lists.openwall.net   lists  /  announce  owl-users  owl-dev  john-users  john-dev  passwdqc-users  yescrypt  popa3d-users  /  oss-security  kernel-hardening  musl  sabotage  tlsify  passwords  /  crypt-dev  xvendor  /  Bugtraq  Full-Disclosure  linux-kernel  linux-netdev  linux-ext4  linux-hardening  linux-cve-announce  PHC 
Open Source and information security mailing list archives
 
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <1369188080.3301.268.camel@edumazet-glaptop>
Date:	Tue, 21 May 2013 19:01:20 -0700
From:	Eric Dumazet <eric.dumazet@...il.com>
To:	Roman Gushchin <klamm@...dex-team.ru>
Cc:	paulmck@...ux.vnet.ibm.com, Dipankar Sarma <dipankar@...ibm.com>,
	zhmurov@...dex-team.ru, linux-kernel@...r.kernel.org,
	netdev@...r.kernel.org, "David S. Miller" <davem@...emloft.net>,
	Alexey Kuznetsov <kuznet@....inr.ac.ru>,
	James Morris <jmorris@...ei.org>,
	Hideaki YOSHIFUJI <yoshfuji@...ux-ipv6.org>,
	Patrick McHardy <kaber@...sh.net>
Subject: Re: [PATCH v2] rcu: fix a race in hlist_nulls_for_each_entry_rcu
 macro

On Tue, 2013-05-21 at 22:12 +0400, Roman Gushchin wrote:
> > If other rcu accessors have the same problem, a more complete patch is
> > needed.
> 
> [PATCH] rcu: fix a race in rcu lists traverse macros
> 
> Some network functions (udp4_lib_lookup2(), for instance) use the
> rcu lists traverse macros (hlist_nulls_for_each_entry_rcu, for instance)
> in a way that assumes restarting of a loop. In this case, it is strictly
> necessary to reread the head->first value from the memory before each scan.
> Without additional hints, gcc caches this value in a register. In this case,
> if a cached node is moved to another chain during the scan, we can loop
> forever getting wrong nulls values and restarting the loop uninterruptedly.
> 
> Signed-off-by: Roman Gushchin <klamm@...dex-team.ru>
> Reported-by: Boris Zhmurov <zhmurov@...dex-team.ru>
> ---
>   include/linux/compiler.h      | 6 ++++++
>   include/linux/rculist.h       | 6 ++++--
>   include/linux/rculist_nulls.h | 3 ++-
>   3 files changed, 12 insertions(+), 3 deletions(-)
> 
> diff --git a/include/linux/compiler.h b/include/linux/compiler.h
> index 92669cd..0e05d7c 100644
> --- a/include/linux/compiler.h
> +++ b/include/linux/compiler.h
> @@ -351,6 +351,12 @@ void ftrace_likely_update(struct ftrace_branch_data *f, int val, int expect);
>    */
>   #define ACCESS_ONCE(x) (*(volatile typeof(x) *)&(x))
> 
> +/*
> + * Prevent the compiler from optimizing accesses to structure member.
> + */
> +#define GET_STRUCT_FIELD_VOLATILE(struct_ptr, field)		\
> +	(((volatile typeof(*struct_ptr) *)struct_ptr)->field)
> +
>   /* Ignore/forbid kprobes attach on very low level functions marked by this attribute: */
>   #ifdef CONFIG_KPROBES
>   # define __kprobes	__attribute__((__section__(".kprobes.text")))
> diff --git a/include/linux/rculist.h b/include/linux/rculist.h
> index 8089e35..6c3eea7 100644
> --- a/include/linux/rculist.h
> +++ b/include/linux/rculist.h
> @@ -282,7 +282,8 @@ static inline void list_splice_init_rcu(struct list_head *list,
>    * as long as the traversal is guarded by rcu_read_lock().
>    */
>   #define list_for_each_entry_rcu(pos, head, member) \
> -	for (pos = list_entry_rcu((head)->next, typeof(*pos), member); \
> +	for (pos = list_entry_rcu(GET_STRUCT_FIELD_VOLATILE(head, next), \
> +				  typeof(*pos), member); \
>   		&pos->member != (head); \
>   		pos = list_entry_rcu(pos->member.next, typeof(*pos), member))
> 
> @@ -348,7 +349,8 @@ static inline void hlist_replace_rcu(struct hlist_node *old,
>   /*
>    * return the first or the next element in an RCU protected hlist
>    */
> -#define hlist_first_rcu(head)	(*((struct hlist_node __rcu **)(&(head)->first)))
> +#define hlist_first_rcu(head)	(*((struct hlist_node __rcu **)		\
> +				   (&GET_STRUCT_FIELD_VOLATILE(head, first))))
>   #define hlist_next_rcu(node)	(*((struct hlist_node __rcu **)(&(node)->next)))
>   #define hlist_pprev_rcu(node)	(*((struct hlist_node __rcu **)((node)->pprev)))
> 
> diff --git a/include/linux/rculist_nulls.h b/include/linux/rculist_nulls.h
> index 2ae1371..b04fd0a 100644
> --- a/include/linux/rculist_nulls.h
> +++ b/include/linux/rculist_nulls.h
> @@ -38,7 +38,8 @@ static inline void hlist_nulls_del_init_rcu(struct hlist_nulls_node *n)
>   }
> 
>   #define hlist_nulls_first_rcu(head) \
> -	(*((struct hlist_nulls_node __rcu __force **)&(head)->first))
> +	(*((struct hlist_nulls_node __rcu __force **)	\
> +	   &(GET_STRUCT_FIELD_VOLATILE(head, first))))
> 
>   #define hlist_nulls_next_rcu(node) \
>   	(*((struct hlist_nulls_node __rcu __force **)&(node)->next))

Please use ACCESS_ONCE(), which is the standard way to deal with this,
and remove the rcu_dereference_raw() in 
hlist_nulls_for_each_entry_rcu()

something like : (for the nulls part only)

diff --git a/include/linux/rculist_nulls.h b/include/linux/rculist_nulls.h
index 2ae1371..1d485d3 100644
--- a/include/linux/rculist_nulls.h
+++ b/include/linux/rculist_nulls.h
@@ -40,6 +40,9 @@ static inline void hlist_nulls_del_init_rcu(struct hlist_nulls_node *n)
 #define hlist_nulls_first_rcu(head) \
 	(*((struct hlist_nulls_node __rcu __force **)&(head)->first))
 
+#define hlist_nulls_first_rcu_once(head) \
+	ACCESS_ONCE(*((struct hlist_nulls_node __rcu __force **)&(head)->first))
+
 #define hlist_nulls_next_rcu(node) \
 	(*((struct hlist_nulls_node __rcu __force **)&(node)->next))
 
@@ -107,7 +110,7 @@ static inline void hlist_nulls_add_head_rcu(struct hlist_nulls_node *n,
  *
  */
 #define hlist_nulls_for_each_entry_rcu(tpos, pos, head, member)                        \
-	for (pos = rcu_dereference_raw(hlist_nulls_first_rcu(head));            \
+	for (pos = hlist_nulls_first_rcu_once(head);                            \
 		(!is_a_nulls(pos)) &&                                           \
 		({ tpos = hlist_nulls_entry(pos, typeof(*tpos), member); 1; }); \
                pos = rcu_dereference_raw(hlist_nulls_next_rcu(pos)))



--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Powered by blists - more mailing lists

Powered by Openwall GNU/*/Linux Powered by OpenVZ