[<prev] [next>] [thread-next>] [day] [month] [year] [list]
Message-ID: <20100319013024.GA28456@Krystal>
Date: Thu, 18 Mar 2010 21:30:24 -0400
From: Mathieu Desnoyers <mathieu.desnoyers@...icios.com>
To: "Paul E. McKenney" <paulmck@...ux.vnet.ibm.com>
Cc: mingo@...e.hu, akpm@...ux-foundation.org, laijs@...fujitsu.com,
dipankar@...ibm.com, josh@...htriplett.org, dvhltc@...ibm.com,
niv@...ibm.com, tglx@...utronix.de, peterz@...radead.org,
rostedt@...dmis.org, Valdis.Kletnieks@...edu, dhowells@...hat.com,
eric.dumazet@...il.com, Alexey Dobriyan <adobriyan@...il.com>,
Peter Zijlstra <a.p.zijlstra@...llo.nl>,
linux-kernel@...r.kernel.org
Subject: [PATCH] tree/tiny rcu: Add debug RCU head option (v2)
Poisoning the rcu_head callback list.
Helps finding racy users of call_rcu(), which results in hangs because list
entries are overwritten and/or skipped.
A lot of non-initialized rcu list heads will be found with this option enabled.
It is important to do not just blindly initialize them before each call_rcu, but
rather to perform the initialization at the proper location, after the memory
has been allocated, so we can effectively detect incorrect call_rcu users.
This patch version does not use "debug objects", although it probably should.
Some day I might find time to look into this transition, but the patch is usable
as is.
The weird #ifdef in the networking code comes from an agreement with Eric
Dumazet about how to disable the build check for the networking code. For those
who wonder about the existence of this build-time check: it generates a build
error when the size of struct dst_entry grows (because it is very performance
sensitive). So the agreement here has been to disable the check when the
DEBUG_RCU_HEAD config option is active.
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@...icios.com>
CC: "Paul E. McKenney" <paulmck@...ux.vnet.ibm.com>
CC: mingo@...e.hu
CC: akpm@...ux-foundation.org
CC: mingo@...e.hu
CC: laijs@...fujitsu.com
CC: dipankar@...ibm.com
CC: josh@...htriplett.org
CC: dvhltc@...ibm.com
CC: niv@...ibm.com
CC: tglx@...utronix.de
CC: peterz@...radead.org
CC: rostedt@...dmis.org
CC: Valdis.Kletnieks@...edu
CC: dhowells@...hat.com
CC: eric.dumazet@...il.com
CC: Alexey Dobriyan <adobriyan@...il.com>
CC: Peter Zijlstra <a.p.zijlstra@...llo.nl>
---
include/linux/rcupdate.h | 13 ++++++++++++-
include/net/dst.h | 2 ++
kernel/rcutiny.c | 9 +++++++++
kernel/rcutree.c | 10 ++++++++++
lib/Kconfig.debug | 9 +++++++++
5 files changed, 42 insertions(+), 1 deletion(-)
Index: linux-2.6-lttng/include/linux/rcupdate.h
===================================================================
--- linux-2.6-lttng.orig/include/linux/rcupdate.h 2010-03-18 20:27:25.000000000 -0400
+++ linux-2.6-lttng/include/linux/rcupdate.h 2010-03-18 20:30:54.000000000 -0400
@@ -49,6 +49,9 @@
struct rcu_head {
struct rcu_head *next;
void (*func)(struct rcu_head *head);
+#ifdef CONFIG_DEBUG_RCU_HEAD
+ struct rcu_head *debug;
+#endif
};
/* Exported common interfaces */
@@ -71,11 +74,19 @@ extern void rcu_init(void);
#error "Unknown RCU implementation specified to kernel configuration"
#endif
+#ifdef CONFIG_DEBUG_RCU_HEAD
+#define RCU_HEAD_INIT { .next = NULL, .func = NULL, .debug = NULL }
+#define INIT_RCU_HEAD(ptr) do { \
+ (ptr)->next = NULL; (ptr)->func = NULL; (ptr)->debug = NULL; \
+} while (0)
+#else
#define RCU_HEAD_INIT { .next = NULL, .func = NULL }
-#define RCU_HEAD(head) struct rcu_head head = RCU_HEAD_INIT
#define INIT_RCU_HEAD(ptr) do { \
(ptr)->next = NULL; (ptr)->func = NULL; \
} while (0)
+#endif
+
+#define RCU_HEAD(head) struct rcu_head head = RCU_HEAD_INIT
#ifdef CONFIG_DEBUG_LOCK_ALLOC
extern struct lockdep_map rcu_lock_map;
Index: linux-2.6-lttng/kernel/rcutree.c
===================================================================
--- linux-2.6-lttng.orig/kernel/rcutree.c 2010-03-18 20:27:25.000000000 -0400
+++ linux-2.6-lttng/kernel/rcutree.c 2010-03-18 20:31:16.000000000 -0400
@@ -39,6 +39,7 @@
#include <asm/atomic.h>
#include <linux/bitops.h>
#include <linux/module.h>
+#include <linux/poison.h>
#include <linux/completion.h>
#include <linux/moduleparam.h>
#include <linux/percpu.h>
@@ -1060,6 +1061,10 @@ static void rcu_do_batch(struct rcu_stat
next = list->next;
prefetch(next);
trace_rcu_tree_callback(list);
+#ifdef CONFIG_DEBUG_RCU_HEAD
+ WARN_ON_ONCE(list->debug != LIST_POISON1);
+ list->debug = NULL;
+#endif
list->func(list);
list = next;
if (++count >= rdp->blimit)
@@ -1350,6 +1355,11 @@ __call_rcu(struct rcu_head *head, void (
unsigned long flags;
struct rcu_data *rdp;
+#ifdef CONFIG_DEBUG_RCU_HEAD
+ WARN_ON_ONCE(head->debug);
+ head->debug = LIST_POISON1;
+#endif
+
head->func = func;
head->next = NULL;
Index: linux-2.6-lttng/lib/Kconfig.debug
===================================================================
--- linux-2.6-lttng.orig/lib/Kconfig.debug 2010-03-18 20:27:25.000000000 -0400
+++ linux-2.6-lttng/lib/Kconfig.debug 2010-03-18 20:27:38.000000000 -0400
@@ -661,6 +661,15 @@ config DEBUG_LIST
If unsure, say N.
+config DEBUG_RCU_HEAD
+ bool "Debug RCU callbacks"
+ depends on DEBUG_KERNEL
+ depends on TREE_RCU
+ help
+ Enable this to turn on debugging of RCU list heads (call_rcu() usage).
+ Seems to find problems more quickly with stress-tests in single-cpu
+ mode.
+
config DEBUG_SG
bool "Debug SG table operations"
depends on DEBUG_KERNEL
Index: linux-2.6-lttng/include/net/dst.h
===================================================================
--- linux-2.6-lttng.orig/include/net/dst.h 2010-03-18 20:27:25.000000000 -0400
+++ linux-2.6-lttng/include/net/dst.h 2010-03-18 20:35:02.000000000 -0400
@@ -159,7 +159,9 @@ static inline void dst_hold(struct dst_e
* If your kernel compilation stops here, please check
* __pad_to_align_refcnt declaration in struct dst_entry
*/
+#ifndef CONFIG_DEBUG_RCU_HEAD
BUILD_BUG_ON(offsetof(struct dst_entry, __refcnt) & 63);
+#endif
atomic_inc(&dst->__refcnt);
}
Index: linux-2.6-lttng/kernel/rcutiny.c
===================================================================
--- linux-2.6-lttng.orig/kernel/rcutiny.c 2010-03-18 20:35:14.000000000 -0400
+++ linux-2.6-lttng/kernel/rcutiny.c 2010-03-18 20:39:12.000000000 -0400
@@ -35,6 +35,7 @@
#include <linux/init.h>
#include <linux/time.h>
#include <linux/cpu.h>
+#include <linux/poison.h>
/* Global control variables for rcupdate callback mechanism. */
struct rcu_ctrlblk {
@@ -163,6 +164,10 @@ static void __rcu_process_callbacks(stru
while (list) {
next = list->next;
prefetch(next);
+#ifdef CONFIG_DEBUG_RCU_HEAD
+ WARN_ON_ONCE(list->debug != LIST_POISON1);
+ list->debug = NULL;
+#endif
list->func(list);
list = next;
}
@@ -210,6 +215,10 @@ static void __call_rcu(struct rcu_head *
{
unsigned long flags;
+#ifdef CONFIG_DEBUG_RCU_HEAD
+ WARN_ON_ONCE(head->debug);
+ head->debug = LIST_POISON1;
+#endif
head->func = func;
head->next = NULL;
--
Mathieu Desnoyers
Operating System Efficiency R&D Consultant
EfficiOS Inc.
http://www.efficios.com
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists