[GIT PULL] core kernel fixes

From: Ingo Molnar
Date: Fri Oct 23 2009 - 10:53:47 EST

Linus,

Please pull the latest core-fixes-for-linus git tree from:

git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip.git core-fixes-for-linus

Thanks,

Ingo

------------------>
Darren Hart (2):
futex: Check for NULL keys in match_futex
futex: Move drop_futex_key_refs out of spinlock'ed region

Paul E. McKenney (3):
rcu: Prevent RCU IPI storms in presence of high call_rcu() load
rcu: Stopgap fix for synchronize_rcu_expedited() for TREE_PREEMPT_RCU
rcu: Fix TREE_PREEMPT_RCU CPU_HOTPLUG bad-luck hang

Thomas Gleixner (1):
futex: Handle spurious wake up


include/linux/rcutree.h | 6 +-----
kernel/futex.c | 24 +++++++++++++++++++-----
kernel/rcutree.c | 44 ++++++++++++++++++++++++++++++++++++++------
kernel/rcutree.h | 10 +++++++---
kernel/rcutree_plugin.h | 46 ++++++++++++++++++++++++++++++++++++++--------
5 files changed, 103 insertions(+), 27 deletions(-)

diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h
index 46e9ab3..9642c6b 100644
--- a/include/linux/rcutree.h
+++ b/include/linux/rcutree.h
@@ -76,11 +76,7 @@ static inline void __rcu_read_unlock_bh(void)

extern void call_rcu_sched(struct rcu_head *head,
void (*func)(struct rcu_head *rcu));
-
-static inline void synchronize_rcu_expedited(void)
-{
- synchronize_sched_expedited();
-}
+extern void synchronize_rcu_expedited(void);

static inline void synchronize_rcu_bh_expedited(void)
{
diff --git a/kernel/futex.c b/kernel/futex.c
index 4949d33..642f3bb 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -150,7 +150,8 @@ static struct futex_hash_bucket *hash_futex(union futex_key *key)
*/
static inline int match_futex(union futex_key *key1, union futex_key *key2)
{
- return (key1->both.word == key2->both.word
+ return (key1 && key2
+ && key1->both.word == key2->both.word
&& key1->both.ptr == key2->both.ptr
&& key1->both.offset == key2->both.offset);
}
@@ -1028,7 +1029,6 @@ static inline
void requeue_pi_wake_futex(struct futex_q *q, union futex_key *key,
struct futex_hash_bucket *hb)
{
- drop_futex_key_refs(&q->key);
get_futex_key_refs(key);
q->key = *key;

@@ -1226,6 +1226,7 @@ retry_private:
*/
if (ret == 1) {
WARN_ON(pi_state);
+ drop_count++;
task_count++;
ret = get_futex_value_locked(&curval2, uaddr2);
if (!ret)
@@ -1304,6 +1305,7 @@ retry_private:
if (ret == 1) {
/* We got the lock. */
requeue_pi_wake_futex(this, &key2, hb2);
+ drop_count++;
continue;
} else if (ret) {
/* -EDEADLK */
@@ -1791,6 +1793,7 @@ static int futex_wait(u32 __user *uaddr, int fshared,
current->timer_slack_ns);
}

+retry:
/* Prepare to wait on uaddr. */
ret = futex_wait_setup(uaddr, val, fshared, &q, &hb);
if (ret)
@@ -1808,9 +1811,14 @@ static int futex_wait(u32 __user *uaddr, int fshared,
goto out_put_key;

/*
- * We expect signal_pending(current), but another thread may
- * have handled it for us already.
+ * We expect signal_pending(current), but we might be the
+ * victim of a spurious wakeup as well.
*/
+ if (!signal_pending(current)) {
+ put_futex_key(fshared, &q.key);
+ goto retry;
+ }
+
ret = -ERESTARTSYS;
if (!abs_time)
goto out_put_key;
@@ -2118,9 +2126,11 @@ int handle_early_requeue_pi_wakeup(struct futex_hash_bucket *hb,
*/
plist_del(&q->list, &q->list.plist);

+ /* Handle spurious wakeups gracefully */
+ ret = -EAGAIN;
if (timeout && !timeout->task)
ret = -ETIMEDOUT;
- else
+ else if (signal_pending(current))
ret = -ERESTARTNOINTR;
}
return ret;
@@ -2198,6 +2208,7 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, int fshared,
debug_rt_mutex_init_waiter(&rt_waiter);
rt_waiter.task = NULL;

+retry:
key2 = FUTEX_KEY_INIT;
ret = get_futex_key(uaddr2, fshared, &key2, VERIFY_WRITE);
if (unlikely(ret != 0))
@@ -2292,6 +2303,9 @@ out_put_keys:
out_key2:
put_futex_key(fshared, &key2);

+ /* Spurious wakeup ? */
+ if (ret == -EAGAIN)
+ goto retry;
out:
if (to) {
hrtimer_cancel(&to->timer);
diff --git a/kernel/rcutree.c b/kernel/rcutree.c
index 705f02a..0536125 100644
--- a/kernel/rcutree.c
+++ b/kernel/rcutree.c
@@ -913,7 +913,20 @@ static void __rcu_offline_cpu(int cpu, struct rcu_state *rsp)
spin_unlock(&rnp->lock); /* irqs remain disabled. */
break;
}
- rcu_preempt_offline_tasks(rsp, rnp, rdp);
+
+ /*
+ * If there was a task blocking the current grace period,
+ * and if all CPUs have checked in, we need to propagate
+ * the quiescent state up the rcu_node hierarchy. But that
+ * is inconvenient at the moment due to deadlock issues if
+ * this should end the current grace period. So set the
+ * offlined CPU's bit in ->qsmask in order to force the
+ * next force_quiescent_state() invocation to clean up this
+ * mess in a deadlock-free manner.
+ */
+ if (rcu_preempt_offline_tasks(rsp, rnp, rdp) && !rnp->qsmask)
+ rnp->qsmask |= mask;
+
mask = rnp->grpmask;
spin_unlock(&rnp->lock); /* irqs remain disabled. */
rnp = rnp->parent;
@@ -958,7 +971,7 @@ static void rcu_offline_cpu(int cpu)
* Invoke any RCU callbacks that have made it to the end of their grace
* period. Thottle as specified by rdp->blimit.
*/
-static void rcu_do_batch(struct rcu_data *rdp)
+static void rcu_do_batch(struct rcu_state *rsp, struct rcu_data *rdp)
{
unsigned long flags;
struct rcu_head *next, *list, **tail;
@@ -1011,6 +1024,13 @@ static void rcu_do_batch(struct rcu_data *rdp)
if (rdp->blimit == LONG_MAX && rdp->qlen <= qlowmark)
rdp->blimit = blimit;

+ /* Reset ->qlen_last_fqs_check trigger if enough CBs have drained. */
+ if (rdp->qlen == 0 && rdp->qlen_last_fqs_check != 0) {
+ rdp->qlen_last_fqs_check = 0;
+ rdp->n_force_qs_snap = rsp->n_force_qs;
+ } else if (rdp->qlen < rdp->qlen_last_fqs_check - qhimark)
+ rdp->qlen_last_fqs_check = rdp->qlen;
+
local_irq_restore(flags);

/* Re-raise the RCU softirq if there are callbacks remaining. */
@@ -1224,7 +1244,7 @@ __rcu_process_callbacks(struct rcu_state *rsp, struct rcu_data *rdp)
}

/* If there are callbacks ready, invoke them. */
- rcu_do_batch(rdp);
+ rcu_do_batch(rsp, rdp);
}

/*
@@ -1288,10 +1308,20 @@ __call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu),
rcu_start_gp(rsp, nestflag); /* releases rnp_root->lock. */
}

- /* Force the grace period if too many callbacks or too long waiting. */
- if (unlikely(++rdp->qlen > qhimark)) {
+ /*
+ * Force the grace period if too many callbacks or too long waiting.
+ * Enforce hysteresis, and don't invoke force_quiescent_state()
+ * if some other CPU has recently done so. Also, don't bother
+ * invoking force_quiescent_state() if the newly enqueued callback
+ * is the only one waiting for a grace period to complete.
+ */
+ if (unlikely(++rdp->qlen > rdp->qlen_last_fqs_check + qhimark)) {
rdp->blimit = LONG_MAX;
- force_quiescent_state(rsp, 0);
+ if (rsp->n_force_qs == rdp->n_force_qs_snap &&
+ *rdp->nxttail[RCU_DONE_TAIL] != head)
+ force_quiescent_state(rsp, 0);
+ rdp->n_force_qs_snap = rsp->n_force_qs;
+ rdp->qlen_last_fqs_check = rdp->qlen;
} else if ((long)(ACCESS_ONCE(rsp->jiffies_force_qs) - jiffies) < 0)
force_quiescent_state(rsp, 1);
local_irq_restore(flags);
@@ -1523,6 +1553,8 @@ rcu_init_percpu_data(int cpu, struct rcu_state *rsp, int preemptable)
rdp->beenonline = 1; /* We have now been online. */
rdp->preemptable = preemptable;
rdp->passed_quiesc_completed = lastcomp - 1;
+ rdp->qlen_last_fqs_check = 0;
+ rdp->n_force_qs_snap = rsp->n_force_qs;
rdp->blimit = blimit;
spin_unlock(&rnp->lock); /* irqs remain disabled. */

diff --git a/kernel/rcutree.h b/kernel/rcutree.h
index b40ac57..1823c6e 100644
--- a/kernel/rcutree.h
+++ b/kernel/rcutree.h
@@ -167,6 +167,10 @@ struct rcu_data {
struct rcu_head *nxtlist;
struct rcu_head **nxttail[RCU_NEXT_SIZE];
long qlen; /* # of queued callbacks */
+ long qlen_last_fqs_check;
+ /* qlen at last check for QS forcing */
+ unsigned long n_force_qs_snap;
+ /* did other CPU force QS recently? */
long blimit; /* Upper limit on a processed batch */

#ifdef CONFIG_NO_HZ
@@ -302,9 +306,9 @@ static void rcu_print_task_stall(struct rcu_node *rnp);
#endif /* #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */
static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp);
#ifdef CONFIG_HOTPLUG_CPU
-static void rcu_preempt_offline_tasks(struct rcu_state *rsp,
- struct rcu_node *rnp,
- struct rcu_data *rdp);
+static int rcu_preempt_offline_tasks(struct rcu_state *rsp,
+ struct rcu_node *rnp,
+ struct rcu_data *rdp);
static void rcu_preempt_offline_cpu(int cpu);
#endif /* #ifdef CONFIG_HOTPLUG_CPU */
static void rcu_preempt_check_callbacks(int cpu);
diff --git a/kernel/rcutree_plugin.h b/kernel/rcutree_plugin.h
index c0cb783..ef2a58c 100644
--- a/kernel/rcutree_plugin.h
+++ b/kernel/rcutree_plugin.h
@@ -304,21 +304,25 @@ static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp)
* parent is to remove the need for rcu_read_unlock_special() to
* make more than two attempts to acquire the target rcu_node's lock.
*
+ * Returns 1 if there was previously a task blocking the current grace
+ * period on the specified rcu_node structure.
+ *
* The caller must hold rnp->lock with irqs disabled.
*/
-static void rcu_preempt_offline_tasks(struct rcu_state *rsp,
- struct rcu_node *rnp,
- struct rcu_data *rdp)
+static int rcu_preempt_offline_tasks(struct rcu_state *rsp,
+ struct rcu_node *rnp,
+ struct rcu_data *rdp)
{
int i;
struct list_head *lp;
struct list_head *lp_root;
+ int retval = rcu_preempted_readers(rnp);
struct rcu_node *rnp_root = rcu_get_root(rsp);
struct task_struct *tp;

if (rnp == rnp_root) {
WARN_ONCE(1, "Last CPU thought to be offlined?");
- return; /* Shouldn't happen: at least one CPU online. */
+ return 0; /* Shouldn't happen: at least one CPU online. */
}
WARN_ON_ONCE(rnp != rdp->mynode &&
(!list_empty(&rnp->blocked_tasks[0]) ||
@@ -342,6 +346,8 @@ static void rcu_preempt_offline_tasks(struct rcu_state *rsp,
spin_unlock(&rnp_root->lock); /* irqs remain disabled */
}
}
+
+ return retval;
}

/*
@@ -393,6 +399,17 @@ void call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu))
EXPORT_SYMBOL_GPL(call_rcu);

/*
+ * Wait for an rcu-preempt grace period. We are supposed to expedite the
+ * grace period, but this is the crude slow compatability hack, so just
+ * invoke synchronize_rcu().
+ */
+void synchronize_rcu_expedited(void)
+{
+ synchronize_rcu();
+}
+EXPORT_SYMBOL_GPL(synchronize_rcu_expedited);
+
+/*
* Check to see if there is any immediate preemptable-RCU-related work
* to be done.
*/
@@ -521,12 +538,15 @@ static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp)

/*
* Because preemptable RCU does not exist, it never needs to migrate
- * tasks that were blocked within RCU read-side critical sections.
+ * tasks that were blocked within RCU read-side critical sections, and
+ * such non-existent tasks cannot possibly have been blocking the current
+ * grace period.
*/
-static void rcu_preempt_offline_tasks(struct rcu_state *rsp,
- struct rcu_node *rnp,
- struct rcu_data *rdp)
+static int rcu_preempt_offline_tasks(struct rcu_state *rsp,
+ struct rcu_node *rnp,
+ struct rcu_data *rdp)
{
+ return 0;
}

/*
@@ -565,6 +585,16 @@ void call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu))
EXPORT_SYMBOL_GPL(call_rcu);

/*
+ * Wait for an rcu-preempt grace period, but make it happen quickly.
+ * But because preemptable RCU does not exist, map to rcu-sched.
+ */
+void synchronize_rcu_expedited(void)
+{
+ synchronize_sched_expedited();
+}
+EXPORT_SYMBOL_GPL(synchronize_rcu_expedited);
+
+/*
* Because preemptable RCU does not exist, it never has any work to do.
*/
static int rcu_preempt_pending(int cpu)
--
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/