Merge branch 'from-linus' into upstream

8 files changed, 28 insertions, 96 deletions

diff --git a/kernel/delayacct.c b/kernel/delayacct.c
index 57ca3730205..36752f124c6 100644
--- a/kernel/delayacct.c
+++ b/kernel/delayacct.c
@@ -41,24 +41,11 @@ void delayacct_init(void)
 
 void __delayacct_tsk_init(struct task_struct *tsk)
 {
-	spin_lock_init(&tsk->delays_lock);
-	/* No need to acquire tsk->delays_lock for allocation here unless
-	   __delayacct_tsk_init called after tsk is attached to tasklist
-	*/
 	tsk->delays = kmem_cache_zalloc(delayacct_cache, SLAB_KERNEL);
 	if (tsk->delays)
 		spin_lock_init(&tsk->delays->lock);
 }
 
-void __delayacct_tsk_exit(struct task_struct *tsk)
-{
-	struct task_delay_info *delays = tsk->delays;
-	spin_lock(&tsk->delays_lock);
-	tsk->delays = NULL;
-	spin_unlock(&tsk->delays_lock);
-	kmem_cache_free(delayacct_cache, delays);
-}
-
 /*
  * Start accounting for a delay statistic using
  * its starting timestamp (@start)
@@ -118,8 +105,6 @@ int __delayacct_add_tsk(struct taskstats *d, struct task_struct *tsk)
 	struct timespec ts;
 	unsigned long t1,t2,t3;
 
-	spin_lock(&tsk->delays_lock);
-
 	/* Though tsk->delays accessed later, early exit avoids
 	 * unnecessary returning of other data
 	 */
@@ -161,7 +146,6 @@ int __delayacct_add_tsk(struct taskstats *d, struct task_struct *tsk)
 	spin_unlock(&tsk->delays->lock);
 
 done:
-	spin_unlock(&tsk->delays_lock);
 	return 0;
 }
 
diff --git a/kernel/exit.c b/kernel/exit.c
index dba194a8d41..d891883420f 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -908,7 +908,6 @@ fastcall NORET_TYPE void do_exit(long code)
 		audit_free(tsk);
 	taskstats_exit_send(tsk, tidstats, group_dead, mycpu);
 	taskstats_exit_free(tidstats);
-	delayacct_tsk_exit(tsk);
 
 	exit_mm(tsk);
 
@@ -1054,7 +1053,7 @@ static int eligible_child(pid_t pid, int options, struct task_struct *p)
 	 * Do not consider thread group leaders that are
 	 * in a non-empty thread group:
 	 */
-	if (current->tgid != p->tgid && delay_group_leader(p))
+	if (delay_group_leader(p))
 		return 2;
 
 	if (security_task_wait(p))
diff --git a/kernel/fork.c b/kernel/fork.c
index aa36c43783c..f9b014e3e70 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -117,6 +117,7 @@ void __put_task_struct(struct task_struct *tsk)
 	security_task_free(tsk);
 	free_uid(tsk->user);
 	put_group_info(tsk->group_info);
+	delayacct_tsk_free(tsk);
 
 	if (!profile_handoff_task(tsk))
 		free_task(tsk);
@@ -1011,7 +1012,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 	retval = -EFAULT;
 	if (clone_flags & CLONE_PARENT_SETTID)
 		if (put_user(p->pid, parent_tidptr))
-			goto bad_fork_cleanup;
+			goto bad_fork_cleanup_delays_binfmt;
 
 	INIT_LIST_HEAD(&p->children);
 	INIT_LIST_HEAD(&p->sibling);
@@ -1277,7 +1278,8 @@ bad_fork_cleanup_policy:
 bad_fork_cleanup_cpuset:
 #endif
 	cpuset_exit(p);
-bad_fork_cleanup:
+bad_fork_cleanup_delays_binfmt:
+	delayacct_tsk_free(p);
 	if (p->binfmt)
 		module_put(p->binfmt->module);
 bad_fork_cleanup_put_domain:
diff --git a/kernel/futex.c b/kernel/futex.c
index b9b8aea5389..9d260e838cf 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -1120,9 +1120,10 @@ static int futex_wait(u32 __user *uaddr, u32 val, unsigned long time)
  * if there are waiters then it will block, it does PI, etc. (Due to
  * races the kernel might see a 0 value of the futex too.)
  */
-static int do_futex_lock_pi(u32 __user *uaddr, int detect, int trylock,
-			    struct hrtimer_sleeper *to)
+static int futex_lock_pi(u32 __user *uaddr, int detect, unsigned long sec,
+			 long nsec, int trylock)
 {
+	struct hrtimer_sleeper timeout, *to = NULL;
 	struct task_struct *curr = current;
 	struct futex_hash_bucket *hb;
 	u32 uval, newval, curval;
@@ -1132,6 +1133,13 @@ static int do_futex_lock_pi(u32 __user *uaddr, int detect, int trylock,
 	if (refill_pi_state_cache())
 		return -ENOMEM;
 
+	if (sec != MAX_SCHEDULE_TIMEOUT) {
+		to = &timeout;
+		hrtimer_init(&to->timer, CLOCK_REALTIME, HRTIMER_ABS);
+		hrtimer_init_sleeper(to, current);
+		to->timer.expires = ktime_set(sec, nsec);
+	}
+
 	q.pi_state = NULL;
  retry:
 	down_read(&curr->mm->mmap_sem);
@@ -1307,7 +1315,7 @@ static int do_futex_lock_pi(u32 __user *uaddr, int detect, int trylock,
 	if (!detect && ret == -EDEADLK && 0)
 		force_sig(SIGKILL, current);
 
-	return ret;
+	return ret != -EINTR ? ret : -ERESTARTNOINTR;
 
  out_unlock_release_sem:
 	queue_unlock(&q, hb);
@@ -1342,76 +1350,6 @@ static int do_futex_lock_pi(u32 __user *uaddr, int detect, int trylock,
 }
 
 /*
- * Restart handler
- */
-static long futex_lock_pi_restart(struct restart_block *restart)
-{
-	struct hrtimer_sleeper timeout, *to = NULL;
-	int ret;
-
-	restart->fn = do_no_restart_syscall;
-
-	if (restart->arg2 || restart->arg3) {
-		to = &timeout;
-		hrtimer_init(&to->timer, CLOCK_REALTIME, HRTIMER_ABS);
-		hrtimer_init_sleeper(to, current);
-		to->timer.expires.tv64 = ((u64)restart->arg1 << 32) |
-			(u64) restart->arg0;
-	}
-
-	pr_debug("lock_pi restart: %p, %d (%d)\n",
-		 (u32 __user *)restart->arg0, current->pid);
-
-	ret = do_futex_lock_pi((u32 __user *)restart->arg0, restart->arg1,
-			       0, to);
-
-	if (ret != -EINTR)
-		return ret;
-
-	restart->fn = futex_lock_pi_restart;
-
-	/* The other values are filled in */
-	return -ERESTART_RESTARTBLOCK;
-}
-
-/*
- * Called from the syscall entry below.
- */
-static int futex_lock_pi(u32 __user *uaddr, int detect, unsigned long sec,
-			 long nsec, int trylock)
-{
-	struct hrtimer_sleeper timeout, *to = NULL;
-	struct restart_block *restart;
-	int ret;
-
-	if (sec != MAX_SCHEDULE_TIMEOUT) {
-		to = &timeout;
-		hrtimer_init(&to->timer, CLOCK_REALTIME, HRTIMER_ABS);
-		hrtimer_init_sleeper(to, current);
-		to->timer.expires = ktime_set(sec, nsec);
-	}
-
-	ret = do_futex_lock_pi(uaddr, detect, trylock, to);
-
-	if (ret != -EINTR)
-		return ret;
-
-	pr_debug("lock_pi interrupted: %p, %d (%d)\n", uaddr, current->pid);
-
-	restart = &current_thread_info()->restart_block;
-	restart->fn = futex_lock_pi_restart;
-	restart->arg0 = (unsigned long) uaddr;
-	restart->arg1 = detect;
-	if (to) {
-		restart->arg2 = to->timer.expires.tv64 & 0xFFFFFFFF;
-		restart->arg3 = to->timer.expires.tv64 >> 32;
-	} else
-		restart->arg2 = restart->arg3 = 0;
-
-	return -ERESTART_RESTARTBLOCK;
-}
-
-/*
  * Userspace attempted a TID -> 0 atomic transition, and failed.
  * This is the in-kernel slowpath: we look up the PI state (if any),
  * and do the rt-mutex unlock.
diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c
index fc4e906aedb..48a53f68af9 100644
--- a/kernel/irq/handle.c
+++ b/kernel/irq/handle.c
@@ -20,6 +20,11 @@
 
 /**
  * handle_bad_irq - handle spurious and unhandled irqs
+ * @irq:       the interrupt number
+ * @desc:      description of the interrupt
+ * @regs:      pointer to a register structure
+ *
+ * Handles spurious and unhandled IRQ's. It also prints a debugmessage.
  */
 void fastcall
 handle_bad_irq(unsigned int irq, struct irq_desc *desc, struct pt_regs *regs)
diff --git a/kernel/panic.c b/kernel/panic.c
index 9b8dcfd1ca9..8010b9b17ac 100644
--- a/kernel/panic.c
+++ b/kernel/panic.c
@@ -173,7 +173,7 @@ const char *print_tainted(void)
 
 void add_taint(unsigned flag)
 {
-	debug_locks_off(); /* can't trust the integrity of the kernel anymore */
+	debug_locks = 0; /* can't trust the integrity of the kernel anymore */
 	tainted |= flag;
 }
 EXPORT_SYMBOL(add_taint);
diff --git a/kernel/power/Kconfig b/kernel/power/Kconfig
index ae44a70aae8..619ecabf7c5 100644
--- a/kernel/power/Kconfig
+++ b/kernel/power/Kconfig
@@ -56,7 +56,7 @@ config PM_TRACE
 
 config SOFTWARE_SUSPEND
 	bool "Software Suspend"
-	depends on PM && SWAP && (X86 && (!SMP || SUSPEND_SMP)) || ((FRV || PPC32) && !SMP)
+	depends on PM && SWAP && ((X86 && (!SMP || SUSPEND_SMP) && !X86_PAE) || ((FRV || PPC32) && !SMP))
 	---help---
 	  Enable the possibility of suspending the machine.
 	  It doesn't need ACPI or APM.
@@ -78,6 +78,10 @@ config SOFTWARE_SUSPEND
 
 	  For more information take a look at <file:Documentation/power/swsusp.txt>.
 
+	  (For now, swsusp is incompatible with PAE aka HIGHMEM_64G on i386.
+	  we need identity mapping for resume to work, and that is trivial
+	  to get with 4MB pages, but less than trivial on PAE).
+
 config PM_STD_PARTITION
 	string "Default resume partition"
 	depends on SOFTWARE_SUSPEND
diff --git a/kernel/spinlock.c b/kernel/spinlock.c
index bfd6ad9c033..fb524b009ee 100644
--- a/kernel/spinlock.c
+++ b/kernel/spinlock.c
@@ -72,7 +72,7 @@ EXPORT_SYMBOL(_write_trylock);
  * not re-enabled during lock-acquire (which the preempt-spin-ops do):
  */
 #if !defined(CONFIG_PREEMPT) || !defined(CONFIG_SMP) || \
-	defined(CONFIG_PROVE_LOCKING)
+	defined(CONFIG_DEBUG_LOCK_ALLOC)
 
 void __lockfunc _read_lock(rwlock_t *lock)
 {