Merge branch 'linus' into x86/mce3

Conflicts:
	arch/x86/kernel/cpu/mcheck/mce_64.c
	arch/x86/kernel/irq.c

Merge reason: Resolve the conflicts above.

Signed-off-by: Ingo Molnar <mingo@elte.hu>

73 files changed, 10869 insertions, 2585 deletions

diff --git a/kernel/Makefile b/kernel/Makefile
index 42423665660..90b53f6dc22 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -93,8 +93,10 @@ obj-$(CONFIG_LATENCYTOP) += latencytop.o
 obj-$(CONFIG_HAVE_GENERIC_DMA_COHERENT) += dma-coherent.o
 obj-$(CONFIG_FUNCTION_TRACER) += trace/
 obj-$(CONFIG_TRACING) += trace/
+obj-$(CONFIG_X86_DS) += trace/
 obj-$(CONFIG_SMP) += sched_cpupri.o
 obj-$(CONFIG_SLOW_WORK) += slow-work.o
+obj-$(CONFIG_PERF_COUNTERS) += perf_counter.o
 
 ifneq ($(CONFIG_SCHED_OMIT_FRAME_POINTER),y)
 # According to Alan Modra <alan@linuxcare.com.au>, the -fno-omit-frame-pointer is
diff --git a/kernel/async.c b/kernel/async.c
index 50540301ed0..27235f5de19 100644
--- a/kernel/async.c
+++ b/kernel/async.c
@@ -92,23 +92,18 @@ extern int initcall_debug;
 static async_cookie_t  __lowest_in_progress(struct list_head *running)
 {
 	struct async_entry *entry;
-	async_cookie_t ret = next_cookie; /* begin with "infinity" value */
 
 	if (!list_empty(running)) {
 		entry = list_first_entry(running,
 			struct async_entry, list);
-		ret = entry->cookie;
+		return entry->cookie;
 	}
 
-	if (!list_empty(&async_pending)) {
-		list_for_each_entry(entry, &async_pending, list)
-			if (entry->running == running) {
-				ret = entry->cookie;
-				break;
-			}
-	}
+	list_for_each_entry(entry, &async_pending, list)
+		if (entry->running == running)
+			return entry->cookie;
 
-	return ret;
+	return next_cookie;	/* "infinity" value */
 }
 
 static async_cookie_t  lowest_in_progress(struct list_head *running)
diff --git a/kernel/compat.c b/kernel/compat.c
index 42d56544460..f6c204f07ea 100644
--- a/kernel/compat.c
+++ b/kernel/compat.c
@@ -882,6 +882,17 @@ compat_sys_rt_sigtimedwait (compat_sigset_t __user *uthese,
 
 }
 
+asmlinkage long
+compat_sys_rt_tgsigqueueinfo(compat_pid_t tgid, compat_pid_t pid, int sig,
+			     struct compat_siginfo __user *uinfo)
+{
+	siginfo_t info;
+
+	if (copy_siginfo_from_user32(&info, uinfo))
+		return -EFAULT;
+	return do_rt_tgsigqueueinfo(tgid, pid, sig, &info);
+}
+
 #ifdef __ARCH_WANT_COMPAT_SYS_TIME
 
 /* compat_time_t is a 32 bit "long" and needs to get converted. */
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index 026faccca86..d5a7e17474e 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -1857,7 +1857,7 @@ struct cgroup_subsys cpuset_subsys = {
 
 int __init cpuset_init_early(void)
 {
-	alloc_bootmem_cpumask_var(&top_cpuset.cpus_allowed);
+	alloc_cpumask_var(&top_cpuset.cpus_allowed, GFP_NOWAIT);
 
 	top_cpuset.mems_generation = cpuset_mems_generation++;
 	return 0;
diff --git a/kernel/cred.c b/kernel/cred.c
index 3a039189d70..1bb4d7e5d61 100644
--- a/kernel/cred.c
+++ b/kernel/cred.c
@@ -167,7 +167,7 @@ EXPORT_SYMBOL(prepare_creds);
 
 /*
  * Prepare credentials for current to perform an execve()
- * - The caller must hold current->cred_exec_mutex
+ * - The caller must hold current->cred_guard_mutex
  */
 struct cred *prepare_exec_creds(void)
 {
@@ -276,7 +276,7 @@ int copy_creds(struct task_struct *p, unsigned long clone_flags)
 	struct cred *new;
 	int ret;
 
-	mutex_init(&p->cred_exec_mutex);
+	mutex_init(&p->cred_guard_mutex);
 
 	if (
 #ifdef CONFIG_KEYS
diff --git a/kernel/exit.c b/kernel/exit.c
index abf9cf3b95c..b6c90b5ef50 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -48,7 +48,8 @@
 #include <linux/tracehook.h>
 #include <linux/fs_struct.h>
 #include <linux/init_task.h>
-#include <trace/sched.h>
+#include <linux/perf_counter.h>
+#include <trace/events/sched.h>
 
 #include <asm/uaccess.h>
 #include <asm/unistd.h>
@@ -56,10 +57,6 @@
 #include <asm/mmu_context.h>
 #include "cred-internals.h"
 
-DEFINE_TRACE(sched_process_free);
-DEFINE_TRACE(sched_process_exit);
-DEFINE_TRACE(sched_process_wait);
-
 static void exit_mm(struct task_struct * tsk);
 
 static void __unhash_process(struct task_struct *p)
@@ -158,6 +155,9 @@ static void delayed_put_task_struct(struct rcu_head *rhp)
 {
 	struct task_struct *tsk = container_of(rhp, struct task_struct, rcu);
 
+#ifdef CONFIG_PERF_COUNTERS
+	WARN_ON_ONCE(tsk->perf_counter_ctxp);
+#endif
 	trace_sched_process_free(tsk);
 	put_task_struct(tsk);
 }
@@ -174,6 +174,7 @@ repeat:
 	atomic_dec(&__task_cred(p)->user->processes);
 
 	proc_flush_task(p);
+
 	write_lock_irq(&tasklist_lock);
 	tracehook_finish_release_task(p);
 	__exit_signal(p);
@@ -975,16 +976,19 @@ NORET_TYPE void do_exit(long code)
 		module_put(tsk->binfmt->module);
 
 	proc_exit_connector(tsk);
+
+	/*
+	 * Flush inherited counters to the parent - before the parent
+	 * gets woken up by child-exit notifications.
+	 */
+	perf_counter_exit_task(tsk);
+
 	exit_notify(tsk, group_dead);
 #ifdef CONFIG_NUMA
 	mpol_put(tsk->mempolicy);
 	tsk->mempolicy = NULL;
 #endif
 #ifdef CONFIG_FUTEX
-	/*
-	 * This must happen late, after the PID is not
-	 * hashed anymore:
-	 */
 	if (unlikely(!list_empty(&tsk->pi_state_list)))
 		exit_pi_state_list(tsk);
 	if (unlikely(current->pi_state_cache))
@@ -1476,6 +1480,7 @@ static int wait_consider_task(struct task_struct *parent, int ptrace,
 		 */
 		if (*notask_error)
 			*notask_error = ret;
+		return 0;
 	}
 
 	if (likely(!ptrace) && unlikely(p->ptrace)) {
diff --git a/kernel/fork.c b/kernel/fork.c
index b9e2edd0072..4430eb1376f 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -61,8 +61,8 @@
 #include <linux/proc_fs.h>
 #include <linux/blkdev.h>
 #include <linux/fs_struct.h>
-#include <trace/sched.h>
 #include <linux/magic.h>
+#include <linux/perf_counter.h>
 
 #include <asm/pgtable.h>
 #include <asm/pgalloc.h>
@@ -71,6 +71,8 @@
 #include <asm/cacheflush.h>
 #include <asm/tlbflush.h>
 
+#include <trace/events/sched.h>
+
 /*
  * Protected counters by write_lock_irq(&tasklist_lock)
  */
@@ -83,8 +85,6 @@ DEFINE_PER_CPU(unsigned long, process_counts) = 0;
 
 __cacheline_aligned DEFINE_RWLOCK(tasklist_lock);  /* outer */
 
-DEFINE_TRACE(sched_process_fork);
-
 int nr_processes(void)
 {
 	int cpu;
@@ -982,6 +982,8 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 	if (!p)
 		goto fork_out;
 
+	ftrace_graph_init_task(p);
+
 	rt_mutex_init_task(p);
 
 #ifdef CONFIG_PROVE_LOCKING
@@ -1089,12 +1091,16 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 #ifdef CONFIG_DEBUG_MUTEXES
 	p->blocked_on = NULL; /* not blocked yet */
 #endif
-	if (unlikely(current->ptrace))
-		ptrace_fork(p, clone_flags);
+
+	p->bts = NULL;
 
 	/* Perform scheduler related setup. Assign this task to a CPU. */
 	sched_fork(p, clone_flags);
 
+	retval = perf_counter_init_task(p);
+	if (retval)
+		goto bad_fork_cleanup_policy;
+
 	if ((retval = audit_alloc(p)))
 		goto bad_fork_cleanup_policy;
 	/* copy all the process information */
@@ -1131,8 +1137,6 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 		}
 	}
 
-	ftrace_graph_init_task(p);
-
 	p->pid = pid_nr(pid);
 	p->tgid = p->pid;
 	if (clone_flags & CLONE_THREAD)
@@ -1141,7 +1145,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 	if (current->nsproxy != p->nsproxy) {
 		retval = ns_cgroup_clone(p, pid);
 		if (retval)
-			goto bad_fork_free_graph;
+			goto bad_fork_free_pid;
 	}
 
 	p->set_child_tid = (clone_flags & CLONE_CHILD_SETTID) ? child_tidptr : NULL;
@@ -1233,7 +1237,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 		spin_unlock(&current->sighand->siglock);
 		write_unlock_irq(&tasklist_lock);
 		retval = -ERESTARTNOINTR;
-		goto bad_fork_free_graph;
+		goto bad_fork_free_pid;
 	}
 
 	if (clone_flags & CLONE_THREAD) {
@@ -1268,8 +1272,6 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 	cgroup_post_fork(p);
 	return p;
 
-bad_fork_free_graph:
-	ftrace_graph_exit_task(p);
 bad_fork_free_pid:
 	if (pid != &init_struct_pid)
 		free_pid(pid);
@@ -1293,6 +1295,7 @@ bad_fork_cleanup_semundo:
 bad_fork_cleanup_audit:
 	audit_free(p);
 bad_fork_cleanup_policy:
+	perf_counter_free_task(p);
 #ifdef CONFIG_NUMA
 	mpol_put(p->mempolicy);
 bad_fork_cleanup_cgroup:
@@ -1406,10 +1409,16 @@ long do_fork(unsigned long clone_flags,
 		if (clone_flags & CLONE_VFORK) {
 			p->vfork_done = &vfork;
 			init_completion(&vfork);
+		} else if (!(clone_flags & CLONE_VM)) {
+			/*
+			 * vfork will do an exec which will call
+			 * set_task_comm()
+			 */
+			perf_counter_fork(p);
 		}
 
 		audit_finish_fork(p);
-		tracehook_report_clone(trace, regs, clone_flags, nr, p);
+		tracehook_report_clone(regs, clone_flags, nr, p);
 
 		/*
 		 * We set PF_STARTING at creation in case tracing wants to
diff --git a/kernel/futex.c b/kernel/futex.c
index d546b2d53a6..80b5ce71659 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -19,6 +19,10 @@
  *  PRIVATE futexes by Eric Dumazet
  *  Copyright (C) 2007 Eric Dumazet <dada1@cosmosbay.com>
  *
+ *  Requeue-PI support by Darren Hart <dvhltc@us.ibm.com>
+ *  Copyright (C) IBM Corporation, 2009
+ *  Thanks to Thomas Gleixner for conceptual design and careful reviews.
+ *
  *  Thanks to Ben LaHaise for yelling "hashed waitqueues" loudly
  *  enough at me, Linus for the original (flawed) idea, Matthew
  *  Kirkwood for proof-of-concept implementation.
@@ -96,8 +100,8 @@ struct futex_pi_state {
  */
 struct futex_q {
 	struct plist_node list;
-	/* There can only be a single waiter */
-	wait_queue_head_t waiter;
+	/* Waiter reference */
+	struct task_struct *task;
 
 	/* Which hash list lock to use: */
 	spinlock_t *lock_ptr;
@@ -107,7 +111,9 @@ struct futex_q {
 
 	/* Optional priority inheritance state: */
 	struct futex_pi_state *pi_state;
-	struct task_struct *task;
+
+	/* rt_waiter storage for requeue_pi: */
+	struct rt_mutex_waiter *rt_waiter;
 
 	/* Bitset for the optional bitmasked wakeup */
 	u32 bitset;
@@ -278,6 +284,25 @@ void put_futex_key(int fshared, union futex_key *key)
 	drop_futex_key_refs(key);
 }
 
+/**
+ * futex_top_waiter() - Return the highest priority waiter on a futex
+ * @hb:     the hash bucket the futex_q's reside in
+ * @key:    the futex key (to distinguish it from other futex futex_q's)
+ *
+ * Must be called with the hb lock held.
+ */
+static struct futex_q *futex_top_waiter(struct futex_hash_bucket *hb,
+					union futex_key *key)
+{
+	struct futex_q *this;
+
+	plist_for_each_entry(this, &hb->chain, list) {
+		if (match_futex(&this->key, key))
+			return this;
+	}
+	return NULL;
+}
+
 static u32 cmpxchg_futex_value_locked(u32 __user *uaddr, u32 uval, u32 newval)
 {
 	u32 curval;
@@ -539,28 +564,160 @@ lookup_pi_state(u32 uval, struct futex_hash_bucket *hb,
 	return 0;
 }
 
+/**
+ * futex_lock_pi_atomic() - atomic work required to acquire a pi aware futex
+ * @uaddr:		the pi futex user address
+ * @hb:			the pi futex hash bucket
+ * @key:		the futex key associated with uaddr and hb
+ * @ps:			the pi_state pointer where we store the result of the
+ *			lookup
+ * @task:		the task to perform the atomic lock work for.  This will
+ *			be "current" except in the case of requeue pi.
+ * @set_waiters:	force setting the FUTEX_WAITERS bit (1) or not (0)
+ *
+ * Returns:
+ *  0 - ready to wait
+ *  1 - acquired the lock
+ * <0 - error
+ *
+ * The hb->lock and futex_key refs shall be held by the caller.
+ */
+static int futex_lock_pi_atomic(u32 __user *uaddr, struct futex_hash_bucket *hb,
+				union futex_key *key,
+				struct futex_pi_state **ps,
+				struct task_struct *task, int set_waiters)
+{
+	int lock_taken, ret, ownerdied = 0;
+	u32 uval, newval, curval;
+
+retry:
+	ret = lock_taken = 0;
+
+	/*
+	 * To avoid races, we attempt to take the lock here again
+	 * (by doing a 0 -> TID atomic cmpxchg), while holding all
+	 * the locks. It will most likely not succeed.
+	 */
+	newval = task_pid_vnr(task);
+	if (set_waiters)
+		newval |= FUTEX_WAITERS;
+
+	curval = cmpxchg_futex_value_locked(uaddr, 0, newval);
+
+	if (unlikely(curval == -EFAULT))
+		return -EFAULT;
+
+	/*
+	 * Detect deadlocks.
+	 */
+	if ((unlikely((curval & FUTEX_TID_MASK) == task_pid_vnr(task))))
+		return -EDEADLK;
+
+	/*
+	 * Surprise - we got the lock. Just return to userspace:
+	 */
+	if (unlikely(!curval))
+		return 1;
+
+	uval = curval;
+
+	/*
+	 * Set the FUTEX_WAITERS flag, so the owner will know it has someone
+	 * to wake at the next unlock.
+	 */
+	newval = curval | FUTEX_WAITERS;
+
+	/*
+	 * There are two cases, where a futex might have no owner (the
+	 * owner TID is 0): OWNER_DIED. We take over the futex in this
+	 * case. We also do an unconditional take over, when the owner
+	 * of the futex died.
+	 *
+	 * This is safe as we are protected by the hash bucket lock !
+	 */
+	if (unlikely(ownerdied || !(curval & FUTEX_TID_MASK))) {
+		/* Keep the OWNER_DIED bit */
+		newval = (curval & ~FUTEX_TID_MASK) | task_pid_vnr(task);
+		ownerdied = 0;
+		lock_taken = 1;
+	}
+
+	curval = cmpxchg_futex_value_locked(uaddr, uval, newval);
+
+	if (unlikely(curval == -EFAULT))
+		return -EFAULT;
+	if (unlikely(curval != uval))
+		goto retry;
+
+	/*
+	 * We took the lock due to owner died take over.
+	 */
+	if (unlikely(lock_taken))
+		return 1;
+
+	/*
+	 * We dont have the lock. Look up the PI state (or create it if
+	 * we are the first waiter):
+	 */
+	ret = lookup_pi_state(uval, hb, key, ps);
+
+	if (unlikely(ret)) {
+		switch (ret) {
+		case -ESRCH:
+			/*
+			 * No owner found for this futex. Check if the
+			 * OWNER_DIED bit is set to figure out whether
+			 * this is a robust futex or not.
+			 */
+			if (get_futex_value_locked(&curval, uaddr))
+				return -EFAULT;
+
+			/*
+			 * We simply start over in case of a robust
+			 * futex. The code above will take the futex
+			 * and return happy.
+			 */
+			if (curval & FUTEX_OWNER_DIED) {
+				ownerdied = 1;
+				goto retry;
+			}
+		default:
+			break;
+		}
+	}
+
+	return ret;
+}
+
 /*
  * The hash bucket lock must be held when this is called.
  * Afterwards, the futex_q must not be accessed.
  */
 static void wake_futex(struct futex_q *q)
 {
-	plist_del(&q->list, &q->list.plist);
+	struct task_struct *p = q->task;
+
 	/*
-	 * The lock in wake_up_all() is a crucial memory barrier after the
-	 * plist_del() and also before assigning to q->lock_ptr.
+	 * We set q->lock_ptr = NULL _before_ we wake up the task. If
+	 * a non futex wake up happens on another CPU then the task
+	 * might exit and p would dereference a non existing task
+	 * struct. Prevent this by holding a reference on p across the
+	 * wake up.
 	 */
-	wake_up(&q->waiter);
+	get_task_struct(p);
+
+	plist_del(&q->list, &q->list.plist);
 	/*
-	 * The waiting task can free the futex_q as soon as this is written,
-	 * without taking any locks.  This must come last.
-	 *
-	 * A memory barrier is required here to prevent the following store to
-	 * lock_ptr from getting ahead of the wakeup. Clearing the lock at the
-	 * end of wake_up() does not prevent this store from moving.
+	 * The waiting task can free the futex_q as soon as
+	 * q->lock_ptr = NULL is written, without taking any locks. A
+	 * memory barrier is required here to prevent the following
+	 * store to lock_ptr from getting ahead of the plist_del.
 	 */
 	smp_wmb();
 	q->lock_ptr = NULL;
+
+	wake_up_state(p, TASK_NORMAL);
+	put_task_struct(p);
 }
 
 static int wake_futex_pi(u32 __user *uaddr, u32 uval, struct futex_q *this)
@@ -689,7 +846,7 @@ static int futex_wake(u32 __user *uaddr, int fshared, int nr_wake, u32 bitset)
 
 	plist_for_each_entry_safe(this, next, head, list) {
 		if (match_futex (&this->key, &key)) {
-			if (this->pi_state) {