signed-off-by: NeilBrown <neilb@xxxxxxxx>
---

Thanks Herbert,
 here is the patch complete with the Acked-by incase that makes it easer
 to apply.

Thanks,
NeilBrown


 include/linux/rhashtable.h | 34 ++++++++++++++++++++++++++--------
 lib/rhashtable.c           |  8 +++++---
 2 files changed, 31 insertions(+), 11 deletions(-)

diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h
index eb7111039247..20f9c6af7473 100644
--- a/include/linux/rhashtable.h
+++ b/include/linux/rhashtable.h
@@ -75,8 +75,19 @@ struct bucket_table {
 	struct rhash_head __rcu *buckets[] ____cacheline_aligned_in_smp;
 };
 
+/*
+ * NULLS_MARKER() expects a hash value with the low
+ * bits mostly likely to be significant, and it discards
+ * the msb.
+ * We git it an address, in which the bottom 2 bits are
+ * always 0, and the msb might be significant.
+ * So we shift the address down one bit to align with
+ * expectations and avoid losing a significant bit.
+ */
+#define	RHT_NULLS_MARKER(ptr)	\
+	((void *)NULLS_MARKER(((unsigned long) (ptr)) >> 1))
 #define INIT_RHT_NULLS_HEAD(ptr)	\
-	((ptr) = (typeof(ptr)) NULLS_MARKER(0))
+	((ptr) = RHT_NULLS_MARKER(&(ptr)))
 
 static inline bool rht_is_a_nulls(const struct rhash_head *ptr)
 {
@@ -471,6 +482,7 @@ static inline struct rhash_head *__rhashtable_lookup(
 		.ht = ht,
 		.key = key,
 	};
+	struct rhash_head __rcu * const *head;
 	struct bucket_table *tbl;
 	struct rhash_head *he;
 	unsigned int hash;
@@ -478,13 +490,19 @@ static inline struct rhash_head *__rhashtable_lookup(
 	tbl = rht_dereference_rcu(ht->tbl, ht);
 restart:
 	hash = rht_key_hashfn(ht, tbl, key, params);
-	rht_for_each_rcu(he, tbl, hash) {
-		if (params.obj_cmpfn ?
-		    params.obj_cmpfn(&arg, rht_obj(ht, he)) :
-		    rhashtable_compare(&arg, rht_obj(ht, he)))
-			continue;
-		return he;
-	}
+	head = rht_bucket(tbl, hash);
+	do {
+		rht_for_each_rcu_continue(he, *head, tbl, hash) {
+			if (params.obj_cmpfn ?
+			    params.obj_cmpfn(&arg, rht_obj(ht, he)) :
+			    rhashtable_compare(&arg, rht_obj(ht, he)))
+				continue;
+			return he;
+		}
+		/* An object might have been moved to a different hash chain,
+		 * while we walk along it - better check and retry.
+		 */
+	} while (he != RHT_NULLS_MARKER(head));
 
 	/* Ensure we see any new tables. */
 	smp_rmb();
diff --git a/lib/rhashtable.c b/lib/rhashtable.c
index 30526afa8343..852ffa5160f1 100644
--- a/lib/rhashtable.c
+++ b/lib/rhashtable.c
@@ -1179,8 +1179,7 @@ struct rhash_head __rcu **rht_bucket_nested(const struct bucket_table *tbl,
 					    unsigned int hash)
 {
 	const unsigned int shift = PAGE_SHIFT - ilog2(sizeof(void *));
-	static struct rhash_head __rcu *rhnull =
-		(struct rhash_head __rcu *)NULLS_MARKER(0);
+	static struct rhash_head __rcu *rhnull;
 	unsigned int index = hash & ((1 << tbl->nest) - 1);
 	unsigned int size = tbl->size >> tbl->nest;
 	unsigned int subhash = hash;
@@ -1198,8 +1197,11 @@ struct rhash_head __rcu **rht_bucket_nested(const struct bucket_table *tbl,
 		subhash >>= shift;
 	}
 
-	if (!ntbl)
+	if (!ntbl) {
+		if (!rhnull)
+			INIT_RHT_NULLS_HEAD(rhnull);
 		return &rhnull;
+	}
 
 	return &ntbl[subhash].bucket;
 
-- 
2.14.0.rc0.dirty

Attachment: signature.asc
Description: PGP signature