Merge with /pub/scm/linux/kernel/git/torvalds/linux-2.6.git

Signed-off-by: Steve French <sfrench@us.ibm.com>

6 files changed, 77 insertions, 33 deletions

diff --git a/kernel/fork.c b/kernel/fork.c
index fbea12d7a943..b373322ca497 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -108,8 +108,10 @@ void free_task(struct task_struct *tsk)
 }
 EXPORT_SYMBOL(free_task);
 
-void __put_task_struct(struct task_struct *tsk)
+void __put_task_struct_cb(struct rcu_head *rhp)
 {
+	struct task_struct *tsk = container_of(rhp, struct task_struct, rcu);
+
 	WARN_ON(!(tsk->exit_state & (EXIT_DEAD | EXIT_ZOMBIE)));
 	WARN_ON(atomic_read(&tsk->usage));
 	WARN_ON(tsk == current);
@@ -1060,6 +1062,12 @@ static task_t *copy_process(unsigned long clone_flags,
 	p->clear_child_tid = (clone_flags & CLONE_CHILD_CLEARTID) ? child_tidptr: NULL;
 
 	/*
+	 * sigaltstack should be cleared when sharing the same VM
+	 */
+	if ((clone_flags & (CLONE_VM|CLONE_VFORK)) == CLONE_VM)
+		p->sas_ss_sp = p->sas_ss_size = 0;
+
+	/*
 	 * Syscall tracing should be turned off in the child regardless
 	 * of CLONE_PTRACE.
 	 */
@@ -1470,9 +1478,7 @@ static int unshare_vm(unsigned long unshare_flags, struct mm_struct **new_mmp)
 
 	if ((unshare_flags & CLONE_VM) &&
 	    (mm && atomic_read(&mm->mm_users) > 1)) {
-		*new_mmp = dup_mm(current);
-		if (!*new_mmp)
-			return -ENOMEM;
+		return -EINVAL;
 	}
 
 	return 0;
@@ -1561,7 +1567,7 @@ asmlinkage long sys_unshare(unsigned long unshare_flags)
 
 		if (new_sigh) {
 			sigh = current->sighand;
-			current->sighand = new_sigh;
+			rcu_assign_pointer(current->sighand, new_sigh);
 			new_sigh = sigh;
 		}
 
diff --git a/kernel/posix-timers.c b/kernel/posix-timers.c
index 216f574b5ffb..fa895fc2ecf5 100644
--- a/kernel/posix-timers.c
+++ b/kernel/posix-timers.c
@@ -353,6 +353,7 @@ static int posix_timer_fn(void *data)
 				hrtimer_forward(&timr->it.real.timer,
 						timr->it.real.interval);
 			ret = HRTIMER_RESTART;
+			++timr->it_requeue_pending;
 		}
 	}
 
diff --git a/kernel/rcupdate.c b/kernel/rcupdate.c
index 0cf8146bd585..8cf15a569fcd 100644
--- a/kernel/rcupdate.c
+++ b/kernel/rcupdate.c
@@ -67,7 +67,43 @@ DEFINE_PER_CPU(struct rcu_data, rcu_bh_data) = { 0L };
 
 /* Fake initialization required by compiler */
 static DEFINE_PER_CPU(struct tasklet_struct, rcu_tasklet) = {NULL};
-static int maxbatch = 10000;
+static int blimit = 10;
+static int qhimark = 10000;
+static int qlowmark = 100;
+#ifdef CONFIG_SMP
+static int rsinterval = 1000;
+#endif
+
+static atomic_t rcu_barrier_cpu_count;
+static struct semaphore rcu_barrier_sema;
+static struct completion rcu_barrier_completion;
+
+#ifdef CONFIG_SMP
+static void force_quiescent_state(struct rcu_data *rdp,
+			struct rcu_ctrlblk *rcp)
+{
+	int cpu;
+	cpumask_t cpumask;
+	set_need_resched();
+	if (unlikely(rdp->qlen - rdp->last_rs_qlen > rsinterval)) {
+		rdp->last_rs_qlen = rdp->qlen;
+		/*
+		 * Don't send IPI to itself. With irqs disabled,
+		 * rdp->cpu is the current cpu.
+		 */
+		cpumask = rcp->cpumask;
+		cpu_clear(rdp->cpu, cpumask);
+		for_each_cpu_mask(cpu, cpumask)
+			smp_send_reschedule(cpu);
+	}
+}
+#else
+static inline void force_quiescent_state(struct rcu_data *rdp,
+			struct rcu_ctrlblk *rcp)
+{
+	set_need_resched();
+}
+#endif
 
 /**
  * call_rcu - Queue an RCU callback for invocation after a grace period.
@@ -92,17 +128,13 @@ void fastcall call_rcu(struct rcu_head *head,
 	rdp = &__get_cpu_var(rcu_data);
 	*rdp->nxttail = head;
 	rdp->nxttail = &head->next;
-
-	if (unlikely(++rdp->count > 10000))
-		set_need_resched();
-
+	if (unlikely(++rdp->qlen > qhimark)) {
+		rdp->blimit = INT_MAX;
+		force_quiescent_state(rdp, &rcu_ctrlblk);
+	}
 	local_irq_restore(flags);
 }
 
-static atomic_t rcu_barrier_cpu_count;
-static struct semaphore rcu_barrier_sema;
-static struct completion rcu_barrier_completion;
-
 /**
  * call_rcu_bh - Queue an RCU for invocation after a quicker grace period.
  * @head: structure to be used for queueing the RCU updates.
@@ -131,12 +163,12 @@ void fastcall call_rcu_bh(struct rcu_head *head,
 	rdp = &__get_cpu_var(rcu_bh_data);
 	*rdp->nxttail = head;
 	rdp->nxttail = &head->next;
-	rdp->count++;
-/*
- *  Should we directly call rcu_do_batch() here ?
- *  if (unlikely(rdp->count > 10000))
- *      rcu_do_batch(rdp);
- */
+
+	if (unlikely(++rdp->qlen > qhimark)) {
+		rdp->blimit = INT_MAX;
+		force_quiescent_state(rdp, &rcu_bh_ctrlblk);
+	}
+
 	local_irq_restore(flags);
 }
 
@@ -199,10 +231,12 @@ static void rcu_do_batch(struct rcu_data *rdp)
 		next = rdp->donelist = list->next;
 		list->func(list);
 		list = next;
-		rdp->count--;
-		if (++count >= maxbatch)
+		rdp->qlen--;
+		if (++count >= rdp->blimit)
 			break;
 	}
+	if (rdp->blimit == INT_MAX && rdp->qlen <= qlowmark)
+		rdp->blimit = blimit;
 	if (!rdp->donelist)
 		rdp->donetail = &rdp->donelist;
 	else
@@ -473,6 +507,7 @@ static void rcu_init_percpu_data(int cpu, struct rcu_ctrlblk *rcp,
 	rdp->quiescbatch = rcp->completed;
 	rdp->qs_pending = 0;
 	rdp->cpu = cpu;
+	rdp->blimit = blimit;
 }
 
 static void __devinit rcu_online_cpu(int cpu)
@@ -567,7 +602,12 @@ void synchronize_kernel(void)
 	synchronize_rcu();
 }
 
-module_param(maxbatch, int, 0);
+module_param(blimit, int, 0);
+module_param(qhimark, int, 0);
+module_param(qlowmark, int, 0);
+#ifdef CONFIG_SMP
+module_param(rsinterval, int, 0);
+#endif
 EXPORT_SYMBOL_GPL(rcu_batches_completed);
 EXPORT_SYMBOL(call_rcu);  /* WARNING: GPL-only in April 2006. */
 EXPORT_SYMBOL(call_rcu_bh);  /* WARNING: GPL-only in April 2006. */
diff --git a/kernel/sched.c b/kernel/sched.c
index 3454bb869fd0..4d46e90f59c3 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -178,13 +178,6 @@ static unsigned int task_timeslice(task_t *p)
 #define task_hot(p, now, sd) ((long long) ((now) - (p)->last_ran)	\
 				< (long long) (sd)->cache_hot_time)
 
-void __put_task_struct_cb(struct rcu_head *rhp)
-{
-	__put_task_struct(container_of(rhp, struct task_struct, rcu));
-}
-
-EXPORT_SYMBOL_GPL(__put_task_struct_cb);
-
 /*
  * These are the runqueue data structures:
  */
@@ -4335,6 +4328,7 @@ void __devinit init_idle(task_t *idle, int cpu)
 	runqueue_t *rq = cpu_rq(cpu);
 	unsigned long flags;
 
+	idle->timestamp = sched_clock();
 	idle->sleep_avg = 0;
 	idle->array = NULL;
 	idle->prio = MAX_PRIO;
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index de2d9109194e..32b48e8ee36e 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -50,6 +50,9 @@
 #include <asm/uaccess.h>
 #include <asm/processor.h>
 
+extern int proc_nr_files(ctl_table *table, int write, struct file *filp,
+                     void __user *buffer, size_t *lenp, loff_t *ppos);
+
 #if defined(CONFIG_SYSCTL)
 
 /* External variables not in a header file. */
@@ -943,7 +946,7 @@ static ctl_table fs_table[] = {
 		.data		= &files_stat,
 		.maxlen		= 3*sizeof(int),
 		.mode		= 0444,
-		.proc_handler	= &proc_dointvec,
+		.proc_handler	= &proc_nr_files,
 	},
 	{
 		.ctl_name	= FS_MAXFILE,
diff --git a/kernel/timer.c b/kernel/timer.c
index bf7c4193b936..2410c18dbeb1 100644
--- a/kernel/timer.c
+++ b/kernel/timer.c
@@ -1354,8 +1354,8 @@ void __init init_timers(void)
 
 #ifdef CONFIG_TIME_INTERPOLATION
 
-struct time_interpolator *time_interpolator;
-static struct time_interpolator *time_interpolator_list;
+struct time_interpolator *time_interpolator __read_mostly;
+static struct time_interpolator *time_interpolator_list __read_mostly;
 static DEFINE_SPINLOCK(time_interpolator_lock);
 
 static inline u64 time_interpolator_get_cycles(unsigned int src)