Re: safety of *mutex_unlock() (Was: [BUG] signal: sighand unprotected when accessed by /proc)

From: Paul E. McKenney
Date: Thu Jun 12 2014 - 19:19:55 EST


On Thu, Jun 12, 2014 at 03:27:48PM -0700, Paul E. McKenney wrote:
> On Thu, Jun 12, 2014 at 11:40:07PM +0200, Thomas Gleixner wrote:

[ . . . ]

> > True. Why should we have users if we would test the crap we produce?
>
> Well, it seems to be passing initial tests as well. Must be my tests
> need more work.

Or, as in this case, must be that I should have my test machine using
the right git-tree branch and correct kernel config. :-/ Updated patch
below, FWIW.

Thanx, Paul

------------------------------------------------------------------------

rcu: Simplify priority boosting by putting rt_mutex in rcu_node

RCU priority boosting currently checks for boosting via a pointer in
task_struct. However, this is not needed: As Oleg noted, if the
rt_mutex is placed in the rcu_node instead of on the booster's stack,
the boostee can simply check it see if it owns the lock. This commit
makes this change, shrinking task_struct by one pointer and the kernel
by twelve lines.

Suggested-by: Oleg Nesterov <oleg@xxxxxxxxxx>
Signed-off-by: Paul E. McKenney <paulmck@xxxxxxxxxxxxxxxxxx>

b/include/linux/init_task.h | 9 +--------
b/include/linux/sched.h | 6 ------
b/kernel/rcu/tree.h | 3 +++
b/kernel/rcu/tree_plugin.h | 20 +++++++++-----------
4 files changed, 13 insertions(+), 25 deletions(-)

diff --git a/include/linux/init_task.h b/include/linux/init_task.h
index 6df7f9fe0d01..2bb4c4f3531a 100644
--- a/include/linux/init_task.h
+++ b/include/linux/init_task.h
@@ -102,12 +102,6 @@ extern struct group_info init_groups;
#define INIT_IDS
#endif

-#ifdef CONFIG_RCU_BOOST
-#define INIT_TASK_RCU_BOOST() \
- .rcu_boost_mutex = NULL,
-#else
-#define INIT_TASK_RCU_BOOST()
-#endif
#ifdef CONFIG_TREE_PREEMPT_RCU
#define INIT_TASK_RCU_TREE_PREEMPT() \
.rcu_blocked_node = NULL,
@@ -119,8 +113,7 @@ extern struct group_info init_groups;
.rcu_read_lock_nesting = 0, \
.rcu_read_unlock_special = 0, \
.rcu_node_entry = LIST_HEAD_INIT(tsk.rcu_node_entry), \
- INIT_TASK_RCU_TREE_PREEMPT() \
- INIT_TASK_RCU_BOOST()
+ INIT_TASK_RCU_TREE_PREEMPT()
#else
#define INIT_TASK_RCU_PREEMPT(tsk)
#endif
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 25f54c79f757..1ffb275976da 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1222,9 +1222,6 @@ struct task_struct {
#ifdef CONFIG_TREE_PREEMPT_RCU
struct rcu_node *rcu_blocked_node;
#endif /* #ifdef CONFIG_TREE_PREEMPT_RCU */
-#ifdef CONFIG_RCU_BOOST
- struct rt_mutex *rcu_boost_mutex;
-#endif /* #ifdef CONFIG_RCU_BOOST */

#if defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT)
struct sched_info sched_info;
@@ -1961,9 +1958,6 @@ static inline void rcu_copy_process(struct task_struct *p)
#ifdef CONFIG_TREE_PREEMPT_RCU
p->rcu_blocked_node = NULL;
#endif /* #ifdef CONFIG_TREE_PREEMPT_RCU */
-#ifdef CONFIG_RCU_BOOST
- p->rcu_boost_mutex = NULL;
-#endif /* #ifdef CONFIG_RCU_BOOST */
INIT_LIST_HEAD(&p->rcu_node_entry);
}

diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h
index 31194ee9dfa6..db3f096ed80b 100644
--- a/kernel/rcu/tree.h
+++ b/kernel/rcu/tree.h
@@ -177,6 +177,9 @@ struct rcu_node {
/* to carry out the boosting is fully */
/* released with no future boostee accesses */
/* before that rt_mutex is re-initialized. */
+ struct rt_mutex boost_mtx;
+ /* Used only for the priority-boosting */
+ /* side effect, not as a lock. */
unsigned long boost_time;
/* When to start boosting (jiffies). */
struct task_struct *boost_kthread_task;
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index 99743e9ea8ed..c93c525b71fe 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -29,6 +29,7 @@
#include <linux/oom.h>
#include <linux/smpboot.h>
#include "../time/tick-internal.h"
+#include "../locking/rtmutex_common.h"

#define RCU_KTHREAD_PRIO 1

@@ -398,11 +399,9 @@ void rcu_read_unlock_special(struct task_struct *t)
#ifdef CONFIG_RCU_BOOST
if (&t->rcu_node_entry == rnp->boost_tasks)
rnp->boost_tasks = np;
- /* Snapshot/clear ->rcu_boost_mutex with rcu_node lock held. */
- if (t->rcu_boost_mutex) {
- rbmp = t->rcu_boost_mutex;
- t->rcu_boost_mutex = NULL;
- }
+ /* Snapshot/clear ->boost_mutex with rcu_node lock held. */
+ if (rt_mutex_owner(&rnp->boost_mtx) == t)
+ rbmp = &rnp->boost_mtx;
#endif /* #ifdef CONFIG_RCU_BOOST */

/*
@@ -1151,7 +1150,6 @@ static void rcu_wake_cond(struct task_struct *t, int status)
static int rcu_boost(struct rcu_node *rnp)
{
unsigned long flags;
- struct rt_mutex mtx;
struct task_struct *t;
struct list_head *tb;

@@ -1202,14 +1200,14 @@ static int rcu_boost(struct rcu_node *rnp)
* section.
*/
t = container_of(tb, struct task_struct, rcu_node_entry);
- rt_mutex_init_proxy_locked(&mtx, t);
- t->rcu_boost_mutex = &mtx;
+ rt_mutex_init_proxy_locked(&rnp->boost_mtx, t);
init_completion(&rnp->boost_completion);
raw_spin_unlock_irqrestore(&rnp->lock, flags);
- rt_mutex_lock(&mtx); /* Side effect: boosts task t's priority. */
- rt_mutex_unlock(&mtx); /* Keep lockdep happy. */
+ /* Lock only for side effect: boosts task t's priority. */
+ rt_mutex_lock(&rnp->boost_mtx);
+ rt_mutex_unlock(&rnp->boost_mtx); /* Then keep lockdep happy. */

- /* Wait until boostee is done accessing mtx before reinitializing. */
+ /* Wait for boostee to be done w/boost_mtx before reinitializing. */
wait_for_completion(&rnp->boost_completion);

return ACCESS_ONCE(rnp->exp_tasks) != NULL ||

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/