Merge git://git.kernel.org/pub/scm/linux/kernel/git/mingo/linux-2.6-sched

* git://git.kernel.org/pub/scm/linux/kernel/git/mingo/linux-2.6-sched:
  futex: correctly return -EFAULT not -EINVAL
  lockdep: in_range() fix
  lockdep: fix debug_show_all_locks()
  sched: style cleanups
  futex: fix for futex_wait signal stack corruption

include/linux/thread_info.h

@@ -7,12 +7,25 @@
 #ifndef _LINUX_THREAD_INFO_H
 #define _LINUX_THREAD_INFO_H
 
+#include <linux/types.h>
+
 /*
  * System call restart block.
  */
 struct restart_block {
 	long (*fn)(struct restart_block *);
+	union {
+		struct {
 			unsigned long arg0, arg1, arg2, arg3;
+		};
+		/* For futex_wait */
+		struct {
+			u32 *uaddr;
+			u32 val;
+			u32 flags;
+			u64 time;
+		} futex;
+	};
 };
 
 extern long do_no_restart_syscall(struct restart_block *parm);

kernel/futex.c

@@ -658,7 +658,7 @@ static int wake_futex_pi(u32 __user *uaddr, u32 uval, struct futex_q *this)
 
 		if (curval == -EFAULT)
 			ret = -EFAULT;
-		if (curval != uval)
+		else if (curval != uval)
 			ret = -EINVAL;
 		if (ret) {
 			spin_unlock(&pi_state->pi_mutex.wait_lock);
@@ -1149,9 +1149,9 @@ static int fixup_pi_state_owner(u32 __user *uaddr, struct futex_q *q,
 
 /*
  * In case we must use restart_block to restart a futex_wait,
- * we encode in the 'arg3' shared capability
+ * we encode in the 'flags' shared capability
  */
-#define ARG3_SHARED  1
+#define FLAGS_SHARED  1
 
 static long futex_wait_restart(struct restart_block *restart);
 
@@ -1290,12 +1290,13 @@ static int futex_wait(u32 __user *uaddr, struct rw_semaphore *fshared,
 		struct restart_block *restart;
 		restart = &current_thread_info()->restart_block;
 		restart->fn = futex_wait_restart;
-		restart->arg0 = (unsigned long)uaddr;
-		restart->arg1 = (unsigned long)val;
-		restart->arg2 = (unsigned long)abs_time;
-		restart->arg3 = 0;
+		restart->futex.uaddr = (u32 *)uaddr;
+		restart->futex.val = val;
+		restart->futex.time = abs_time->tv64;
+		restart->futex.flags = 0;
+
 		if (fshared)
-			restart->arg3 |= ARG3_SHARED;
+			restart->futex.flags |= FLAGS_SHARED;
 		return -ERESTART_RESTARTBLOCK;
 	}
 
@@ -1310,15 +1311,15 @@ static int futex_wait(u32 __user *uaddr, struct rw_semaphore *fshared,
 
 static long futex_wait_restart(struct restart_block *restart)
 {
-	u32 __user *uaddr = (u32 __user *)restart->arg0;
-	u32 val = (u32)restart->arg1;
-	ktime_t *abs_time = (ktime_t *)restart->arg2;
+	u32 __user *uaddr = (u32 __user *)restart->futex.uaddr;
 	struct rw_semaphore *fshared = NULL;
+	ktime_t t;
 
+	t.tv64 = restart->futex.time;
 	restart->fn = do_no_restart_syscall;
-	if (restart->arg3 & ARG3_SHARED)
+	if (restart->futex.flags & FLAGS_SHARED)
 		fshared = &current->mm->mmap_sem;
-	return (long)futex_wait(uaddr, fshared, val, abs_time);
+	return (long)futex_wait(uaddr, fshared, restart->futex.val, &t);
 }
 
 

kernel/lockdep.c

@@ -3054,11 +3054,6 @@ void __init lockdep_info(void)
 #endif
 }
 
-static inline int in_range(const void *start, const void *addr, const void *end)
-{
-	return addr >= start && addr <= end;
-}
-
 static void
 print_freed_lock_bug(struct task_struct *curr, const void *mem_from,
 		     const void *mem_to, struct held_lock *hlock)
@@ -3080,6 +3075,13 @@ print_freed_lock_bug(struct task_struct *curr, const void *mem_from,
 	dump_stack();
 }
 
+static inline int not_in_range(const void* mem_from, unsigned long mem_len,
+				const void* lock_from, unsigned long lock_len)
+{
+	return lock_from + lock_len <= mem_from ||
+		mem_from + mem_len <= lock_from;
+}
+
 /*
  * Called when kernel memory is freed (or unmapped), or if a lock
  * is destroyed or reinitialized - this code checks whether there is
@@ -3087,7 +3089,6 @@ print_freed_lock_bug(struct task_struct *curr, const void *mem_from,
  */
 void debug_check_no_locks_freed(const void *mem_from, unsigned long mem_len)
 {
-	const void *mem_to = mem_from + mem_len, *lock_from, *lock_to;
 	struct task_struct *curr = current;
 	struct held_lock *hlock;
 	unsigned long flags;
@@ -3100,14 +3101,11 @@ void debug_check_no_locks_freed(const void *mem_from, unsigned long mem_len)
 	for (i = 0; i < curr->lockdep_depth; i++) {
 		hlock = curr->held_locks + i;
 
-		lock_from = (void *)hlock->instance;
-		lock_to = (void *)(hlock->instance + 1);
-
-		if (!in_range(mem_from, lock_from, mem_to) &&
-					!in_range(mem_from, lock_to, mem_to))
+		if (not_in_range(mem_from, mem_len, hlock->instance,
+					sizeof(*hlock->instance)))
 			continue;
 
-		print_freed_lock_bug(curr, mem_from, mem_to, hlock);
+		print_freed_lock_bug(curr, mem_from, mem_from + mem_len, hlock);
 		break;
 	}
 	local_irq_restore(flags);
@@ -3173,6 +3171,13 @@ void debug_show_all_locks(void)
 		printk(" locked it.\n");
 
 	do_each_thread(g, p) {
+		/*
+		 * It's not reliable to print a task's held locks
+		 * if it's not sleeping (or if it's not the current
+		 * task):
+		 */
+		if (p->state == TASK_RUNNING && p != current)
+			continue;
 		if (p->lockdep_depth)
 			lockdep_print_held_locks(p);
 		if (!unlock)

kernel/sched.c

@@ -211,7 +211,6 @@ static inline struct task_group *task_group(struct task_struct *p)
 #else
 	tg = &init_task_group;
 #endif
-
 	return tg;
 }
 
@@ -249,14 +248,15 @@ struct cfs_rq {
 #ifdef CONFIG_FAIR_GROUP_SCHED
 	struct rq *rq;	/* cpu runqueue to which this cfs_rq is attached */
 
-	/* leaf cfs_rqs are those that hold tasks (lowest schedulable entity in
+	/*
+	 * leaf cfs_rqs are those that hold tasks (lowest schedulable entity in
 	 * a hierarchy). Non-leaf lrqs hold other higher schedulable entities
 	 * (like users, containers etc.)
 	 *
 	 * leaf_cfs_rq_list ties together list of leaf cfs_rq's in a cpu. This
 	 * list is used during load balance.
 	 */
-	struct list_head leaf_cfs_rq_list; /* Better name : task_cfs_rq_list? */
+	struct list_head leaf_cfs_rq_list;
 	struct task_group *tg;	/* group that "owns" this runqueue */
 #endif
 };
@@ -4390,8 +4390,8 @@ do_sched_setscheduler(pid_t pid, int policy, struct sched_param __user *param)
  * @policy: new policy.
  * @param: structure containing the new RT priority.
  */
-asmlinkage long sys_sched_setscheduler(pid_t pid, int policy,
-				       struct sched_param __user *param)
+asmlinkage long
+sys_sched_setscheduler(pid_t pid, int policy, struct sched_param __user *param)
 {
 	/* negative values for policy are not valid */
 	if (policy < 0)
@@ -5245,11 +5245,12 @@ static void move_task_off_dead_cpu(int dead_cpu, struct task_struct *p)
 			 * kernel threads (both mm NULL), since they never
 			 * leave kernel.
 			 */
-			if (p->mm && printk_ratelimit())
+			if (p->mm && printk_ratelimit()) {
 				printk(KERN_INFO "process %d (%s) no "
 				       "longer affine to cpu%d\n",
 					task_pid_nr(p), p->comm, dead_cpu);
 			}
+		}
 	} while (!__migrate_task_irq(p, dead_cpu, dest_cpu));
 }
 
@@ -5612,9 +5613,11 @@ migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu)
 		migrate_nr_uninterruptible(rq);
 		BUG_ON(rq->nr_running != 0);
 
-		/* No need to migrate the tasks: it was best-effort if
+		/*
+		 * No need to migrate the tasks: it was best-effort if
 		 * they didn't take sched_hotcpu_mutex. Just wake up
-		 * the requestors. */
+		 * the requestors.
+		 */
 		spin_lock_irq(&rq->lock);
 		while (!list_empty(&rq->migration_queue)) {
 			struct migration_req *req;
@@ -5999,8 +6002,8 @@ int sched_smt_power_savings = 0, sched_mc_power_savings = 0;
 static DEFINE_PER_CPU(struct sched_domain, cpu_domains);
 static DEFINE_PER_CPU(struct sched_group, sched_group_cpus);
 
-static int cpu_to_cpu_group(int cpu, const cpumask_t *cpu_map,
-			    struct sched_group **sg)
+static int
+cpu_to_cpu_group(int cpu, const cpumask_t *cpu_map, struct sched_group **sg)
 {
 	if (sg)
 		*sg = &per_cpu(sched_group_cpus, cpu);
@@ -6017,8 +6020,8 @@ static DEFINE_PER_CPU(struct sched_group, sched_group_core);
 #endif
 
 #if defined(CONFIG_SCHED_MC) && defined(CONFIG_SCHED_SMT)
-static int cpu_to_core_group(int cpu, const cpumask_t *cpu_map,
-			     struct sched_group **sg)
+static int
+cpu_to_core_group(int cpu, const cpumask_t *cpu_map, struct sched_group **sg)
 {
 	int group;
 	cpumask_t mask = per_cpu(cpu_sibling_map, cpu);
@@ -6029,8 +6032,8 @@ static int cpu_to_core_group(int cpu, const cpumask_t *cpu_map,
 	return group;
 }
 #elif defined(CONFIG_SCHED_MC)
-static int cpu_to_core_group(int cpu, const cpumask_t *cpu_map,
-			     struct sched_group **sg)
+static int
+cpu_to_core_group(int cpu, const cpumask_t *cpu_map, struct sched_group **sg)
 {
 	if (sg)
 		*sg = &per_cpu(sched_group_core, cpu);
@@ -6041,8 +6044,8 @@ static int cpu_to_core_group(int cpu, const cpumask_t *cpu_map,
 static DEFINE_PER_CPU(struct sched_domain, phys_domains);
 static DEFINE_PER_CPU(struct sched_group, sched_group_phys);
 
-static int cpu_to_phys_group(int cpu, const cpumask_t *cpu_map,
-			     struct sched_group **sg)
+static int
+cpu_to_phys_group(int cpu, const cpumask_t *cpu_map, struct sched_group **sg)
 {
 	int group;
 #ifdef CONFIG_SCHED_MC
@@ -7193,16 +7196,17 @@ cpu_cgroup_create(struct cgroup_subsys *ss, struct cgroup *cgrp)
 	return &tg->css;
 }
 
-static void cpu_cgroup_destroy(struct cgroup_subsys *ss,
-			       struct cgroup *cgrp)
+static void
+cpu_cgroup_destroy(struct cgroup_subsys *ss, struct cgroup *cgrp)
 {
 	struct task_group *tg = cgroup_tg(cgrp);
 
 	sched_destroy_group(tg);
 }
 
-static int cpu_cgroup_can_attach(struct cgroup_subsys *ss,
-			     struct cgroup *cgrp, struct task_struct *tsk)
+static int
+cpu_cgroup_can_attach(struct cgroup_subsys *ss, struct cgroup *cgrp,
+		      struct task_struct *tsk)
 {
 	/* We don't support RT-tasks being in separate groups */
 	if (tsk->sched_class != &fair_sched_class)
@@ -7308,8 +7312,8 @@ static struct cgroup_subsys_state *cpuacct_create(
 }
 
 /* destroy an existing cpu accounting group */
-static void cpuacct_destroy(struct cgroup_subsys *ss,
-			    struct cgroup *cont)
+static void
+cpuacct_destroy(struct cgroup_subsys *ss, struct cgroup *cont)
 {
 	struct cpuacct *ca = cgroup_ca(cont);