This is a note to let you know that I've just added the patch titled
net: force a reload of first item in hlist_nulls_for_each_entry_rcu
to the 3.4-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=summary
The filename of the patch is:
net-force-a-reload-of-first-item-in-hlist_nulls_for_each_entry_rcu.patch
and it can be found in the queue-3.4 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable@xxxxxxxxxxxxxxx> know about it.
>From 6c8fd20ab8a15d7882d35278a1969c77acceb64d Mon Sep 17 00:00:00 2001
From: Eric Dumazet <eric.dumazet@xxxxxxxxx>
Date: Wed, 29 May 2013 09:06:27 +0000
Subject: net: force a reload of first item in hlist_nulls_for_each_entry_rcu
From: Eric Dumazet <eric.dumazet@xxxxxxxxx>
[ Upstream commit c87a124a5d5e8cf8e21c4363c3372bcaf53ea190 ]
Roman Gushchin discovered that udp4_lib_lookup2() was not reloading
first item in the rcu protected list, in case the loop was restarted.
This produced soft lockups as in https://lkml.org/lkml/2013/4/16/37
rcu_dereference(X)/ACCESS_ONCE(X) seem to not work as intended if X is
ptr->field :
In some cases, gcc caches the value or ptr->field in a register.
Use a barrier() to disallow such caching, as documented in
Documentation/atomic_ops.txt line 114
Thanks a lot to Roman for providing analysis and numerous patches.
Diagnosed-by: Roman Gushchin <klamm@xxxxxxxxxxxxxx>
Signed-off-by: Eric Dumazet <edumazet@xxxxxxxxxx>
Reported-by: Boris Zhmurov <zhmurov@xxxxxxxxxxxxxx>
Signed-off-by: Roman Gushchin <klamm@xxxxxxxxxxxxxx>
Acked-by: Paul E. McKenney <paulmck@xxxxxxxxxxxxxxxxxx>
Signed-off-by: David S. Miller <davem@xxxxxxxxxxxxx>
Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>
---
include/linux/rculist_nulls.h | 7 ++++++-
1 file changed, 6 insertions(+), 1 deletion(-)
--- a/include/linux/rculist_nulls.h
+++ b/include/linux/rculist_nulls.h
@@ -105,9 +105,14 @@ static inline void hlist_nulls_add_head_
* @head: the head for your list.
* @member: the name of the hlist_nulls_node within the struct.
*
+ * The barrier() is needed to make sure compiler doesn't cache first element [1],
+ * as this loop can be restarted [2]
+ * [1] Documentation/atomic_ops.txt around line 114
+ * [2] Documentation/RCU/rculist_nulls.txt around line 146
*/
#define hlist_nulls_for_each_entry_rcu(tpos, pos, head, member) \
- for (pos = rcu_dereference_raw(hlist_nulls_first_rcu(head)); \
+ for (({barrier();}), \
+ pos = rcu_dereference_raw(hlist_nulls_first_rcu(head)); \
(!is_a_nulls(pos)) && \
({ tpos = hlist_nulls_entry(pos, typeof(*tpos), member); 1; }); \
pos = rcu_dereference_raw(hlist_nulls_next_rcu(pos)))
Patches currently in stable-queue which might be from eric.dumazet@xxxxxxxxx are
queue-3.4/net-force-a-reload-of-first-item-in-hlist_nulls_for_each_entry_rcu.patch
--
To unsubscribe from this list: send the line "unsubscribe stable" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html